[{"benchmark":"aa-index","model":"grok-4","score":73.2,"metric":"percent"},{"benchmark":"aa-index","model":"openreasoning-nemotron-1.5b","score":31,"metric":"percent"},{"benchmark":"aa-index","model":"openreasoning-nemotron-14b","score":60.9,"metric":"percent"},{"benchmark":"aa-index","model":"openreasoning-nemotron-32b","score":64.3,"metric":"percent"},{"benchmark":"aa-index","model":"openreasoning-nemotron-7b","score":54.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5","score":75.6,"metric":"percent"},{"benchmark":"acebench","model":"kimi-k2","score":82.2,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"qwen3-32b","score":85.1,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"phi-3.128k","score":55.53,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"gemma-7b","score":51.8,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"granite-7b","score":48.2,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"mistral-7b","score":55,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"mistral-7b-instruct","score":55.45,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"granite-c-8b","score":53.09,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"granite-c-instruct-8b","score":50.53,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"llama-3-8b","score":61.53,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"llama-3.1-8b","score":51.46,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"mixtral-8x7b","score":65.53,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"granite-13b","score":47.79,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"codestral-22b","score":67.4,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"mixtral-8x22b","score":55.63,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"deepseek-instruct-33b","score":57.58,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"llama-c-34b","score":59.02,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"llama-2-70b","score":55.72,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"llama-c-70b","score":59.09,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"llama-3-70b","score":78.71,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"llama-3.1-70b","score":66.67,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"llama-3.1-405b","score":80.49,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"gpt-4o-mini","score":77.74,"metric":"percent"},{"benchmark":"acp-bench-bool","model":"gpt-4o","score":81.84,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-3.3-70b","score":82.1,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"phi-3.128k","score":34.75,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"gemma-7b","score":28.93,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"granite-7b","score":29.67,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"mistral-7b","score":28.67,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"mistral-7b-instruct","score":37.3,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"granite-c-8b","score":29.21,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"granite-c-instruct-8b","score":32.63,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-3-8b","score":44.05,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-3.1-8b","score":41.52,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"mixtral-8x7b","score":51.44,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"granite-13b","score":26.66,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"codestral-22b","score":40.97,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"mixtral-8x22b","score":39.25,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"deepseek-instruct-33b","score":35.11,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-c-34b","score":35.71,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-2-70b","score":29.71,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-c-70b","score":32.87,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-3-70b","score":74.3,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-3.1-70b","score":66.94,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"llama-3.1-405b","score":77.42,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"gpt-4o-mini","score":56.5,"metric":"percent"},{"benchmark":"acp-bench-mcq","model":"gpt-4o","score":74.97,"metric":"percent"},{"benchmark":"agentdojo","model":"claude-3.7-sonnet","score":88.66,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-235b-a22b-thinking","score":89.2,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-pro","score":90.9,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5","score":89.7,"metric":"percent"},{"benchmark":"ai2d","model":"claude-opus-4.1","score":86.4,"metric":"percent"},{"benchmark":"ai2d","model":"dots-vlm1","score":88.4,"metric":"percent"},{"benchmark":"agentharm","model":"grok-code-fast-1","score":17,"metric":"percent"},{"benchmark":"agieval","model":"afm-4.5b","score":30.04,"metric":"percent"},{"benchmark":"agieval","model":"gemma-2-2b","score":24.2,"metric":"percent"},{"benchmark":"agieval","model":"gemma-3-4b-it","score":28.13,"metric":"percent"},{"benchmark":"agieval","model":"gemma-2-7b","score":41.7,"metric":"percent"},{"benchmark":"agieval","model":"llama-3-70b-base","score":63,"metric":"average/acc_char"},{"benchmark":"agieval","model":"llama-3-8b-base","score":47.1,"metric":"average/acc_char"},{"benchmark":"agieval","model":"llama-3.1-405b-base","score":71.6,"metric":"percent"},{"benchmark":"agieval","model":"llama-3.1-405b-base","score":71.6,"metric":"average/acc_char"},{"benchmark":"agieval","model":"llama-3.1-70b-base","score":64.6,"metric":"average/acc_char"},{"benchmark":"agieval","model":"llama-3.1-8b-base","score":47.8,"metric":"average/acc_char"},{"benchmark":"agieval","model":"qwen3-4b","score":27.6,"metric":"percent"},{"benchmark":"agieval","model":"smollm3-3b","score":30.15,"metric":"percent"},{"benchmark":"ai2d","model":"cambrian-1-34b","score":79.7,"metric":"percent"},{"benchmark":"ai2d","model":"cambrian-1-8b","score":73,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3-haiku","score":86.7,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3-opus","score":88.1,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3.5-sonnet","score":94.7,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3.7-sonnet","score":81.4,"metric":"percent"},{"benchmark":"ai2d","model":"fastvlm-0.5b","score":68,"metric":"percent"},{"benchmark":"ai2d","model":"fastvlm-1.5b","score":77.4,"metric":"percent"},{"benchmark":"ai2d","model":"fastvlm-7b","score":83.6,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-1.5-flash","score":91.7,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-1.5-pro","score":94.4,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-3-27b-vl","score":80.2,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-3-27b-it","score":84.5,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4.1v","score":87.9,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4.5v","score":88.1,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4o","score":82.6,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4o-0513","score":94.2,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4v","score":89.4,"metric":"percent"},{"benchmark":"ai2d","model":"internvl-8b","score":85.2,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-8b","score":83.8,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-llama-3-76b","score":87.6,"metric":"percent"},{"benchmark":"ai2d","model":"kimi-vl-a3b-thinking-2506","score":81.9,"metric":"percent"},{"benchmark":"ai2d","model":"llama-3.2v-11b-instruct","score":91.1,"metric":"percent"},{"benchmark":"ai2d","model":"llama-3.2v-90b-instruct","score":92.3,"metric":"percent"},{"benchmark":"ai2d","model":"llava-1.5-13b","score":61.1,"metric":"percent"},{"benchmark":"ai2d","model":"llava-1.5-7b","score":55.5,"metric":"percent"},{"benchmark":"ai2d","model":"llava-onevision-72b","score":85.6,"metric":"percent"},{"benchmark":"ai2d","model":"llava-onevision-7b","score":81.4,"metric":"percent"},{"benchmark":"ai2d","model":"mimo-vl-7b-rl","score":83.5,"metric":"percent"},{"benchmark":"ai2d","model":"mimo-vl-7b-sft","score":83.2,"metric":"percent"},{"benchmark":"ai2d","model":"mistral-small-3.1-24b-instruct","score":93.72,"metric":"percent"},{"benchmark":"ai2d","model":"molmo-72b","score":96.3,"metric":"percent"},{"benchmark":"ai2d","model":"molmo-7b-d","score":93.2,"metric":"percent"},{"benchmark":"ai2d","model":"molmo-7b-o","score":90.7,"metric":"percent"},{"benchmark":"ai2d","model":"molmoe-1b","score":86.4,"metric":"percent"},{"benchmark":"ai2d","model":"paligemma-mix-3b","score":72.3,"metric":"percent"},{"benchmark":"ai2d","model":"phi-3.5-vision-4b","score":78.1,"metric":"percent"},{"benchmark":"ai2d","model":"pixtral-12b","score":93.8,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2-vl-72b","score":88.1,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2-vl-7b","score":83,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2.5-vl-7b","score":83.9,"metric":"percent"},{"benchmark":"ai2d","model":"step-3","score":83.7,"metric":"percent"},{"benchmark":"ai2d","model":"xgen-mm-interleave-4b","score":74.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-3.7-sonnet","score":64.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-opus-4","score":72,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-r1","score":56.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-tng-r1t-chimera","score":48.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-tng-r1t2-chimera","score":64.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3-0528","score":71.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3.1","score":76.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3.1-terminus","score":76.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3.2-exp","score":74.5,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-pro","score":72.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4o","score":25.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-5","score":88,"metric":"percent"},{"benchmark":"aider-polyglot","model":"grok-3-beta-think","score":53.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"grok-4","score":79.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o1","score":61.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o1-2024-12-17","score":61.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3","score":81.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3-mini","score":53.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3-pro","score":84.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o4-mini","score":72,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-235b-a22b","score":61.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-30b-a3b","score":35.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-32b","score":50.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-32b-nothinking","score":40,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-next-80b-a3b-instruct","score":49.8,"metric":"percent"},{"benchmark":"aider-code-editing","model":"ling-1t","score":83.65,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-v3.1-terminus","score":88.16,"metric":"percent"},{"benchmark":"aider-code-editing","model":"kimi-k2-0905","score":85.34,"metric":"percent"},{"benchmark":"aider-code-editing","model":"gpt-5","score":84.4,"metric":"percent"},{"benchmark":"aider-code-editing","model":"gemini-2.5-pro","score":89.85,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1","score":79.8,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-distill-qwen-1.5b","score":29.1,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-tng-r1t-chimera","score":74.7,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-tng-r1t2-chimera","score":82.3,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v3","score":59.4,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v3-0528","score":91.4,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v3.1-thinking","score":91.87,"metric":"percent"},{"benchmark":"aime-2024","model":"ernie-4.5","score":54.8,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon-h1-0.5b-instruct","score":3.75,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon-h1-1.5b","score":11.25,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon-h1-1.5b-deep","score":14.37,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon-h1-34b-instruct","score":23.75,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon-h1-3b","score":11.88,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon-h1-7b","score":16.04,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon3-10b","score":9.79,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon3-1b","score":0.41,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon3-3b","score":3.96,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon3-7b","score":8.75,"metric":"percent"},{"benchmark":"aime-2024","model":"gemini-2.5-pro","score":92,"metric":"percent"},{"benchmark":"aime-2024","model":"gemma-3-12b-it","score":22.5,"metric":"percent"},{"benchmark":"aime-2024","model":"gemma-3-1b-it","score":0.9,"metric":"percent"},{"benchmark":"aime-2024","model":"gemma-3-27b-it","score":27.5,"metric":"percent"},{"benchmark":"aime-2024","model":"gemma-3-4b-it","score":6.67,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4.1","score":48.1,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-5-high","score":94.78,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-120b","score":89.58,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-20b","score":76.88,"metric":"percent"},{"benchmark":"aime-2024","model":"grok-3-beta-think","score":83.9,"metric":"percent"},{"benchmark":"aime-2024","model":"grok-3-mini","score":95.8,"metric":"percent"},{"benchmark":"aime-2024","model":"k2-think","score":86.26,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.1-8b-base","score":5.42,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.2-1.24b","score":1.1,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.2-1.24b-base","score":1.46,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.2-3b-base","score":11.67,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.3-70b","score":12.92,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-4-scout-17b","score":27.92,"metric":"percent"},{"benchmark":"aime-2024","model":"mobilellm-r1-950m","score":15.5,"metric":"percent"},{"benchmark":"aime-2024","model":"nemotron-32b","score":87.09,"metric":"percent"},{"benchmark":"aime-2024","model":"o1","score":74.3,"metric":"percent"},{"benchmark":"aime-2024","model":"o1-2024-12-17","score":74.3,"metric":"percent"},{"benchmark":"aime-2024","model":"o3-high","score":92.26,"metric":"percent"},{"benchmark":"aime-2024","model":"o3-mini","score":79.6,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-2-0425-1b-instruct","score":0.6,"metric":"percent"},{"benchmark":"aime-2024","model":"openreasoning-nemotron-1.5b","score":55.5,"metric":"percent"},{"benchmark":"aime-2024","model":"openreasoning-nemotron-14b","score":87.8,"metric":"percent"},{"benchmark":"aime-2024","model":"openreasoning-nemotron-32b","score":89.2,"metric":"percent"},{"benchmark":"aime-2024","model":"openreasoning-nemotron-7b","score":84.7,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-0.5b","score":0.62,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-1.5b","score":2.29,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-32b-instruct","score":17.92,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-3b","score":6.25,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-72b-instruct","score":17.29,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-7b","score":12.29,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-0.6b","score":11.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-0.8b","score":2.71,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-1.7b","score":12.5,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-235b-a22b","score":40.1,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b","score":70.63,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-32b","score":81.4,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-4b","score":22.29,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-8b","score":28.33,"metric":"percent"},{"benchmark":"aime-2024","model":"qwq-32b","score":79.38,"metric":"percent"},{"benchmark":"aime-2024","model":"smollm2-1.7b-instruct","score":0.2,"metric":"percent"},{"benchmark":"aime-2024","model":"minimax-m1-80k","score":86,"metric":"percent"},{"benchmark":"aime-2024","model":"minimax-m1-40k","score":83.3,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-0528","score":91.4,"metric":"percent"},{"benchmark":"aime-2024","model":"seed-thinking-v1.5","score":86.7,"metric":"percent"},{"benchmark":"aime-2024","model":"o3","score":91.6,"metric":"percent"},{"benchmark":"aime-2025","model":"apriel-5b-instruct","score":4.3,"metric":"percent"},{"benchmark":"aime-2025","model":"aquif-3-3.2b","score":9.6,"metric":"percent"},{"benchmark":"aime-2025","model":"aquif-3.5-2.7b","score":13.4,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4","score":33.9,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1","score":70,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-tng-r1t-chimera","score":58.3,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-tng-r1t2-chimera","score":70,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3","score":25,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3-0528","score":87.5,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.1-thinking","score":49.8,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.1-terminus","score":88.4,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.2-exp","score":89.3,"metric":"percent"},{"benchmark":"aime-2025","model":"ernie-4.5","score":35.1,"metric":"percent"},{"benchmark":"aime-2025","model":"ernie-4.5-21b-a3b-pt","score":16.1,"metric":"percent"},{"benchmark":"aime-2025","model":"minimax-m1-80k","score":76.9,"metric":"percent"},{"benchmark":"aime-2025","model":"minimax-m1-40k","score":74.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-235b-a22b","score":81.5,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0528","score":87.5,"metric":"percent"},{"benchmark":"aime-2025","model":"seed-thinking-v1.5","score":74,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4","score":75.5,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-pro","score":88,"metric":"percent"},{"benchmark":"aime-2025","model":"o3","score":88.9,"metric":"percent"},{"benchmark":"aime-2025","model":"exaone-3.5-2.4b","score":4.5,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon-h1-0.5b-instruct","score":4.38,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon-h1-1.5b","score":9.58,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon-h1-1.5b-deep","score":11.04,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon-h1-34b-instruct","score":16.67,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon-h1-3b","score":13.33,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon-h1-7b","score":13.96,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon3-10b","score":5.42,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon3-1b","score":0.21,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon3-3b","score":2.29,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon3-7b","score":6.25,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash","score":75.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash-thinking","score":72,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-pro","score":86.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-12b-it","score":18.75,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-1b-it","score":1.25,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-27b-it","score":22.71,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-4b-it","score":12.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4.1","score":36.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5","score":90.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-high","score":94.6,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-pro","score":96.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":78.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b","score":74.58,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b-medium","score":73.33,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-3-beta-think","score":77.3,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4","score":93.3,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-think","score":77.72,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2","score":49.5,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2-instruct","score":49.2,"metric":"percent"},{"benchmark":"aime-2025","model":"ling-1t","score":70.42,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.1-terminus","score":55.21,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2-0905","score":50.16,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5","score":59.43,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-pro","score":70.1,"metric":"percent"},{"benchmark":"aime-2025","model":"ling-mini-2.0","score":47,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.1-3b","score":0.3,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.1-8b-base","score":0.42,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.2-1.24b-base","score":0,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.2-3b-base","score":0.21,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.3-70b","score":1.25,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-4-scout-17b","score":8.96,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-32b","score":82.71,"metric":"percent"},{"benchmark":"aime-2025","model":"o1","score":70,"metric":"percent"},{"benchmark":"aime-2025","model":"o1-2024-12-17","score":79.2,"metric":"percent"},{"benchmark":"aime-2025","model":"o3","score":87.5,"metric":"percent"},{"benchmark":"aime-2025","model":"o3-high","score":86.58,"metric":"percent"},{"benchmark":"aime-2025","model":"o3-mini","score":74.8,"metric":"percent"},{"benchmark":"aime-2025","model":"o4-mini","score":82.5,"metric":"percent"},{"benchmark":"aime-2025","model":"openreasoning-nemotron-1.5b","score":45.6,"metric":"percent"},{"benchmark":"aime-2025","model":"openreasoning-nemotron-14b","score":82,"metric":"percent"},{"benchmark":"aime-2025","model":"openreasoning-nemotron-32b","score":84,"metric":"percent"},{"benchmark":"aime-2025","model":"openreasoning-nemotron-7b","score":78.2,"metric":"percent"},{"benchmark":"aime-2025","model":"phi-4-mini-3.8b","score":5.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-0.5b","score":0.21,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-1.5b","score":1.25,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-32b-instruct","score":11.46,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-3b","score":2.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-72b-instruct","score":15.21,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-7b","score":9.58,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-0.8b","score":1.67,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-1.7b","score":8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-235b-a22b-thinking-2507","score":1.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b","score":85,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-thinking-2507","score":85,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b","score":72.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b-nothinking","score":20.2,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b-thinking","score":72.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b","score":9.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-instruct-2507","score":48.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b","score":19.17,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b-nothinking-2504","score":23.4,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b-thinking","score":71.25,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-max-instruct-preview","score":80.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-next-80b-a3b-instruct","score":69.5,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-next-80b-a3b-thinking","score":87.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwq-32b","score":69.17,"metric":"percent"},{"benchmark":"aime-2025","model":"ring-mini-2.0","score":74.06,"metric":"percent"},{"benchmark":"aime-2025","model":"smollm3-3b","score":9.3,"metric":"percent"},{"benchmark":"all-angles-bench","model":"gemma-3-27b-vl","score":48.2,"metric":"percent"},{"benchmark":"all-angles-bench","model":"glm-4.1v","score":52.7,"metric":"percent"},{"benchmark":"all-angles-bench","model":"glm-4.5v","score":56.9,"metric":"percent"},{"benchmark":"all-angles-bench","model":"kimi-vl-a3b-thinking-2506","score":48.9,"metric":"percent"},{"benchmark":"all-angles-bench","model":"step-3","score":52.4,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon-h1-0.5b-instruct","score":10.79,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon-h1-1.5b","score":28.18,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon-h1-1.5b-deep","score":27.12,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon-h1-34b-instruct","score":48.32,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon-h1-3b","score":31.09,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon-h1-7b","score":40.23,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon3-10b","score":24.31,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon3-1b","score":6.98,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon3-3b","score":14.82,"metric":"percent"},{"benchmark":"alpacaeval","model":"falcon3-7b","score":27.56,"metric":"percent"},{"benchmark":"alpacaeval","model":"gemma-3-12b-it","score":43.55,"metric":"percent"},{"benchmark":"alpacaeval","model":"gemma-3-1b-it","score":17.87,"metric":"percent"},{"benchmark":"alpacaeval","model":"gemma-3-27b-it","score":56.16,"metric":"percent"},{"benchmark":"alpacaeval","model":"gemma-3-4b-it","score":39.64,"metric":"percent"},{"benchmark":"alpacaeval","model":"llama-3.1-8b-base","score":25.48,"metric":"percent"},{"benchmark":"alpacaeval","model":"llama-3.2-1.24b-base","score":9.38,"metric":"percent"},{"benchmark":"alpacaeval","model":"llama-3.2-3b-base","score":19.69,"metric":"percent"},{"benchmark":"alpacaeval","model":"llama-3.3-70b","score":38.27,"metric":"percent"},{"benchmark":"alpacaeval","model":"llama-4-scout-17b","score":36.26,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen2.5-0.5b","score":3.26,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen2.5-1.5b","score":9.54,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen2.5-32b-instruct","score":39.26,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen2.5-3b","score":17.37,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen2.5-72b-instruct","score":49.29,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen2.5-7b","score":29.48,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen3-0.8b","score":9.59,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen3-1.7b","score":21.89,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen3-32b","score":64.21,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen3-4b","score":36.51,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen3-8b","score":46.13,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-r1","score":87.6,"metric":"percent"},{"benchmark":"amc-23","model":"falcon-h1-0.5b-instruct","score":33.13,"metric":"percent"},{"benchmark":"amc-23","model":"falcon-h1-1.5b","score":43.59,"metric":"percent"},{"benchmark":"amc-23","model":"falcon-h1-1.5b-deep","score":56.56,"metric":"percent"},{"benchmark":"amc-23","model":"falcon-h1-34b-instruct","score":69.38,"metric":"percent"},{"benchmark":"amc-23","model":"falcon-h1-3b","score":55.63,"metric":"percent"},{"benchmark":"amc-23","model":"falcon-h1-7b","score":56.72,"metric":"percent"},{"benchmark":"amc-23","model":"falcon3-10b","score":45.78,"metric":"percent"},{"benchmark":"amc-23","model":"falcon3-1b","score":6.87,"metric":"percent"},{"benchmark":"amc-23","model":"falcon3-3b","score":29.69,"metric":"percent"},{"benchmark":"amc-23","model":"falcon3-7b","score":40,"metric":"percent"},{"benchmark":"amc-23","model":"gemma-3-12b-it","score":66.88,"metric":"percent"},{"benchmark":"amc-23","model":"gemma-3-1b-it","score":19.22,"metric":"percent"},{"benchmark":"amc-23","model":"gemma-3-27b-it","score":77.81,"metric":"percent"},{"benchmark":"amc-23","model":"gemma-3-4b-it","score":48.12,"metric":"percent"},{"benchmark":"amc-23","model":"llama-3.1-8b-base","score":22.81,"metric":"percent"},{"benchmark":"amc-23","model":"llama-3.2-1.24b-base","score":7.19,"metric":"percent"},{"benchmark":"amc-23","model":"llama-3.2-3b-base","score":22.66,"metric":"percent"},{"benchmark":"amc-23","model":"llama-3.3-70b","score":39.38,"metric":"percent"},{"benchmark":"amc-23","model":"llama-4-scout-17b","score":69.06,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-0.5b","score":12.5,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-1.5b","score":24.06,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-32b-instruct","score":68.75,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-3b","score":39.84,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-72b-instruct","score":67.34,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-7b","score":53.91,"metric":"percent"},{"benchmark":"amc-23","model":"qwen3-0.8b","score":27.97,"metric":"percent"},{"benchmark":"amc-23","model":"qwen3-1.7b","score":46.09,"metric":"percent"},{"benchmark":"amc-23","model":"qwen3-32b","score":67.34,"metric":"percent"},{"benchmark":"amc-23","model":"qwen3-4b","score":66.88,"metric":"percent"},{"benchmark":"amc-23","model":"qwen3-8b","score":70.78,"metric":"percent"},{"benchmark":"androidworld","model":"gemma-3-27b-vl","score":4.4,"metric":"percent"},{"benchmark":"androidworld","model":"glm-4.1v","score":41.7,"metric":"percent"},{"benchmark":"androidworld","model":"glm-4.5v","score":57,"metric":"percent"},{"benchmark":"api-bank","model":"llama-3-70b","score":85.1,"metric":"acc"},{"benchmark":"api-bank","model":"llama-3-8b","score":48.3,"metric":"acc"},{"benchmark":"api-bank","model":"llama-3.1-405b","score":92,"metric":"acc"},{"benchmark":"api-bank","model":"llama-3.1-70b","score":90,"metric":"acc"},{"benchmark":"api-bank","model":"llama-3.1-8b","score":82.6,"metric":"acc"},{"benchmark":"arc-agi-1","model":"claude-opus-4","score":22.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4","score":23.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro","score":41,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5","score":65.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini","score":54.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-oss-20b-medium","score":18.62,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4","score":66.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"ling-1t","score":43.81,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v3.1-terminus","score":14.69,"metric":"percent"},{"benchmark":"arc-agi-1","model":"kimi-k2-0905","score":14.06,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5","score":22.19,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro","score":18.94,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3","score":75.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-mini","score":34.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-pro","score":59.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o4-mini","score":58.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3-8b-thinking","score":4.38,"metric":"percent"},{"benchmark":"arc-agi-1","model":"ring-mini-2.0","score":20.12,"metric":"percent"},{"benchmark":"arc-agi-1","model":"ring-1t-preview","score":50.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro","score":45.44,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v3.1-terminus-thinking","score":40.62,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3-235b-a22b-thinking-2507","score":48.12,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5","score":51.88,"metric":"percent"},{"benchmark":"arc-agi-1","model":"ring-flash-linear-2.0","score":28.31,"metric":"percent"},{"benchmark":"arc-agi-1","model":"ring-flash-2.0","score":33.06,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3-32b-thinking-2504","score":8.75,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash","score":30.88,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-oss-120b-medium","score":30.44,"metric":"percent"},{"benchmark":"arc-agi-1","model":"seed-oss-36b-instruct","score":32,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3-next-80b-a3b-thinking","score":44.25,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-pro","score":70.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4-thinking","score":66.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-sonnet-thinking-32k","score":63.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-high","score":65.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4-20250514-thinking-16k","score":35.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-medium","score":56.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-sonnet-thinking-8k","score":46.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-sonnet-thinking-16k","score":48.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-high","score":60.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o4-mini-high","score":58.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4-20250514-thinking-16k","score":40,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-sonnet-thinking-1k","score":31,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-pro-high","score":59.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro-thinking-32k","score":37,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4-20250514-thinking-8k","score":30.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-high","score":54.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro-thinking-16k","score":41,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-medium","score":37.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-preview-low","score":75.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro-preview-06-05","score":33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro-preview-thinking-1k","score":31.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-mini-high","score":34.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-medium","score":53.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro-thinking-8k","score":29.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-nano-high","score":16.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-thinking-24k","score":32.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"architects","score":56,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o4-mini-medium","score":41.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-thinking-1k","score":16,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-thinking-8k","score":25.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4-20250514-thinking-8k","score":29,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-mini-medium","score":22.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-pro-low","score":44.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-low","score":41.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-thinking-16k","score":33.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-pro-medium","score":57,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-low","score":44,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-05-20","score":33.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o4-mini-low","score":21.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-minimal","score":5.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"icecuber","score":17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-r1","score":15.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"codex-mini-latest","score":27.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3-235b-a22b-instruct-2507","score":11,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-r1-0528","score":21.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-3.7-sonnet-thinking-8k","score":21.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-nano-medium","score":20.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4-20250514-thinking-1k","score":28,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o1-mini","score":14,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-low","score":26.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-4.5","score":10.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-3.7-sonnet-thinking-16k","score":28.6,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-4.1","score":5.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-3-mini","score":16.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-3.7-sonnet-thinking-1k","score":11.6,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-3.7-sonnet","score":13.6,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-4o","score":4.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4","score":1.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4","score":1.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro","score":4.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5","score":9.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini","score":4.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4","score":16,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3","score":6.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-mini","score":3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-pro","score":4.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o4-mini","score":6.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-pro","score":18.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4-thinking","score":16,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking-32k","score":13.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-high","score":9.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4-20250514-thinking-16k","score":8.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-medium","score":7.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking-8k","score":6.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking-16k","score":6.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-high","score":6.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o4-mini-high","score":6.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4-20250514-thinking-16k","score":5.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking-1k","score":5.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-pro-high","score":4.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-thinking-32k","score":4.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4-20250514-thinking-8k","score":4.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-high","score":4.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-thinking-16k","score":4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-medium","score":4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-preview-low","score":4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-preview-06-05","score":3.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4.5","score":3.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-preview-thinking-1k","score":3.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-mini-high","score":3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-medium","score":3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-thinking-8k","score":2.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-nano-high","score":2.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-thinking-24k","score":2.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"architects","score":2.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o4-mini-medium","score":2.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-thinking-1k","score":2.2,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-thinking-8k","score":2.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4-20250514-thinking-8k","score":2.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-mini-medium","score":2.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-pro-low","score":2.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-low","score":2,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-thinking-16k","score":2,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-pro-medium","score":1.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-low","score":1.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-05-20","score":1.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o4-mini-low","score":1.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-minimal","score":1.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"icecuber","score":1.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.0-flash","score":1.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-r1","score":1.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"codex-mini-latest","score":1.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"qwen3-235b-a22b-instruct-2507","score":1.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-r1-0528","score":1.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-3.7-sonnet-thinking-8k","score":0.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-nano-medium","score":0.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4-20250514-thinking-1k","score":0.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o1-mini","score":0.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-low","score":0.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-1.5-pro","score":0.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4.5","score":0.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-3.7-sonnet-thinking-16k","score":0.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4.1","score":0.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-3-mini","score":0.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-3.7-sonnet-thinking-1k","score":0.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-3.7-sonnet","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4o","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4o-mini","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4.1-nano","score":0,"metric":"percent"},{"benchmark":"arc-average","model":"llama-1b","score":41.6,"metric":"percent"},{"benchmark":"arc-average","model":"llama-1b-pretrained","score":49.2,"metric":"percent"},{"benchmark":"arc-average","model":"qwen2.5-1.5b-instruct","score":46.2,"metric":"percent"},{"benchmark":"arc-average","model":"qwen2.5-1.5b-pretrained","score":58.5,"metric":"percent"},{"benchmark":"arc-average","model":"smollm1-1.7b-instruct","score":43.7,"metric":"percent"},{"benchmark":"arc-average","model":"smollm1-1.7b-pretrained","score":59.9,"metric":"percent"},{"benchmark":"arc-average","model":"smollm2-1.7b-instruct","score":51.7,"metric":"percent"},{"benchmark":"arc-average","model":"smollm2-1.7b-pretrained","score":60.5,"metric":"percent"},{"benchmark":"arc-average","model":"smollm2-135m-base","score":43.9,"metric":"percent"},{"benchmark":"arc-average","model":"smollm2-135m-instruct","score":37.3,"metric":"percent"},{"benchmark":"arc-average","model":"smollm2-135m-pretrained","score":43.9,"metric":"percent"},{"benchmark":"arc-cf","model":"smollm3-3b","score":65.61,"metric":"percent"},{"benchmark":"arc-challenge","model":"claude-3-haiku","score":89.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"claude-3-sonnet","score":93.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"claude-3-opus","score":96.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"command-r-plus","score":71,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon-h1-0.5b-instruct","score":37.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon-h1-1.5b","score":42.06,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon-h1-1.5b-deep","score":43.86,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon-h1-34b-instruct","score":61.01,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon-h1-3b","score":49.57,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon-h1-7b","score":59.98,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon3-10b","score":54.44,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon3-1b","score":43.09,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon3-3b","score":48.21,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon3-7b","score":54.35,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2-27b","score":71.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2-2b","score":42.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2-7b","score":53.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2-9b","score":68.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-12b-it","score":51.96,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-1b-it","score":34.13,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-270m-it","score":28.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-27b-it","score":54.52,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-4b-it","score":44.88,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-pt-270m","score":29,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-pt-27b","score":61.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"granite-3.3-8b-base","score":50.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"jamba-1.5-large","score":93,"metric":"percent"},{"benchmark":"arc-challenge","model":"jamba-1.5-mini","score":85.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-70b","score":94.4,"metric":"acc"},{"benchmark":"arc-challenge","model":"llama-3-70b-base","score":93.1,"metric":"acc_char"},{"benchmark":"arc-challenge","model":"llama-3-8b","score":82.4,"metric":"acc"},{"benchmark":"arc-challenge","model":"llama-3-8b-base","score":79.4,"metric":"acc_char"},{"benchmark":"arc-challenge","model":"llama-3.1-405b","score":96.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-405b","score":96.9,"metric":"acc"},{"benchmark":"arc-challenge","model":"llama-3.1-405b-base","score":96.1,"metric":"acc_char"},{"benchmark":"arc-challenge","model":"llama-3.1-70b","score":94.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-70b","score":94.8,"metric":"acc"},{"benchmark":"arc-challenge","model":"llama-3.1-70b-base","score":92.9,"metric":"acc_char"},{"benchmark":"arc-challenge","model":"llama-3.1-8b","score":83.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-8b","score":83.4,"metric":"acc"},{"benchmark":"arc-challenge","model":"llama-3.1-8b-base","score":52.39,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-8b-base","score":79.7,"metric":"acc_char"},{"benchmark":"arc-challenge","model":"llama-3.1-nemotron-70b","score":69.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-1.24b-base","score":34.64,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-3b","score":78.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-3b-base","score":44.88,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.3-70b","score":63.65,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-4-scout-17b","score":56.14,"metric":"percent"},{"benchmark":"arc-challenge","model":"ministral-8b","score":71.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-small-3-24b-base","score":91.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"nova-lite","score":92.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"nova-micro","score":90.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"nova-pro","score":94.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-3.5-mini-instruct","score":84.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-3.5-moe-instruct","score":91,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-4-mini","score":83.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2-72b-instruct","score":68.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-0.5b","score":33.28,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-1.5b","score":40.53,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-14b-instruct","score":67.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-32b-instruct","score":44.54,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-3b","score":43.77,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-72b-instruct","score":46.59,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-7b","score":41.38,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-coder-32b-instruct","score":70.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-coder-7b-instruct","score":60.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-0.8b","score":31.06,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-1.7b","score":34.81,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-32b","score":48.98,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-4b","score":37.71,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-8b","score":42.06,"metric":"percent"},{"benchmark":"arc-challenge","model":"trlm-135m","score":40.61,"metric":"percent"},{"benchmark":"arc-challenge","model":"rnd1-base-0910","score":63.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"dream-7b-instruct","score":59.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"llada-8b-instruct","score":47.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-30b-a3b","score":55.7,"metric":"percent"},{"benchmark":"arc-challenge-chat","model":"qwen2.5-72b-instruct","score":96.2,"metric":"percent"},{"benchmark":"arc-challenge-multilingual","model":"llama-3.3-70b","score":42.9,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-2-2b","score":73.2,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-2-7b","score":81.5,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-3-pt-270m","score":57.7,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-3-pt-27b","score":89,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-r1","score":93.2,"metric":"percent"},{"benchmark":"arena-hard","model":"gemini-2.5-pro","score":96.4,"metric":"percent"},{"benchmark":"arena-hard","model":"grok-3-beta-think","score":null,"metric":"percent"},{"benchmark":"arena-hard","model":"o1","score":92.1,"metric":"percent"},{"benchmark":"arena-hard","model":"o1-2024-12-17","score":92.1,"metric":"percent"},{"benchmark":"arena-hard","model":"o3-mini","score":89,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen3-235b-a22b","score":95.6,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen3-32b","score":93.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"claude-opus-4","score":51.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"deepseek-v3.1-thinking","score":61.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemini-2.5-flash-thinking","score":56.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"kimi-k2","score":66.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-235b-a22b","score":79.2,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-235b-a22b-thinking-2507","score":79.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-30b-a3b","score":69,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-30b-a3b-thinking-2507","score":56,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-32b-nothinking","score":34.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-32b-thinking","score":48.4,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-max-instruct-preview","score":86.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-moe-2507","score":88.2,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-next-80b-a3b-instruct","score":82.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-next-80b-a3b-thinking","score":62.3,"metric":"percent"},{"benchmark":"astabench","model":"claude-3.5-haiku","score":20.3,"metric":"percent"},{"benchmark":"astabench","model":"claude-3.7-sonnet","score":16.2,"metric":"percent"},{"benchmark":"astabench","model":"claude-sonnet-4","score":53,"metric":"percent"},{"benchmark":"astabench","model":"gemini-2.5-flash","score":25.7,"metric":"percent"},{"benchmark":"astabench","model":"gpt-4.1","score":33,"metric":"percent"},{"benchmark":"astabench","model":"gpt-4o","score":16,"metric":"percent"},{"benchmark":"astabench","model":"gpt-5","score":43.3,"metric":"percent"},{"benchmark":"astabench","model":"gpt-5-mini","score":31.5,"metric":"percent"},{"benchmark":"astabench","model":"llama-4-scout-17b","score":12.4,"metric":"percent"},{"benchmark":"astabench","model":"o3","score":39.8,"metric":"percent"},{"benchmark":"astabench","model":"o3-2025-04-16","score":2.6,"metric":"percent"},{"benchmark":"astabench","model":"gpt-4.1-2025-04-14","score":2.4,"metric":"percent"},{"benchmark":"astabench","model":"claude-sonnet-4-20250514","score":2.3,"metric":"percent"},{"benchmark":"astabench","model":"gemini-2.5-pro","score":2.2,"metric":"percent"},{"benchmark":"astabench","model":"gemini-2.5-flash-2024-05","score":2.1,"metric":"percent"},{"benchmark":"astabench","model":"claude-3.5-haiku-20241022","score":1.9,"metric":"percent"},{"benchmark":"astabench","model":"youcom-search-api","score":1.6,"metric":"percent"},{"benchmark":"astabench","model":"llama-4-scout-17b-16e","score":1.6,"metric":"percent"},{"benchmark":"astabench","model":"gpt-5-mini-2025-08","score":1.1,"metric":"percent"},{"benchmark":"astabench","model":"gpt-5-2025-08-07","score":1.1,"metric":"percent"},{"benchmark":"astabench","model":"gpt-4o-2024-08-06","score":0.5,"metric":"percent"},{"benchmark":"autocodebench","model":"claude-opus-4-thinking","score":52.4,"metric":"percent"},{"benchmark":"autocodebench","model":"claude-sonnet-4-thinking","score":51.1,"metric":"percent"},{"benchmark":"autocodebench","model":"o3-high","score":51.1,"metric":"percent"},{"benchmark":"autocodebench","model":"grok-4","score":50.9,"metric":"percent"},{"benchmark":"autocodebench","model":"claude-opus-4","score":50.9,"metric":"percent"},{"benchmark":"autocodebench","model":"deepseek-r1-0528","score":50.2,"metric":"percent"},{"benchmark":"autocodebench","model":"o4-mini","score":50,"metric":"percent"},{"benchmark":"autocodebench","model":"claude-sonnet-4","score":49.3,"metric":"percent"},{"benchmark":"autocodebench","model":"gemini-2.5-pro","score":48.7,"metric":"percent"},{"benchmark":"autocodebench","model":"deepseek-v3-0324","score":48.1,"metric":"percent"},{"benchmark":"autocodebench","model":"gpt-4.1-2025-04-14","score":48,"metric":"percent"},{"benchmark":"autocodebench","model":"kimi-k2-instruct-0711","score":47.8,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-235b-a22b-thinking-2507","score":47.7,"metric":"percent"},{"benchmark":"autocodebench","model":"glm-4.5","score":46.6,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen-3-235b-a22b-thinking","score":45.9,"metric":"percent"},{"benchmark":"autocodebench","model":"gemini-2.5-flash","score":45.7,"metric":"percent"},{"benchmark":"autocodebench","model":"seed1.6","score":45.3,"metric":"percent"},{"benchmark":"autocodebench","model":"seed1.6-thinking","score":45,"metric":"percent"},{"benchmark":"autocodebench","model":"seed1.6-thinking","score":44.7,"metric":"percent"},{"benchmark":"autocodebench","model":"hunyuan-turbos","score":43.8,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-235b-a22b-instruct-2507","score":43.1,"metric":"percent"},{"benchmark":"autocodebench","model":"seed1.6","score":42.9,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-32b-thinking","score":41.7,"metric":"percent"},{"benchmark":"autocodebench","model":"gpt-4o-2024-11-20","score":41.1,"metric":"percent"},{"benchmark":"autocodebench","model":"glm-4.5-air","score":40.8,"metric":"percent"},{"benchmark":"autocodebench","model":"ernie-x1","score":39.6,"metric":"percent"},{"benchmark":"autocodebench","model":"deepseek-coder-v2-instruct","score":37.7,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-14b-thinking","score":37.6,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen2.5-coder-32b-instruct","score":35.8,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen2.5-72b-instruct","score":34.3,"metric":"percent"},{"benchmark":"autocodebench","model":"hunyuan-coder-b8-preview","score":33.4,"metric":"percent"},{"benchmark":"autocodebench","model":"seed-coder-8b-instruct","score":32.3,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-32b","score":31,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-14b","score":28.6,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-8b-thinking","score":28.5,"metric":"percent"},{"benchmark":"autocodebench","model":"deepseek-coder-33b-instruct","score":28.5,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-4b-thinking","score":24.3,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-8b","score":23.3,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen2.5-coder-7b-instruct","score":22.5,"metric":"percent"},{"benchmark":"autocodebench","model":"deepseek-coder-6.7b-instruct","score":20.5,"metric":"percent"},{"benchmark":"autocodebench","model":"opencoder-8b-instruct","score":19.3,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"claude-opus-4","score":64.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"claude-sonnet-4","score":62,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"deepseek-r1","score":61.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"deepseek-v3","score":56.8,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"gemini-2.5-pro","score":59.1,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"gpt-4.1","score":56.9,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"grok-4","score":63,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"o3-high","score":63.2,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"o4-mini","score":60.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-235b-a22b","score":57.3,"metric":"percent"},{"benchmark":"balrog","model":"grok-4","score":43.6,"metric":"percent"},{"benchmark":"balrog","model":"gemini-2.5-pro-exp-03.25","score":43.3,"metric":"percent"},{"benchmark":"balrog","model":"deepseek-r1","score":34.9,"metric":"percent"},{"benchmark":"balrog","model":"gemini-2.5-flash","score":33.5,"metric":"percent"},{"benchmark":"balrog","model":"gpt-5-minimal-think","score":32.8,"metric":"percent"},{"benchmark":"balrog","model":"claude-3.5-sonnet-20241022","score":32.6,"metric":"percent"},{"benchmark":"balrog","model":"gpt-4o-2024-05-13","score":32.3,"metric":"percent"},{"benchmark":"balrog","model":"grok-3-beta","score":29.5,"metric":"percent"},{"benchmark":"balrog","model":"reka-flash-3","score":29.2,"metric":"percent"},{"benchmark":"balrog","model":"llama-3.1-70b-instruct","score":27.9,"metric":"percent"},{"benchmark":"balrog","model":"llama-3.2-90b-instruct","score":27.3,"metric":"percent"},{"benchmark":"balrog","model":"llama-3.3-70b-instruct","score":23,"metric":"percent"},{"benchmark":"balrog","model":"gemini-1.5-pro-002","score":21,"metric":"percent"},{"benchmark":"balrog","model":"deepseek-r1-distill-qwen-32b","score":19.5,"metric":"percent"},{"benchmark":"balrog","model":"claude-3.5-haiku-20241022","score":19.3,"metric":"percent"},{"benchmark":"balrog","model":"mistral-nemo-instruct-2407","score":17.6,"metric":"percent"},{"benchmark":"balrog","model":"gpt-4o-mini-2024-07-18","score":17.4,"metric":"percent"},{"benchmark":"balrog","model":"llama-3.2-11b-instruct","score":16.8,"metric":"percent"},{"benchmark":"balrog","model":"qwen2.5-72b-instruct","score":16.2,"metric":"percent"},{"benchmark":"balrog","model":"llama-3.1-8b-instruct","score":15.1,"metric":"percent"},{"benchmark":"balrog","model":"gemini-1.5-flash-002","score":14.6,"metric":"percent"},{"benchmark":"balrog","model":"qwen2-vl-72b-instruct","score":12.8,"metric":"percent"},{"benchmark":"balrog","model":"phi-4","score":11.6,"metric":"percent"},{"benchmark":"balrog","model":"llama-3.2-3b-instruct","score":10.1,"metric":"percent"},{"benchmark":"balrog","model":"qwen2.5-7b-instruct","score":7.8,"metric":"percent"},{"benchmark":"balrog","model":"llama-3.2-1b-instruct","score":6.6,"metric":"percent"},{"benchmark":"balrog","model":"qwen2-vl-7b-instruct","score":3.7,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3","score":91,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3-base","score":88.4,"metric":"percent"},{"benchmark":"bbh","model":"ernie-4.5","score":94.3,"metric":"percent"},{"benchmark":"bbh","model":"falcon-3-1b-base","score":6.76,"metric":"percent"},{"benchmark":"bbh","model":"falcon-e-1b-base","score":12.28,"metric":"percent"},{"benchmark":"bbh","model":"falcon-h1-0.5b-instruct","score":42.91,"metric":"percent"},{"benchmark":"bbh","model":"falcon-h1-1.5b","score":46.47,"metric":"percent"},{"benchmark":"bbh","model":"falcon-h1-1.5b-deep","score":54.43,"metric":"percent"},{"benchmark":"bbh","model":"falcon-h1-34b-instruct","score":70.68,"metric":"percent"},{"benchmark":"bbh","model":"falcon-h1-3b","score":53.69,"metric":"percent"},{"benchmark":"bbh","model":"falcon-h1-7b","score":62.28,"metric":"percent"},{"benchmark":"bbh","model":"falcon3-10b","score":58.09,"metric":"percent"},{"benchmark":"bbh","model":"falcon3-1b","score":34.47,"metric":"percent"},{"benchmark":"bbh","model":"falcon3-3b","score":45.02,"metric":"percent"},{"benchmark":"bbh","model":"falcon3-7b","score":52.12,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-12b-it","score":85.7,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-1b-it","score":39.1,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-270m-it","score":26.7,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-27b-it","score":87.6,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-4b-it","score":72.2,"metric":"percent"},{"benchmark":"bbh","model":"glm-4.5-base","score":86.2,"metric":"percent"},{"benchmark":"bbh","model":"gpt-4.1","score":84.1,"metric":"percent"},{"benchmark":"bbh","model":"kimi-k2-base","score":88.7,"metric":"percent"},{"benchmark":"bbh","model":"llama-1b","score":27.6,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-70b-base","score":81.3,"metric":"average/em"},{"benchmark":"bbh","model":"llama-3-8b-base","score":61.1,"metric":"average/em"},{"benchmark":"bbh","model":"llama-3.1-405b-base","score":85.9,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-405b-base","score":85.9,"metric":"average/em"},{"benchmark":"bbh","model":"llama-3.1-70b-base","score":81.6,"metric":"average/em"},{"benchmark":"bbh","model":"llama-3.1-8b-base","score":48.58,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-8b-base","score":64.2,"metric":"average/em"},{"benchmark":"bbh","model":"llama-3.2-1.24b-base","score":33.21,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.2-3b-base","score":41.47,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.3-70b","score":69.15,"metric":"percent"},{"benchmark":"bbh","model":"llama-spark-8b","score":29.77,"metric":"percent"},{"benchmark":"bbh","model":"llama-4-maverick-base","score":87.1,"metric":"percent"},{"benchmark":"bbh","model":"llama-4-scout-17b","score":64.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-max","score":89.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-0.5b","score":33.26,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-1.5b","score":42.41,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-1.5b-instruct","score":35.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-32b-instruct","score":68.72,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-3b","score":46.55,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-72b-instruct","score":86.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-7b","score":53.76,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-0.6b","score":11.75,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-0.8b","score":32.95,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-1.7b","score":35.18,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-235b-a22b","score":84.5,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-235b-a22b-base","score":88.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-32b","score":62.47,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-4b","score":51.07,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-8b","score":47.47,"metric":"percent"},{"benchmark":"bbh","model":"smollm1-1.7b-instruct","score":25.7,"metric":"percent"},{"benchmark":"bbh","model":"smollm2-1.7b-base","score":12.64,"metric":"percent"},{"benchmark":"bbh","model":"smollm2-1.7b-instruct","score":32.2,"metric":"percent"},{"benchmark":"bbh","model":"smollm2-135m-instruct","score":28.2,"metric":"percent"},{"benchmark":"bbh","model":"smollm2-360m-base","score":5.54,"metric":"percent"},{"benchmark":"bbl-hard","model":"llama-3.1-405b-base","score":85.9,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-4o","score":45.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-5","score":62.6,"metric":"percent"},{"benchmark":"tau2-airline","model":"o3","score":64.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4.1","score":82.4,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-4o","score":63.4,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-5","score":81.1,"metric":"percent"},{"benchmark":"tau2-retail","model":"o3","score":80.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.1","score":71.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-sonnet-4","score":64.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-pro","score":54.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5","score":96.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-high","score":84.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-minimal","score":67,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-120b","score":65.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"grok-4","score":74.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"grok-code-fast-1","score":75.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2-instruct-0905","score":73.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"o3","score":80.7,"metric":"percent"},{"benchmark":"beyondaime","model":"qwen3-moe-2507","score":57.6,"metric":"percent"},{"benchmark":"bfcl","model":"llama-3-70b","score":83,"metric":"acc"},{"benchmark":"bfcl","model":"llama-3-8b","score":60.3,"metric":"acc"},{"benchmark":"bfcl","model":"llama-3.1-3b","score":92.3,"metric":"percent"},{"benchmark":"bfcl","model":"llama-3.1-405b","score":88.5,"metric":"acc"},{"benchmark":"bfcl","model":"llama-3.1-70b","score":84.8,"metric":"acc"},{"benchmark":"bfcl","model":"llama-3.1-8b","score":76.1,"metric":"acc"},{"benchmark":"bfcl","model":"qwen3-1.7b","score":89.5,"metric":"percent"},{"benchmark":"bfcl","model":"qwen3-4b","score":95,"metric":"percent"},{"benchmark":"bfcl","model":"smollm3-3b","score":92.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"deepseek-r1","score":56.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemini-2.5-flash-thinking","score":68.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemini-2.5-pro","score":62.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"glm-4.5","score":77.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"o1","score":67.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"o1-2024-12-17","score":67.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"o3-mini","score":64.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-235b-a22b","score":70.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-235b-a22b-thinking-2507","score":71.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-30b-a3b","score":65.1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-30b-a3b-thinking-2507","score":72.4,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-32b","score":70.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-32b-nothinking","score":63,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-32b-thinking","score":70.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-next-80b-a3b-instruct","score":70.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-next-80b-a3b-thinking","score":72,"metric":"percent"},{"benchmark":"big-bench","model":"gemma-2-2b","score":35.2,"metric":"percent"},{"benchmark":"big-bench","model":"gemma-2-7b","score":55.1,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemma-3-12b-it","score":16.3,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemma-3-1b-it","score":7.2,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemma-3-4b-it","score":11,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"ling-1t","score":47.34,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"deepseek-v3.1-terminus","score":34.83,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"kimi-k2-0905","score":39.75,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gpt-5","score":42.86,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemini-2.5-pro","score":29.08,"metric":"percent"},{"benchmark":"biolp-bench","model":"grok-code-fast-1","score":19.9,"metric":"percent"},{"benchmark":"bird-sql","model":"gemma-3-27b-it","score":54.4,"metric":"percent"},{"benchmark":"blend","model":"qwen2.5-72b-instruct","score":75.4,"metric":"percent"},{"benchmark":"blink","model":"claude-3.7-sonnet","score":62.3,"metric":"percent"},{"benchmark":"blink","model":"gemma-3-27b-vl","score":52.9,"metric":"percent"},{"benchmark":"blink","model":"gemma-3-27b-it","score":53.3,"metric":"percent"},{"benchmark":"blink","model":"glm-4.1v","score":65.1,"metric":"percent"},{"benchmark":"blink","model":"glm-4.5v","score":65.3,"metric":"percent"},{"benchmark":"blink","model":"gpt-4o","score":60,"metric":"percent"},{"benchmark":"blink","model":"internvl-8b","score":55.5,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-235b-a22b-thinking","score":67.1,"metric":"percent"},{"benchmark":"blink","model":"kimi-vl-a3b-thinking-2506","score":53.5,"metric":"percent"},{"benchmark":"blink","model":"mimo-vl-7b-rl","score":62.4,"metric":"percent"},{"benchmark":"blink","model":"mimo-vl-7b-sft","score":62.5,"metric":"percent"},{"benchmark":"blink","model":"qwen2.5-vl-7b","score":56.4,"metric":"percent"},{"benchmark":"blink","model":"step-3","score":62.7,"metric":"percent"},{"benchmark":"blink","model":"gemini-2.5-pro","score":70.6,"metric":"percent"},{"benchmark":"blink","model":"gpt-5","score":71,"metric":"percent"},{"benchmark":"blink","model":"claude-opus-4.1","score":64.1,"metric":"percent"},{"benchmark":"blink","model":"seed1.5-vl-thinking","score":72.1,"metric":"percent"},{"benchmark":"blink","model":"qwen2.5-vl-72b","score":61.7,"metric":"percent"},{"benchmark":"blink","model":"gemini-2.5-pro","score":71.86,"metric":"percent"},{"benchmark":"blink","model":"seed1.5-vl-thinking","score":72.38,"metric":"percent"},{"benchmark":"blink","model":"dots-vlm1","score":66.33,"metric":"percent"},{"benchmark":"boolq","model":"gemma-2-27b","score":84.8,"metric":"percent"},{"benchmark":"boolq","model":"gemma-2-2b","score":69.4,"metric":"percent"},{"benchmark":"boolq","model":"gemma-2-7b","score":83.2,"metric":"percent"},{"benchmark":"boolq","model":"gemma-2-9b","score":84.2,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3-pt-270m","score":61.4,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3n-e2b","score":76.4,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3n-e2b-instructed-litert-preview","score":76.4,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3n-e4b","score":81.6,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3n-e4b-instructed-litert-preview","score":81.6,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-65b","score":85.3,"metric":"percent"},{"benchmark":"boolq","model":"llama-3-70b-base","score":79,"metric":"acc_char"},{"benchmark":"boolq","model":"llama-3-8b-base","score":75.7,"metric":"acc_char"},{"benchmark":"boolq","model":"llama-3.1-405b-base","score":80,"metric":"acc_char"},{"benchmark":"boolq","model":"llama-3.1-70b-base","score":79.4,"metric":"acc_char"},{"benchmark":"boolq","model":"llama-3.1-8b-base","score":75,"metric":"acc_char"},{"benchmark":"boolq","model":"phi-3.5-mini-instruct","score":78,"metric":"percent"},{"benchmark":"boolq","model":"phi-3.5-moe-instruct","score":84.6,"metric":"percent"},{"benchmark":"boolq","model":"phi-4-mini","score":81.2,"metric":"percent"},{"benchmark":"boolq","model":"trlm-135m","score":62.17,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-sonnet-4","score":14.7,"metric":"avg@3"},{"benchmark":"browsecomp","model":"claude-sonnet-4.5","score":19.6,"metric":"avg@3"},{"benchmark":"browsecomp","model":"deepseek-v3.1","score":30,"metric":"avg@3"},{"benchmark":"browsecomp","model":"deepseek-v3.1-terminus","score":38.5,"metric":"avg@3"},{"benchmark":"browsecomp","model":"deepseek-v3.2-exp","score":40.1,"metric":"avg@3"},{"benchmark":"browsecomp","model":"glm-4.5","score":26.4,"metric":"avg@3"},{"benchmark":"browsecomp","model":"glm-4.6","score":45.1,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5","score":54.9,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2","score":14.1,"metric":"avg@3"},{"benchmark":"browsecomp","model":"o3","score":49.7,"metric":"avg@3"},{"benchmark":"browsecomp","model":"o4-mini","score":28.3,"metric":"avg@3"},{"benchmark":"browsecomp","model":"openai-deepresearch","score":51.5,"metric":"avg@3"},{"benchmark":"browsecomp","model":"tongyi-deepresearch","score":43.4,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"claude-sonnet-4","score":29.1,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"deepseek-v3.1","score":49.2,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"deepseek-v3.1-terminus","score":45,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"deepseek-v3.2-exp","score":47.9,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"deepseek-v3.1-thinking","score":49.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"glm-4.5","score":37.5,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"kimi-k2","score":28.8,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"o3","score":58.1,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"openai-deepresearch","score":42.9,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"tongyi-deepresearch","score":46.7,"metric":"avg@3"},{"benchmark":"buzzbench","model":"claude-3.5-haiku","score":53.34,"metric":"percent"},{"benchmark":"buzzbench","model":"claude-3.5-sonnet","score":61.94,"metric":"percent"},{"benchmark":"buzzbench","model":"claude-3.7-sonnet","score":68.2,"metric":"percent"},{"benchmark":"buzzbench","model":"deepseek-r1","score":62.73,"metric":"percent"},{"benchmark":"buzzbench","model":"gemini-1.5-pro","score":54.9,"metric":"percent"},{"benchmark":"buzzbench","model":"gemini-2.0-flash","score":54.39,"metric":"percent"},{"benchmark":"buzzbench","model":"gemini-2.5-pro","score":71.09,"metric":"percent"},{"benchmark":"buzzbench","model":"gpt-4.1","score":67.1,"metric":"percent"},{"benchmark":"buzzbench","model":"gpt-4o","score":69.11,"metric":"percent"},{"benchmark":"buzzbench","model":"o1","score":59.28,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3","score":87.3,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3-base","score":90.1,"metric":"percent"},{"benchmark":"c-eval","model":"ernie-4.5","score":90.6,"metric":"percent"},{"benchmark":"c-eval","model":"glm-4.5-base","score":86.9,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-4.1","score":77.9,"metric":"percent"},{"benchmark":"c-eval","model":"kimi-k2-base","score":92.5,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3.1-405b-base","score":72.5,"metric":"percent"},{"benchmark":"c-eval","model":"llama-4-maverick-base","score":80.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2.5-max","score":92.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2.5-72b-instruct","score":90.7,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-235b-a22b","score":86.1,"metric":"percent"},{"benchmark":"c3-bench","model":"deepseek-v3-base","score":78.6,"metric":"percent"},{"benchmark":"c3-bench","model":"glm-4.5-base","score":83.1,"metric":"percent"},{"benchmark":"c3-bench","model":"hunyuan-7b-instruct","score":68.5,"metric":"percent"},{"benchmark":"cfeval","model":"gemini-2.5-flash-thinking","score":1995,"metric":"ELO"},{"benchmark":"cfeval","model":"qwen3-235b-a22b-thinking-2507","score":2134,"metric":"ELO"},{"benchmark":"cfeval","model":"qwen3-30b-a3b-thinking-2507","score":2044,"metric":"ELO"},{"benchmark":"cfeval","model":"qwen3-32b-thinking","score":1986,"metric":"ELO"},{"benchmark":"cfeval","model":"qwen3-next-80b-a3b-thinking","score":2071,"metric":"ELO"},{"benchmark":"charades-sta","model":"qwen3-vl-235b-a22b-thinking","score":63.5,"metric":"percent"},{"benchmark":"charades-sta","model":"seed1.5-vl-thinking","score":64,"metric":"percent"},{"benchmark":"charades-sta","model":"internvl-8b","score":25.4,"metric":"percent"},{"benchmark":"charades-sta","model":"mimo-vl-7b-rl","score":50,"metric":"percent"},{"benchmark":"charades-sta","model":"mimo-vl-7b-sft","score":38.5,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen2.5-vl-7b","score":43.6,"metric":"percent"},{"benchmark":"chartmuseum","model":"gemma-3-27b-vl","score":23.9,"metric":"percent"},{"benchmark":"chartmuseum","model":"glm-4.1v","score":48.8,"metric":"percent"},{"benchmark":"chartmuseum","model":"glm-4.5v","score":55.3,"metric":"percent"},{"benchmark":"chartmuseum","model":"gpt-5-mini","score":63.3,"metric":"percent"},{"benchmark":"chartmuseum","model":"kimi-vl-a3b-thinking-2506","score":33.6,"metric":"percent"},{"benchmark":"chartmuseum","model":"step-3","score":40,"metric":"percent"},{"benchmark":"chartqa","model":"cambrian-1-34b","score":75.6,"metric":"percent"},{"benchmark":"chartqa","model":"cambrian-1-8b","score":73.3,"metric":"percent"},{"benchmark":"chartqa","model":"claude-3-haiku","score":81.7,"metric":"percent"},{"benchmark":"chartqa","model":"claude-3-opus","score":80.8,"metric":"percent"},{"benchmark":"chartqa","model":"claude-3.5-sonnet","score":90.8,"metric":"percent"},{"benchmark":"chartqa","model":"claude-3.7-sonnet","score":92.2,"metric":"percent"},{"benchmark":"chartqa","model":"fastvlm-0.5b","score":76,"metric":"percent"},{"benchmark":"chartqa","model":"fastvlm-1.5b","score":80.1,"metric":"percent"},{"benchmark":"chartqa","model":"fastvlm-7b","score":85,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-1.5-flash","score":85.4,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-1.5-pro","score":87.2,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-flash","score":79.5,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-3-27b-it","score":78,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-4o","score":86.7,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-4o-0513","score":85.7,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-4v","score":78.1,"metric":"percent"},{"benchmark":"chartqa","model":"internvl-8b","score":89.6,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2-8b","score":83.3,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2-llama-3-76b","score":88.4,"metric":"percent"},{"benchmark":"chartqa","model":"llama-3.2v-11b-instruct","score":83.4,"metric":"percent"},{"benchmark":"chartqa","model":"llama-3.2v-90b-instruct","score":85.5,"metric":"percent"},{"benchmark":"chartqa","model":"llama-4-maverick","score":90,"metric":"percent"},{"benchmark":"chartqa","model":"llama-4-maverick-17b-128e-instruct","score":90,"metric":"percent"},{"benchmark":"chartqa","model":"llama-4-maverick-17b-128e-base","score":85.3,"metric":"percent"},{"benchmark":"chartqa","model":"llama-4-maverick-base","score":85.3,"metric":"percent"},{"benchmark":"chartqa","model":"llama-4-scout-17b","score":88.8,"metric":"percent"},{"benchmark":"chartqa","model":"llama-4-scout-17b-16e","score":88.8,"metric":"percent"},{"benchmark":"chartqa","model":"llama-4-scout-17b-16e-base","score":83.4,"metric":"percent"},{"benchmark":"chartqa","model":"llama-4-scout-17b-base","score":83.4,"metric":"percent"},{"benchmark":"chartqa","model":"llava-1.5-13b","score":18.2,"metric":"percent"},{"benchmark":"chartqa","model":"llava-1.5-7b","score":17.8,"metric":"percent"},{"benchmark":"chartqa","model":"llava-onevision-72b","score":83.7,"metric":"percent"},{"benchmark":"chartqa","model":"llava-onevision-7b","score":80,"metric":"percent"},{"benchmark":"chartqa","model":"mimo-vl-7b-rl","score":91.7,"metric":"percent"},{"benchmark":"chartqa","model":"mimo-vl-7b-sft","score":92.9,"metric":"percent"},{"benchmark":"chartqa","model":"molmo-72b","score":87.3,"metric":"percent"},{"benchmark":"chartqa","model":"molmo-7b-d","score":84.1,"metric":"percent"},{"benchmark":"chartqa","model":"molmo-7b-o","score":80.4,"metric":"percent"},{"benchmark":"chartqa","model":"molmoe-1b","score":78,"metric":"percent"},{"benchmark":"chartqa","model":"moondream-9b-a2b","score":86.6,"metric":"percent"},{"benchmark":"chartqa","model":"paligemma-mix-3b","score":33.7,"metric":"percent"},{"benchmark":"chartqa","model":"phi-3.5-vision-4b","score":81.8,"metric":"percent"},{"benchmark":"chartqa","model":"pixtral-12b","score":81.8,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2-vl-72b","score":88.3,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2-vl-7b","score":83,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2.5-vl-7b","score":90.2,"metric":"percent"},{"benchmark":"chartqa","model":"xgen-mm-interleave-4b","score":60,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gemma-3-27b-vl","score":37.6,"metric":"percent"},{"benchmark":"chartqa-pro","model":"glm-4.1v","score":59.5,"metric":"percent"},{"benchmark":"chartqa-pro","model":"glm-4.5v","score":64,"metric":"percent"},{"benchmark":"chartqa-pro","model":"kimi-vl-a3b-thinking-2506","score":23.7,"metric":"percent"},{"benchmark":"chartqa-pro","model":"step-3","score":56.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-3.7-sonnet","score":89.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemma-3-27b-it","score":63.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4o","score":86.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl-8b","score":73.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"mimo-vl-7b-rl","score":86.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"mimo-vl-7b-sft","score":87,"metric":"percent"},{"benchmark":"charxiv-dq","model":"o3-high","score":95,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2.5-vl-7b","score":73.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2.5-vl-72b","score":88.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-2.5-pro","score":90.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"seed1.5-vl-thinking","score":89.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"dots-vlm1","score":92.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-3.7-sonnet","score":63,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemma-3-27b-it","score":29.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4o","score":52,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5","score":81.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-235b-a22b-thinking","score":66.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl-8b","score":37.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3-8b","score":37.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3.5-4b","score":39.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"keye-vl-8b","score":40,"metric":"percent"},{"benchmark":"charxiv-rq","model":"kimi-vl-a3b-thinking-2506","score":47.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"mimo-vl-7b-rl","score":56.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"mimo-vl-7b-sft","score":54.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"o3","score":78.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"o3-high","score":78.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-pro","score":67.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.1","score":63.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"dots-vlm1","score":64.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2.5-vl-7b","score":42.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"r-4b-base","score":56.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2.5-vl-72b","score":48.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-pro","score":68.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed1.5-vl-thinking","score":63.4,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v3","score":72,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v3-base","score":72.1,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"ernie-4.5","score":77.1,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"glm-4.5-base","score":76.1,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"gpt-4.1","score":64,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"kimi-k2-base","score":77.6,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"llama-4-maverick-base","score":53.5,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"qwen3-235b-a22b","score":63,"metric":"percent"},{"benchmark":"clockbench","model":"gemini-2.5-pro","score":13.3,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-r1","score":92.8,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v3-base","score":82.7,"metric":"percent"},{"benchmark":"cluewsc","model":"glm-4.5-base","score":83.5,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-4.1","score":78.1,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5-mini","score":77.5,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-4","score":76.2,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-3","score":75.2,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5","score":74.9,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-4.1-mini","score":74.6,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-sonnet-4","score":74,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-sonnet-4-thinking","score":74,"metric":"percent"},{"benchmark":"caselaw-v2","model":"deepseek-v3-0324","score":73.6,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gemini-2.5-pro","score":72.7,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-4-fast","score":72.7,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-4.1-opus-thinking","score":72.3,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-4-fast-thinking","score":71.4,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-opus-4.1","score":71.1,"metric":"percent"},{"benchmark":"caselaw-v2","model":"deepseek-r1","score":70.1,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-3.7-sonnet-thinking","score":70.1,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-4o-2024-11-20","score":69.8,"metric":"percent"},{"benchmark":"caselaw-v2","model":"o3","score":69.5,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gemini-2.5-flash","score":68.2,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-oss-120b","score":66.6,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-3.7-sonnet","score":66.2,"metric":"percent"},{"benchmark":"caselaw-v2","model":"glm-4.5","score":66.2,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-3-mini-fast-low-reasoning","score":65.9,"metric":"percent"},{"benchmark":"caselaw-v2","model":"qwen3-max-instruct-preview","score":65.3,"metric":"percent"},{"benchmark":"caselaw-v2","model":"o4-mini","score":64,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-3-mini-fast-high-reasoning","score":64,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5-nano","score":63.3,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-4o-2024-08-06","score":62.1,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-oss-20b","score":53.4,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-4.1-nano","score":51.4,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v3","score":94.8,"metric":"percent"},{"benchmark":"cmath","model":"ernie-4.5","score":96.7,"metric":"percent"},{"benchmark":"cmath","model":"gpt-4.1","score":92.8,"metric":"percent"},{"benchmark":"cmath","model":"qwen3-235b-a22b","score":95.7,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v3","score":88.2,"metric":"percent"},{"benchmark":"cmmlu","model":"ernie-4.5","score":90.2,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-4.1","score":78.1,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3.1-405b-base","score":73.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2.5-max","score":91.9,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2.5-72b-instruct","score":89.9,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-235b-a22b","score":87.5,"metric":"percent"},{"benchmark":"codeforces","model":"deepseek-r1","score":2029,"metric":"ELO"},{"benchmark":"codeforces-percentile","model":"deepseek-v3","score":51.6,"metric":"percent"},{"benchmark":"codeforces","model":"deepseek-v3.1","score":2091,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v3.1-terminus","score":2046,"metric":"ELO"},{"benchmark":"codeforces","model":"ling-1t","score":1901,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v3.1-terminus","score":1582,"metric":"ELO"},{"benchmark":"codeforces","model":"kimi-k2-0905","score":1574,"metric":"ELO"},{"benchmark":"codeforces","model":"gpt-5","score":1120,"metric":"ELO"},{"benchmark":"codeforces","model":"gemini-2.5-pro","score":1675,"metric":"ELO"},{"benchmark":"artifactsbench","model":"ling-1t","score":59.31,"metric":"percent"},{"benchmark":"artifactsbench","model":"deepseek-v3.1-terminus","score":43.29,"metric":"percent"},{"benchmark":"artifactsbench","model":"kimi-k2-0905","score":44.87,"metric":"percent"},{"benchmark":"artifactsbench","model":"gpt-5","score":41.04,"metric":"percent"},{"benchmark":"artifactsbench","model":"gemini-2.5-pro","score":60.28,"metric":"percent"},{"benchmark":"artifactsbench","model":"gpt-5","score":72.55,"metric":"percent"},{"benchmark":"artifactsbench","model":"claude-opus-4.1","score":59.76,"metric":"percent"},{"benchmark":"artifactsbench","model":"gemini-2.5-pro","score":57.74,"metric":"percent"},{"benchmark":"artifactsbench","model":"claude-sonnet-4-20250514","score":57.28,"metric":"percent"},{"benchmark":"artifactsbench","model":"gpt-oss-120b","score":56.91,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3-235b-a22b-thinking-2507","score":55.01,"metric":"percent"},{"benchmark":"artifactsbench","model":"o3-2025-04-16","score":54.04,"metric":"percent"},{"benchmark":"artifactsbench","model":"glm-4.5","score":51.33,"metric":"percent"},{"benchmark":"artifactsbench","model":"claude-3.7-sonnet-20250219","score":51.32,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3-235b-a22b-instruct-2507","score":50.62,"metric":"percent"},{"benchmark":"artifactsbench","model":"glm-4.5-air","score":48.9,"metric":"percent"},{"benchmark":"artifactsbench","model":"deepseek-r1-0528","score":47.73,"metric":"percent"},{"benchmark":"artifactsbench","model":"kimi-k2-instruct","score":47.65,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3-coder-480b-a35b-instruct","score":47.15,"metric":"percent"},{"benchmark":"artifactsbench","model":"gpt-4.1-2025-04-14","score":45.95,"metric":"percent"},{"benchmark":"artifactsbench","model":"deepseek-v3-0324","score":43.5,"metric":"percent"},{"benchmark":"artifactsbench","model":"deepseek-r1","score":41.41,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3-235b-a22b","score":41.09,"metric":"percent"},{"benchmark":"artifactsbench","model":"hunyuan-80b-a13b-instruct","score":40.95,"metric":"percent"},{"benchmark":"artifactsbench","model":"claude-3.5-sonnet-20241022","score":39.85,"metric":"percent"},{"benchmark":"artifactsbench","model":"kat-v1-40b","score":35.21,"metric":"percent"},{"benchmark":"artifactsbench","model":"gpt-4o","score":33.54,"metric":"percent"},{"benchmark":"codeforces","model":"deepseek-v3.2-exp","score":2121,"metric":"ELO"},{"benchmark":"codeforces-percentile","model":"ernie-4.5-21b-a3b-pt","score":21.7,"metric":"percent"},{"benchmark":"codeforces","model":"gemini-2.5-pro","score":2001,"metric":"ELO"},{"benchmark":"codeforces","model":"gpt-oss-120b","score":2622,"metric":"ELO"},{"benchmark":"codeforces","model":"gpt-oss-20b","score":2516,"metric":"ELO"},{"benchmark":"codeforces-percentile","model":"gpt-oss-20b-medium","score":82.25,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"ling-mini-2.0","score":59.5,"metric":"percent"},{"benchmark":"codeforces","model":"ling-flash-2.0","score":1600,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen3-32b-nothinking","score":678,"metric":"ELO"},{"benchmark":"codeforces","model":"seed-oss-36b-instruct","score":605,"metric":"ELO"},{"benchmark":"codeforces","model":"hunyuan-80b-a13b-instruct","score":683,"metric":"ELO"},{"benchmark":"codeforces","model":"o1","score":1891,"metric":"ELO"},{"benchmark":"codeforces","model":"o1-2024-12-17","score":1891,"metric":"ELO"},{"benchmark":"codeforces","model":"o1-mini","score":1650,"metric":"ELO"},{"benchmark":"codeforces","model":"o1-preview","score":1258,"metric":"ELO"},{"benchmark":"codeforces","model":"o3","score":2706,"metric":"ELO"},{"benchmark":"codeforces","model":"o3-mini","score":2036,"metric":"ELO"},{"benchmark":"codeforces","model":"o4-mini","score":2719,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen-3","score":2056,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen3-235b-a22b","score":2056,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen3-32b","score":1977,"metric":"ELO"},{"benchmark":"codeforces-percentile","model":"qwen3-4b-instruct-2507","score":55.4,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"qwen3-8b-nothinking-2504","score":28.2,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"qwen3-8b-thinking","score":73.31,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"ring-mini-2.0","score":84.8,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"ring-1t-preview","score":94.69,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"gemini-2.5-pro","score":86.84,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"deepseek-v3.1-terminus-thinking","score":93.86,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"qwen3-235b-a22b-thinking-2507","score":93.01,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"gpt-5","score":86.84,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"ring-flash-linear-2.0","score":89.9,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"ring-flash-2.0","score":90.23,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"qwen3-32b-thinking-2504","score":84.25,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"gemini-2.5-flash","score":81.59,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"gpt-oss-120b-medium","score":89.67,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"seed-oss-36b-instruct","score":83.78,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"qwen3-next-80b-a3b-thinking","score":89.77,"metric":"percent"},{"benchmark":"collie","model":"gpt-4o","score":61,"metric":"percent"},{"benchmark":"collie","model":"gpt-5","score":99,"metric":"percent"},{"benchmark":"collie","model":"o3","score":98.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"gemma-2-2b","score":65.3,"metric":"percent"},{"benchmark":"commonsenseqa","model":"gemma-2-7b","score":71.3,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-1b-pretrained","score":41.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-3-70b-base","score":83.8,"metric":"acc_char"},{"benchmark":"commonsenseqa","model":"llama-3-8b-base","score":72.6,"metric":"acc_char"},{"benchmark":"commonsenseqa","model":"llama-3.1-405b-base","score":85.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-3.1-405b-base","score":85.8,"metric":"acc_char"},{"benchmark":"commonsenseqa","model":"llama-3.1-70b-base","score":84.1,"metric":"acc_char"},{"benchmark":"commonsenseqa","model":"llama-3.1-8b-base","score":75,"metric":"acc_char"},{"benchmark":"commonsenseqa","model":"qwen2.5-1.5b-pretrained","score":34.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"smollm1-1.7b-pretrained","score":38,"metric":"percent"},{"benchmark":"commonsenseqa","model":"smollm2-1.7b-pretrained","score":43.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"smollm2-135m-base","score":33.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"smollm2-135m-pretrained","score":33.9,"metric":"percent"},{"benchmark":"complexfuncbench","model":"gpt-4o","score":66.5,"metric":"percent"},{"benchmark":"cona","model":"k2-think","score":97,"metric":"percent"},{"benchmark":"countbench","model":"claude-3.7-sonnet","score":90.2,"metric":"percent"},{"benchmark":"countbench","model":"gemma-3-27b-it","score":77.2,"metric":"percent"},{"benchmark":"countbench","model":"gpt-4o","score":85.7,"metric":"percent"},{"benchmark":"countbench","model":"internvl-8b","score":80,"metric":"percent"},{"benchmark":"countbench","model":"mimo-vl-7b-rl","score":90.4,"metric":"percent"},{"benchmark":"countbench","model":"mimo-vl-7b-sft","score":87,"metric":"percent"},{"benchmark":"countbench","model":"qwen2.5-vl-7b","score":74.1,"metric":"percent"},{"benchmark":"countbench","model":"r-4b-base","score":92.6,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-235b-a22b-thinking","score":93.7,"metric":"percent"},{"benchmark":"countbench","model":"gemini-2.5-pro","score":91,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5","score":91.7,"metric":"percent"},{"benchmark":"countbench","model":"claude-opus-4.1","score":93.1,"metric":"percent"},{"benchmark":"countbench","model":"seed1.5-vl-thinking","score":93.7,"metric":"percent"},{"benchmark":"countbench","model":"qwen2.5-vl-72b","score":92.4,"metric":"percent"},{"benchmark":"countbench","model":"gemini-2.5-pro","score":91.79,"metric":"percent"},{"benchmark":"countbench","model":"seed1.5-vl-thinking","score":89,"metric":"percent"},{"benchmark":"countbench","model":"dots-vlm1","score":91.99,"metric":"percent"},{"benchmark":"countbenchqa","model":"cambrian-1-34b","score":75.6,"metric":"percent"},{"benchmark":"countbenchqa","model":"cambrian-1-8b","score":76.4,"metric":"percent"},{"benchmark":"countbenchqa","model":"claude-3-haiku","score":83,"metric":"percent"},{"benchmark":"countbenchqa","model":"claude-3-opus","score":83.6,"metric":"percent"},{"benchmark":"countbenchqa","model":"claude-3.5-sonnet","score":89.7,"metric":"percent"},{"benchmark":"countbenchqa","model":"claude-sonnet-4","score":90.1,"metric":"percent"},{"benchmark":"countbenchqa","model":"gemini-1.5-flash","score":81.6,"metric":"percent"},{"benchmark":"countbenchqa","model":"gemini-1.5-pro","score":85.8,"metric":"percent"},{"benchmark":"countbenchqa","model":"gemini-2.5-flash","score":81.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"gpt-4o-0513","score":87.9,"metric":"percent"},{"benchmark":"countbenchqa","model":"gpt-4v","score":69.9,"metric":"percent"},{"benchmark":"countbenchqa","model":"gpt-5","score":89.3,"metric":"percent"},{"benchmark":"countbenchqa","model":"internvl2-8b","score":57.8,"metric":"percent"},{"benchmark":"countbenchqa","model":"internvl2-llama-3-76b","score":74.7,"metric":"percent"},{"benchmark":"countbenchqa","model":"llama-3.2v-11b-instruct","score":73.1,"metric":"percent"},{"benchmark":"countbenchqa","model":"llama-3.2v-90b-instruct","score":78.5,"metric":"percent"},{"benchmark":"countbenchqa","model":"llava-1.5-13b","score":47.1,"metric":"percent"},{"benchmark":"countbenchqa","model":"llava-1.5-7b","score":40.1,"metric":"percent"},{"benchmark":"countbenchqa","model":"llava-onevision-72b","score":84.3,"metric":"percent"},{"benchmark":"countbenchqa","model":"llava-onevision-7b","score":78.8,"metric":"percent"},{"benchmark":"countbenchqa","model":"molmo-72b","score":91.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"molmo-7b-d","score":88.5,"metric":"percent"},{"benchmark":"countbenchqa","model":"molmo-7b-o","score":89,"metric":"percent"},{"benchmark":"countbenchqa","model":"molmoe-1b","score":87.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"moondream-9b-a2b","score":93.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"paligemma-mix-3b","score":80.6,"metric":"percent"},{"benchmark":"countbenchqa","model":"phi-3.5-vision-4b","score":64.6,"metric":"percent"},{"benchmark":"countbenchqa","model":"pixtral-12b","score":78.8,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen2-vl-72b","score":80.4,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen2-vl-7b","score":76.5,"metric":"percent"},{"benchmark":"countbenchqa","model":"xgen-mm-interleave-4b","score":81.9,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-235b-a22b-thinking","score":11,"metric":"percent"},{"benchmark":"hypersim","model":"gemini-2.5-pro","score":2.2,"metric":"percent"},{"benchmark":"hypersim","model":"seed1.5-vl-thinking","score":9.4,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-235b-a22b-thinking","score":34.9,"metric":"percent"},{"benchmark":"sunrgbd","model":"seed1.5-vl-thinking","score":32.5,"metric":"percent"},{"benchmark":"objectron","model":"qwen3-vl-235b-a22b-thinking","score":71.2,"metric":"percent"},{"benchmark":"objectron","model":"gemini-2.5-pro","score":5.5,"metric":"percent"},{"benchmark":"objectron","model":"seed1.5-vl-thinking","score":8.1,"metric":"percent"},{"benchmark":"arkitscenes","model":"qwen3-vl-235b-a22b-thinking","score":53.7,"metric":"percent"},{"benchmark":"arkitscenes","model":"gemini-2.5-pro","score":7.4,"metric":"percent"},{"benchmark":"arkitscenes","model":"seed1.5-vl-thinking","score":30.3,"metric":"percent"},{"benchmark":"creative-story-writing-v3","model":"claude-opus-4.1","score":8.538,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"command-a","score":7.459,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"deepseek-v3.1","score":8.507,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"deepseek-v3.1-thinking","score":8.517,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"ernie-4.5","score":8.11,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"gemini-2.5-pro","score":8.602,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"glm-4.5","score":7.803,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"gpt-5","score":8.723,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"gpt-oss-120b","score":7.726,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"grok-4","score":8.068,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"kimi-k2","score":8.693,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"kimi-k2-instruct-0905","score":8.749,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"llama-4-maverick","score":6.37,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"mistral-medium-3.1","score":8.629,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"o3-pro","score":8.628,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"qwen3-235b-a22b-thinking-2507","score":8.495,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"qwen3-max-instruct-preview","score":8.711,"metric":"score"},{"benchmark":"creative-writing-longform","model":"claude-3.5-sonnet","score":70.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-3.7-sonnet","score":71.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-opus-4.1","score":74.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-sonnet-4","score":73.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-r1","score":70.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-tng-r1t2-chimera","score":76.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v3-0528","score":78.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v3.1-thinking","score":73.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-2.5-pro","score":72,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-4.5","score":69.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5","score":71.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"hermes-4-405b","score":66.8,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"claude-3.5-sonnet","score":1444.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-opus-4.1","score":1631,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-sonnet-4","score":1499.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-r1","score":1500,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v3","score":1477.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-4o","score":1480.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5","score":1628.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"jan-v1","score":72.08,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"jan-v1-2509","score":75.73,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"jan-v1-edge","score":45.31,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"kimi-k2-instruct","score":1648.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-medium-3.1","score":1489,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"o3","score":1661,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"qwen-1.7b-thinking","score":46.96,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-235b-a22b","score":87.5,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-30b-a3b","score":86,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"ling-flash-2.0","score":85.17,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-32b-nothinking","score":77.57,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"seed-oss-36b-instruct","score":82.17,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gpt-oss-120b","score":79.09,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-4b-thinking-2507","score":65.74,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-next-80b-a3b-instruct","score":85.3,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v3","score":69.8,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-4","score":82,"metric":"percent"},{"benchmark":"crux-o","model":"llama-3.1-405b-base","score":59.9,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-max","score":79.1,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-72b-instruct","score":66.6,"metric":"percent"},{"benchmark":"crag","model":"jamba-mini-1.6","score":76.2,"metric":"percent"},{"benchmark":"crag","model":"ministral-8b","score":52,"metric":"percent"},{"benchmark":"crag","model":"llama-3.1-8b","score":60,"metric":"percent"},{"benchmark":"crag","model":"command-r7b","score":23.1,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon-h1-0.5b-instruct","score":25.75,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon-h1-1.5b","score":39.57,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon-h1-1.5b-deep","score":52.32,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon-h1-34b-instruct","score":73.07,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon-h1-3b","score":56.25,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon-h1-7b","score":66.51,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon3-10b","score":59.57,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon3-1b","score":15.58,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon3-3b","score":44.38,"metric":"percent"},{"benchmark":"cruxeval","model":"falcon3-7b","score":55,"metric":"percent"},{"benchmark":"cruxeval","model":"gemma-3-12b-it","score":67.67,"metric":"percent"},{"benchmark":"cruxeval","model":"gemma-3-1b-it","score":12.7,"metric":"percent"},{"benchmark":"cruxeval","model":"gemma-3-27b-it","score":74.82,"metric":"percent"},{"benchmark":"cruxeval","model":"gemma-3-4b-it","score":52.13,"metric":"percent"},{"benchmark":"cruxeval","model":"llama-3.1-8b-base","score":21.57,"metric":"percent"},{"benchmark":"cruxeval","model":"llama-3.2-1.24b-base","score":0.06,"metric":"percent"},{"benchmark":"cruxeval","model":"llama-3.2-3b-base","score":17.75,"metric":"percent"},{"benchmark":"cruxeval","model":"llama-3.3-70b","score":69.53,"metric":"percent"},{"benchmark":"cruxeval","model":"llama-4-scout-17b","score":68.32,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen2.5-0.5b","score":14.88,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen2.5-1.5b","score":34.76,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen2.5-32b-instruct","score":73.5,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen2.5-3b","score":43.26,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen2.5-72b-instruct","score":75.63,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen2.5-7b","score":56.9,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-0.8b","score":23.63,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-1.7b","score":18.88,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-32b","score":78.45,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-4b","score":69.63,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-8b","score":72.7,"metric":"percent"},{"benchmark":"cultural-bench","model":"llama-3.3-70b","score":81,"metric":"percent"},{"benchmark":"cv-bench","model":"claude-3.7-sonnet","score":75.4,"metric":"percent"},{"benchmark":"cv-bench","model":"gemma-3-27b-vl","score":74.6,"metric":"percent"},{"benchmark":"cv-bench","model":"gemma-3-27b-it","score":70.4,"metric":"percent"},{"benchmark":"cv-bench","model":"glm-4.1v","score":85,"metric":"percent"},{"benchmark":"cv-bench","model":"glm-4.5v","score":87.3,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-4o","score":76,"metric":"percent"},{"benchmark":"cv-bench","model":"internvl-8b","score":81,"metric":"percent"},{"benchmark":"cv-bench","model":"kimi-vl-a3b-thinking-2506","score":79.1,"metric":"percent"},{"benchmark":"cv-bench","model":"mimo-vl-7b-rl","score":82.3,"metric":"percent"},{"benchmark":"cv-bench","model":"mimo-vl-7b-sft","score":81.8,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen2.5-vl-7b","score":75.4,"metric":"percent"},{"benchmark":"cv-bench","model":"step-3","score":80.9,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen2.5-vl-72b","score":84.15,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-2.5-pro","score":85.36,"metric":"percent"},{"benchmark":"cv-bench","model":"seed1.5-vl-thinking","score":89.68,"metric":"percent"},{"benchmark":"cv-bench","model":"dots-vlm1","score":85.65,"metric":"percent"},{"benchmark":"cybench","model":"o3-mini","score":22.5,"metric":"percent"},{"benchmark":"cyberattack-assistance","model":"k2-think","score":47,"metric":"percent"},{"benchmark":"design2code","model":"gemma-3-27b-vl","score":16.1,"metric":"percent"},{"benchmark":"design2code","model":"glm-4.1v","score":64.7,"metric":"percent"},{"benchmark":"design2code","model":"glm-4.5v","score":82.2,"metric":"percent"},{"benchmark":"design2code","model":"kimi-vl-a3b-thinking-2506","score":38.8,"metric":"percent"},{"benchmark":"design2code","model":"step-3","score":34.1,"metric":"percent"},{"benchmark":"design2code","model":"qwen3-vl-235b-a22b-thinking","score":93.4,"metric":"percent"},{"benchmark":"design2code","model":"gemini-2.5-pro","score":89.2,"metric":"percent"},{"benchmark":"design2code","model":"gpt-5","score":92.5,"metric":"percent"},{"benchmark":"design2code","model":"claude-opus-4.1","score":88.5,"metric":"percent"},{"benchmark":"designarena","model":"claude-4.5-sonnet-thinking","score":1410,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-4","score":1363,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-4.1","score":1341,"metric":"elo"},{"benchmark":"designarena","model":"claude-4.1-opus-thinking","score":1337,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-4","score":1337,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5-minimal","score":1329,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-r1-0528","score":1318,"metric":"elo"},{"benchmark":"designarena","model":"claude-3.7-sonnet","score":1315,"metric":"elo"},{"benchmark":"designarena","model":"glm-4.5","score":1307,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-coder-480b-a35b-instruct","score":1306,"metric":"elo"},{"benchmark":"designarena","model":"gemini-2.5-pro","score":1301,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-4-thinking","score":1291,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3-0324","score":1289,"metric":"elo"},{"benchmark":"designarena","model":"grok-4-fast","score":1289,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3.1-thinking","score":1281,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5-high","score":1279,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-4.5","score":1276,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-coder-v2","score":1268,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-235b-a22b-instruct-2507","score":1265,"metric":"elo"},{"benchmark":"designarena","model":"mistral-medium-2505","score":1263,"metric":"elo"},{"benchmark":"designarena","model":"glm-4.5-air","score":1262,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5-mini","score":1255,"metric":"elo"},{"benchmark":"designarena","model":"glm-4.6","score":1253,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-coder-30b-a3b-instruct","score":1253,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3.1","score":1253,"metric":"elo"},{"benchmark":"designarena","model":"gemini-2.5-flash-preview-09-2025","score":1249,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2-instruct-0905","score":1247,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2-0905-preview","score":1240,"metric":"elo"},{"benchmark":"designarena","model":"glm-4-32b","score":1237,"metric":"elo"},{"benchmark":"designarena","model":"grok-3","score":1236,"metric":"elo"},{"benchmark":"designarena","model":"mistral-medium-3.1","score":1233,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5-nano","score":1231,"metric":"elo"},{"benchmark":"designarena","model":"o3","score":1228,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-max","score":1226,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2","score":1224,"metric":"elo"},{"benchmark":"designarena","model":"v0-1.5-md","score":1222,"metric":"elo"},{"benchmark":"designarena","model":"gpt-4.1","score":1213,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3.2-exp","score":1210,"metric":"elo"},{"benchmark":"designarena","model":"gemini-2.5-flash-lite-preview-09-2025","score":1210,"metric":"elo"},{"benchmark":"designarena","model":"devstral-medium","score":1207,"metric":"elo"},{"benchmark":"designarena","model":"magistral-medium-2506","score":1206,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2-turbo-preview","score":1203,"metric":"elo"},{"benchmark":"designarena","model":"gpt-4.1-mini","score":1192,"metric":"elo"},{"benchmark":"designarena","model":"grok-4","score":1190,"metric":"elo"},{"benchmark":"designarena","model":"gpt-4.1-nano","score":1182,"metric":"elo"},{"benchmark":"designarena","model":"v0-1.5-lg","score":1181,"metric":"elo"},{"benchmark":"designarena","model":"o4-mini","score":1181,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-235b-a22b-thinking-2507","score":1174,"metric":"elo"},{"benchmark":"designarena","model":"gemini-2.5-flash","score":1169,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-235b-a22b","score":1166,"metric":"elo"},{"benchmark":"designarena","model":"codestral-2508","score":1164,"metric":"elo"},{"benchmark":"designarena","model":"grok-code-fast-1","score":1150,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-30b-a3b","score":1144,"metric":"elo"},{"benchmark":"designarena","model":"magistral-medium-1.2","score":1140,"metric":"elo"},{"benchmark":"designarena","model":"grok-4-fast-thinking","score":1137,"metric":"elo"},{"benchmark":"designarena","model":"gpt-oss-120b","score":1135,"metric":"elo"},{"benchmark":"designarena","model":"mistral-small-3.2-24b-instruct","score":1135,"metric":"elo"},{"benchmark":"designarena","model":"uigen-x-32b-0707","score":1130,"metric":"elo"},{"benchmark":"designarena","model":"grok-3-mini","score":1119,"metric":"elo"},{"benchmark":"designarena","model":"command-a","score":1119,"metric":"elo"},{"benchmark":"designarena","model":"webgen-small","score":1119,"metric":"elo"},{"benchmark":"designarena","model":"llama-4-maverick","score":1107,"metric":"elo"},{"benchmark":"designarena","model":"magistral-small-1.2","score":1099,"metric":"elo"},{"benchmark":"designarena","model":"magistral-small-1.1","score":1099,"metric":"elo"},{"benchmark":"designarena","model":"grok-2","score":1098,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-30b-a3b-thinking-2507","score":1094,"metric":"elo"},{"benchmark":"designarena","model":"gpt-4o","score":1091,"metric":"elo"},{"benchmark":"designarena","model":"mistral-large-2.1-2411","score":1088,"metric":"elo"},{"benchmark":"designarena","model":"gemini-1.5-pro","score":1073,"metric":"elo"},{"benchmark":"designarena","model":"uigen-x-4b","score":1065,"metric":"elo"},{"benchmark":"designarena","model":"codestral-2501","score":1056,"metric":"elo"},{"benchmark":"designarena","model":"gpt-oss-20b","score":1051,"metric":"elo"},{"benchmark":"designarena","model":"devstral-small-1.1","score":1042,"metric":"elo"},{"benchmark":"designarena","model":"magistral-medium-1.1","score":1039,"metric":"elo"},{"benchmark":"designarena","model":"amazon-nova-premier","score":1034,"metric":"elo"},{"benchmark":"designarena","model":"llama-4-scout","score":1031,"metric":"elo"},{"benchmark":"designarena","model":"amazon-nova-pro-v1.0","score":1006,"metric":"elo"},{"benchmark":"detailbench","model":"deepseek-v3","score":3.6,"metric":"percent"},{"benchmark":"detailbench","model":"deepseek-v3.1","score":2.2,"metric":"percent"},{"benchmark":"detailbench","model":"gemini-2.5-pro","score":2.9,"metric":"percent"},{"benchmark":"detailbench","model":"gpt-5","score":0.7,"metric":"percent"},{"benchmark":"detailbench","model":"llama-4-maverick","score":8.7,"metric":"percent"},{"benchmark":"detailbench","model":"llama-4-scout-17b","score":4.3,"metric":"percent"},{"benchmark":"dialogue-safety","model":"k2-think","score":99,"metric":"percent"},{"benchmark":"dices350","model":"k2-think","score":73,"metric":"percent"},{"benchmark":"do-anything-now","model":"k2-think","score":43,"metric":"percent"},{"benchmark":"do-not-answer","model":"k2-think","score":88,"metric":"percent"},{"benchmark":"docvqa","model":"cambrian-1-34b","score":75.5,"metric":"percent"},{"benchmark":"docvqa","model":"cambrian-1-8b","score":77.8,"metric":"percent"},{"benchmark":"docvqa","model":"claude-3-haiku","score":88.8,"metric":"percent"},{"benchmark":"docvqa","model":"claude-3-opus","score":89.3,"metric":"percent"},{"benchmark":"docvqa","model":"claude-3.5-sonnet","score":95.2,"metric":"percent"},{"benchmark":"docvqa","model":"claude-3.7-sonnet","score":94.1,"metric":"percent"},{"benchmark":"docvqa","model":"claude-opus-4.1","score":92.5,"metric":"percent"},{"benchmark":"docvqa","model":"fastvlm-0.5b","score":82.5,"metric":"percent"},{"benchmark":"docvqa","model":"fastvlm-1.5b","score":88.3,"metric":"percent"},{"benchmark":"docvqa","model":"fastvlm-7b","score":93.2,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-1.5-flash","score":89.9,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-1.5-pro","score":93.1,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-flash","score":94.2,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-pro","score":92.6,"metric":"percent"},{"benchmark":"docvqa","model":"gemma-3-27b-it","score":86.6,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4o","score":93,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4o-0513","score":92.8,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4v","score":87.2,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5","score":91.5,"metric":"percent"},{"benchmark":"docvqa","model":"internvl-8b","score":89.4,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2-8b","score":91.6,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2-llama-3-76b","score":94.1,"metric":"percent"},{"benchmark":"docvqa","model":"llama-3.2v-11b-instruct","score":88.4,"metric":"percent"},{"benchmark":"docvqa","model":"llama-3.2v-90b-instruct","score":90.1,"metric":"percent"},{"benchmark":"docvqa","model":"llama-4-maverick","score":94.4,"metric":"percent"},{"benchmark":"docvqa","model":"llama-4-maverick-17b-128e-instruct","score":94.4,"metric":"percent"},{"benchmark":"docvqa","model":"llama-4-maverick-17b-128e-base","score":91.6,"metric":"percent"},{"benchmark":"docvqa","model":"llama-4-maverick-base","score":91.6,"metric":"percent"},{"benchmark":"docvqa","model":"llama-4-scout-17b","score":94.4,"metric":"percent"},{"benchmark":"docvqa","model":"llama-4-scout-17b-16e","score":94.4,"metric":"percent"},{"benchmark":"docvqa","model":"llama-4-scout-17b-16e-base","score":89.4,"metric":"percent"},{"benchmark":"docvqa","model":"llama-4-scout-17b-base","score":89.4,"metric":"percent"},{"benchmark":"docvqa","model":"llava-1.5-13b","score":30.3,"metric":"percent"},{"benchmark":"docvqa","model":"llava-1.5-7b","score":28.1,"metric":"percent"},{"benchmark":"docvqa","model":"llava-onevision-72b","score":91.3,"metric":"percent"},{"benchmark":"docvqa","model":"llava-onevision-7b","score":87.5,"metric":"percent"},{"benchmark":"docvqa","model":"mimo-vl-7b-rl","score":95.7,"metric":"percent"},{"benchmark":"docvqa","model":"mimo-vl-7b-sft","score":95.2,"metric":"percent"},{"benchmark":"docvqa","model":"molmo-72b","score":93.5,"metric":"percent"},{"benchmark":"docvqa","model":"molmo-7b-d","score":92.2,"metric":"percent"},{"benchmark":"docvqa","model":"molmo-7b-o","score":90.8,"metric":"percent"},{"benchmark":"docvqa","model":"molmoe-1b","score":77.7,"metric":"percent"},{"benchmark":"docvqa","model":"moondream-9b-a2b","score":88.3,"metric":"percent"},{"benchmark":"docvqa","model":"paligemma-mix-3b","score":31.3,"metric":"percent"},{"benchmark":"docvqa","model":"phi-3.5-vision-4b","score":69.3,"metric":"percent"},{"benchmark":"docvqa","model":"pixtral-12b","score":90.7,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2-vl-72b","score":96.5,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2-vl-7b","score":94.5,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2.5-vl-7b","score":95.5,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-235b-a22b-thinking","score":96.5,"metric":"percent"},{"benchmark":"docvqa","model":"seed1.5-vl-thinking","score":96.9,"metric":"percent"},{"benchmark":"docvqa","model":"xgen-mm-interleave-4b","score":61.4,"metric":"percent"},{"benchmark":"drop","model":"claude-3.7-sonnet","score":87.2,"metric":"percent"},{"benchmark":"drop","model":"deepseek-r1","score":92.2,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v3","score":89.7,"metric":"percent"},{"benchmark":"drop","model":"ernie-4.5","score":91.1,"metric":"percent"},{"benchmark":"drop","model":"gemma-3-27b-it","score":72.2,"metric":"percent"},{"benchmark":"drop","model":"gpt-4.1","score":89.2,"metric":"percent"},{"benchmark":"drop","model":"gpt-4o","score":81.5,"metric":"percent"},{"benchmark":"drop","model":"internvl-8b","score":77.5,"metric":"percent"},{"benchmark":"drop","model":"llama-3-70b-base","score":79.7,"metric":"f1"},{"benchmark":"drop","model":"llama-3-8b-base","score":58.4,"metric":"f1"},{"benchmark":"drop","model":"llama-3.1-405b-base","score":84.8,"metric":"f1"},{"benchmark":"drop","model":"llama-3.1-70b-base","score":79.6,"metric":"f1"},{"benchmark":"drop","model":"llama-3.1-8b-base","score":59.5,"metric":"f1"},{"benchmark":"drop","model":"mimo-vl-7b-rl","score":85.1,"metric":"percent"},{"benchmark":"drop","model":"mimo-vl-7b-sft","score":82.7,"metric":"percent"},{"benchmark":"drop","model":"qwen2.5-vl-7b","score":67.6,"metric":"percent"},{"benchmark":"drop","model":"qwen3-235b-a22b","score":88.7,"metric":"percent"},{"benchmark":"dynamath","model":"gemma-3-27b-vl","score":28.5,"metric":"percent"},{"benchmark":"dynamath","model":"glm-4.1v","score":42.5,"metric":"percent"},{"benchmark":"dynamath","model":"glm-4.5v","score":53.9,"metric":"percent"},{"benchmark":"dynamath","model":"gpt-4o","score":63.7,"metric":"percent"},{"benchmark":"dynamath","model":"internvl3-8b","score":23.9,"metric":"percent"},{"benchmark":"dynamath","model":"internvl3.5-4b","score":35.7,"metric":"percent"},{"benchmark":"dynamath","model":"keye-vl-8b","score":35.3,"metric":"percent"},{"benchmark":"dynamath","model":"kimi-vl-a3b-thinking-2506","score":28.1,"metric":"percent"},{"benchmark":"dynamath","model":"qwen2.5-vl-7b","score":20.1,"metric":"percent"},{"benchmark":"dynamath","model":"r-4b-base","score":39.5,"metric":"percent"},{"benchmark":"dynamath","model":"step-3","score":50.1,"metric":"percent"},{"benchmark":"eclektic","model":"gemma-3-27b-it","score":16.7,"metric":"percent"},{"benchmark":"economically-important-tasks","model":"gpt-5","score":47.1,"metric":"percent"},{"benchmark":"economically-important-tasks","model":"o3","score":33.5,"metric":"percent"},{"benchmark":"egoschema","model":"gemini-1.0-pro","score":55.7,"metric":"percent"},{"benchmark":"egoschema","model":"gemini-2.0-flash","score":71.5,"metric":"percent"},{"benchmark":"egoschema","model":"gemini-2.0-flash-lite-preview","score":67.2,"metric":"percent"},{"benchmark":"egoschema","model":"gpt-4o","score":72.2,"metric":"percent"},{"benchmark":"egoschema","model":"internvl-8b","score":68.2,"metric":"percent"},{"benchmark":"egoschema","model":"mimo-vl-7b-rl","score":59.6,"metric":"percent"},{"benchmark":"egoschema","model":"mimo-vl-7b-sft","score":60.4,"metric":"percent"},{"benchmark":"egoschema","model":"nova-lite","score":71.4,"metric":"percent"},{"benchmark":"egoschema","model":"nova-pro","score":72.1,"metric":"percent"},{"benchmark":"egoschema","model":"qwen2-vl-72b-instruct","score":77.9,"metric":"percent"},{"benchmark":"egoschema","model":"qwen2.5-omni-7b","score":68.6,"metric":"percent"},{"benchmark":"egoschema","model":"qwen2.5-vl-72b-instruct","score":76.2,"metric":"percent"},{"benchmark":"egoschema","model":"qwen2.5-vl-7b","score":62.4,"metric":"percent"},{"benchmark":"eqbench","model":"claude-3.5-sonnet","score":82.58,"metric":"percent"},{"benchmark":"eqbench","model":"gemini-1.5-pro","score":82.67,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4","score":81.32,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4-turbo","score":82.04,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4o","score":82.19,"metric":"percent"},{"benchmark":"eqbench","model":"hermes-3-llama-3.1-405b","score":79.51,"metric":"percent"},{"benchmark":"eqbench","model":"hermes-4-70b","score":80.5,"metric":"percent"},{"benchmark":"eqbench","model":"jan-v1-2509","score":85,"metric":"percent"},{"benchmark":"eqbench","model":"jan-v1-edge","score":57.2,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.1-405b","score":83.41,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.2-90b-vision","score":79.91,"metric":"percent"},{"benchmark":"eqbench","model":"qwen-1.7b-thinking","score":54.53,"metric":"percent"},{"benchmark":"eqbench","model":"qwen3-4b-thinking-2507","score":82.61,"metric":"percent"},{"benchmark":"eqbench","model":"rys-xlarge","score":80.69,"metric":"percent"},{"benchmark":"eqbench","model":"rys-xlarge-base","score":81.67,"metric":"percent"},{"benchmark":"eqbench-3","model":"claude-opus-4.1","score":1276.9,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemini-2.5-pro","score":1454.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"glm-4.5","score":1297.4,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-4o","score":1349,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-5","score":1342,"metric":"ELO"},{"benchmark":"eqbench-3","model":"hermes-4-405b","score":1438.1,"metric":"ELO"},{"benchmark":"eqbench-3","model":"kimi-k2-instruct","score":1554.9,"metric":"ELO"},{"benchmark":"eqbench-3","model":"o3","score":1500,"metric":"ELO"},{"benchmark":"eqbench-3","model":"o4-mini","score":1277.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"qwen3-235b-a22b","score":1261.8,"metric":"ELO"},{"benchmark":"erqa","model":"gemma-3-27b-vl","score":37.5,"metric":"percent"},{"benchmark":"erqa","model":"glm-4.1v","score":45.8,"metric":"percent"},{"benchmark":"erqa","model":"glm-4.5v","score":50,"metric":"percent"},{"benchmark":"erqa","model":"gpt-4o","score":35.2,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5","score":65.7,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-235b-a22b-thinking","score":52.5,"metric":"percent"},{"benchmark":"erqa","model":"kimi-vl-a3b-thinking-2506","score":36,"metric":"percent"},{"benchmark":"erqa","model":"o3","score":64,"metric":"percent"},{"benchmark":"erqa","model":"step-3","score":44.5,"metric":"percent"},{"benchmark":"erqa","model":"gemini-2.5-pro","score":55.3,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-4.1","score":36.3,"metric":"percent"},{"benchmark":"evalplus","model":"claude-3.5-sonnet","score":81.7,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-coder-v2-instruct","score":82.3,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-v2.5","score":83.5,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-v3","score":86.6,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-v3-base","score":65.6,"metric":"percent"},{"benchmark":"evalplus","model":"falcon-h1-1.5b-deep","score":68.9,"metric":"percent"},{"benchmark":"evalplus","model":"glm-4.5-base","score":78.1,"metric":"percent"},{"benchmark":"evalplus","model":"coda-1.7b-instruct","score":55.4,"metric":"percent"},{"benchmark":"evalplus","model":"dream-7b-base","score":53.7,"metric":"percent"},{"benchmark":"evalplus","model":"dream-7b-instruct","score":54.9,"metric":"percent"},{"benchmark":"evalplus","model":"llada-8b-instruct","score":30.2,"metric":"percent"},{"benchmark":"evalplus","model":"coda-1.7b-base","score":34.9,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-4-turbo","score":86.6,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-4o","score":87.2,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-4o-mini","score":83.5,"metric":"percent"},{"benchmark":"evalplus","model":"kimi-k2-base","score":80.3,"metric":"percent"},{"benchmark":"evalplus","model":"llama-4-maverick-base","score":65.5,"metric":"percent"},{"benchmark":"evalplus","model":"o1-mini","score":89,"metric":"percent"},{"benchmark":"evalplus","model":"o1-preview","score":89,"metric":"percent"},{"benchmark":"evalplus","model":"qwen2.5-coder-32b-instruct","score":87.2,"metric":"percent"},{"benchmark":"evalplus","model":"qwen3-235b-a22b-base","score":77.6,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-2.5-pro","score":87.8,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-12b-it","score":75.8,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-1b-it","score":36.4,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-27b-it","score":74.9,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-4b-it","score":70.1,"metric":"percent"},{"benchmark":"facts-grounding","model":"jamba-mini-1.6","score":72.7,"metric":"percent"},{"benchmark":"facts-grounding","model":"jamba-mini-1.7","score":79,"metric":"percent"},{"benchmark":"factscore","model":"gpt-5","score":99,"metric":"percent"},{"benchmark":"factscore","model":"o3","score":94.3,"metric":"percent"},{"benchmark":"few-shot-attack","model":"k2-think","score":96,"metric":"percent"},{"benchmark":"finance-reasoning","model":"ling-1t","score":87.45,"metric":"percent"},{"benchmark":"finance-reasoning","model":"deepseek-v3.1-terminus","score":86.44,"metric":"percent"},{"benchmark":"finance-reasoning","model":"kimi-k2-0905","score":84.83,"metric":"percent"},{"benchmark":"finance-reasoning","model":"gpt-5","score":86.28,"metric":"percent"},{"benchmark":"finance-reasoning","model":"gemini-2.5-pro","score":86.65,"metric":"percent"},{"benchmark":"financebench-fulldoc","model":"jamba-mini-1.6","score":45.4,"metric":"percent"},{"benchmark":"financebench-fulldoc","model":"ministral-8b","score":19.2,"metric":"percent"},{"benchmark":"financebench-fulldoc","model":"llama-3.1-8b","score":28.4,"metric":"percent"},{"benchmark":"financebench-fulldoc","model":"command-r7b","score":2.8,"metric":"percent"},{"benchmark":"finsearchcomp","model":"grok-4","score":68.9,"metric":"percent"},{"benchmark":"finsearchcomp","model":"gpt-5-thinking","score":63.9,"metric":"percent"},{"benchmark":"finsearchcomp","model":"gemini-2.5-pro","score":42.6,"metric":"percent"},{"benchmark":"finsearchcomp","model":"doubao-1.5-vision-pro","score":39.1,"metric":"percent"},{"benchmark":"finsearchcomp","model":"qwen3-235b-a22b-thinking-2507","score":37.4,"metric":"percent"},{"benchmark":"finsearchcomp","model":"yuanbao-deepseek-v3","score":30.5,"metric":"percent"},{"benchmark":"finsearchcomp","model":"yuanbao-hunyuan-t1-thinking","score":29.8,"metric":"percent"},{"benchmark":"finsearchcomp","model":"yuanbao-deepseek-r1","score":29.8,"metric":"percent"},{"benchmark":"finsearchcomp","model":"doubao-1.5-vision-pro-thinking","score":29.8,"metric":"percent"},{"benchmark":"finsearchcomp","model":"kimi-k2","score":29.5,"metric":"percent"},{"benchmark":"finsearchcomp","model":"deepseek-r1","score":17.2,"metric":"percent"},{"benchmark":"finsearchcomp","model":"ernie-x1","score":16.6,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"doubao-1.5-vision-pro","score":54.2,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"yuanbao-deepseek-r1","score":52.5,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"grok-4","score":51.9,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"yuanbao-hunyuan-t1-thinking","score":50.5,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"doubao-1.5-vision-pro-thinking","score":49,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"yuanbao-deepseek-v3","score":48.8,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"gpt-5-thinking","score":46.4,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"ernie-x1","score":40.8,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"deepseek-r1","score":40.5,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"kimi-k2","score":38.3,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"gemini-2.5-pro","score":36.8,"metric":"percent"},{"benchmark":"finsearchcomp-cn","model":"qwen3-235b-a22b-thinking-2507","score":21.9,"metric":"percent"},{"benchmark":"flame-react-eval","model":"gemma-3-27b-vl","score":27.5,"metric":"percent"},{"benchmark":"flame-react-eval","model":"glm-4.1v","score":72.5,"metric":"percent"},{"benchmark":"flame-react-eval","model":"glm-4.5v","score":82.5,"metric":"percent"},{"benchmark":"flame-react-eval","model":"kimi-vl-a3b-thinking-2506","score":36.3,"metric":"percent"},{"benchmark":"flame-react-eval","model":"step-3","score":63.8,"metric":"percent"},{"benchmark":"frames","model":"claude-sonnet-4","score":80.7,"metric":"percent"},{"benchmark":"frames","model":"deepseek-r1","score":82.5,"metric":"percent"},{"benchmark":"frames","model":"deepseek-v3.1","score":83.7,"metric":"percent"},{"benchmark":"frames","model":"glm-4.5","score":78.9,"metric":"percent"},{"benchmark":"frames","model":"kimi-k2","score":72,"metric":"percent"},{"benchmark":"frames","model":"kimi-researcher","score":78.8,"metric":"percent"},{"benchmark":"frames","model":"o3","score":84,"metric":"percent"},{"benchmark":"frames","model":"tongyi-deepresearch","score":90.6,"metric":"percent"},{"benchmark":"freshqa","model":"jan-v1","score":54.05,"metric":"percent"},{"benchmark":"freshqa","model":"jan-v1-2509","score":55.07,"metric":"percent"},{"benchmark":"freshqa","model":"jan-v1-edge","score":21.28,"metric":"percent"},{"benchmark":"freshqa","model":"qwen-1.7b-thinking","score":17.57,"metric":"percent"},{"benchmark":"freshqa","model":"qwen3-4b-thinking-2507","score":66.89,"metric":"percent"},{"benchmark":"frontiermath","model":"gpt-5-pro","score":32.1,"metric":"percent"},{"benchmark":"fullstackbench","model":"deepseek-v3","score":64.7,"metric":"percent"},{"benchmark":"fullstackbench","model":"ernie-4.5","score":67.1,"metric":"percent"},{"benchmark":"fullstackbench","model":"gpt-4.1","score":68.5,"metric":"percent"},{"benchmark":"fullstackbench","model":"hunyuan-7b-instruct","score":56.3,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3-235b-a22b","score":57.1,"metric":"percent"},{"benchmark":"fullstackbench","model":"ling-1t","score":56.55,"metric":"percent"},{"benchmark":"fullstackbench","model":"deepseek-v3.1-terminus","score":55.48,"metric":"percent"},{"benchmark":"fullstackbench","model":"kimi-k2-0905","score":54,"metric":"percent"},{"benchmark":"fullstackbench","model":"gpt-5","score":50.92,"metric":"percent"},{"benchmark":"fullstackbench","model":"gemini-2.5-pro","score":48.19,"metric":"percent"},{"benchmark":"gaia","model":"claude-sonnet-4","score":68.3,"metric":"avg@3"},{"benchmark":"gaia","model":"deepseek-v3.1","score":63.1,"metric":"avg@3"},{"benchmark":"gaia","model":"glm-4.5","score":66,"metric":"avg@3"},{"benchmark":"gaia","model":"kimi-k2","score":57.7,"metric":"avg@3"},{"benchmark":"gaia","model":"o4-mini","score":60,"metric":"avg@3"},{"benchmark":"gaia","model":"openai-deepresearch","score":67.4,"metric":"avg@3"},{"benchmark":"gaia","model":"tongyi-deepresearch","score":70.9,"metric":"avg@3"},{"benchmark":"gaia2","model":"llama-3.3-70b-instruct","score":4.4,"metric":"percent"},{"benchmark":"gaia2","model":"llama-4-maverick","score":7.4,"metric":"percent"},{"benchmark":"gaia2","model":"gpt-4o","score":7.4,"metric":"percent"},{"benchmark":"gaia2","model":"qwen3-235b-a22b","score":11.6,"metric":"percent"},{"benchmark":"gaia2","model":"grok-4","score":12.9,"metric":"percent"},{"benchmark":"gaia2","model":"kimi-k2","score":20.1,"metric":"percent"},{"benchmark":"gaia2","model":"gemini-2.5-pro","score":25.8,"metric":"percent"},{"benchmark":"gaia2","model":"claude-sonnet-4","score":34.8,"metric":"percent"},{"benchmark":"gaia2","model":"gpt-5-minimal","score":18.2,"metric":"percent"},{"benchmark":"gaia2","model":"gpt-5-low","score":34.6,"metric":"percent"},{"benchmark":"gaia2","model":"gpt-5-high","score":42.1,"metric":"percent"},{"benchmark":"gandalf-ignore","model":"k2-think","score":87,"metric":"percent"},{"benchmark":"geobench","model":"glm-4.5v","score":79.7,"metric":"percent"},{"benchmark":"geobench1","model":"gemma-3-27b-vl","score":57.5,"metric":"percent"},{"benchmark":"geobench1","model":"glm-4.1v","score":76,"metric":"percent"},{"benchmark":"geobench1","model":"glm-4.5v","score":79.7,"metric":"percent"},{"benchmark":"geobench1","model":"kimi-vl-a3b-thinking-2506","score":48,"metric":"percent"},{"benchmark":"geobench1","model":"step-3","score":72.9,"metric":"percent"},{"benchmark":"global-mmlu","model":"llama-3.1-3b","score":46.8,"metric":"percent"},{"benchmark":"global-mmlu","model":"llama-3.3-70b","score":77.8,"metric":"percent"},{"benchmark":"global-mmlu","model":"qwen2.5-3b","score":50.54,"metric":"percent"},{"benchmark":"global-mmlu","model":"qwen3-1.7b","score":49.5,"metric":"percent"},{"benchmark":"global-mmlu","model":"qwen3-4b","score":65.1,"metric":"percent"},{"benchmark":"global-mmlu","model":"smollm3-3b","score":53.5,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemini-2.5-pro","score":89.2,"metric":"percent"},{"benchmark":"glue","model":"turing-ulr-v6","score":91.3,"metric":"percent"},{"benchmark":"gmai-mmbench","model":"gpt-4o","score":53.5,"metric":"percent"},{"benchmark":"gorilla-api-bench","model":"llama-3-70b","score":14.7,"metric":"acc"},{"benchmark":"gorilla-api-bench","model":"llama-3-8b","score":1.7,"metric":"acc"},{"benchmark":"gorilla-api-bench","model":"llama-3.1-405b","score":35.3,"metric":"acc"},{"benchmark":"gorilla-api-bench","model":"llama-3.1-70b","score":29.7,"metric":"acc"},{"benchmark":"gorilla-api-bench","model":"llama-3.1-8b","score":8.2,"metric":"acc"},{"benchmark":"gpqa","model":"aquif-3-0.4b","score":28.5,"metric":"percent"},{"benchmark":"gpqa","model":"aquif-3.5-a0.6b","score":30.2,"metric":"percent"},{"benchmark":"gpqa","model":"falcon-3-1b-base","score":11.34,"metric":"percent"},{"benchmark":"gpqa","model":"falcon-e-1b-base","score":2.8,"metric":"percent"},{"benchmark":"gpqa","model":"falcon-h1-0.5b-instruct","score":29.95,"metric":"percent"},{"benchmark":"gpqa","model":"falcon-h1-1.5b","score":26.34,"metric":"percent"},{"benchmark":"gpqa","model":"falcon-h1-1.5b-deep","score":33.22,"metric":"percent"},{"benchmark":"gpqa","model":"falcon-h1-34b-instruct","score":41.53,"metric":"percent"},{"benchmark":"gpqa","model":"falcon-h1-3b","score":33.89,"metric":"percent"},{"benchmark":"gpqa","model":"falcon-h1-7b","score":36.33,"metric":"percent"},{"benchmark":"gpqa","model":"falcon3-10b","score":33.39,"metric":"percent"},{"benchmark":"gpqa","model":"falcon3-1b","score":26.76,"metric":"percent"},{"benchmark":"gpqa","model":"falcon3-3b","score":28.69,"metric":"percent"},{"benchmark":"gpqa","model":"falcon3-7b","score":31.21,"metric":"percent"},{"benchmark":"gpqa","model":"gemini-2.5-flash-thinking","score":82.8,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3-12b-it","score":33.98,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3-1b-it","score":21.07,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3-27b-it","score":36.49,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3-4b-it","score":29.19,"metric":"percent"},{"benchmark":"gpqa","model":"grok-4","score":88.4,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2-1.2b","score":31.47,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2-350m","score":27.46,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2-700m","score":28.48,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-70b","score":39.5,"metric":"em"},{"benchmark":"gpqa","model":"llama-3-8b","score":34.6,"metric":"em"},{"benchmark":"gpqa","model":"llama-3.1-405b","score":50.7,"metric":"em"},{"benchmark":"gpqa","model":"llama-3.1-70b","score":46.7,"metric":"em"},{"benchmark":"gpqa","model":"llama-3.1-8b","score":30.4,"metric":"em"},{"benchmark":"gpqa","model":"llama-3.1-8b-base","score":32.72,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.2-1.24b","score":28.84,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.2-1.24b-base","score":26.59,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.2-3b-base","score":28.94,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.3-70b","score":31.99,"metric":"percent"},{"benchmark":"gpqa","model":"llama-4-scout-17b","score":31.8,"metric":"percent"},{"benchmark":"gpqa","model":"openreasoning-nemotron-1.5b","score":31.6,"metric":"percent"},{"benchmark":"gpqa","model":"openreasoning-nemotron-14b","score":71.6,"metric":"percent"},{"benchmark":"gpqa","model":"openreasoning-nemotron-32b","score":73.1,"metric":"percent"},{"benchmark":"gpqa","model":"openreasoning-nemotron-7b","score":61.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-0.5b","score":26.85,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-1.5b","score":26.26,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-32b-instruct","score":34.31,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-3b","score":28.69,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-72b-instruct","score":37.67,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-7b","score":31.79,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-0.6b","score":22.14,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-0.8b","score":22.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-1.7b","score":27.72,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-235b-a22b","score":77.5,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-235b-a22b-thinking-2507","score":81.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-30b-a3b","score":70.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-30b-a3b-thinking-2507","score":73.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b","score":30.2,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b-nothinking","score":54.6,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b-thinking","score":68.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-4b","score":28.02,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-8b","score":25.84,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-next-80b-a3b-instruct","score":72.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-next-80b-a3b-thinking","score":77.2,"metric":"percent"},{"benchmark":"gpqa","model":"smollm2-1.7b-base","score":9.3,"metric":"percent"},{"benchmark":"gpqa","model":"smollm2-360m-base","score":0,"metric":"percent"},{"benchmark":"gpqa","model":"llama-spark-8b","score":6.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"afm-4.5b","score":27.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apriel-5b-instruct","score":28.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"aquif-3-3.2b","score":36.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"aquif-3-moe-17b-a2.8b","score":56.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"aquif-3.5-2.7b","score":35.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-3.7-sonnet","score":66,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.1","score":80.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1","score":71.08,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-tng-r1t-chimera","score":72,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-tng-r1t2-chimera","score":77.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3-0528","score":81,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.1","score":80.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.1-terminus","score":80.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.2-exp","score":79.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.1-thinking","score":79.46,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"exaone-3.5-2.4b","score":28.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon-h1-0.5b-instruct","score":27.95,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon-h1-1.5b","score":35.19,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon-h1-1.5b-deep","score":40.57,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon-h1-34b-instruct","score":49.66,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon-h1-3b","score":38.72,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon-h1-7b","score":56.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon3-10b","score":34.68,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon3-1b","score":31.31,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon3-3b","score":29.29,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon3-7b","score":37.21,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash","score":79,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-pro","score":84.51,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-4b-it","score":33.33,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-12b-it","score":40.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-1b-it","score":19.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-27b-it","score":40.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-4b-it","score":30.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.5","score":79.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.6","score":81,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-4.1-nano","score":50.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-4o","score":50.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-high","score":85.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-pro","score":89.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b","score":77.04,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b","score":65.45,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b-medium","score":65.53,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"grok-4","score":87.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"internvl-8b","score":33.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-think","score":71.08,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-3b","score":29.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-405b","score":49,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-8b-base","score":31.31,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.2-1.24b-base","score":25.08,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.2-3b-base","score":29.97,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.3-70b","score":50.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-4-maverick","score":69.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-4-maverick-17b-128e-instruct","score":69.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-4-scout-17b","score":57.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-4-scout-17b-16e","score":57.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-vl-7b-rl","score":58.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-vl-7b-sft","score":56.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-32b","score":74.98,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o3","score":82.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o3-high","score":81.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"phi-4-14b","score":56.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"phi-4-mini-3.8b","score":25.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen2.5-0.5b","score":24.24,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen2.5-1.5b","score":25.59,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen2.5-32b-instruct","score":40.74,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen2.5-3b","score":32.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen2.5-72b-instruct","score":44.95,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen2.5-7b","score":33,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen2.5-vl-7b","score":30.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-0.8b","score":25.08,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-1.7b","score":31.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-14b","score":54.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-235b-a22b","score":81.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b","score":73.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-32b","score":49.49,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b","score":39.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b","score":27.78,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-8b","score":43.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-8b-thinking","score":62,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwq-32b","score":66.24,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ring-mini-2.0","score":68.24,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"smollm3-3b","score":19.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"smollm3-3b","score":35.7,"metric":"percent"},{"benchmark":"gpqa-main","model":"llama-3.3-70b","score":59.6,"metric":"percent"},{"benchmark":"graphwalks-128k","model":"qwen3-moe-2507","score":80.72,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gpt-4.5","score":72,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"claude-sonnet-4","score":84,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo1-3b","score":74.75,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo1-7b","score":78.5,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo1.5-3b","score":83.2,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo1.5-72b","score":84.5,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo1.5-7b","score":84,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"qwen2.5-vl-3b","score":76.4,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"qwen2.5-vl-72b","score":85.4,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"qwen2.5-vl-7b","score":80.7,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"ui-tars-1.5-7b","score":84.2,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"ui-venus-72b","score":75.5,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"ui-venus-7b","score":82.3,"metric":"percent"},{"benchmark":"gsm-plus","model":"llama-3.1-3b","score":59.2,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen2.5-3b","score":74.1,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3-1.7b","score":68.3,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3-4b","score":82.1,"metric":"percent"},{"benchmark":"gsm-plus","model":"smollm3-3b","score":72.8,"metric":"percent"},{"benchmark":"gsm8k","model":"aquif-3-0.4b","score":52.1,"metric":"percent"},{"benchmark":"gsm8k","model":"aquif-3.5-a0.6b","score":50.7,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3-opus","score":95,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3.5-sonnet","score":96.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2.5","score":95.1,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3","score":96.3,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3-base","score":87.6,"metric":"percent"},{"benchmark":"gsm8k","model":"ernie-4.5","score":96.6,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-h1-0.5b-instruct","score":68.39,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-h1-1.5b","score":74.98,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-h1-1.5b-deep","score":82.34,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-h1-34b-instruct","score":83.62,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-h1-3b","score":84.76,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-h1-7b","score":81.65,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon3-10b","score":85.06,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon3-1b","score":44.05,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon3-3b","score":74.68,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon3-7b","score":81.05,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-2b","score":17.7,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-7b","score":46.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-12b-it","score":87.49,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-1b-it","score":59.59,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-4b-it","score":77.41,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-pt-1b","score":2.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-pt-270m","score":1.1,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4.5-base","score":79.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4.1","score":95.9,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4.5","score":97,"metric":"percent"},{"benchmark":"gsm8k","model":"kimi-k2-base","score":92.1,"metric":"percent"},{"benchmark":"gsm8k","model":"kimi-k2-instruct","score":97.3,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2-1.2b","score":58.3,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2-350m","score":30.1,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2-700m","score":46.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1b","score":26.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1b-pretrained","score":7.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b","score":93,"metric":"em_maj1@1"},{"benchmark":"gsm8k","model":"llama-3-8b","score":80.6,"metric":"em_maj1@1"},{"benchmark":"gsm8k","model":"llama-3.1-405b","score":96.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-405b","score":96.8,"metric":"em_maj1@1"},{"benchmark":"gsm8k","model":"llama-3.1-405b-base","score":89,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b","score":95.1,"metric":"em_maj1@1"},{"benchmark":"gsm8k","model":"llama-3.1-8b","score":84.5,"metric":"em_maj1@1"},{"benchmark":"gsm8k","model":"llama-3.1-8b-base","score":82.49,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-1.24b","score":35.71,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-1.24b-base","score":6.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-3b-base","score":77.26,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.3-70b","score":93.71,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-4-maverick-base","score":87.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-4-scout-17b","score":90.37,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1-140m-base","score":16.3,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1-360m-base","score":39.4,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1-950m-base","score":61.6,"metric":"percent"},{"benchmark":"gsm8k","model":"o1","score":97.1,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-2-0425-1b-base","score":39.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-max","score":94.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-0.5b","score":38.51,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-1.5b","score":57.47,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-1.5b-instruct","score":42.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-1.5b-pretrained","score":61.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-32b-instruct","score":95.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-3b","score":57.54,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-72b-instruct","score":95.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-7b","score":71.95,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-0.6b","score":36.47,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-0.6b-base","score":60.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-0.8b","score":36.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-1.7b","score":51.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-235b-a22b","score":96.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-235b-a22b-base","score":94.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-32b","score":88.78,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-4b","score":80.44,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-8b","score":78.92,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm1-1.7b-instruct","score":4.62,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm1-1.7b-pretrained","score":5.5,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-1.7b-base","score":31.8,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-1.7b-instruct","score":48.2,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-1.7b-pretrained","score":31,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-135m-base","score":1.6,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-135m-instruct","score":1.4,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-135m-pretrained","score":1.4,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-360m-base","score":5,"metric":"percent"},{"benchmark":"gsm8k-platinum","model":"olmo-2-0325-32b-instruct","score":89.5,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-3.5-sonnet-20241022","score":4.6,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-3.7-sonnet","score":3.8,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-opus-4","score":6.9,"metric":"percent"},{"benchmark":"gso-benchmark","model":"glm-4.5-air","score":2.9,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-5-high","score":6.9,"metric":"percent"},{"benchmark":"gso-benchmark","model":"kimi-k2-instruct","score":4.9,"metric":"percent"},{"benchmark":"gso-benchmark","model":"o3-high","score":8.8,"metric":"percent"},{"benchmark":"gso-benchmark","model":"o3-mini-high","score":1.3,"metric":"percent"},{"benchmark":"gso-benchmark","model":"o4-mini-high","score":3.6,"metric":"percent"},{"benchmark":"gso-benchmark","model":"qwen3-coder-480b-a35b","score":4.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-opus-4.1","score":60.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.5-pro","score":63.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-3-27b-vl","score":45.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"glm-4.1v","score":63.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"glm-4.5v","score":65.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5","score":65.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"kimi-vl-a3b-thinking-2506","score":59.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-235b-a22b-thinking","score":66.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"step-3","score":64.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2.5-vl-72b","score":56.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.5-pro","score":63.07,"metric":"percent"},{"benchmark":"hallusionbench","model":"seed1.5-vl-thinking","score":63.49,"metric":"percent"},{"benchmark":"hallusionbench","model":"dots-vlm1","score":64.83,"metric":"percent"},{"benchmark":"harmbench","model":"k2-think","score":56,"metric":"percent"},{"benchmark":"harmfulq","model":"chatgpt","score":74.3,"metric":"percent"},{"benchmark":"harmfulq","model":"gpt-4","score":79.4,"metric":"percent"},{"benchmark":"harmfulq","model":"k2-think","score":99,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-4o","score":32,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-5","score":67.2,"metric":"percent"},{"benchmark":"healthbench","model":"o3","score":59.8,"metric":"percent"},{"benchmark":"healthbench","model":"ring-flash-linear-2.0","score":49.1,"metric":"percent"},{"benchmark":"healthbench","model":"ring-flash-2.0","score":51.6,"metric":"percent"},{"benchmark":"healthbench","model":"qwen3-32b-thinking-2504","score":47.61,"metric":"percent"},{"benchmark":"healthbench","model":"gemini-2.5-flash","score":49.57,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-oss-120b-medium","score":46.61,"metric":"percent"},{"benchmark":"healthbench","model":"seed-oss-36b-instruct","score":54.99,"metric":"percent"},{"benchmark":"healthbench","model":"qwen3-next-80b-a3b-thinking","score":59.82,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gpt-5","score":46.2,"metric":"percent"},{"benchmark":"healthbench-hard","model":"o3","score":31.6,"metric":"percent"},{"benchmark":"healthbench-hard-hallucinations","model":"gpt-4o","score":15.8,"metric":"percent"},{"benchmark":"healthbench-hard-hallucinations","model":"gpt-5","score":1.6,"metric":"percent"},{"benchmark":"healthbench-hard-hallucinations","model":"o3","score":12.9,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v3-base","score":96.4,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-h1-0.5b-instruct","score":51.93,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-h1-1.5b","score":63.33,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-h1-1.5b-deep","score":65.54,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-h1-34b-instruct","score":81.94,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-h1-3b","score":69.85,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-h1-7b","score":75.92,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon3-10b","score":75.57,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon3-1b","score":58.53,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon3-3b","score":64.24,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon3-7b","score":71.81,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2-2b","score":71.4,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2-7b","score":81.2,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-12b-it","score":55.63,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-1b-it","score":42.24,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-270m-it","score":37.7,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-27b-it","score":57.25,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-4b-it","score":47.68,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-pt-270m","score":40.9,"metric":"percent"},{"benchmark":"hellaswag","model":"glm-4.5-base","score":87.1,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-5","score":87.3,"metric":"percent"},{"benchmark":"hellaswag","model":"kimi-k2-base","score":96.2,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-1b","score":56.1,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-1b-pretrained","score":61.2,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-8b-base","score":71.28,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.2-1.24b-base","score":55.3,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.2-3b-base","score":63.74,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.3-70b","score":70.24,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-4-scout-17b","score":65.03,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-0.5b","score":52.38,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-1.5b","score":62.23,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-1.5b-instruct","score":60.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-1.5b-pretrained","score":66.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-32b-instruct","score":73.95,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-3b","score":64.21,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-72b-instruct","score":68.79,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-7b","score":63.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-0.8b","score":42.17,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-1.7b","score":49.27,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-32b","score":68.89,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-4b","score":55.31,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-8b","score":60.56,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm1-1.7b-instruct","score":55.5,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm1-1.7b-pretrained","score":62.9,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm2-1.7b-instruct","score":66.1,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm2-1.7b-pretrained","score":68.7,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm2-135m-base","score":42.1,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm2-135m-instruct","score":40.9,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm2-135m-pretrained","score":42.1,"metric":"percent"},{"benchmark":"helmet-longqa","model":"jamba-mini-1.6","score":46.9,"metric":"percent"},{"benchmark":"helmet-longqa","model":"ministral-8b","score":33,"metric":"percent"},{"benchmark":"helmet-longqa","model":"llama-3.1-8b","score":29.2,"metric":"percent"},{"benchmark":"helmet-longqa","model":"command-r7b","score":9.6,"metric":"percent"},{"benchmark":"hellaswag-multilingual","model":"apertus-70b-instruct","score":55.3,"metric":"percent"},{"benchmark":"math","model":"gemma-3-27b-it","score":71.1,"metric":"percent"},{"benchmark":"herobench","model":"claude-sonnet-4","score":17.2,"metric":"percent"},{"benchmark":"herobench","model":"claude-sonnet-4-thinking","score":44.4,"metric":"percent"},{"benchmark":"herobench","model":"deepseek-r1-0528","score":21.7,"metric":"percent"},{"benchmark":"herobench","model":"deepseek-r1-70b","score":11.2,"metric":"percent"},{"benchmark":"herobench","model":"deepseek-v3","score":7.2,"metric":"percent"},{"benchmark":"herobench","model":"gemini-2.5-flash","score":26.1,"metric":"percent"},{"benchmark":"herobench","model":"gemini-2.5-pro","score":62.9,"metric":"percent"},{"benchmark":"herobench","model":"gigachat-2-max","score":2.8,"metric":"percent"},{"benchmark":"herobench","model":"gpt-4.1","score":31.7,"metric":"percent"},{"benchmark":"herobench","model":"gpt-4.1-mini","score":16.1,"metric":"percent"},{"benchmark":"herobench","model":"gpt-5","score":83.9,"metric":"percent"},{"benchmark":"herobench","model":"gpt-5-mini","score":35,"metric":"percent"},{"benchmark":"herobench","model":"gpt-oss-120b","score":8.9,"metric":"percent"},{"benchmark":"herobench","model":"grok-4","score":91.7,"metric":"percent"},{"benchmark":"herobench","model":"kimi-k2","score":8.3,"metric":"percent"},{"benchmark":"herobench","model":"magistral-medium","score":9.4,"metric":"percent"},{"benchmark":"herobench","model":"o3","score":60.6,"metric":"percent"},{"benchmark":"herobench","model":"o4-mini","score":35,"metric":"percent"},{"benchmark":"herobench","model":"qwen3-235b-a22b","score":13.3,"metric":"percent"},{"benchmark":"herobench","model":"qwen3-235b-a22b-thinking-2507","score":24.4,"metric":"percent"},{"benchmark":"herobench","model":"qwen3-32b","score":1.7,"metric":"percent"},{"benchmark":"herobench","model":"qwen3-32b-thinking","score":10,"metric":"percent"},{"benchmark":"herobench","model":"qwen3-8b","score":0,"metric":"percent"},{"benchmark":"herobench","model":"qwen3-8b-thinking","score":3.9,"metric":"percent"},{"benchmark":"rlhf","model":"k2-think","score":95,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"antgroup-finix-s1-32b","score":0.6,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"deepseek-r1","score":14.3,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"deepseek-tng-r1t2-chimera","score":5.5,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"deepseek-v3-0528","score":7.7,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"gemini-2.0-flash-001","score":0.7,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"gemini-2.0-flash-lite-preview","score":1.2,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"gemini-2.0-pro-exp","score":0.8,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"glm-4-9b-chat","score":1.3,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"gpt-4.5","score":1.2,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"kimi-k2-instruct","score":1.1,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"o3-mini-high","score":0.8,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"vectara-mockingbird-2-echo","score":0.9,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemini-2.0-pro","score":65.2,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4","score":20.3,"metric":"avg@3"},{"benchmark":"hle","model":"claude-sonnet-4.5","score":17.3,"metric":"percent"},{"benchmark":"hle","model":"deepseek-r1","score":8.5,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.1","score":15.9,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.1-terminus","score":21.7,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.2-exp","score":19.8,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.1-thinking","score":8.4,"metric":"percent"},{"benchmark":"hle","model":"ernie-4.5-21b-a3b-pt","score":5.1,"metric":"percent"},{"benchmark":"hle","model":"gemini-2.5-pro","score":19.93,"metric":"percent"},{"benchmark":"hle","model":"gemini-deepresearch","score":26.9,"metric":"avg@3"},{"benchmark":"hle","model":"glm-4.5","score":21.2,"metric":"avg@3"},{"benchmark":"hle","model":"glm-4.6","score":17.2,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5-high","score":26.3,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5-pro","score":30.7,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-120b","score":18.58,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-20b","score":11.23,"metric":"percent"},{"benchmark":"hle","model":"k2-think","score":9.95,"metric":"percent"},{"benchmark":"hle","model":"kimi-k2","score":18.1,"metric":"avg@3"},{"benchmark":"hle","model":"kimi-researcher","score":26.9,"metric":"avg@3"},{"benchmark":"hle","model":"ling-mini-2.0","score":6,"metric":"percent"},{"benchmark":"hle","model":"nemotron-32b","score":12.26,"metric":"percent"},{"benchmark":"hle","model":"o3","score":24.9,"metric":"avg@3"},{"benchmark":"hle","model":"o3-high","score":22.34,"metric":"percent"},{"benchmark":"hle","model":"o4-mini","score":17.7,"metric":"avg@3"},{"benchmark":"hle","model":"openai-deepresearch","score":26.6,"metric":"avg@3"},{"benchmark":"hle","model":"openreasoning-nemotron-1.5b","score":5.5,"metric":"percent"},{"benchmark":"hle","model":"openreasoning-nemotron-14b","score":10.1,"metric":"percent"},{"benchmark":"hle","model":"openreasoning-nemotron-32b","score":11.9,"metric":"percent"},{"benchmark":"hle","model":"openreasoning-nemotron-7b","score":8.3,"metric":"percent"},{"benchmark":"hle","model":"qwen3-235b-a22b","score":14.23,"metric":"percent"},{"benchmark":"hle","model":"qwen3-30b-a3b","score":6.14,"metric":"percent"},{"benchmark":"hle","model":"qwen3-4b-instruct-2507","score":4.6,"metric":"percent"},{"benchmark":"hle","model":"qwen3-8b-nothinking-2504","score":4,"metric":"percent"},{"benchmark":"hle","model":"qwq-32b","score":9.98,"metric":"percent"},{"benchmark":"hle","model":"tongyi-deepresearch","score":32.9,"metric":"avg@3"},{"benchmark":"hmmt","model":"gpt-5-pro","score":100,"metric":"percent"},{"benchmark":"hmmt","model":"o3","score":93.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-r1","score":47.08,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.1-thinking","score":83.54,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.1-terminus","score":86.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.2-exp","score":83.6,"metric":"percent"},{"benchmark":"hmmt-2025","model":"ernie-4.5-21b-a3b-pt","score":6.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-2.5-flash-thinking","score":64.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-2.5-pro","score":74.18,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-5-high","score":91.79,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-oss-120b","score":81.88,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-oss-20b","score":69.38,"metric":"percent"},{"benchmark":"hmmt-2025","model":"k2-think","score":66.46,"metric":"percent"},{"benchmark":"hmmt-2025","model":"ling-mini-2.0","score":35.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"nemotron-32b","score":67.29,"metric":"percent"},{"benchmark":"hmmt-2025","model":"o3-high","score":80.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"openreasoning-nemotron-1.5b","score":31.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"openreasoning-nemotron-14b","score":71.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"openreasoning-nemotron-32b","score":73.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"openreasoning-nemotron-7b","score":63.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-235b-a22b","score":83.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-235b-a22b-thinking-2507","score":83.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-30b-a3b","score":71.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-30b-a3b-thinking-2507","score":71.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-32b-nothinking","score":9.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-32b-thinking","score":51.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-4b-instruct-2507","score":29.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-8b-nothinking-2504","score":11.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-next-80b-a3b-instruct","score":54.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-next-80b-a3b-thinking","score":73.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwq-32b","score":51.46,"metric":"percent"},{"benchmark":"hle","model":"deepseek-r1-distill-qwen-1.5b","score":3.3,"metric":"percent"},{"benchmark":"hle","model":"phi-4-mini","score":4.2,"metric":"percent"},{"benchmark":"hle","model":"granite-4.0-micro","score":5.1,"metric":"percent"},{"benchmark":"hle","model":"llama-3.2-3b","score":5.2,"metric":"percent"},{"benchmark":"hle","model":"gemma-3-4b","score":5.2,"metric":"percent"},{"benchmark":"hle","model":"qwen3-1.7b","score":4.8,"metric":"percent"},{"benchmark":"hle","model":"qwen3-4b","score":5.1,"metric":"percent"},{"benchmark":"hle","model":"jamba-reasoning-3b","score":6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-sonnet-4","score":94.51,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3","score":89.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ernie-4.5","score":92.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon-h1-0.5b-instruct","score":45.12,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon-h1-1.5b","score":61.59,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon-h1-1.5b-deep","score":73.78,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon-h1-34b-instruct","score":81.71,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon-h1-3b","score":70.73,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon-h1-7b","score":81.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon3-10b","score":75,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon3-1b","score":20.73,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon3-3b","score":45.73,"metric":"percent"},{"benchmark":"humaneval-plus","model":"falcon3-7b","score":65.85,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-12b-it","score":75.61,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-1b-it","score":37.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-27b-it","score":78.05,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-4b-it","score":61.59,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4.1","score":92.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-8b-base","score":61.59,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.2-1.24b-base","score":29.88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.2-3b-base","score":50,"metric":"percent"},{"benchmark":"humaneval-plus","model":"coda-1.7b-base","score":23.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"coda-1.7b-instruct","score":47.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"dream-7b-base","score":50,"metric":"percent"},{"benchmark":"humaneval-plus","model":"dream-7b-instruct","score":53.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llada-8b-instruct","score":31.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.3-70b","score":79.87,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-4-scout-17b","score":78.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-0.5b","score":32.32,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-1.5b","score":50.61,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-32b-instruct","score":82.32,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-3b","score":68.29,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-72b-instruct","score":80.49,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-7b","score":73.78,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-0.8b","score":37.19,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-1.7b","score":60.96,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-235b-a22b","score":89.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-32b","score":85.37,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-4b","score":76.83,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-8b","score":79.27,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-r1-distill-qwen-1.5b","score":13,"metric":"percent"},{"benchmark":"ifbench","model":"phi-4-mini","score":21,"metric":"percent"},{"benchmark":"ifbench","model":"llama-3.2-3b","score":26,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-3-4b","score":28,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-4b","score":33,"metric":"percent"},{"benchmark":"ifbench","model":"jamba-reasoning-3b","score":52,"metric":"percent"},{"benchmark":"ifeval","model":"jamba-mini-1.6","score":68,"metric":"percent"},{"benchmark":"ifeval","model":"jamba-mini-1.7","score":76,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-3-1b-it","score":17.72,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5","score":73.1,"metric":"percent"},{"benchmark":"ifbench","model":"jan-v1","score":39.1,"metric":"percent"},{"benchmark":"ifbench","model":"jan-v1-2509","score":40.9,"metric":"percent"},{"benchmark":"ifbench","model":"jan-v1-edge","score":18.51,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-1.2b","score":20.7,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-350m","score":16.41,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-700m","score":20.56,"metric":"percent"},{"benchmark":"ifbench","model":"llama-3.2-1.24b","score":16.86,"metric":"percent"},{"benchmark":"ifbench","model":"qwen-1.7b-thinking","score":22.09,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-0.6b","score":19.75,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-1.7b","score":21.27,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-1.7b","score":27,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-4b-thinking-2507","score":48.06,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-235b-a22b","score":71.9,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-32b","score":73,"metric":"percent"},{"benchmark":"multi-if","model":"o1-2024-12-17","score":48.8,"metric":"percent"},{"benchmark":"multi-if","model":"deepseek-r1","score":67.7,"metric":"percent"},{"benchmark":"multi-if","model":"gemini-2.5-pro","score":77.8,"metric":"percent"},{"benchmark":"multi-if","model":"o3-mini","score":48.4,"metric":"percent"},{"benchmark":"ifeval","model":"afm-4.5b","score":67.03,"metric":"percent"},{"benchmark":"ifeval","model":"apriel-5b-instruct","score":80.8,"metric":"percent"},{"benchmark":"ifeval","model":"aquif-3-3.2b","score":78.9,"metric":"percent"},{"benchmark":"ifeval","model":"aquif-3.5-2.7b","score":78.9,"metric":"percent"},{"benchmark":"ifeval","model":"claude-3.7-sonnet","score":88.7,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v3","score":82.3,"metric":"percent"},{"benchmark":"ifeval","model":"ernie-4.5","score":88,"metric":"percent"},{"benchmark":"ifeval","model":"exaone-3.5-2.4b","score":73.6,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-3-1b-base","score":24.28,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-e-1b-base","score":32.9,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-h1-0.5b-instruct","score":72.07,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-h1-1.5b","score":80.66,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-h1-1.5b-deep","score":83.5,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-h1-34b-instruct","score":89.37,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-h1-3b","score":85.05,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-h1-7b","score":85.35,"metric":"percent"},{"benchmark":"ifeval","model":"falcon3-10b","score":78.84,"metric":"percent"},{"benchmark":"ifeval","model":"falcon3-1b","score":54.26,"metric":"percent"},{"benchmark":"ifeval","model":"falcon3-3b","score":69.1,"metric":"percent"},{"benchmark":"ifeval","model":"falcon3-7b","score":76.59,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-2.5-flash-thinking","score":89.8,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-4b-it","score":83.93,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-12b-it","score":88.9,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-1b-it","score":80.2,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-270m-it","score":51.2,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-27b-it","score":88.9,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-4b-it","score":90.2,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4.1","score":87.4,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4o","score":82.5,"metric":"percent"},{"benchmark":"ifeval","model":"internvl-8b","score":87.2,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-1.2b","score":74.89,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-350m","score":65.12,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-700m","score":72.23,"metric":"percent"},{"benchmark":"ifeval","model":"llama-1b","score":53.5,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3-70b","score":82.9,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3-70b-base","score":81.75,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3-8b","score":76.8,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-3b","score":71.6,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-405b","score":88.6,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-70b","score":87.5,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-8b","score":80.4,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-8b-base","score":77.04,"metric":"percent"},{"benchmark":"ifeval","model":"llama-spark-8b","score":79.11,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.2-1.24b","score":52.39,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.2-1.24b-base","score":55.34,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.2-3b-base","score":74,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.3-70b","score":89.94,"metric":"percent"},{"benchmark":"ifeval","model":"llama-4-scout-17b","score":86.32,"metric":"percent"},{"benchmark":"ifeval","model":"mimo-vl-7b-rl","score":75.9,"metric":"percent"},{"benchmark":"ifeval","model":"mimo-vl-7b-sft","score":75.3,"metric":"percent"},{"benchmark":"ifeval","model":"mixtral-8x22b","score":73.08,"metric":"percent"},{"benchmark":"ifeval","model":"o3-mini-high","score":93.9,"metric":"percent"},{"benchmark":"ifeval","model":"phi-4-mini-3.8b","score":68.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2-72b","score":80.56,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-0.5b","score":32.11,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-1.5b","score":45.33,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-1.5b-instruct","score":47.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-32b-instruct","score":81.79,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-3b","score":65.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-72b-instruct","score":86.35,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-7b","score":75.25,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-vl-7b","score":75.1,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-0.6b","score":64.24,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-0.8b","score":62.16,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-1.7b","score":73.98,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-235b-a22b","score":88.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-235b-a22b-thinking-2507","score":87.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b","score":84.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-thinking-2507","score":88.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-32b","score":86.97,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-32b-nothinking","score":83.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-32b-thinking","score":85,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b","score":71.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b","score":48.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-8b","score":83.43,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-next-80b-a3b-instruct","score":87.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-next-80b-a3b-thinking","score":88.9,"metric":"percent"},{"benchmark":"ifeval","model":"smollm1-1.7b-instruct","score":23.1,"metric":"percent"},{"benchmark":"ifeval","model":"smollm2-1.7b-base","score":24.4,"metric":"percent"},{"benchmark":"ifeval","model":"smollm2-1.7b-instruct","score":56.7,"metric":"percent"},{"benchmark":"ifeval","model":"smollm2-135m-instruct","score":29.9,"metric":"percent"},{"benchmark":"ifeval","model":"smollm3-3b","score":46.64,"metric":"percent"},{"benchmark":"ifeval","model":"smollm2-360m-base","score":21.15,"metric":"percent"},{"benchmark":"ifeval","model":"smollm3-3b","score":76.7,"metric":"percent"},{"benchmark":"include","model":"gemini-2.5-flash-thinking","score":83.9,"metric":"percent"},{"benchmark":"include","model":"llama-3.3-70b","score":71.9,"metric":"percent"},{"benchmark":"include","model":"qwen3-235b-a22b","score":79.5,"metric":"percent"},{"benchmark":"include","model":"qwen3-235b-a22b-thinking-2507","score":81,"metric":"percent"},{"benchmark":"include","model":"qwen3-30b-a3b","score":71.9,"metric":"percent"},{"benchmark":"include","model":"qwen3-30b-a3b-thinking-2507","score":74.4,"metric":"percent"},{"benchmark":"include","model":"qwen3-32b-nothinking","score":70.9,"metric":"percent"},{"benchmark":"include","model":"qwen3-32b-thinking","score":73.7,"metric":"percent"},{"benchmark":"include","model":"qwen3-next-80b-a3b-instruct","score":78.9,"metric":"percent"},{"benchmark":"include","model":"qwen3-next-80b-a3b-thinking","score":78.9,"metric":"percent"},{"benchmark":"include-v2","model":"gemma-3-27b-it","score":46.9,"metric":"percent"},{"benchmark":"infoqa","model":"cambrian-1-34b","score":46,"metric":"percent"},{"benchmark":"infoqa","model":"cambrian-1-8b","score":41.6,"metric":"percent"},{"benchmark":"infoqa","model":"claude-3-haiku","score":56.1,"metric":"percent"},{"benchmark":"infoqa","model":"claude-3-opus","score":55.6,"metric":"percent"},{"benchmark":"infoqa","model":"claude-3.5-sonnet","score":74.3,"metric":"percent"},{"benchmark":"infoqa","model":"gemini-1.5-flash","score":75.3,"metric":"percent"},{"benchmark":"infoqa","model":"gemini-1.5-pro","score":81,"metric":"percent"},{"benchmark":"infoqa","model":"gpt-4o-0513","score":79.2,"metric":"percent"},{"benchmark":"infoqa","model":"gpt-4v","score":75.1,"metric":"percent"},{"benchmark":"infoqa","model":"internvl2-8b","score":74.8,"metric":"percent"},{"benchmark":"infoqa","model":"internvl2-llama-3-76b","score":82,"metric":"percent"},{"benchmark":"infoqa","model":"llama-3.2v-11b-instruct","score":63.6,"metric":"percent"},{"benchmark":"infoqa","model":"llama-3.2v-90b-instruct","score":67.2,"metric":"percent"},{"benchmark":"infoqa","model":"llava-1.5-13b","score":29.4,"metric":"percent"},{"benchmark":"infoqa","model":"llava-1.5-7b","score":25.8,"metric":"percent"},{"benchmark":"infoqa","model":"llava-onevision-72b","score":74.9,"metric":"percent"},{"benchmark":"infoqa","model":"llava-onevision-7b","score":68.8,"metric":"percent"},{"benchmark":"infoqa","model":"molmo-72b","score":81.9,"metric":"percent"},{"benchmark":"infoqa","model":"molmo-7b-d","score":72.6,"metric":"percent"},{"benchmark":"infoqa","model":"molmo-7b-o","score":70,"metric":"percent"},{"benchmark":"infoqa","model":"molmoe-1b","score":53.9,"metric":"percent"},{"benchmark":"infoqa","model":"paligemma-mix-3b","score":21.4,"metric":"percent"},{"benchmark":"infoqa","model":"phi-3.5-vision-4b","score":36.6,"metric":"percent"},{"benchmark":"infoqa","model":"pixtral-12b","score":50.8,"metric":"percent"},{"benchmark":"infoqa","model":"qwen2-vl-72b","score":84.5,"metric":"percent"},{"benchmark":"infoqa","model":"qwen2-vl-7b","score":76.5,"metric":"percent"},{"benchmark":"infoqa","model":"xgen-mm-interleave-4b","score":31.5,"metric":"percent"},{"benchmark":"infovqa","model":"claude-3.7-sonnet","score":65.5,"metric":"percent"},{"benchmark":"infovqa","model":"fastvlm-0.5b","score":46.4,"metric":"percent"},{"benchmark":"infovqa","model":"fastvlm-1.5b","score":59.7,"metric":"percent"},{"benchmark":"infovqa","model":"fastvlm-7b","score":75.8,"metric":"percent"},{"benchmark":"infovqa","model":"gemma-3-27b-it","score":70.6,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-4o","score":82.1,"metric":"percent"},{"benchmark":"infovqa","model":"internvl-8b","score":70.7,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-235b-a22b-thinking","score":89.5,"metric":"percent"},{"benchmark":"infovqa","model":"mimo-vl-7b-rl","score":88,"metric":"percent"},{"benchmark":"infovqa","model":"mimo-vl-7b-sft","score":87.2,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-2.5-pro","score":84.2,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-5","score":79,"metric":"percent"},{"benchmark":"infovqa","model":"claude-opus-4.1","score":69.4,"metric":"percent"},{"benchmark":"infovqa","model":"seed1.5-vl-thinking","score":91.2,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2.5-vl-7b","score":81.4,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"claude-sonnet-4","score":81.99,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gemini-2.5-flash","score":62.97,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gemini-2.5-pro","score":72.06,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"glm-4.5","score":63.41,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-4.1","score":76.31,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5","score":81.2,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5-mini","score":74.49,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5-nano","score":61.08,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"kimi-k2-instruct","score":73.09,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"o3","score":75.1,"metric":"percent"},{"benchmark":"l-eval","model":"gpt-4","score":73.11,"metric":"percent"},{"benchmark":"lambada","model":"gpt-3","score":86.4,"metric":"percent"},{"benchmark":"latent-jailbreak","model":"belle-7b-2m","score":59.6,"metric":"percent"},{"benchmark":"latent-jailbreak","model":"chatglm2-6b","score":24.7,"metric":"percent"},{"benchmark":"latent-jailbreak","model":"gpt-3.5-turbo","score":77.4,"metric":"percent"},{"benchmark":"latent-jailbreak","model":"k2-think","score":37,"metric":"percent"},{"benchmark":"livebench","model":"chatgpt-4o","score":54.74,"metric":"percent"},{"benchmark":"livebench","model":"claude-3.5-haiku","score":39.51,"metric":"percent"},{"benchmark":"livebench","model":"claude-3.5-sonnet","score":51.8,"metric":"percent"},{"benchmark":"livebench","model":"claude-3.7-sonnet","score":58.48,"metric":"percent"},{"benchmark":"livebench","model":"claude-3.7-sonnet-thinking","score":67.43,"metric":"percent"},{"benchmark":"livebench","model":"claude-opus-4","score":65.93,"metric":"percent"},{"benchmark":"livebench","model":"claude-opus-4-thinking","score":72.93,"metric":"percent"},{"benchmark":"livebench","model":"claude-sonnet-4","score":63.37,"metric":"percent"},{"benchmark":"livebench","model":"claude-sonnet-4-thinking","score":72.08,"metric":"percent"},{"benchmark":"livebench","model":"claude-4.1-opus-thinking","score":73.48,"metric":"percent"},{"benchmark":"livebench","model":"claude-opus-4","score":74.6,"metric":"percent"},{"benchmark":"livebench","model":"command-a","score":44.17,"metric":"percent"},{"benchmark":"livebench","model":"command-r","score":27.15,"metric":"percent"},{"benchmark":"livebench","model":"command-r-plus","score":30.14,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-r1","score":71.6,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-r1","score":65.15,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-r1-2025-05-28","score":70.1,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-r1-distill-llama-70b","score":48.53,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-r1-distill-qwen-32b","score":41.44,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-v3","score":66.3,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-v3-0324","score":55.99,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-v3.1","score":62.55,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-v3.1-thinking","score":71.3,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-v3.1-thinking","score":70.75,"metric":"percent"},{"benchmark":"livebench","model":"ernie-4.5","score":68.9,"metric":"percent"},{"benchmark":"livebench","model":"falcon-h1-0.5b-instruct","score":20.8,"metric":"percent"},{"benchmark":"livebench","model":"falcon-h1-1.5b","score":34.13,"metric":"percent"},{"benchmark":"livebench","model":"falcon-h1-1.5b-deep","score":36.83,"metric":"percent"},{"benchmark":"livebench","model":"falcon-h1-34b-instruct","score":46.26,"metric":"percent"},{"benchmark":"livebench","model":"falcon-h1-3b","score":36.86,"metric":"percent"},{"benchmark":"livebench","model":"falcon-h1-7b","score":45.74,"metric":"percent"},{"benchmark":"livebench","model":"falcon3-10b","score":34.3,"metric":"percent"},{"benchmark":"livebench","model":"falcon3-1b","score":14.1,"metric":"percent"},{"benchmark":"livebench","model":"falcon3-3b","score":26.01,"metric":"percent"},{"benchmark":"livebench","model":"falcon3-7b","score":32.35,"metric":"percent"},{"benchmark":"livebench","model":"gemini-2.0-flash-lite","score":46.78,"metric":"percent"},{"benchmark":"livebench","model":"gemini-2.5-flash","score":64.42,"metric":"percent"},{"benchmark":"livebench","model":"gemini-2.5-flash-lite-preview-thinking","score":57.53,"metric":"percent"},{"benchmark":"livebench","model":"gemini-2.5-flash-thinking","score":74.3,"metric":"percent"},{"benchmark":"livebench","model":"gemini-2.5-pro","score":82.4,"metric":"percent"},{"benchmark":"livebench","model":"gemini-2.5-pro","score":69.39,"metric":"percent"},{"benchmark":"livebench","model":"gemini-2.5-pro-max-thinking","score":70.95,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3-12b","score":37.08,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3-27b","score":42,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3-4b","score":23.33,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3-12b-it","score":49.23,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3-1b-it","score":18.79,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3-27b-it","score":55.41,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3-4b-it","score":36.7,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3n-e2b-it","score":21.74,"metric":"percent"},{"benchmark":"livebench","model":"gemma-3n-e4b-it","score":27.85,"metric":"percent"},{"benchmark":"livebench","model":"glm-4.5","score":63.55,"metric":"percent"},{"benchmark":"livebench","model":"glm-4.5-air","score":59.93,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4.1","score":67.7,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4.1","score":55.9,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4.1-mini","score":51.57,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4.1-nano","score":40.51,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4.5-preview","score":58.65,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4o","score":47.43,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-chat","score":60.78,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-high","score":78.59,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-low","score":75.34,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-medium","score":76.45,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-mini","score":70.69,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-mini-high","score":72.2,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-mini-low","score":63.85,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-mini-minimal","score":51.93,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-minimal","score":56.46,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-nano","score":58.74,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-nano-high","score":58.47,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-nano-low","score":45.45,"metric":"percent"},{"benchmark":"livebench","model":"gpt-5-nano-minimal","score":32.09,"metric":"percent"},{"benchmark":"livebench","model":"gpt-oss-120b","score":54.6,"metric":"percent"},{"benchmark":"livebench","model":"grok-3-beta","score":56.05,"metric":"percent"},{"benchmark":"livebench","model":"grok-3-mini-beta-high","score":62.36,"metric":"percent"},{"benchmark":"livebench","model":"grok-4","score":72.11,"metric":"percent"},{"benchmark":"livebench","model":"grok-code-fast","score":57.94,"metric":"percent"},{"benchmark":"livebench","model":"hunyuan-turbos","score":43.99,"metric":"percent"},{"benchmark":"livebench","model":"kimi-k2","score":76.4,"metric":"percent"},{"benchmark":"livebench","model":"kimi-k2-instruct","score":62.7,"metric":"percent"},{"benchmark":"livebench","model":"llama-3.1-8b-base","score":31.73,"metric":"percent"},{"benchmark":"livebench","model":"llama-3.2-1.24b-base","score":14.97,"metric":"percent"},{"benchmark":"livebench","model":"llama-3.2-3b-base","score":26.37,"metric":"percent"},{"benchmark":"livebench","model":"llama-3.3-70b","score":53.11,"metric":"percent"},{"benchmark":"livebench","model":"llama-4-maverick-17b-128e-instruct","score":47.78,"metric":"percent"},{"benchmark":"livebench","model":"llama-4-scout-17b","score":54.21,"metric":"percent"},{"benchmark":"livebench","model":"mistral-large","score":43.31,"metric":"percent"},{"benchmark":"livebench","model":"mistral-medium-3","score":50.65,"metric":"percent"},{"benchmark":"livebench","model":"mistral-small","score":40.55,"metric":"percent"},{"benchmark":"livebench","model":"o1","score":75.7,"metric":"percent"},{"benchmark":"livebench","model":"o3-high","score":74.61,"metric":"percent"},{"benchmark":"livebench","model":"o3-medium","score":71.98,"metric":"percent"},{"benchmark":"livebench","model":"o3-mini","score":70,"metric":"percent"},{"benchmark":"livebench","model":"o3-pro-high","score":74.72,"metric":"percent"},{"benchmark":"livebench","model":"o4-mini-high","score":71.52,"metric":"percent"},{"benchmark":"livebench","model":"o4-mini-medium","score":66.87,"metric":"percent"},{"benchmark":"livebench","model":"phi-4-reasoning-plus","score":49.27,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-235b-a22b-instruct-2507","score":64.72,"metric":"percent"},{"benchmark":"livebench","model":"qwen-3-235b-a22b-thinking","score":64.93,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-235b-a22b-thinking-2507","score":70.76,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-30b-a3b","score":59.02,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-32b","score":63.71,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-coder-480b-a35b-instruct","score":60.45,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-0.5b","score":14.27,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-1.5b","score":21.65,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-32b-instruct","score":52.92,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-3b","score":27.32,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-72b-instruct","score":54.03,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-72b-instruct-turbo","score":42.51,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-7b","score":37.13,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-max","score":51.93,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-0.8b","score":27.78,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-1.7b","score":40.73,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-235b-a22b","score":75.4,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-235b-a22b-thinking-2507","score":78.4,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-30b-a3b","score":69,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-30b-a3b-thinking-2507","score":76.8,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-32b","score":74.9,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-32b-nothinking","score":59.8,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-32b-thinking","score":74.9,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-4b","score":51.34,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-8b","score":56.19,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-max-instruct-preview","score":79.3,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-next-80b-a3b-instruct","score":75.8,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-next-80b-a3b-thinking","score":76.6,"metric":"percent"},{"benchmark":"livecodebench","model":"apriel-5b-instruct","score":11.6,"metric":"percent"},{"benchmark":"livecodebench","model":"aquif-3-3.2b","score":15.4,"metric":"percent"},{"benchmark":"livecodebench","model":"aquif-3-moe-17b-a2.8b","score":28.6,"metric":"percent"},{"benchmark":"livecodebench","model":"aquif-3.5-2.7b","score":23.1,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3-haiku","score":20.2,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.5-sonnet-20241022","score":36.4,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4","score":46.9,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4-thinking","score":56.6,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4","score":48.9,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4","score":47.1,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4-thinking","score":55.9,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1","score":61.01,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-235b-a22b","score":70.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-32b","score":65.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o1-2024-12-17","score":63.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepseek-r1","score":64.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"grok-3-beta-think","score":70.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-2.5-pro","score":70.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o3-mini","score":66.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-0528","score":73.1,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-distill-qwen-1.5b","score":19.9,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3","score":27.2,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.1","score":74.8,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.1-terminus","score":74.9,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-1t","score":61.68,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.1-terminus","score":48.02,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-0905","score":48.95,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5","score":48.57,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":45.43,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-exp","score":74.1,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3-base","score":26.6,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.1-thinking","score":66.59,"metric":"percent"},{"benchmark":"livecodebench","model":"ernie-4.5","score":38.8,"metric":"percent"},{"benchmark":"livecodebench","model":"ernie-4.5-21b-a3b-pt","score":26.1,"metric":"percent"},{"benchmark":"livecodebench","model":"exaone-3.5-2.4b","score":12.5,"metric":"percent"},{"benchmark":"livecodebench","model":"exaone-4.0-32b","score":70,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon-h1-0.5b-instruct","score":7.05,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon-h1-1.5b","score":17.61,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon-h1-1.5b-deep","score":23.87,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon-h1-34b-instruct","score":49.71,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon-h1-3b","score":26.81,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon-h1-7b","score":35.03,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon3-10b","score":19.77,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon3-1b","score":0.78,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon3-3b","score":3.13,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon3-7b","score":12.72,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-04-17","score":60.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-05-20","score":61.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-thinking","score":61.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":58.24,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro-05-06","score":71.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro-06-05","score":73.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-12b-it","score":30.92,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-1b-it","score":2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-27b-it","score":26.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-4b-it","score":11.2,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-base","score":28.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4-turbo-2024-04-09","score":28.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4.1","score":40.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4.1-nano","score":32.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o-2024-08-06","score":29.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o-mini-2024-07-18","score":27.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-high","score":87,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":74.53,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b","score":73.22,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b-medium","score":54.9,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-3-beta-think","score":70.6,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-3-mini-high","score":66.7,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-4","score":81.9,"metric":"percent"},{"benchmark":"livecodebench","model":"k2-think","score":63.97,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2","score":48.9,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-base","score":28.1,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-mini-2.0","score":34.8,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-3b","score":3.4,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-405b","score":27.7,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-8b-base","score":15.85,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.2-1.24b","score":4.1,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.2-1.24b-base","score":2.35,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.2-3b-base","score":2.74,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.3-70b","score":33.3,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-4-maverick","score":43.4,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-4-maverick-17b-128e-instruct","score":43.4,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-4-maverick-base","score":25.1,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-4-scout-17b","score":32.8,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-4-scout-17b-16e","score":32.8,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-small-3.1-24b-instruct","score":27.5,"metric":"percent"},{"benchmark":"livecodebench","model":"mobilellm-r1-140m","score":1,"metric":"percent"},{"benchmark":"livecodebench","model":"mobilellm-r1-360m","score":4.8,"metric":"percent"},{"benchmark":"livecodebench","model":"mobilellm-r1-950m","score":19.9,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-32b","score":57.79,"metric":"percent"},{"benchmark":"livecodebench","model":"o1","score":63.9,"metric":"percent"},{"benchmark":"livecodebench","model":"o3-high","score":75.8,"metric":"percent"},{"benchmark":"livecodebench","model":"o3-mini","score":66.3,"metric":"percent"},{"benchmark":"livecodebench","model":"o3-mini-2025-01-31-high","score":67.4,"metric":"percent"},{"benchmark":"livecodebench","model":"o3-mini-2025-01-31-low","score":57,"metric":"percent"},{"benchmark":"livecodebench","model":"o3-mini-2025-01-31-med","score":63,"metric":"percent"},{"benchmark":"livecodebench","model":"o4-mini-high","score":80.2,"metric":"percent"},{"benchmark":"livecodebench","model":"o4-mini-low","score":65.9,"metric":"percent"},{"benchmark":"livecodebench","model":"o4-mini-medium","score":74.2,"metric":"percent"},{"benchmark":"livecodebench","model":"opencodereasoning-nemotron-1.1-32b","score":66.8,"metric":"percent"},{"benchmark":"livecodebench","model":"openreasoning-nemotron-1.5b","score":28.6,"metric":"percent"},{"benchmark":"livecodebench","model":"openreasoning-nemotron-14b","score":67.8,"metric":"percent"},{"benchmark":"livecodebench","model":"openreasoning-nemotron-32b","score":69.8,"metric":"percent"},{"benchmark":"livecodebench","model":"openreasoning-nemotron-7b","score":63.3,"metric":"percent"},{"benchmark":"livecodebench","model":"phi-4-14b","score":25.2,"metric":"percent"},{"benchmark":"livecodebench","model":"phi-4-mini-3.8b","score":10.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-0.5b","score":2.94,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-1.5b","score":12.52,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-32b-instruct","score":49.12,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-3b","score":10.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-72b-instruct","score":54.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-7b","score":32.68,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-0.6b","score":14.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-0.8b","score":9.78,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-1.7b","score":15,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-14b","score":29,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b","score":65.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b-thinking-2507","score":74.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b","score":43.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-thinking-2507","score":66,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b","score":65.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b-nothinking","score":29.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b-thinking","score":60.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b","score":21.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-instruct-2507","score":31.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b","score":45.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b-nothinking-2504","score":26.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b-thinking","score":56.94,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-max-instruct-preview","score":57.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b-instruct","score":56.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b-thinking","score":68.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwq-32b","score":65.22,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-mini-2.0","score":62.56,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-1t-preview","score":78.3,"metric":"percent"},{"benchmark":"livecodebench","model":"smollm2-1.7b-instruct","score":4.4,"metric":"percent"},{"benchmark":"livecodebench","model":"smollm2-360m-instruct","score":0.7,"metric":"percent"},{"benchmark":"livecodebench","model":"smollm3-3b","score":15.2,"metric":"percent"},{"benchmark":"livecodebench","model":"xbai-o4-medium","score":65,"metric":"percent"},{"benchmark":"livemcp-101","model":"claude-3.7-sonnet","score":29.7,"metric":"percent"},{"benchmark":"livemcp-101","model":"claude-opus-4.1","score":41.58,"metric":"percent"},{"benchmark":"livemcp-101","model":"claude-sonnet-4","score":43.56,"metric":"percent"},{"benchmark":"livemcp-101","model":"gemini-2.5-flash","score":10.89,"metric":"percent"},{"benchmark":"livemcp-101","model":"gemini-2.5-pro","score":27.72,"metric":"percent"},{"benchmark":"livemcp-101","model":"gpt-4.1","score":35.64,"metric":"percent"},{"benchmark":"livemcp-101","model":"gpt-4.1-mini","score":17.82,"metric":"percent"},{"benchmark":"livemcp-101","model":"gpt-4o","score":21.78,"metric":"percent"},{"benchmark":"livemcp-101","model":"gpt-4o-mini","score":8.91,"metric":"percent"},{"benchmark":"livemcp-101","model":"gpt-5","score":58.42,"metric":"percent"},{"benchmark":"livemcp-101","model":"gpt-5-mini","score":43.56,"metric":"percent"},{"benchmark":"livemcp-101","model":"llama-3.1-8b","score":0.99,"metric":"percent"},{"benchmark":"livemcp-101","model":"llama-3.3-70b","score":1.98,"metric":"percent"},{"benchmark":"livemcp-101","model":"o3","score":46.53,"metric":"percent"},{"benchmark":"livemcp-101","model":"o4-mini","score":40.59,"metric":"percent"},{"benchmark":"livemcp-101","model":"qwen3-235b-a22b","score":22.77,"metric":"percent"},{"benchmark":"livemcp-101","model":"qwen3-32b","score":18.81,"metric":"percent"},{"benchmark":"livemcp-101","model":"qwen3-8b","score":3.96,"metric":"percent"},{"benchmark":"lmarena-text","model":"claude-opus-4","score":1420,"metric":"score"},{"benchmark":"lmarena-text","model":"claude-opus-4.1","score":1451,"metric":"score"},{"benchmark":"lmarena-text","model":"gemini-2.5-pro","score":1455,"metric":"score"},{"benchmark":"lmarena-text","model":"gpt-4.5","score":1439,"metric":"score"},{"benchmark":"lmarena-text","model":"gpt-4o","score":1441,"metric":"score"},{"benchmark":"lmarena-text","model":"gpt-5","score":1442,"metric":"score"},{"benchmark":"lmarena-text","model":"grok-4","score":1422,"metric":"score"},{"benchmark":"lmarena-text","model":"kimi-k2-instruct","score":1420,"metric":"score"},{"benchmark":"lmarena-text","model":"o3","score":1444,"metric":"score"},{"benchmark":"lmarena-text","model":"qwen3-max-instruct-preview","score":1428,"metric":"score"},{"benchmark":"logicvista","model":"gemma-3-27b-vl","score":47.3,"metric":"percent"},{"benchmark":"logicvista","model":"glm-4.1v","score":60.4,"metric":"percent"},{"benchmark":"logicvista","model":"glm-4.5v","score":62.4,"metric":"percent"},{"benchmark":"logicvista","model":"internvl3-8b","score":43.6,"metric":"percent"},{"benchmark":"logicvista","model":"internvl3.5-4b","score":56.4,"metric":"percent"},{"benchmark":"logicvista","model":"keye-vl-8b","score":50.6,"metric":"percent"},{"benchmark":"logicvista","model":"kimi-vl-a3b-thinking-2506","score":51.4,"metric":"percent"},{"benchmark":"logicvista","model":"qwen2.5-vl-7b","score":44.5,"metric":"percent"},{"benchmark":"logicvista","model":"r-4b-base","score":59.1,"metric":"percent"},{"benchmark":"logicvista","model":"step-3","score":60.2,"metric":"percent"},{"benchmark":"longbench","model":"jamba-mini-1.6","score":32,"metric":"percent"},{"benchmark":"longbench","model":"ministral-8b","score":17.5,"metric":"percent"},{"benchmark":"longbench","model":"llama-3.1-8b","score":17.7,"metric":"percent"},{"benchmark":"longbench","model":"command-r7b","score":2,"metric":"percent"},{"benchmark":"longbench-v2","model":"hunyuan-4b-instruct","score":44.1,"metric":"percent"},{"benchmark":"longfact-concepts","model":"gpt-5","score":99.3,"metric":"percent"},{"benchmark":"longfact-concepts","model":"o3","score":95.5,"metric":"percent"},{"benchmark":"longfact-objects","model":"gpt-5","score":99.2,"metric":"percent"},{"benchmark":"longfact-objects","model":"o3","score":94.9,"metric":"percent"},{"benchmark":"longmemeval","model":"gpt-4o-mini","score":71.1,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-235b-a22b-thinking","score":63.6,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-2.5-pro","score":73,"metric":"percent"},{"benchmark":"lvbench","model":"seed1.5-vl-thinking","score":64.6,"metric":"percent"},{"benchmark":"lvbench","model":"gemma-3-27b-vl","score":45.9,"metric":"percent"},{"benchmark":"lvbench","model":"glm-4.1v","score":44,"metric":"percent"},{"benchmark":"lvbench","model":"glm-4.5v","score":53.8,"metric":"percent"},{"benchmark":"lvbench","model":"kimi-vl-a3b-thinking-2506","score":47.6,"metric":"percent"},{"benchmark":"mantis","model":"claude-3.7-sonnet","score":75.1,"metric":"percent"},{"benchmark":"mantis","model":"gemma-3-27b-it","score":70,"metric":"percent"},{"benchmark":"mantis","model":"gpt-4o","score":75.6,"metric":"percent"},{"benchmark":"mantis","model":"internvl-8b","score":72.8,"metric":"percent"},{"benchmark":"mantis","model":"mimo-vl-7b-rl","score":78.3,"metric":"percent"},{"benchmark":"mantis","model":"mimo-vl-7b-sft","score":78.8,"metric":"percent"},{"benchmark":"mantis","model":"qwen2.5-vl-7b","score":74.7,"metric":"percent"},{"benchmark":"mantis","model":"qwen2.5-vl-72b","score":79.26,"metric":"percent"},{"benchmark":"mantis","model":"gemini-2.5-pro","score":84.33,"metric":"percent"},{"benchmark":"mantis","model":"seed1.5-vl-thinking","score":82.3,"metric":"percent"},{"benchmark":"mantis","model":"dots-vlm1","score":86.18,"metric":"percent"},{"benchmark":"mask","model":"claude-sonnet-4-thinking","score":95.33,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4-1-20250805-thinking","score":94.2,"metric":"percent"},{"benchmark":"mask","model":"gpt-oss-120b","score":92,"metric":"percent"},{"benchmark":"mask","model":"claude-sonnet-4","score":89.27,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4-thinking","score":87.87,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4.1-20250805","score":87.4,"metric":"percent"},{"benchmark":"mask","model":"gpt-oss-20b","score":86.46,"metric":"percent"},{"benchmark":"mask","model":"o3-high","score":84.47,"metric":"percent"},{"benchmark":"mask","model":"o3-medium","score":82.6,"metric":"percent"},{"benchmark":"mask","model":"gpt-5-mini-2025-08","score":82.6,"metric":"percent"},{"benchmark":"mask","model":"o3-pro-high","score":82.5,"metric":"percent"},{"benchmark":"mask","model":"claude-3.7-sonnet-thinking","score":82.13,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4","score":80.28,"metric":"percent"},{"benchmark":"mask","model":"gpt-5-2025-08-07","score":79.33,"metric":"percent"},{"benchmark":"mask","model":"claude-3-opus","score":79,"metric":"percent"},{"benchmark":"mask","model":"o4-mini-high","score":78.6,"metric":"percent"},{"benchmark":"mask","model":"o4-mini-medium","score":72.93,"metric":"percent"},{"benchmark":"mask","model":"claude-3.5-sonnet-20241022","score":72.33,"metric":"percent"},{"benchmark":"mask","model":"claude-3.7-sonnet-20250219","score":72.27,"metric":"percent"},{"benchmark":"mask","model":"o1-pro","score":61.6,"metric":"percent"},{"benchmark":"mask","model":"glm-4.5","score":61.46,"metric":"percent"},{"benchmark":"mask","model":"llama-3.1-405b-instruct","score":61.4,"metric":"percent"},{"benchmark":"mask","model":"gpt-4.1-nano","score":61.4,"metric":"percent"},{"benchmark":"mask","model":"glm-4.5-air","score":60.8,"metric":"percent"},{"benchmark":"mask","model":"gpt-4o-2024-11-20","score":60.07,"metric":"percent"},{"benchmark":"mask","model":"o1-2024-12-17","score":59.27,"metric":"percent"},{"benchmark":"mask","model":"deepseek-r1","score":57.32,"metric":"percent"},{"benchmark":"mask","model":"gpt-4.5-preview","score":56.93,"metric":"percent"},{"benchmark":"mask","model":"magistral-medium-1.2","score":56.5,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.5-pro-exp-03.25","score":55.93,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.5-pro-preview-06-05","score":55.67,"metric":"percent"},{"benchmark":"mask","model":"llama-3.2-90b-vision","score":54.07,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.5-pro-preview-05-06","score":53.07,"metric":"percent"},{"benchmark":"mask","model":"deepseek-r1-0528","score":53,"metric":"percent"},{"benchmark":"mask","model":"llama-3.3-70b-instruct","score":51.93,"metric":"percent"},{"benchmark":"mask","model":"gpt-4.1","score":51.13,"metric":"percent"},{"benchmark":"mask","model":"gpt-4.1-mini","score":50,"metric":"percent"},{"benchmark":"mask","model":"o3-mini-2025-01-31-low","score":49.73,"metric":"percent"},{"benchmark":"mask","model":"llama-4-maverick","score":49.73,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.0-flash-thinking-exp-01-21","score":49.53,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.5-flash-preview-05-20","score":49.13,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.0-flash","score":49.07,"metric":"percent"},{"benchmark":"mask","model":"o3-mini-2025-01-31-med","score":48.93,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.0-pro-exp-02-05","score":48.67,"metric":"percent"},{"benchmark":"mask","model":"mistral-large-2411","score":47.53,"metric":"percent"},{"benchmark":"mask","model":"o3-mini-2025-01-31-high","score":46.8,"metric":"percent"},{"benchmark":"mask","model":"kimi-k2-instruct","score":46.67,"metric":"percent"},{"benchmark":"mask","model":"deepseek-v3.1","score":46.27,"metric":"percent"},{"benchmark":"mask","model":"deepseek-v3-0324","score":44.53,"metric":"percent"},{"benchmark":"mask","model":"mistral-medium-3","score":42.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-r1-distill-qwen-1.5b","score":83.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3","score":61.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3-base","score":62.6,"metric":"percent"},{"benchmark":"math","model":"gemma-2-2b","score":11.8,"metric":"percent"},{"benchmark":"math","model":"gemma-2-7b","score":24.3,"metric":"percent"},{"benchmark":"math","model":"gemma-3-1b-it","score":45.4,"metric":"percent"},{"benchmark":"math","model":"gemma-3-270m-it","score":6.8,"metric":"percent"},{"benchmark":"math","model":"gemma-3-pt-1b","score":0.6,"metric":"percent"},{"benchmark":"math","model":"gemma-3-pt-270m","score":0.6,"metric":"percent"},{"benchmark":"math","model":"glm-4.5-base","score":61,"metric":"percent"},{"benchmark":"math","model":"kimi-k2-base","score":70.2,"metric":"percent"},{"benchmark":"math","model":"llama-3-70b","score":51,"metric":"final_em"},{"benchmark":"math","model":"llama-3-8b","score":29.1,"metric":"final_em"},{"benchmark":"math","model":"llama-3.1-405b","score":73.8,"metric":"final_em"},{"benchmark":"math","model":"llama-3.1-405b-base","score":53.5,"metric":"em_maj1@1"},{"benchmark":"math","model":"llama-3.1-70b","score":68,"metric":"final_em"},{"benchmark":"math","model":"llama-3.1-70b-base","score":41.6,"metric":"em_maj1@1"},{"benchmark":"math","model":"llama-3.1-8b","score":51.9,"metric":"final_em"},{"benchmark":"math","model":"llama-3.2-1.24b","score":24.8,"metric":"percent"},{"benchmark":"math","model":"llama-3.2-1.24b-base","score":1.6,"metric":"percent"},{"benchmark":"math","model":"llama-4-maverick-17b-128e-base","score":61.2,"metric":"em_maj1@1"},{"benchmark":"math","model":"llama-4-maverick-base","score":61.2,"metric":"em_maj1@1"},{"benchmark":"math","model":"llama-4-scout-17b-16e-base","score":50.3,"metric":"em_maj1@1"},{"benchmark":"math","model":"llama-4-scout-17b-base","score":50.3,"metric":"em_maj1@1"},{"benchmark":"math","model":"mobilellm-r1-140m","score":7.4,"metric":"percent"},{"benchmark":"math","model":"mobilellm-r1-140m-base","score":4.6,"metric":"percent"},{"benchmark":"math","model":"mobilellm-r1-360m","score":26.6,"metric":"percent"},{"benchmark":"math","model":"mobilellm-r1-360m-base","score":13.4,"metric":"percent"},{"benchmark":"math","model":"mobilellm-r1-950m","score":74,"metric":"percent"},{"benchmark":"math","model":"mobilellm-r1-950m-base","score":26.8,"metric":"percent"},{"benchmark":"math","model":"o3-mini","score":97.9,"metric":"percent"},{"benchmark":"math","model":"olmo-2-0425-1b-base","score":5.2,"metric":"percent"},{"benchmark":"math","model":"olmo-2-0425-1b-instruct","score":19.2,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-max","score":68.5,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-72b-instruct","score":62.1,"metric":"percent"},{"benchmark":"math","model":"qwen3-0.6b","score":29.8,"metric":"percent"},{"benchmark":"math","model":"qwen3-0.6b-base","score":29.8,"metric":"percent"},{"benchmark":"math","model":"qwen3-235b-a22b-base","score":71.8,"metric":"percent"},{"benchmark":"math","model":"smollm2-1.7b-base","score":11.6,"metric":"percent"},{"benchmark":"math","model":"smollm2-1.7b-instruct","score":19.2,"metric":"percent"},{"benchmark":"math","model":"smollm2-135m-base","score":0.4,"metric":"percent"},{"benchmark":"math","model":"smollm2-135m-instruct","score":3,"metric":"percent"},{"benchmark":"math","model":"smollm2-360m-base","score":1.8,"metric":"percent"},{"benchmark":"math","model":"smollm2-360m-instruct","score":3.4,"metric":"percent"},{"benchmark":"math500","model":"aquif-3-moe-17b-a2.8b","score":91.4,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v3","score":94,"metric":"percent"},{"benchmark":"math500","model":"ernie-4.5","score":96.4,"metric":"percent"},{"benchmark":"math500","model":"falcon-h1-0.5b-instruct","score":58.4,"metric":"percent"},{"benchmark":"math500","model":"falcon-h1-1.5b","score":74,"metric":"percent"},{"benchmark":"math500","model":"falcon-h1-1.5b-deep","score":77.8,"metric":"percent"},{"benchmark":"math500","model":"falcon-h1-34b-instruct","score":83.8,"metric":"percent"},{"benchmark":"math500","model":"falcon-h1-3b","score":74.2,"metric":"percent"},{"benchmark":"math500","model":"falcon-h1-7b","score":73.4,"metric":"percent"},{"benchmark":"math500","model":"falcon3-10b","score":68.6,"metric":"percent"},{"benchmark":"math500","model":"falcon3-1b","score":19.8,"metric":"percent"},{"benchmark":"math500","model":"falcon3-3b","score":54.2,"metric":"percent"},{"benchmark":"math500","model":"falcon3-7b","score":69,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-12b-it","score":86.2,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-1b-it","score":45.4,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-27b-it","score":88.3,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-4b-it","score":76.4,"metric":"percent"},{"benchmark":"math500","model":"gpt-4.1","score":92.8,"metric":"percent"},{"benchmark":"math500","model":"gpt-4.1-nano","score":84.8,"metric":"percent"},{"benchmark":"math500","model":"gpt-5","score":99.2,"metric":"percent"},{"benchmark":"math500","model":"llama-3.1-8b-base","score":45.8,"metric":"percent"},{"benchmark":"math500","model":"llama-3.2-1.24b-base","score":13.2,"metric":"percent"},{"benchmark":"math500","model":"llama-3.2-3b-base","score":41.2,"metric":"percent"},{"benchmark":"math500","model":"llama-3.3-70b","score":70.6,"metric":"percent"},{"benchmark":"math500","model":"llama-4-scout-17b","score":83.2,"metric":"percent"},{"benchmark":"math500","model":"mistral-small-3.1-24b-instruct","score":88.3,"metric":"percent"},{"benchmark":"math500","model":"phi-4-14b","score":80.8,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-0.5b","score":27.8,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-1.5b","score":48.4,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-32b-instruct","score":82.2,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-3b","score":64.2,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-72b-instruct","score":83.6,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-7b","score":75.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-0.8b","score":46,"metric":"percent"},{"benchmark":"math500","model":"qwen3-1.7b","score":73,"metric":"percent"},{"benchmark":"math500","model":"qwen3-14b","score":89.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-235b-a22b","score":91.2,"metric":"percent"},{"benchmark":"math500","model":"qwen3-32b","score":82,"metric":"percent"},{"benchmark":"math500","model":"qwen3-4b","score":85,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b","score":83.8,"metric":"percent"},{"benchmark":"mathqa","model":"qwen3-32b","score":50.5,"metric":"percent"},{"benchmark":"mathverse-vision","model":"gemma-3-27b-vl","score":34,"metric":"percent"},{"benchmark":"mathverse-vision","model":"glm-4.1v","score":68.4,"metric":"percent"},{"benchmark":"mathverse-vision","model":"glm-4.5v","score":72.1,"metric":"percent"},{"benchmark":"mathverse-vision","model":"internvl3-8b","score":32.4,"metric":"percent"},{"benchmark":"mathverse-vision","model":"internvl3.5-4b","score":40.8,"metric":"percent"},{"benchmark":"mathverse-vision","model":"keye-vl-8b","score":61.7,"metric":"percent"},{"benchmark":"mathverse-vision","model":"kimi-vl-a3b-thinking-2506","score":54.6,"metric":"percent"},{"benchmark":"mathverse-vision","model":"qwen2.5-vl-7b","score":41.2,"metric":"percent"},{"benchmark":"mathverse-vision","model":"r-4b-base","score":64.9,"metric":"percent"},{"benchmark":"mathverse-vision","model":"step-3","score":62.7,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-235b-a22b-thinking","score":85,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gemini-2.5-pro","score":82.9,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gpt-5","score":84.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"claude-opus-4.1","score":70.6,"metric":"percent"},{"benchmark":"mathverse-mini","model":"glm-4.5v","score":72.1,"metric":"percent"},{"benchmark":"mathvision","model":"dots-vlm1","score":69.64,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.5-pro","score":72.34,"metric":"percent"},{"benchmark":"mathvision","model":"gemma-3-27b-vl","score":39.8,"metric":"percent"},{"benchmark":"mathvision","model":"glm-4.1v","score":54.4,"metric":"percent"},{"benchmark":"mathvision","model":"glm-4.5v","score":65.6,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-vl-a3b-thinking-2506","score":54.4,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2.5-vl-72b","score":39.4,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-235b-a22b-thinking","score":74.6,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.5-pro","score":73.3,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5","score":70.9,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.1","score":64.3,"metric":"percent"},{"benchmark":"mathvision","model":"seed1.5-vl-thinking","score":68.77,"metric":"percent"},{"benchmark":"mathvision","model":"step-3","score":64.8,"metric":"percent"},{"benchmark":"mathvista","model":"dots-vlm1","score":85,"metric":"percent"},{"benchmark":"mathvista","model":"gemma-3-27b-vl","score":64.3,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-pro","score":83.5,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.1v","score":80.7,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.5v","score":84.6,"metric":"percent"},{"benchmark":"mathvista","model":"kimi-vl-a3b-thinking-2506","score":80.1,"metric":"percent"},{"benchmark":"mathvista","model":"llama-4-maverick","score":73.7,"metric":"percent"},{"benchmark":"mathvista","model":"llama-4-maverick-17b-128e-instruct","score":73.7,"metric":"percent"},{"benchmark":"mathvista","model":"llama-4-scout-17b","score":70.7,"metric":"percent"},{"benchmark":"mathvista","model":"llama-4-scout-17b-16e","score":70.7,"metric":"percent"},{"benchmark":"mathvista","model":"o3","score":86.8,"metric":"percent"},{"benchmark":"mathvista","model":"qwen2.5-vl-72b","score":74.6,"metric":"percent"},{"benchmark":"mathvista","model":"seed1.5-vl-thinking","score":86.1,"metric":"percent"},{"benchmark":"mathvista","model":"step-3","score":79.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"cambrian-1-34b","score":53.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"cambrian-1-8b","score":49,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-3-haiku","score":46.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-3-opus","score":50.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-3.5-sonnet","score":67.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-opus-4.1","score":75.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-1.5-flash","score":58.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-1.5-pro","score":63.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-2.5-pro","score":82.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4o-0513","score":63.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4v","score":58.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-5","score":81.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2-8b","score":58.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2-llama-3-76b","score":65.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"kimi-vl-a3b-thinking","score":80.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llama-3.2v-11b-instruct","score":51.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llama-3.2v-90b-instruct","score":57.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-1.5-13b","score":27.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-1.5-7b","score":25.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-onevision-72b","score":67.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-onevision-7b","score":63.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"molmo-72b","score":58.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"molmo-7b-d","score":51.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"molmo-7b-o","score":44.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"molmoe-1b","score":34,"metric":"percent"},{"benchmark":"mathvista-mini","model":"paligemma-mix-3b","score":28.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"phi-3.5-vision-4b","score":43.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"pixtral-12b","score":58,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2-vl-72b","score":70.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2-vl-7b","score":58.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-235b-a22b-thinking","score":85.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"seed-1.5-vl","score":85.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"xgen-mm-interleave-4b","score":40.5,"metric":"percent"},{"benchmark":"mbpp","model":"o1-preview","score":95.5,"metric":"percent"},{"benchmark":"mbpp","model":"o1-mini","score":93.1,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-32b-instruct","score":90.5,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-1.5-pro","score":89.7,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-v2-instruct","score":89.4,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3.5-sonnet","score":89.4,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3-opus","score":89.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v3","score":87.6,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2.5","score":87.6,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4o-2024-08-06","score":87.6,"metric":"percent"},{"benchmark":"mbpp","model":"grok-3-beta","score":86,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4-turbo-2024-04-09","score":85.7,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4o-mini-2024-07-18","score":85.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-1.5-flash","score":84.7,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3-sonnet-mar-2024","score":83.6,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-3.5-turbo-nov-2023","score":82.5,"metric":"percent"},{"benchmark":"mbpp","model":"opencoder-8b-instruct","score":82,"metric":"percent"},{"benchmark":"mbpp","model":"artigenz-coder-ds-6.7b","score":80.7,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-33b-instruct","score":80.4,"metric":"percent"},{"benchmark":"mbpp","model":"opencodeinterpreter-ds-33b","score":80.2,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3-haiku-mar-2024","score":80.2,"metric":"percent"},{"benchmark":"mbpp","model":"codeqwen1.5-7b-chat","score":79.4,"metric":"percent"},{"benchmark":"mbpp","model":"magicoder-s-ds-6.7b","score":79.4,"metric":"percent"},{"benchmark":"mbpp","model":"whiterabbitneo-33b-v1","score":79.4,"metric":"percent"},{"benchmark":"mbpp","model":"starcoder2-15b-instruct-v0.1","score":78,"metric":"percent"},{"benchmark":"mbpp","model":"xwincoder-34b","score":77,"metric":"percent"},{"benchmark":"mbpp","model":"opencodeinterpreter-ds-6.7b","score":76.5,"metric":"percent"},{"benchmark":"mbpp","model":"code-millenials-34b","score":76.2,"metric":"percent"},{"benchmark":"mbpp","model":"dream-7b-base","score":68.7,"metric":"percent"},{"benchmark":"mbpp","model":"dream-7b-instruct","score":68.3,"metric":"percent"},{"benchmark":"mbpp","model":"llada-8b-instruct","score":31.5,"metric":"percent"},{"benchmark":"mbpp","model":"coda-1.7b-instruct","score":47.2,"metric":"percent"},{"benchmark":"mbpp","model":"coda-1.7b-base","score":35.2,"metric":"percent"},{"benchmark":"mbpp","model":"speechless-coder-ds-6.7b","score":75.9,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-1.0-pro","score":75.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-7b-instruct-v1.5","score":75.2,"metric":"percent"},{"benchmark":"mbpp","model":"wizardcoder-python-34b-v1.0","score":75.1,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-6.7b-instruct","score":74.9,"metric":"percent"},{"benchmark":"mbpp","model":"wavecoder-ultra-6.7b","score":74.9,"metric":"percent"},{"benchmark":"mbpp","model":"starchat2-15b-v0.1","score":74.9,"metric":"percent"},{"benchmark":"mbpp","model":"command-r-plus","score":74.3,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x22b-instruct-v0.1","score":73.8,"metric":"percent"},{"benchmark":"mbpp","model":"speechless-codellama-34b-v2.0","score":73.8,"metric":"percent"},{"benchmark":"mbpp","model":"codeqwen1.5-7b","score":73.5,"metric":"percent"},{"benchmark":"mbpp","model":"speechless-starcoder2-15b","score":73.5,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-large","score":72.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-72b-chat","score":72.5,"metric":"percent"},{"benchmark":"mbpp","model":"codestral-22b-v0.1","score":72.5,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-6.7b-base","score":72,"metric":"percent"},{"benchmark":"mbpp","model":"magicoder-s-cl-7b","score":70.6,"metric":"percent"},{"benchmark":"mbpp","model":"dolphin-2.6-mixtral-8x7b","score":70.6,"metric":"percent"},{"benchmark":"mbpp","model":"codegemma-7b-it","score":70.4,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-34b","score":69.3,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-8b-instruct","score":68.3,"metric":"percent"},{"benchmark":"mbpp","model":"databricks-dbrx-instruct","score":67.2,"metric":"percent"},{"benchmark":"mbpp","model":"speechless-starcoder2-7b","score":66.7,"metric":"percent"},{"benchmark":"mbpp","model":"phi-3-mini-4k-instruct","score":65.9,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-1.3b-instruct","score":65.3,"metric":"percent"},{"benchmark":"mbpp","model":"codegemma-7b","score":65.1,"metric":"percent"},{"benchmark":"mbpp","model":"wizardcoder-15b-v1.0","score":64.3,"metric":"percent"},{"benchmark":"mbpp","model":"speechless-coding-7b-16k-tora","score":64.2,"metric":"percent"},{"benchmark":"mbpp","model":"phi-2-2.7b","score":64,"metric":"percent"},{"benchmark":"mbpp","model":"openchat-3.5-7b-0106","score":63.8,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-13b","score":63.5,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b","score":59.5,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x7b-instruct-v0.1","score":59.5,"metric":"percent"},{"benchmark":"mbpp","model":"wizardcoder-python-7b-v1.0","score":58.5,"metric":"percent"},{"benchmark":"mbpp","model":"mistralhermes-codepro-7b-v1","score":57.4,"metric":"percent"},{"benchmark":"mbpp","model":"speechless-code-mistral-7b-v1.0","score":57.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-1.1-7b-it","score":57.1,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-1.3b-base","score":56.9,"metric":"percent"},{"benchmark":"mbpp","model":"codet5-16b","score":56.6,"metric":"percent"},{"benchmark":"mbpp","model":"codegemma-2b","score":55.6,"metric":"percent"},{"benchmark":"mbpp","model":"starcoder-15b","score":55.1,"metric":"percent"},{"benchmark":"mbpp","model":"codegen-16b","score":54.2,"metric":"percent"},{"benchmark":"mbpp","model":"codet5-6b","score":52.9,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-7b","score":52.6,"metric":"percent"},{"benchmark":"mbpp","model":"openhermes-2.5-code-290k-13b","score":52.4,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b","score":51.9,"metric":"percent"},{"benchmark":"mbpp","model":"codegen-6b","score":50.8,"metric":"percent"},{"benchmark":"mbpp","model":"xdan-l1-chat-rl-v1-7b","score":50.3,"metric":"percent"},{"benchmark":"mbpp","model":"codet5-2b","score":48.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-7b-it","score":47.1,"metric":"percent"},{"benchmark":"mbpp","model":"codegen-2b","score":46.3,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-instruct-v0.2","score":44.7,"metric":"percent"},{"benchmark":"mbpp","model":"solar-10.7b-instruct-v1.0","score":43.9,"metric":"percent"},{"benchmark":"mbpp","model":"zephyr-7b-beta","score":42.1,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2b","score":41.8,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-1.1-2b-it","score":29.8,"metric":"percent"},{"benchmark":"mbpp","model":"zyte-1b","score":9.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ernie-4.5","score":81,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon-h1-0.5b-instruct","score":33.07,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon-h1-1.5b","score":56.35,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon-h1-1.5b-deep","score":56.61,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon-h1-34b-instruct","score":71.43,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon-h1-3b","score":67.46,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon-h1-7b","score":68.78,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon3-10b","score":64.02,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon3-1b","score":17.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon3-3b","score":55.29,"metric":"percent"},{"benchmark":"mbpp-plus","model":"falcon3-7b","score":65.87,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-12b-it","score":72.22,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-1b-it","score":50,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-27b-it","score":74.07,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-4b-it","score":66.93,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4.1","score":79.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-70b","score":82.5,"metric":"pass@1"},{"benchmark":"mbpp-plus","model":"llama-3-8b","score":70.6,"metric":"pass@1"},{"benchmark":"mbpp-plus","model":"llama-3.1-405b","score":88.6,"metric":"pass@1"},{"benchmark":"mbpp-plus","model":"llama-3.1-70b","score":86,"metric":"pass@1"},{"benchmark":"mbpp-plus","model":"llama-3.1-8b","score":72.8,"metric":"pass@1"},{"benchmark":"mbpp-plus","model":"llama-3.1-8b-base","score":55.03,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.2-1.24b-base","score":29.37,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.2-3b-base","score":50.53,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.3-70b","score":73.81,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-4-scout-17b","score":64.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-0.5b","score":39.68,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-1.5b","score":56.08,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-32b-instruct","score":74.07,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-3b","score":60.85,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-72b-instruct","score":75.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-7b","score":68.25,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-0.8b","score":47.08,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-1.7b","score":49.74,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-235b-a22b","score":77,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-32b","score":71.96,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-4b","score":59.79,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-8b","score":62.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"o1-preview","score":80.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"o1-mini","score":78.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-32b-instruct","score":77,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-v2-instruct","score":75.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-1.5-pro","score":74.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3.5-sonnet","score":74.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v2.5","score":74.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4-turbo","score":73.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3-opus","score":73.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3","score":73,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4o-2024-08-06","score":72.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4o-mini-2024-07-18","score":72.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"opencoder-8b-instruct","score":71.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-33b-instruct","score":70.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-3.5-turbo-nov-2023","score":69.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"artigenz-coder-ds-6.7b","score":69.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3-sonnet-mar-2024","score":69.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codeqwen1.5-7b-chat","score":69,"metric":"percent"},{"benchmark":"mbpp-plus","model":"magicoder-s-ds-6.7b","score":69,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3-haiku-mar-2024","score":68.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"opencodeinterpreter-ds-33b","score":68.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-1.5-flash","score":67.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"whiterabbitneo-33b-v1","score":66.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"opencodeinterpreter-ds-6.7b","score":66.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-6.7b-instruct","score":65.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"grok-3-beta","score":65.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"starcoder2-15b-instruct-v0.1","score":65.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"xwincoder-34b","score":64.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"starchat2-15b-v0.1","score":64.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"code-millenials-34b","score":64.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"speechless-coder-ds-6.7b","score":64.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mixtral-8x22b-instruct-v0.1","score":64.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"command-r-plus","score":63.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"wavecoder-ultra-6.7b","score":63.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"wizardcoder-python-34b-v1.0","score":63.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"speechless-starcoder2-15b","score":62.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-7b-instruct-v1.5","score":62.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codestral-22b-v0.1","score":61.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen1.5-72b-chat","score":61.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-1.0-pro","score":61.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"speechless-codellama-34b-v2.0","score":61.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codeqwen1.5-7b","score":60.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"magicoder-s-cl-7b","score":60.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistral-large","score":59.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"dolphin-2.6-mixtral-8x7b","score":59,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-6.7b-base","score":58.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"coda-1.7b-instruct","score":63.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"dream-7b-base","score":57.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"dream-7b-instruct","score":56.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llada-8b-instruct","score":28.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"coda-1.7b-base","score":46,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codegemma-7b-it","score":56.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codellama-34b","score":56.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"speechless-starcoder2-7b","score":56.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"databricks-dbrx-instruct","score":55.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.1-8b-instruct","score":55.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-1.3b-instruct","score":54.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"openchat-3.5-7b-0106","score":54.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"wizardcoder-15b-v1.0","score":54.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"phi-3-mini-4k-instruct","score":54.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"phi-2-2.7b","score":54.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codellama-13b","score":52.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codegemma-7b","score":52.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"speechless-coding-7b-16k-tora","score":50.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mixtral-8x7b-instruct-v0.1","score":49.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"wizardcoder-python-7b-v1.0","score":49.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"speechless-code-mistral-7b-v1.0","score":48.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-1.3b-base","score":47.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codet5-16b","score":47.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codellama-7b","score":46.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codegemma-2b","score":46.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistralhermes-codepro-7b-v1","score":46.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"starcoder-15b","score":46.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"openhermes-2.5-code-290k-13b","score":45.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codegen-16b","score":45.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-1.1-7b-it","score":45,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-7b","score":43.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codegen-6b","score":42.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistral-7b","score":42.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codet5-6b","score":41.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"xdan-l1-chat-rl-v1-7b","score":41.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codet5-2b","score":38.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-7b-it","score":36.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"solar-10.7b-instruct-v1.0","score":36.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codegen-2b","score":36,"metric":"percent"},{"benchmark":"mbpp-plus","model":"zephyr-7b-beta","score":34.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-2b","score":34.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-1.1-2b-it","score":23.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"zyte-1b","score":7.5,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-opus-4.1","score":29.9,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-sonnet-4","score":28.2,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5","score":46.9,"metric":"percent"},{"benchmark":"mcpmark","model":"grok-4","score":31.7,"metric":"percent"},{"benchmark":"mcpmark","model":"grok-code-fast-1","score":20.5,"metric":"percent"},{"benchmark":"mcpmark","model":"kimi-k2-instruct","score":21.9,"metric":"percent"},{"benchmark":"mcpmark","model":"o3","score":25.4,"metric":"percent"},{"benchmark":"mcpmark","model":"o4-mini","score":17.3,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3-coder-plus","score":24.8,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3-max-instruct-preview","score":17.7,"metric":"percent"},{"benchmark":"meeseeks-zh","model":"longcat-flash","score":43.03,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3.5-haiku","score":85.6,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3.5-sonnet","score":92,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3-opus","score":90.7,"metric":"percent"},{"benchmark":"mgsm","model":"gemini-1.5-pro","score":87.5,"metric":"percent"},{"benchmark":"mgsm","model":"gemma-3-1b-it","score":43.6,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4-turbo","score":88.5,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4o","score":90.5,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4o-mini","score":87,"metric":"percent"},{"benchmark":"mgsm","model":"lfm2-1.2b","score":55.04,"metric":"percent"},{"benchmark":"mgsm","model":"lfm2-350m","score":29.52,"metric":"percent"},{"benchmark":"mgsm","model":"lfm2-700m","score":45.36,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.1-405b","score":91.6,"metric":"em"},{"benchmark":"mgsm","model":"llama-3.1-70b","score":86.9,"metric":"em"},{"benchmark":"mgsm","model":"llama-3.1-8b","score":68.9,"metric":"em"},{"benchmark":"mgsm","model":"llama-3.2-1.24b","score":29.12,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.2-90b-vision","score":86.9,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.3-70b","score":91.1,"metric":"percent"},{"benchmark":"mgsm","model":"llama-4-maverick","score":92.3,"metric":"percent"},{"benchmark":"mgsm","model":"llama-4-maverick-17b-128e-instruct","score":92.3,"metric":"percent"},{"benchmark":"mgsm","model":"llama-4-maverick-17b-128e-base","score":92.3,"metric":"percent"},{"benchmark":"mgsm","model":"llama-4-scout-17b","score":90.6,"metric":"percent"},{"benchmark":"mgsm","model":"llama-4-scout-17b-16e","score":90.6,"metric":"percent"},{"benchmark":"mgsm","model":"llama-4-scout-17b-16e-base","score":90.6,"metric":"percent"},{"benchmark":"mgsm","model":"o1","score":90.8,"metric":"percent"},{"benchmark":"mgsm","model":"o3-mini","score":92,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-0.6b","score":41.28,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-1.7b","score":66.56,"metric":"percent"},{"benchmark":"mgsm","model":"claude-opus-4-1-20250805-thinking","score":94.4,"metric":"percent"},{"benchmark":"mgsm","model":"claude-opus-4.1-20250805","score":94.2,"metric":"percent"},{"benchmark":"mgsm","model":"claude-opus-4","score":93.8,"metric":"percent"},{"benchmark":"mgsm","model":"o4-mini","score":93.4,"metric":"percent"},{"benchmark":"mgsm","model":"claude-sonnet-4","score":93,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3.7-sonnet-thinking","score":93,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-5","score":92.8,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3.5-sonnet-20241022","score":92.6,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-5-mini","score":92.6,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-235b-a22b","score":92.5,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-max-instruct-preview","score":92.4,"metric":"percent"},{"benchmark":"mgsm","model":"llama-4-maverick","score":92.4,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3.7-sonnet","score":92.4,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-r1","score":92.3,"metric":"percent"},{"benchmark":"mgsm","model":"gemini-2.5-pro-exp-03.25","score":92.2,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v3","score":92.1,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-oss-120b","score":92,"metric":"percent"},{"benchmark":"mgsm","model":"o3","score":91.7,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v3-0324","score":91.7,"metric":"percent"},{"benchmark":"mgsm","model":"grok-3","score":91.3,"metric":"percent"},{"benchmark":"mgsm","model":"o3-mini","score":91.3,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.3-instruct-turbo-70b","score":91.1,"metric":"percent"},{"benchmark":"mgsm","model":"kimi-k2-instruct","score":90.9,"metric":"percent"},{"benchmark":"mgsm","model":"grok-4","score":90.9,"metric":"percent"},{"benchmark":"mgsm","model":"claude-sonnet-4-thinking","score":90.9,"metric":"percent"},{"benchmark":"mgsm","model":"mistral-medium-3.1","score":90.9,"metric":"percent"},{"benchmark":"mgsm","model":"glm-4.5","score":90.8,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4o-2024-08-06","score":90.7,"metric":"percent"},{"benchmark":"mgsm","model":"grok-3-mini-fast-high-reasoning","score":90.4,"metric":"percent"},{"benchmark":"mgsm","model":"grok-3-mini-fast-low-reasoning","score":90.4,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4o-2024-11-20","score":90.4,"metric":"percent"},{"benchmark":"mgsm","model":"gemini-2.5-flash-preview-05-20-thinking","score":90,"metric":"percent"},{"benchmark":"mgsm","model":"gemini-2.5-flash-preview-05-20","score":89.8,"metric":"percent"},{"benchmark":"mgsm","model":"o1","score":89.3,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-5-nano","score":89.3,"metric":"percent"},{"benchmark":"mgsm","model":"gemini-1.5-pro-002","score":89.2,"metric":"percent"},{"benchmark":"mgsm","model":"gemini-2.0-flash-001","score":89,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-oss-20b","score":89,"metric":"percent"},{"benchmark":"mgsm","model":"llama-4-scout","score":88,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4.1-mini","score":87.8,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4.1","score":87.7,"metric":"percent"},{"benchmark":"mgsm","model":"mistral-large-2411","score":87.2,"metric":"percent"},{"benchmark":"mgsm","model":"gemini-1.5-flash-002","score":86.6,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.3-nemotron-super-thinking","score":86.4,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4o-mini","score":86.2,"metric":"percent"},{"benchmark":"mgsm","model":"grok-2","score":86.1,"metric":"percent"},{"benchmark":"mgsm","model":"command-a","score":85.7,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3.5-haiku-20241022","score":84.6,"metric":"percent"},{"benchmark":"mgsm","model":"mistral-small-3.1-24b-instruct","score":84.2,"metric":"percent"},{"benchmark":"mgsm","model":"mistral-small-1.0","score":84,"metric":"percent"},{"benchmark":"mgsm","model":"jamba-1.5-large","score":77.4,"metric":"percent"},{"benchmark":"mgsm","model":"jamba-1.6-large","score":71.2,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4.1-nano","score":69.3,"metric":"percent"},{"benchmark":"mgsm","model":"jamba-mini-1.6","score":41.7,"metric":"percent"},{"benchmark":"mgsm","model":"jamba-1.5-mini","score":29.6,"metric":"percent"},{"benchmark":"mcp-universe","model":"gpt-5-high","score":44.16,"metric":"percent"},{"benchmark":"mcp-universe","model":"gpt-5-medium","score":43.72,"metric":"percent"},{"benchmark":"mcp-universe","model":"grok-4","score":33.33,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-sonnet-4-thinking","score":30.3,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-opus-4.1","score":29.44,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-sonnet-4","score":29.44,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-opus-4","score":28.14,"metric":"percent"},{"benchmark":"mcp-universe","model":"grok-4-fast","score":27.27,"metric":"percent"},{"benchmark":"mcp-universe","model":"grok-code-fast-1","score":26.41,"metric":"percent"},{"benchmark":"mcp-universe","model":"o3-mini-medium","score":26.41,"metric":"percent"},{"benchmark":"mcp-universe","model":"o4-mini-medium","score":25.97,"metric":"percent"},{"benchmark":"mcp-universe","model":"glm-4.5","score":24.68,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-3.7-sonnet","score":24.24,"metric":"percent"},{"benchmark":"mcp-universe","model":"qwen3-coder-480b-a35b-instruct","score":22.94,"metric":"percent"},{"benchmark":"mcp-universe","model":"gemini-2.5-pro","score":22.08,"metric":"percent"},{"benchmark":"mcp-universe","model":"deepseek-v3.1","score":22.08,"metric":"percent"},{"benchmark":"mcp-universe","model":"gemini-2.5-flash","score":21.65,"metric":"percent"},{"benchmark":"mcp-universe","model":"deepseek-v3.1-terminus","score":21.65,"metric":"percent"},{"benchmark":"mcp-universe","model":"kimi-k2-instruct-0905","score":19.91,"metric":"percent"},{"benchmark":"mcp-universe","model":"glm-4.5-air","score":19.48,"metric":"percent"},{"benchmark":"mcp-universe","model":"kimi-k2-instruct-0711","score":19.05,"metric":"percent"},{"benchmark":"mcp-universe","model":"gpt-4.1","score":18.18,"metric":"percent"},{"benchmark":"mcp-universe","model":"qwen3-max-instruct-preview","score":18.18,"metric":"percent"},{"benchmark":"mcp-universe","model":"qwen3-235b-a22b-instruct-2507","score":18.18,"metric":"percent"},{"benchmark":"mcp-universe","model":"gpt-4o-2024-08-06","score":15.58,"metric":"percent"},{"benchmark":"mcp-universe","model":"deepseek-v3","score":14.29,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"llama-3.3-70b","score":92.2,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"llama-3.1-405b","score":90.9,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-1.5-flash","score":87.7,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gpt-4o","score":86.4,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"o3-mini-high","score":86.4,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-1.5-pro","score":85.5,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-2.5-pro-preview-05-06","score":85,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-2.0-flash","score":85,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"o3-mini","score":84.5,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"grok-2","score":82.7,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gpt-4.5","score":80.5,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-3.5-haiku","score":76.4,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"command-r","score":76.4,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"o4-mini","score":75.5,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-3.5-sonnet","score":75,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"o1","score":71.8,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-opus-4.1","score":65.9,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-sonnet-4","score":65.5,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"grok-4","score":65,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-3.7-sonnet","score":64.5,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-3.7-sonnet-thinking","score":63.6,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"o3","score":62.7,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gpt-5-thinking","score":56.8,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-sonnet-4.5","score":53.6,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-4.5-sonnet-thinking","score":40,"metric":"percent"},{"benchmark":"mixeval","model":"afm-4.5b","score":73.75,"metric":"percent"},{"benchmark":"mixeval","model":"gemma-3-4b-it","score":64.3,"metric":"percent"},{"benchmark":"mixeval","model":"qwen3-4b","score":77.05,"metric":"percent"},{"benchmark":"mixeval","model":"smollm3-3b","score":72.8,"metric":"percent"},{"benchmark":"mixeval-hard","model":"llama-3.1-3b","score":24.9,"metric":"percent"},{"benchmark":"mixeval-hard","model":"qwen2.5-3b","score":27.6,"metric":"percent"},{"benchmark":"mixeval-hard","model":"qwen3-1.7b","score":24.3,"metric":"percent"},{"benchmark":"mixeval-hard","model":"qwen3-4b","score":31.6,"metric":"percent"},{"benchmark":"mixeval-hard","model":"smollm3-3b","score":26.9,"metric":"percent"},{"benchmark":"mlogiqa","model":"qwen3-32b","score":62.8,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-235b-a22b-thinking","score":83.8,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-2.5-pro","score":85.6,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5","score":86.2,"metric":"percent"},{"benchmark":"mlvu","model":"claude-opus-4.1","score":73.5,"metric":"percent"},{"benchmark":"mlvu","model":"seed1.5-vl-thinking","score":82.1,"metric":"percent"},{"benchmark":"mlvu","model":"smolvlm2-0.256b","score":40.6,"metric":"percent"},{"benchmark":"mlvu","model":"smolvlm2-0.5b","score":47.3,"metric":"percent"},{"benchmark":"mlvu","model":"smolvlm2-2.2b","score":55.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"claude-3.7-sonnet","score":83.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemma-3-27b-vl","score":84.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemma-3-27b-it","score":82.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"glm-4.1v","score":84.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"glm-4.5v","score":88.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4o","score":84.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl-8b","score":82.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"keye-vl-8b","score":89.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"kimi-vl-a3b-thinking-2506","score":80.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mimo-vl-7b-rl","score":82,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mimo-vl-7b-sft","score":81.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-235b-a22b-thinking","score":90.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemini-2.5-pro","score":90.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gpt-5","score":85.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"claude-opus-4.1","score":84.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"seed1.5-vl-thinking","score":89.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"minicpm-v-2.0-3b","score":69.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"vila1.5-3b","score":61.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"phi-3-vision-4b","score":78.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"mm1.5-3b","score":72.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"internvl2.5-2b","score":77.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"internvl2.5-4b","score":78.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen2.5-vl-3b","score":76.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"janus-pro-1.5b","score":75.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"harmon-1.5b","score":65.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"blip-3o-4b","score":78.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"emu3-8b","score":58.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"janus-pro-7b","score":79.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen2.5-omni-7b","score":74.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"bagel-14b","score":85,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"manzano-3b","score":78.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"manzano-30b","score":83.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemini-1.5-pro","score":82.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemini-2.5-pro","score":86.3,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-235b-a22b-thinking","score":8.5,"metric":"score"},{"benchmark":"mm-mt-bench","model":"gemini-2.5-pro","score":8.4,"metric":"score"},{"benchmark":"mm-mt-bench","model":"gpt-5","score":7.6,"metric":"score"},{"benchmark":"mm-mt-bench","model":"claude-opus-4.1","score":7.8,"metric":"score"},{"benchmark":"miabench","model":"qwen3-vl-235b-a22b-thinking","score":92.7,"metric":"percent"},{"benchmark":"miabench","model":"gemini-2.5-pro","score":92.3,"metric":"percent"},{"benchmark":"miabench","model":"gpt-5","score":92.4,"metric":"percent"},{"benchmark":"miabench","model":"claude-opus-4.1","score":91.2,"metric":"percent"},{"benchmark":"miabench","model":"seed1.5-vl-thinking","score":92.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2.5-vl-7b","score":83.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"step-3","score":81.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2.5-vl-72b","score":88.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.5-pro","score":89,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"seed1.5-vl-thinking","score":89.78,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"dots-vlm1","score":88.24,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3.7-sonnet","score":84.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemma-3-27b-vl","score":80.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemma-3-27b-it","score":81.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4.1v","score":85.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4.5v","score":88.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o","score":84.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl-8b","score":83.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"keye-vl-8b","score":89.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"kimi-vl-a3b-thinking-2506","score":84.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mimo-vl-7b-rl","score":84.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mimo-vl-7b-sft","score":84.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2.5-vl-7b","score":83.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"step-3","score":81.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2.5-vl-72b","score":89.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.5-pro","score":89.55,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"seed1.5-vl-thinking","score":89.47,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"dots-vlm1","score":89.32,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"claude-3.7-sonnet","score":40.6,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"gemma-3-27b-it","score":47.9,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"gpt-4o","score":58.5,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"internvl-8b","score":58.5,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"mimo-vl-7b-rl","score":55.5,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"mimo-vl-7b-sft","score":55,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"qwen2.5-vl-7b","score":51.2,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"claude-3.7-sonnet","score":50.8,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gemma-3-27b-it","score":51.9,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gpt-4o","score":57.5,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl-8b","score":56.1,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"mimo-vl-7b-rl","score":59.1,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"mimo-vl-7b-sft","score":57.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen2.5-vl-7b","score":57.4,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gemma-3-27b-vl","score":28.4,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"glm-4.1v","score":42.4,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"glm-4.5v","score":44.7,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-235b-a22b-thinking","score":56.2,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gemini-2.5-pro","score":55.6,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gpt-5","score":51.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"claude-opus-4.1","score":54.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"seed1.5-vl-thinking","score":52.7,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"kimi-vl-a3b-thinking-2506","score":42.1,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"step-3","score":31.8,"metric":"percent"},{"benchmark":"mmlu","model":"afm-4.5b","score":65.88,"metric":"percent"},{"benchmark":"mmlu","model":"apriel-5b-instruct","score":64.6,"metric":"percent"},{"benchmark":"mmlu","model":"aquif-3-0.4b","score":55.6,"metric":"percent"},{"benchmark":"mmlu","model":"aquif-3-3.2b","score":67.5,"metric":"percent"},{"benchmark":"mmlu","model":"aquif-3-moe-17b-a2.8b","score":83.2,"metric":"percent"},{"benchmark":"mmlu","model":"aquif-3.5-2.7b","score":70.2,"metric":"percent"},{"benchmark":"mmlu","model":"aquif-3.5-a0.6b","score":60.5,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3.7-sonnet","score":90.2,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-4","score":92.8,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-4.1","score":93.4,"metric":"percent"},{"benchmark":"mmlu","model":"claude-sonnet-4","score":91.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-r1","score":90.3,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3","score":86.5,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3-base","score":87.2,"metric":"percent"},{"benchmark":"mmlu","model":"ernie-4.5","score":86.5,"metric":"percent"},{"benchmark":"mmlu","model":"exaone-3.5-2.4b","score":60.4,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-h1-0.5b-instruct","score":53.4,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-h1-1.5b","score":62.03,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-h1-1.5b-deep","score":66.11,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-h1-34b-instruct","score":84.05,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-h1-3b","score":68.3,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-h1-7b","score":76.83,"metric":"percent"},{"benchmark":"mmlu","model":"falcon3-10b","score":74.01,"metric":"percent"},{"benchmark":"mmlu","model":"falcon3-1b","score":46.1,"metric":"percent"},{"benchmark":"mmlu","model":"falcon3-3b","score":56.76,"metric":"percent"},{"benchmark":"mmlu","model":"falcon3-7b","score":70.81,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-2.5-pro","score":92.4,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-2b","score":42.3,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-7b","score":64.3,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-12b-it","score":72.5,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-1b-it","score":40.08,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b-it","score":78.6,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-4b-it","score":59.63,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-4b-it","score":59.6,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-pt-1b","score":26.1,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-pt-270m","score":26.5,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.5-base","score":86.1,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4.1","score":90.3,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4.1-nano","score":80.1,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-5","score":93.5,"metric":"percent"},{"benchmark":"mmlu","model":"grok-4","score":91.6,"metric":"percent"},{"benchmark":"mmlu","model":"kimi-k2-base","score":87.8,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2-1.2b","score":55.23,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2-350m","score":43.43,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2-700m","score":49.9,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-70b","score":82,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3-70b","score":80.9,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3-70b-base","score":79.5,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"llama-3-8b","score":68.5,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3-8b","score":65.3,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3-8b-base","score":66.7,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"llama-3.1-405b","score":87.3,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3.1-405b","score":88.6,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3.1-405b-base","score":85.2,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"llama-3.1-70b","score":83.6,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3.1-70b","score":86,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3.1-70b-base","score":79.3,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"llama-3.1-8b","score":69.4,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3.1-8b","score":73,"metric":"macro_avg/acc"},{"benchmark":"mmlu","model":"llama-3.1-8b-base","score":68.67,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-8b-base","score":66.7,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"llama-3.2-1.24b","score":46.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.2-1.24b-base","score":32,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.2-3b-base","score":61.74,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.3-70b","score":82.08,"metric":"percent"},{"benchmark":"mmlu","model":"llama-4-maverick-17b-128e-base","score":85.5,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"llama-4-maverick-base","score":85.5,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"llama-4-scout-17b","score":80.4,"metric":"percent"},{"benchmark":"mmlu","model":"llama-4-scout-17b-16e-base","score":79.6,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"llama-4-scout-17b-base","score":79.6,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu","model":"mistral-small-3.1-24b-instruct","score":80.5,"metric":"percent"},{"benchmark":"mmlu","model":"mobilellm-r1-360m-base","score":26.8,"metric":"percent"},{"benchmark":"mmlu","model":"mobilellm-r1-950m-base","score":47.4,"metric":"percent"},{"benchmark":"mmlu","model":"o3","score":92.3,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-2-0425-1b-base","score":42.4,"metric":"percent"},{"benchmark":"mmlu","model":"phi-4-14b","score":84.8,"metric":"percent"},{"benchmark":"mmlu","model":"phi-4-mini-3.8b","score":67.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-max","score":87.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-0.5b","score":46.07,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-1.5b","score":59.76,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-32b-instruct","score":82.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-3b","score":65.09,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-72b-instruct","score":86.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-7b","score":73.64,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-0.6b","score":44.93,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-0.6b-base","score":52.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-0.8b","score":44.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-1.7b","score":59.11,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-14b","score":82,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-235b-a22b","score":85.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-235b-a22b-base","score":87.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-32b","score":80.89,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-4b","score":70.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-4b","score":44.97,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b","score":71.56,"metric":"percent"},{"benchmark":"mmlu","model":"smollm3-3b","score":59.53,"metric":"percent"},{"benchmark":"mmlu","model":"smollm2-1.7b-base","score":50,"metric":"percent"},{"benchmark":"mmlu","model":"smollm2-360m-base","score":24.7,"metric":"percent"},{"benchmark":"mmlu-cf","model":"qwen3-4b-base","score":47.65,"metric":"percent"},{"benchmark":"mmlu-cloze","model":"smollm2-135m-base","score":31.5,"metric":"percent"},{"benchmark":"mmlu-cloze","model":"smollm2-135m-instruct","score":29.3,"metric":"percent"},{"benchmark":"mmlu-cloze","model":"smollm2-135m-pretrained","score":31.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3.7-sonnet","score":81,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.1","score":87.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3","score":81.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.1","score":84.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.1-terminus","score":85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.2-exp","score":85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ernie-4.5","score":78.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ernie-4.5-21b-a3b-pt","score":65.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-3-1b-base","score":3.91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-e-1b-base","score":17.82,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-h1-0.5b-instruct","score":31.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-h1-1.5b","score":37.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-h1-1.5b-deep","score":41.89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-h1-34b-instruct","score":58.73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-h1-3b","score":43.69,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-h1-7b","score":51.75,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon3-10b","score":44.05,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon3-1b","score":18.49,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon3-3b","score":29.71,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon3-7b","score":40.73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-flash-thinking","score":81.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-pro","score":86,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-12b-it","score":39.88,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-1b-it","score":14.46,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-27b-it","score":45.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-4b-it","score":29.71,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4.1","score":80.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4.5","score":86.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4o","score":69.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5","score":87.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b","score":65.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-4","score":87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"hunyuan-t1","score":87.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"internvl-8b","score":58.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-mini-2.0","score":65.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-70b","score":63.4,"metric":"micro_avg/acc_char"},{"benchmark":"mmlu-pro","model":"llama-3-70b-base","score":55,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu-pro","model":"llama-3-8b","score":45.5,"metric":"micro_avg/acc_char"},{"benchmark":"mmlu-pro","model":"llama-3-8b-base","score":36.2,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu-pro","model":"llama-3.1-405b","score":73.4,"metric":"micro_avg/acc_char"},{"benchmark":"mmlu-pro","model":"llama-3.1-405b-base","score":61.6,"metric":"macro_avg/em"},{"benchmark":"mmlu-pro","model":"llama-3.1-70b","score":66.4,"metric":"micro_avg/acc_char"},{"benchmark":"mmlu-pro","model":"llama-3.1-70b-base","score":53.8,"metric":"macro_avg/em"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b","score":48.3,"metric":"micro_avg/acc_char"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b-base","score":36.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b-base","score":37.1,"metric":"macro_avg/acc_char"},{"benchmark":"mmlu-pro","model":"llama-3.2-1.24b-base","score":16.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-3b-base","score":27.44,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.3-70b","score":68.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-spark-8b","score":30.23,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-maverick","score":80.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-maverick-17b-128e-instruct","score":80.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-maverick-17b-128e-base","score":62.9,"metric":"macro_avg/em"},{"benchmark":"mmlu-pro","model":"llama-4-maverick-base","score":62.9,"metric":"macro_avg/em"},{"benchmark":"mmlu-pro","model":"llama-4-scout-17b","score":74.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-scout-17b-16e","score":74.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-scout-17b-16e-base","score":58.2,"metric":"macro_avg/em"},{"benchmark":"mmlu-pro","model":"llama-4-scout-17b-base","score":58.2,"metric":"macro_avg/em"},{"benchmark":"mmlu-pro","model":"mimo-vl-7b-rl","score":64.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-vl-7b-sft","score":59.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"o1","score":89.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"o3-high","score":85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openreasoning-nemotron-1.5b","score":47.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openreasoning-nemotron-14b","score":77.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openreasoning-nemotron-32b","score":80,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openreasoning-nemotron-7b","score":71.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-max","score":69,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-0.5b","score":18.73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-1.5b","score":28.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-32b-instruct","score":56.63,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-3b","score":32.76,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-72b-instruct","score":58.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-7b","score":43.23,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-vl-7b","score":48.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-0.6b","score":13.98,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-0.8b","score":16.95,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":23.54,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":57,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-a22b","score":83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-a22b-thinking-2507","score":84.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b","score":78.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-thinking-2507","score":80.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b","score":54.68,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b-nothinking","score":71.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b-thinking","score":79.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b","score":29.75,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b","score":70,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b-instruct-2507","score":62.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b","score":34.64,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b-nothinking-2504","score":52.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-next-80b-a3b-instruct","score":80.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-next-80b-a3b-thinking","score":82.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed1.5-thinking","score":87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed1.6","score":86.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm2-1.7b-base","score":3.91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm2-360m-base","score":1.88,"metric":"percent"},{"benchmark":"mmlu-pro-cf","model":"qwen3-4b-base","score":24.92,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"llama-1b","score":12.7,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"llama-1b-pretrained","score":11.7,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"qwen2.5-1.5b-instruct","score":24.2,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"qwen2.5-1.5b-pretrained","score":13.7,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"qwen3-4b-base","score":41.07,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"smollm1-1.7b-instruct","score":11.7,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"smollm1-1.7b-pretrained","score":10.8,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"smollm2-1.7b-instruct","score":19.3,"metric":"percent"},{"benchmark":"mmlu-pro-mcf","model":"smollm2-1.7b-pretrained","score":19.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"gemini-2.5-flash-thinking","score":80.2,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-235b-a22b","score":79.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-235b-a22b-thinking-2507","score":81,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-30b-a3b","score":72,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-30b-a3b-thinking-2507","score":76.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-32b-nothinking","score":69.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-32b-thinking","score":74.6,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-next-80b-a3b-instruct","score":76.7,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-next-80b-a3b-thinking","score":78.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3.1-thinking","score":93.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemini-2.5-flash-thinking","score":92.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-235b-a22b","score":93.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-235b-a22b-thinking-2507","score":93.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-30b-a3b","score":81.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-30b-a3b-thinking-2507","score":91.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-32b-nothinking","score":85.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-32b-thinking","score":90.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-next-80b-a3b-instruct","score":90.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-next-80b-a3b-thinking","score":92.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon-h1-0.5b-instruct","score":54.55,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon-h1-1.5b","score":64.13,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon-h1-1.5b-deep","score":67.3,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon-h1-34b-instruct","score":83.57,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon-h1-3b","score":69.93,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon-h1-7b","score":77.61,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon3-10b","score":70.57,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon3-1b","score":39.64,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon3-3b","score":56.11,"metric":"percent"},{"benchmark":"mmlu-stem","model":"falcon3-7b","score":67.43,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-3-12b-it","score":66.54,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-3-1b-it","score":35.39,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-3-27b-it","score":73.55,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-3-4b-it","score":52.17,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.1-8b-base","score":59.31,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.2-1.24b-base","score":39.16,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.2-3b-base","score":51.92,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.3-70b","score":74.88,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-4-scout-17b","score":75.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-0.5b","score":39.83,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-1.5b","score":54.04,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-32b-instruct","score":82.37,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-3b","score":59.78,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-72b-instruct","score":82.59,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-7b","score":69.36,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen3-0.8b","score":39.3,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen3-1.7b","score":54.3,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen3-32b","score":81.64,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen3-4b","score":67.46,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen3-8b","score":66.89,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-3-1b-it","score":34.43,"metric":"percent"},{"benchmark":"mmmlu","model":"lfm2-1.2b","score":46.73,"metric":"percent"},{"benchmark":"mmmlu","model":"lfm2-350m","score":37.99,"metric":"percent"},{"benchmark":"mmmlu","model":"lfm2-700m","score":43.28,"metric":"percent"},{"benchmark":"mmmlu","model":"llama-3.2-1.24b","score":38.15,"metric":"percent"},{"benchmark":"mmmlu","model":"o1","score":87.7,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-0.6b","score":30.84,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-1.7b","score":46.51,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-sonnet-4.5","score":89.1,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-opus-4.1","score":89.5,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-sonnet-4","score":86.5,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5","score":89.4,"metric":"percent"},{"benchmark":"mmmlu-german","model":"tfree-hat-pretrained-7b-base","score":61.8,"metric":"percent"},{"benchmark":"mmmu","model":"cambrian-1-34b","score":49.7,"metric":"percent"},{"benchmark":"mmmu","model":"cambrian-1-8b","score":42.7,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3-haiku","score":50.2,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3-opus","score":59.4,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3.5-sonnet","score":68.3,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3.7-sonnet","score":69.8,"metric":"percent"},{"benchmark":"mmmu","model":"claude-opus-4","score":79.8,"metric":"percent"},{"benchmark":"mmmu","model":"claude-opus-4.1","score":77.1,"metric":"percent"},{"benchmark":"mmmu","model":"claude-sonnet-4","score":76.9,"metric":"percent"},{"benchmark":"mmmu","model":"dots-vlm1","score":80.11,"metric":"percent"},{"benchmark":"mmmu","model":"ernie-4.5","score":70,"metric":"percent"},{"benchmark":"mmmu","model":"fastvlm-0.5b","score":33.9,"metric":"percent"},{"benchmark":"mmmu","model":"fastvlm-1.5b","score":37.8,"metric":"percent"},{"benchmark":"mmmu","model":"fastvlm-7b","score":45.4,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.5-flash","score":56.1,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.5-pro","score":62.2,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-flash","score":73.2,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-pro","score":84.22,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-3-27b-vl","score":62,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-3-27b-it","score":64.9,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.1v","score":68,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.5v","score":75.4,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4o","score":72.2,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4o-0513","score":69.1,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4v","score":63.1,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5","score":84.2,"metric":"percent"},{"benchmark":"mmmu","model":"grok-4","score":80.9,"metric":"percent"},{"benchmark":"mmmu","model":"internvl-8b","score":62.7,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-8b","score":51.2,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-llama-3-76b","score":58.2,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3-8b","score":62.2,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-4b","score":66.6,"metric":"percent"},{"benchmark":"mmmu","model":"keye-vl-8b","score":66.8,"metric":"percent"},{"benchmark":"mmmu","model":"kimi-vl-a3b-thinking-2506","score":64,"metric":"percent"},{"benchmark":"mmmu","model":"llama-3.2v-11b-instruct","score":50.7,"metric":"percent"},{"benchmark":"mmmu","model":"llama-3.2v-90b-instruct","score":60.3,"metric":"percent"},{"benchmark":"mmmu","model":"llama-4-maverick","score":73.4,"metric":"percent"},{"benchmark":"mmmu","model":"llama-4-maverick-17b-128e-instruct","score":73.4,"metric":"percent"},{"benchmark":"mmmu","model":"llama-4-scout-17b","score":69.4,"metric":"percent"},{"benchmark":"mmmu","model":"llama-4-scout-17b-16e","score":69.4,"metric":"percent"},{"benchmark":"mmmu","model":"llava-1.5-13b","score":37,"metric":"percent"},{"benchmark":"mmmu","model":"llava-1.5-7b","score":35.7,"metric":"percent"},{"benchmark":"mmmu","model":"llava-onevision-72b","score":56.8,"metric":"percent"},{"benchmark":"mmmu","model":"llava-onevision-7b","score":48.8,"metric":"percent"},{"benchmark":"mmmu","model":"mimo-vl","score":66.7,"metric":"percent"},{"benchmark":"mmmu","model":"mimo-vl-7b-rl","score":66.7,"metric":"percent"},{"benchmark":"mmmu","model":"mimo-vl-7b-sft","score":64.6,"metric":"percent"},{"benchmark":"mmmu","model":"molmo-72b","score":54.1,"metric":"percent"},{"benchmark":"mmmu","model":"molmo-7b-d","score":45.3,"metric":"percent"},{"benchmark":"mmmu","model":"molmo-7b-o","score":39.3,"metric":"percent"},{"benchmark":"mmmu","model":"molmoe-1b","score":34.9,"metric":"percent"},{"benchmark":"mmmu","model":"o3","score":82.9,"metric":"percent"},{"benchmark":"mmmu","model":"paligemma-mix-3b","score":34.9,"metric":"percent"},{"benchmark":"mmmu","model":"phi-3.5-vision-4b","score":43,"metric":"percent"},{"benchmark":"mmmu","model":"pixtral-12b","score":52.5,"metric":"percent"},{"benchmark":"mmmu","model":"qvq-72b","score":70.3,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2-vl-72b","score":64.5,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2-vl-7b","score":54.1,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2.5-vl-7b","score":58.6,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2.5-vl-72b","score":69.3,"metric":"percent"},{"benchmark":"mmmu","model":"seed1.5-vl-thinking","score":79.89,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-235b-a22b-instruct","score":78.7,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-235b-a22b-thinking","score":80.6,"metric":"percent"},{"benchmark":"mmmu","model":"r-4b-base","score":68.1,"metric":"percent"},{"benchmark":"mmmu","model":"step-3","score":74.2,"metric":"percent"},{"benchmark":"mmmu","model":"xgen-mm-interleave-4b","score":41.1,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-pro","score":81.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-3.7-sonnet","score":56.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.1","score":64.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"dots-vlm1","score":70.11,"metric":"percent"},{"benchmark":"mmmu-pro","model":"dots-vlm1","score":70.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-3-27b-vl","score":37.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-3-27b-it","score":37.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-pro","score":76.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-pro","score":68.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"glm-4.1v","score":57.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"glm-4.5v","score":65.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-4o","score":59.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5","score":78.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl-8b","score":45.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-vl-a3b-thinking-2506","score":46.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llama-4-maverick","score":59.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llama-4-maverick-17b-128e-instruct","score":59.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llama-4-scout-17b","score":52.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llama-4-scout-17b-16e","score":52.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mimo-vl-7b-rl","score":46.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mimo-vl-7b-sft","score":45.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"o3","score":76.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2.5-vl-7b","score":34.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2.5-vl-72b","score":51.91,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-235b-a22b-thinking","score":69.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed1.5-vl-thinking","score":68.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-235b-a22b-instruct","score":68.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed-1.5-vl","score":59.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"step-3","score":58.6,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-30b-a3b-instruct","score":74.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-30b-a3b-instruct","score":60.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-30b-a3b-instruct","score":80.1,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-30b-a3b-instruct","score":60.2,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-30b-a3b-instruct","score":60,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-30b-a3b-instruct","score":24,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-30b-a3b-instruct","score":87,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-30b-a3b-instruct","score":73.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-30b-a3b-instruct","score":72.1,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-30b-a3b-instruct","score":52.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-30b-a3b-instruct","score":61.5,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-30b-a3b-instruct","score":8.1,"metric":"score"},{"benchmark":"miabench","model":"qwen3-vl-30b-a3b-instruct","score":91.2,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-30b-a3b-instruct","score":95,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-30b-a3b-instruct","score":82,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-30b-a3b-instruct","score":85,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-30b-a3b-instruct","score":90.3,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-30b-a3b-instruct","score":63.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-30b-a3b-instruct","score":57.8,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-30b-a3b-instruct","score":80.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-30b-a3b-instruct","score":85.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-30b-a3b-instruct","score":48.9,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-30b-a3b-instruct","score":89.8,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-30b-a3b-instruct","score":47.5,"metric":"percent"},{"benchmark":"arkitscenes","model":"qwen3-vl-30b-a3b-instruct","score":56.1,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-30b-a3b-instruct","score":12.5,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-30b-a3b-instruct","score":38.1,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-30b-a3b-instruct","score":67.7,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3-vl-30b-a3b-instruct","score":62.9,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-30b-a3b-instruct","score":43,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-30b-a3b-instruct","score":63.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-30b-a3b-instruct","score":76.4,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-30b-a3b-instruct","score":53.1,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-30b-a3b-instruct","score":62.9,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-30b-a3b-instruct","score":72.3,"metric":"percent"},{"benchmark":"video-mme","model":"qwen3-vl-30b-a3b-instruct","score":74.5,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-30b-a3b-instruct","score":81.3,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-30b-a3b-instruct","score":62.5,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen3-vl-30b-a3b-instruct","score":60.3,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-30b-a3b-instruct","score":68.7,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3-vl-30b-a3b-instruct","score":94.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-30b-a3b-instruct","score":61,"metric":"percent"},{"benchmark":"osworld","model":"qwen3-vl-30b-a3b-instruct","score":61,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3-vl-30b-a3b-instruct","score":54.3,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-30b-a3b-instruct","score":30.3,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-30b-a3b-instruct","score":81.2,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-30b-a3b-instruct","score":89.5,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-30b-a3b-instruct","score":80,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-30b-a3b-instruct","score":82.5,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-30b-a3b-instruct","score":75.9,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-30b-a3b-instruct","score":79.3,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"claude-3.7-sonnet","score":45.8,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"gemma-3-27b-it","score":24.9,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"gpt-4o","score":36.1,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl-8b","score":37.8,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"mimo-vl-7b-rl","score":40.3,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"mimo-vl-7b-sft","score":39.4,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"qwen2.5-vl-7b","score":29.4,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-3-27b-vl","score":60,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4.1v","score":72.9,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4.5v","score":75.3,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3-8b","score":68.7,"metric":"percent"},{"benchmark":"mmstar","model":"keye-vl-8b","score":72.8,"metric":"percent"},{"benchmark":"mmstar","model":"kimi-vl-a3b-thinking-2506","score":70.4,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-pro","score":77.5,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5","score":76.4,"metric":"percent"},{"benchmark":"mmstar","model":"claude-opus-4.1","score":72.1,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-4b","score":77.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2.5-vl-7b","score":64.1,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-235b-a22b-thinking","score":78.7,"metric":"percent"},{"benchmark":"mmstar","model":"r-4b-base","score":73.1,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-235b-a22b-thinking","score":61.3,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-2.5-pro","score":65.4,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5","score":61.8,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-opus-4.1","score":56.7,"metric":"percent"},{"benchmark":"simplevqa","model":"seed1.5-vl-thinking","score":63.4,"metric":"percent"},{"benchmark":"mmstar","model":"step-3","score":69,"metric":"percent"},{"benchmark":"mmvet","model":"r-4b-base","score":85.9,"metric":"percent"},{"benchmark":"mmvp","model":"r-4b-rl","score":80.7,"metric":"percent"},{"benchmark":"mmvp","model":"qwen2.5-vl-72b","score":66,"metric":"percent"},{"benchmark":"mmvp","model":"gemini-2.5-pro","score":67.33,"metric":"percent"},{"benchmark":"mmvp","model":"seed1.5-vl-thinking","score":73.33,"metric":"percent"},{"benchmark":"mmvp","model":"dots-vlm1","score":72,"metric":"percent"},{"benchmark":"mmvu","model":"gemma-3-27b-vl","score":57.7,"metric":"percent"},{"benchmark":"mmvu","model":"glm-4.1v","score":59.4,"metric":"percent"},{"benchmark":"mmvu","model":"glm-4.5v","score":68.7,"metric":"percent"},{"benchmark":"mmvu","model":"kimi-vl-a3b-thinking-2506","score":57.5,"metric":"percent"},{"benchmark":"motionbench","model":"gemma-3-27b-vl","score":47.8,"metric":"percent"},{"benchmark":"motionbench","model":"glm-4.1v","score":59,"metric":"percent"},{"benchmark":"motionbench","model":"glm-4.5v","score":62.4,"metric":"percent"},{"benchmark":"motionbench","model":"kimi-vl-a3b-thinking-2506","score":54.3,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gemini-2.5-flash","score":74,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon-h1-0.5b-instruct","score":7.06,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon-h1-1.5b","score":8.46,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon-h1-1.5b-deep","score":8.53,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon-h1-34b-instruct","score":9.2,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon-h1-3b","score":8.72,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon-h1-7b","score":8.85,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon3-10b","score":8.46,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon3-1b","score":6.03,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon3-3b","score":7.79,"metric":"percent"},{"benchmark":"mt-bench","model":"falcon3-7b","score":8.73,"metric":"percent"},{"benchmark":"mt-bench","model":"gemma-3-12b-it","score":8.69,"metric":"percent"},{"benchmark":"mt-bench","model":"gemma-3-1b-it","score":7.03,"metric":"percent"},{"benchmark":"mt-bench","model":"gemma-3-27b-it","score":8.75,"metric":"percent"},{"benchmark":"mt-bench","model":"gemma-3-4b-it","score":8.24,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-1b","score":5.48,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.1-8b-base","score":8.29,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.2-1.24b-base","score":6.37,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.2-3b-base","score":7.96,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.3-70b","score":8.98,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-4-scout-17b","score":8.98,"metric":"percent"},{"benchmark":"mt-bench","model":"mistral-small-3.1-24b-instruct","score":7.3,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-0.5b","score":4.71,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-1.5b","score":7.1,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-1.5b-instruct","score":6.52,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-32b-instruct","score":9.09,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-3b","score":7.79,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-72b-instruct","score":9.16,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-7b","score":8.45,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen3-0.8b","score":5.75,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen3-1.7b","score":7.61,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen3-32b","score":9.05,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen3-4b","score":8.45,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen3-8b","score":8.74,"metric":"percent"},{"benchmark":"mt-bench","model":"smollm1-1.7b-instruct","score":4.33,"metric":"percent"},{"benchmark":"mt-bench","model":"smollm2-1.7b-instruct","score":6.13,"metric":"percent"},{"benchmark":"mt-bench","model":"smollm2-135m-instruct","score":1.98,"metric":"percent"},{"benchmark":"mteb-code-v1","model":"embeddinggemma-300m","score":68.76,"metric":"percent"},{"benchmark":"mteb-english-v2","model":"embeddinggemma-300m","score":68.36,"metric":"percent"},{"benchmark":"mteb-multilingual-v2","model":"embeddinggemma-300m","score":61.15,"metric":"percent"},{"benchmark":"mtob-full-book","model":"llama-4-maverick","score":50.8,"metric":"percent"},{"benchmark":"mtob-full-book","model":"llama-4-maverick-17b-128e-instruct","score":50.8,"metric":"percent"},{"benchmark":"mtob-full-book","model":"llama-4-scout-17b","score":39.7,"metric":"percent"},{"benchmark":"mtob-full-book","model":"llama-4-scout-17b-16e","score":39.7,"metric":"percent"},{"benchmark":"mtob-half-book","model":"llama-4-maverick","score":54,"metric":"percent"},{"benchmark":"mtob-half-book","model":"llama-4-maverick-17b-128e-instruct","score":54,"metric":"percent"},{"benchmark":"mtob-half-book","model":"llama-4-scout-17b","score":42.2,"metric":"percent"},{"benchmark":"mtob-half-book","model":"llama-4-scout-17b-16e","score":42.2,"metric":"percent"},{"benchmark":"muirbench","model":"gemma-3-27b-vl","score":50.3,"metric":"percent"},{"benchmark":"muirbench","model":"glm-4.1v","score":74.7,"metric":"percent"},{"benchmark":"muirbench","model":"glm-4.5v","score":75.3,"metric":"percent"},{"benchmark":"muirbench","model":"kimi-vl-a3b-thinking-2506","score":63.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-235b-a22b-thinking","score":84.3,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-2.5-pro","score":79.1,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5","score":82.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"claude-opus-4.1","score":69.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"robobrain-2.0","score":78.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-235b-a22b-thinking","score":69.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-2.5-pro","score":36.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5","score":23.8,"metric":"percent"},{"benchmark":"refspatialbench","model":"robobrain-2.0","score":54,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-235b-a22b-thinking","score":73.9,"metric":"percent"},{"benchmark":"robospatialhome","model":"gemini-2.5-pro","score":47.5,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-5","score":53.5,"metric":"percent"},{"benchmark":"robospatialhome","model":"robobrain-2.0","score":72.4,"metric":"percent"},{"benchmark":"muirbench","model":"step-3","score":75,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3-vl-235b-a22b-thinking","score":80.1,"metric":"percent"},{"benchmark":"muirbench","model":"gemini-2.5-pro","score":77.2,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-5","score":77.5,"metric":"percent"},{"benchmark":"muirbench","model":"dots-vlm1","score":78.6,"metric":"percent"},{"benchmark":"muirbench","model":"qwen2.5-vl-72b","score":69.38,"metric":"percent"},{"benchmark":"muirbench","model":"gemini-2.5-pro","score":70.5,"metric":"percent"},{"benchmark":"muirbench","model":"seed1.5-vl-thinking","score":79.77,"metric":"percent"},{"benchmark":"muirbench","model":"dots-vlm1","score":78.58,"metric":"percent"},{"benchmark":"multi-if","model":"deepseek-v3","score":66.9,"metric":"percent"},{"benchmark":"multi-if","model":"ernie-4.5","score":76.6,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-4.1","score":70.8,"metric":"percent"},{"benchmark":"multi-if","model":"o1","score":48.8,"metric":"percent"},{"benchmark":"multi-if","model":"o3-mini-high","score":79.5,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-235b-a22b","score":70.2,"metric":"percent"},{"benchmark":"multi-ifeval","model":"gemini-2.5-flash-thinking","score":74.4,"metric":"percent"},{"benchmark":"multi-ifeval","model":"llama-3.3-70b","score":88.7,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-235b-a22b","score":77.5,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-235b-a22b-thinking-2507","score":80.6,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-30b-a3b","score":67.9,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-30b-a3b-thinking-2507","score":76.4,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-32b-nothinking","score":70.7,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-32b-thinking","score":73,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-next-80b-a3b-instruct","score":75.8,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-next-80b-a3b-thinking","score":77.8,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"claude-sonnet-4","score":35.7,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"deepseek-v3.1-thinking","score":29,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"glm-4.5","score":31.7,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"kimi-k2-instruct-0711","score":31.3,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"kimi-k2-instruct-0905","score":33.5,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"qwen3-coder-480b-a35b","score":32.7,"metric":"percent"},{"benchmark":"multi-swe-bench-flash","model":"qwen3-coder-480b-a35b","score":25.3,"metric":"percent"},{"benchmark":"multi-swe-bench-mini","model":"qwen3-coder-480b-a35b","score":25.8,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-4o","score":40.3,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5","score":69.6,"metric":"percent"},{"benchmark":"multichallenge","model":"o3","score":60.4,"metric":"percent"},{"benchmark":"multilingual-jailbreak","model":"k2-think","score":83,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gpt-4.1","score":87.3,"metric":"percent"},{"benchmark":"multipl-e","model":"hunyuan-7b-pretrain","score":60.41,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-235b-a22b","score":87.9,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-30b-a3b","score":83.8,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-32b-nothinking","score":76.9,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-next-80b-a3b-instruct","score":87.8,"metric":"percent"},{"benchmark":"multipl-e","model":"ling-1t","score":77.91,"metric":"percent"},{"benchmark":"multipl-e","model":"deepseek-v3.1-terminus","score":77.68,"metric":"percent"},{"benchmark":"multipl-e","model":"kimi-k2-0905","score":73.54,"metric":"percent"},{"benchmark":"multipl-e","model":"gpt-5","score":76.66,"metric":"percent"},{"benchmark":"multipl-e","model":"gemini-2.5-pro","score":71.48,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"llama-3.1-405b","score":75.2,"metric":"pass@1"},{"benchmark":"multipl-e-humaneval","model":"llama-3.1-70b","score":65.5,"metric":"pass@1"},{"benchmark":"multipl-e-humaneval","model":"llama-3.1-8b","score":50.8,"metric":"pass@1"},{"benchmark":"multipl-e-mbpp","model":"llama-3.1-405b","score":65.7,"metric":"pass@1"},{"benchmark":"multipl-e-mbpp","model":"llama-3.1-70b","score":62,"metric":"pass@1"},{"benchmark":"multipl-e-mbpp","model":"llama-3.1-8b","score":52.4,"metric":"pass@1"},{"benchmark":"musr","model":"afm-4.5b","score":38.76,"metric":"percent"},{"benchmark":"musr","model":"command-r7b","score":43.3,"metric":"percent"},{"benchmark":"musr","model":"deepseek-v3","score":65.9,"metric":"percent"},{"benchmark":"musr","model":"ernie-4.5","score":69.9,"metric":"percent"},{"benchmark":"musr","model":"falcon-3-1b-base","score":9.71,"metric":"percent"},{"benchmark":"musr","model":"falcon-e-1b-base","score":3.65,"metric":"percent"},{"benchmark":"musr","model":"gemma-3-4b-it","score":39.95,"metric":"percent"},{"benchmark":"musr","model":"gpt-4.1","score":62.6,"metric":"percent"},{"benchmark":"musr","model":"qwen2.5-0.5b","score":2.08,"metric":"percent"},{"benchmark":"musr","model":"qwen2.5-1.5b","score":5.27,"metric":"percent"},{"benchmark":"musr","model":"qwen3-0.6b","score":3.38,"metric":"percent"},{"benchmark":"musr","model":"qwen3-1.7b","score":13.65,"metric":"percent"},{"benchmark":"musr","model":"qwen3-4b","score":41.14,"metric":"percent"},{"benchmark":"musr","model":"llama-spark-8b","score":2.62,"metric":"percent"},{"benchmark":"musr","model":"qwen3-235b-a22b","score":66.8,"metric":"percent"},{"benchmark":"musr","model":"smollm3-3b","score":36.77,"metric":"percent"},{"benchmark":"musr","model":"smollm2-1.7b-base","score":4.6,"metric":"percent"},{"benchmark":"musr","model":"smollm2-360m-base","score":7.73,"metric":"percent"},{"benchmark":"mvbench","model":"gemma-3-27b-vl","score":43.5,"metric":"percent"},{"benchmark":"mvbench","model":"glm-4.1v","score":68.4,"metric":"percent"},{"benchmark":"mvbench","model":"glm-4.5v","score":73,"metric":"percent"},{"benchmark":"mvbench","model":"kimi-vl-a3b-thinking-2506","score":59.7,"metric":"percent"},{"benchmark":"mvbench","model":"smolvlm2-0.256b","score":32.7,"metric":"percent"},{"benchmark":"mvbench","model":"smolvlm2-0.5b","score":39.73,"metric":"percent"},{"benchmark":"mvbench","model":"smolvlm2-2.2b","score":46.27,"metric":"percent"},{"benchmark":"natural2code","model":"gemini-2.0-flash","score":92.9,"metric":"percent"},{"benchmark":"natural2code","model":"gemini-1.5-pro","score":85.4,"metric":"percent"},{"benchmark":"natural2code","model":"gemma-3-27b-it","score":84.5,"metric":"percent"},{"benchmark":"natural2code","model":"gemma-3-12b-it","score":80.7,"metric":"percent"},{"benchmark":"natural2code","model":"gemini-1.5-flash","score":79.8,"metric":"percent"},{"benchmark":"natural2code","model":"gemini-1.5-flash-8b-001","score":75.5,"metric":"percent"},{"benchmark":"natural2code","model":"gemma-3-4b-it","score":70.3,"metric":"percent"},{"benchmark":"natural2code","model":"gemma-3-1b-it","score":56,"metric":"percent"},{"benchmark":"naturalquestions","model":"gemma-2-2b","score":12.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"gemma-2-7b","score":23,"metric":"percent"},{"benchmark":"naturalquestions","model":"gemma-3-pt-27b","score":36.1,"metric":"percent"},{"benchmark":"nexus","model":"llama-3-70b","score":47.8,"metric":"macro_avg/acc"},{"benchmark":"nexus","model":"llama-3-8b","score":18.1,"metric":"macro_avg/acc"},{"benchmark":"nexus","model":"llama-3.1-405b","score":58.7,"metric":"macro_avg/acc"},{"benchmark":"nexus","model":"llama-3.1-70b","score":56.7,"metric":"macro_avg/acc"},{"benchmark":"nexus","model":"llama-3.1-8b","score":38.5,"metric":"macro_avg/acc"},{"benchmark":"ocrbench","model":"claude-3.7-sonnet","score":80.6,"metric":"percent"},{"benchmark":"ocrbench","model":"fastvlm-0.5b","score":63.9,"metric":"percent"},{"benchmark":"ocrbench","model":"fastvlm-1.5b","score":70.2,"metric":"percent"},{"benchmark":"ocrbench","model":"fastvlm-7b","score":73.1,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-3-27b-vl","score":75.9,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-3-27b-it","score":77.6,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4.1v","score":84.2,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4.5v","score":86.5,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4o","score":84.3,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl-8b","score":88,"metric":"percent"},{"benchmark":"ocrbench","model":"kimi-vl-a3b-thinking-2506","score":86.9,"metric":"percent"},{"benchmark":"ocrbench","model":"mimo-vl-7b-rl","score":86.6,"metric":"percent"},{"benchmark":"ocrbench","model":"mimo-vl-7b-sft","score":87.6,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2.5-vl-7b","score":89.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-235b-a22b-thinking","score":66.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemini-2.5-pro","score":54.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gpt-5","score":53,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"claude-opus-4.1","score":48.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-235b-a22b-thinking","score":63.5,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gemini-2.5-pro","score":48.5,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gpt-5","score":43.2,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"claude-opus-4.1","score":43.7,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-235b-a22b-thinking","score":81.5,"metric":"percent"},{"benchmark":"cc-ocr","model":"gemini-2.5-pro","score":77.2,"metric":"percent"},{"benchmark":"cc-ocr","model":"gpt-5","score":68.3,"metric":"percent"},{"benchmark":"cc-ocr","model":"claude-opus-4.1","score":69.1,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-235b-a22b-thinking","score":43.2,"metric":"percent"},{"benchmark":"odinw-13","model":"gemini-2.5-pro","score":33.7,"metric":"percent"},{"benchmark":"odinw-13","model":"gpt-5","score":43.2,"metric":"percent"},{"benchmark":"odinw-13","model":"seed1.5-vl-thinking","score":41.3,"metric":"percent"},{"benchmark":"ocrbench","model":"step-3","score":83.7,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-2.5-flash-thinking","score":23.5,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-235b-a22b-thinking-2507","score":32.5,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-30b-a3b-thinking-2507","score":25.1,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-32b-thinking","score":24.1,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-next-80b-a3b-thinking","score":29.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"hunyuan-7b-instruct","score":76.5,"metric":"percent"},{"benchmark":"olympic-arena","model":"deepseek-v3","score":76.2,"metric":"percent"},{"benchmark":"olympic-arena","model":"ernie-4.5","score":75.3,"metric":"percent"},{"benchmark":"olympic-arena","model":"gpt-4.1","score":69.5,"metric":"percent"},{"benchmark":"olympic-arena","model":"qwen3-235b-a22b","score":63.7,"metric":"percent"},{"benchmark":"omni-math-hard","model":"deepseek-r1","score":51.33,"metric":"percent"},{"benchmark":"omni-math-hard","model":"deepseek-v3.1-thinking","score":53.22,"metric":"percent"},{"benchmark":"omni-math-hard","model":"falcon-3-1b-base","score":3.32,"metric":"percent"},{"benchmark":"omni-math-hard","model":"falcon-e-1b-base","score":10.97,"metric":"percent"},{"benchmark":"omni-math-hard","model":"gemini-2.5-pro","score":69.36,"metric":"percent"},{"benchmark":"omni-math-hard","model":"gpt-5-high","score":73.61,"metric":"percent"},{"benchmark":"omni-math-hard","model":"gpt-oss-120b","score":57.76,"metric":"percent"},{"benchmark":"omni-math-hard","model":"gpt-oss-20b","score":41.51,"metric":"percent"},{"benchmark":"omni-math-hard","model":"k2-think","score":60.73,"metric":"percent"},{"benchmark":"omni-math-hard","model":"nemotron-32b","score":58.88,"metric":"percent"},{"benchmark":"omni-math-hard","model":"o3-high","score":59.39,"metric":"percent"},{"benchmark":"omni-math-hard","model":"qwen2.5-0.5b","score":3.93,"metric":"percent"},{"benchmark":"omni-math-hard","model":"qwen2.5-1.5b","score":9.14,"metric":"percent"},{"benchmark":"omni-math-hard","model":"qwen3-0.6b","score":5.89,"metric":"percent"},{"benchmark":"omni-math-hard","model":"qwen3-1.7b","score":13.95,"metric":"percent"},{"benchmark":"omni-math-hard","model":"qwen3-235b-a22b","score":56.91,"metric":"percent"},{"benchmark":"omni-math-hard","model":"qwen3-30b-a3b","score":23.87,"metric":"percent"},{"benchmark":"omni-math-hard","model":"qwq-32b","score":46.93,"metric":"percent"},{"benchmark":"omni-math-hard","model":"smollm2-1.7b-base","score":2.64,"metric":"percent"},{"benchmark":"omni-math-hard","model":"smollm2-360m-base","score":1.21,"metric":"percent"},{"benchmark":"omni-math","model":"ring-flash-linear-2.0","score":56.6,"metric":"percent"},{"benchmark":"omni-math","model":"ring-flash-2.0","score":59.9,"metric":"percent"},{"benchmark":"omni-math","model":"qwen3-32b-thinking-2504","score":56.2,"metric":"percent"},{"benchmark":"omni-math","model":"gemini-2.5-flash","score":59.8,"metric":"percent"},{"benchmark":"omni-math","model":"gpt-oss-120b-medium","score":50.8,"metric":"percent"},{"benchmark":"omni-math","model":"seed-oss-36b-instruct","score":61.1,"metric":"percent"},{"benchmark":"omni-math","model":"qwen3-next-80b-a3b-thinking","score":61.7,"metric":"percent"},{"benchmark":"omni-math","model":"ling-1t","score":74.46,"metric":"percent"},{"benchmark":"omni-math","model":"deepseek-v3.1-terminus","score":64.77,"metric":"percent"},{"benchmark":"omni-math","model":"kimi-k2-0905","score":62.42,"metric":"percent"},{"benchmark":"omni-math","model":"gpt-5","score":61.09,"metric":"percent"},{"benchmark":"omni-math","model":"gemini-2.5-pro","score":72.02,"metric":"percent"},{"benchmark":"omnispatial","model":"gemma-3","score":40.8,"metric":"percent"},{"benchmark":"omnispatial","model":"gemma-3-27b-vl","score":40.8,"metric":"percent"},{"benchmark":"omnispatial","model":"glm-4.1v","score":47.7,"metric":"percent"},{"benchmark":"omnispatial","model":"glm-4.5v","score":51,"metric":"percent"},{"benchmark":"omnispatial","model":"kimi-vl","score":37.3,"metric":"percent"},{"benchmark":"omnispatial","model":"kimi-vl-a3b-thinking-2506","score":37.3,"metric":"percent"},{"benchmark":"omnispatial","model":"step-3","score":47,"metric":"percent"},{"benchmark":"one-sided-statement","model":"k2-think","score":77,"metric":"percent"},{"benchmark":"openbookqa","model":"gemma-2-2b","score":47.8,"metric":"percent"},{"benchmark":"openbookqa","model":"gemma-2-7b","score":52.8,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-1b-pretrained","score":38.4,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen-3","score":96.4,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen2.5-1.5b-pretrained","score":40,"metric":"percent"},{"benchmark":"openbookqa","model":"smollm1-1.7b-pretrained","score":42.4,"metric":"percent"},{"benchmark":"openbookqa","model":"smollm2-1.7b-pretrained","score":42.2,"metric":"percent"},{"benchmark":"openbookqa","model":"smollm2-135m-base","score":34.6,"metric":"percent"},{"benchmark":"openbookqa","model":"smollm2-135m-pretrained","score":34.6,"metric":"percent"},{"benchmark":"openrewrite-eval","model":"llama-1b","score":39.2,"metric":"rougel"},{"benchmark":"openrewrite-eval","model":"qwen2.5-1.5b-instruct","score":46.9,"metric":"rougel"},{"benchmark":"openrewrite-eval","model":"smollm2-1.7b-instruct","score":44.9,"metric":"rougel"},{"benchmark":"optmath","model":"ling-1t","score":57.68,"metric":"percent"},{"benchmark":"optmath","model":"deepseek-v3.1-terminus","score":35.99,"metric":"percent"},{"benchmark":"optmath","model":"kimi-k2-0905","score":35.84,"metric":"percent"},{"benchmark":"optmath","model":"gpt-5","score":39.16,"metric":"percent"},{"benchmark":"optmath","model":"gemini-2.5-pro","score":42.77,"metric":"percent"},{"benchmark":"osworld","model":"qwen3-vl-235b-a22b-thinking","score":38.1,"metric":"percent"},{"benchmark":"osworld","model":"seed1.5-vl-thinking","score":36.7,"metric":"percent"},{"benchmark":"osworld","model":"claude-sonnet-4.5","score":61.4,"metric":"percent"},{"benchmark":"osworld","model":"claude-opus-4.1","score":44.4,"metric":"percent"},{"benchmark":"osworld","model":"claude-sonnet-4","score":42.2,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-235b-a22b-thinking","score":68.3,"metric":"percent"},{"benchmark":"osworld-g","model":"gemini-2.5-pro","score":45.2,"metric":"percent"},{"benchmark":"osworld-g","model":"seed1.5-vl-thinking","score":62.9,"metric":"percent"},{"benchmark":"osworld-g","model":"claude-sonnet-4","score":59.6,"metric":"percent"},{"benchmark":"osworld-g","model":"holo1-3b","score":42.16,"metric":"percent"},{"benchmark":"osworld-g","model":"holo1-7b","score":47.25,"metric":"percent"},{"benchmark":"osworld-g","model":"holo1.5-3b","score":61.57,"metric":"percent"},{"benchmark":"osworld-g","model":"holo1.5-72b","score":71.8,"metric":"percent"},{"benchmark":"osworld-g","model":"holo1.5-7b","score":66.27,"metric":"percent"},{"benchmark":"osworld-g","model":"mimo-vl-7b-rl","score":56.1,"metric":"percent"},{"benchmark":"osworld-g","model":"mimo-vl-7b-sft","score":54.7,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen2.5-vl-3b","score":34.31,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen2.5-vl-72b","score":61.96,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen2.5-vl-7b","score":40.59,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-tars-1.5-7b","score":61.4,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-venus-72b","score":70.4,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-venus-7b","score":58.8,"metric":"percent"},{"benchmark":"osworld2","model":"gemma-3-27b-vl","score":6.2,"metric":"percent"},{"benchmark":"osworld2","model":"glm-4.1v","score":14.9,"metric":"percent"},{"benchmark":"osworld2","model":"glm-4.5v","score":35.8,"metric":"percent"},{"benchmark":"osworld2","model":"kimi-vl-a3b-thinking-2506","score":8.2,"metric":"percent"},{"benchmark":"penguinscrolls","model":"hunyuan-4b-instruct","score":83.1,"metric":"percent"},{"benchmark":"persona-modulation","model":"k2-think","score":59,"metric":"percent"},{"benchmark":"personal-info-leak-fs","model":"k2-think","score":86,"metric":"percent"},{"benchmark":"physical-safety","model":"k2-think","score":49,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-v3-base","score":84.7,"metric":"percent"},{"benchmark":"piqa","model":"gemma-2-2b","score":77.3,"metric":"percent"},{"benchmark":"piqa","model":"gemma-2-7b","score":81.2,"metric":"percent"},{"benchmark":"piqa","model":"gemma-3-270m-it","score":66.2,"metric":"percent"},{"benchmark":"piqa","model":"gemma-3-pt-270m","score":67.7,"metric":"percent"},{"benchmark":"piqa","model":"gemma-3-pt-27b","score":83.3,"metric":"percent"},{"benchmark":"piqa","model":"glm-4.5-base","score":87.1,"metric":"percent"},{"benchmark":"piqa","model":"llama-1b","score":72.3,"metric":"percent"},{"benchmark":"piqa","model":"llama-1b-pretrained","score":74.8,"metric":"percent"},{"benchmark":"piqa","model":"qwen2.5-1.5b-instruct","score":73.2,"metric":"percent"},{"benchmark":"piqa","model":"qwen2.5-1.5b-pretrained","score":76.1,"metric":"percent"},{"benchmark":"piqa","model":"smollm1-1.7b-instruct","score":71.6,"metric":"percent"},{"benchmark":"piqa","model":"smollm1-1.7b-pretrained","score":76,"metric":"percent"},{"benchmark":"piqa","model":"smollm2-1.7b-instruct","score":74.4,"metric":"percent"},{"benchmark":"piqa","model":"smollm2-1.7b-pretrained","score":77.6,"metric":"percent"},{"benchmark":"piqa","model":"smollm2-135m-base","score":68.4,"metric":"percent"},{"benchmark":"piqa","model":"smollm2-135m-instruct","score":66.3,"metric":"percent"},{"benchmark":"piqa","model":"smollm2-135m-pretrained","score":68.4,"metric":"percent"},{"benchmark":"piqa","model":"trlm-135m","score":64.91,"metric":"percent"},{"benchmark":"pixmocount","model":"cambrian-1-34b","score":50.7,"metric":"percent"},{"benchmark":"pixmocount","model":"cambrian-1-8b","score":46.6,"metric":"percent"},{"benchmark":"pixmocount","model":"claude-3-haiku","score":43.9,"metric":"percent"},{"benchmark":"pixmocount","model":"claude-3-opus","score":43.3,"metric":"percent"},{"benchmark":"pixmocount","model":"claude-3.5-sonnet","score":58.3,"metric":"percent"},{"benchmark":"pixmocount","model":"claude-3.7-sonnet","score":53.5,"metric":"percent"},{"benchmark":"pixmocount","model":"gemini-1.5-flash","score":61.1,"metric":"percent"},{"benchmark":"pixmocount","model":"gemini-1.5-pro","score":64.3,"metric":"percent"},{"benchmark":"pixmocount","model":"gemma-3-27b-it","score":48.6,"metric":"percent"},{"benchmark":"pixmocount","model":"gpt-4o","score":54.4,"metric":"percent"},{"benchmark":"pixmocount","model":"gpt-4o-0513","score":59.6,"metric":"percent"},{"benchmark":"pixmocount","model":"gpt-4v","score":45,"metric":"percent"},{"benchmark":"pixmocount","model":"internvl-8b","score":62,"metric":"percent"},{"benchmark":"pixmocount","model":"internvl2-8b","score":43.9,"metric":"percent"},{"benchmark":"pixmocount","model":"internvl2-llama-3-76b","score":54.6,"metric":"percent"},{"benchmark":"pixmocount","model":"llama-3.2v-11b-instruct","score":47.4,"metric":"percent"},{"benchmark":"pixmocount","model":"llama-3.2v-90b-instruct","score":58.5,"metric":"percent"},{"benchmark":"pixmocount","model":"llava-1.5-13b","score":35.2,"metric":"percent"},{"benchmark":"pixmocount","model":"llava-1.5-7b","score":27.6,"metric":"percent"},{"benchmark":"pixmocount","model":"llava-onevision-72b","score":60.7,"metric":"percent"},{"benchmark":"pixmocount","model":"llava-onevision-7b","score":54.4,"metric":"percent"},{"benchmark":"pixmocount","model":"mimo-vl-7b-rl","score":79.4,"metric":"percent"},{"benchmark":"pixmocount","model":"mimo-vl-7b-sft","score":79.4,"metric":"percent"},{"benchmark":"pixmocount","model":"molmo-72b","score":85.2,"metric":"percent"},{"benchmark":"pixmocount","model":"molmo-7b-d","score":84.8,"metric":"percent"},{"benchmark":"pixmocount","model":"molmo-7b-o","score":83.3,"metric":"percent"},{"benchmark":"pixmocount","model":"molmoe-1b","score":79.6,"metric":"percent"},{"benchmark":"pixmocount","model":"paligemma-mix-3b","score":60,"metric":"percent"},{"benchmark":"pixmocount","model":"phi-3.5-vision-4b","score":38.3,"metric":"percent"},{"benchmark":"pixmocount","model":"pixtral-12b","score":51.7,"metric":"percent"},{"benchmark":"pixmocount","model":"qwen2-vl-72b","score":55.7,"metric":"percent"},{"benchmark":"pixmocount","model":"qwen2-vl-7b","score":48,"metric":"percent"},{"benchmark":"pixmocount","model":"qwen2.5-vl-7b","score":60.7,"metric":"percent"},{"benchmark":"pixmocount","model":"xgen-mm-interleave-4b","score":50.2,"metric":"percent"},{"benchmark":"polymath","model":"gemini-2.5-flash-thinking","score":49.8,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-235b-a22b","score":50.2,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-235b-a22b-thinking-2507","score":60.1,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-30b-a3b","score":43.1,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-30b-a3b-thinking-2507","score":52.6,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-32b-nothinking","score":22.5,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-32b-thinking","score":47.4,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-next-80b-a3b-instruct","score":45.9,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-next-80b-a3b-thinking","score":56.3,"metric":"percent"},{"benchmark":"prompt-extraction-robustness","model":"k2-think","score":35,"metric":"percent"},{"benchmark":"prompt-injection","model":"k2-think","score":77,"metric":"percent"},{"benchmark":"quac","model":"llama-3-70b-base","score":51.1,"metric":"f1"},{"benchmark":"quac","model":"llama-3-8b-base","score":44.4,"metric":"f1"},{"benchmark":"quac","model":"llama-3.1-405b-base","score":53.6,"metric":"percent"},{"benchmark":"quac","model":"llama-3.1-405b-base","score":53.6,"metric":"f1"},{"benchmark":"quac","model":"llama-3.1-70b-base","score":51.1,"metric":"f1"},{"benchmark":"quac","model":"llama-3.1-8b-base","score":44.9,"metric":"f1"},{"benchmark":"realworldqa","model":"cambrian-1-34b","score":67.8,"metric":"percent"},{"benchmark":"realworldqa","model":"cambrian-1-8b","score":64.2,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-3-haiku","score":45.5,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-3-opus","score":49.8,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-3.5-sonnet","score":60.1,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-opus-4.1","score":69.9,"metric":"percent"},{"benchmark":"realworldqa","model":"fastvlm-0.5b","score":56.1,"metric":"percent"},{"benchmark":"realworldqa","model":"fastvlm-1.5b","score":61.2,"metric":"percent"},{"benchmark":"realworldqa","model":"fastvlm-7b","score":67.2,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-1.5-flash","score":67.5,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-1.5-pro","score":70.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-2.5-pro","score":78,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-4o-0513","score":75.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-4v","score":61.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5","score":82.8,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl-8b","score":70.6,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-8b","score":64.2,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-llama-3-76b","score":72.7,"metric":"percent"},{"benchmark":"realworldqa","model":"llama-3.2v-11b-instruct","score":64.1,"metric":"percent"},{"benchmark":"realworldqa","model":"llama-3.2v-90b-instruct","score":69.8,"metric":"percent"},{"benchmark":"realworldqa","model":"llava-1.5-13b","score":55.3,"metric":"percent"},{"benchmark":"realworldqa","model":"llava-1.5-7b","score":54.8,"metric":"percent"},{"benchmark":"realworldqa","model":"llava-onevision-72b","score":71.9,"metric":"percent"},{"benchmark":"realworldqa","model":"llava-onevision-7b","score":66.3,"metric":"percent"},{"benchmark":"realworldqa","model":"molmo-72b","score":75.2,"metric":"percent"},{"benchmark":"realworldqa","model":"molmo-7b-d","score":70.7,"metric":"percent"},{"benchmark":"realworldqa","model":"molmo-7b-o","score":67.5,"metric":"percent"},{"benchmark":"realworldqa","model":"molmoe-1b","score":60.4,"metric":"percent"},{"benchmark":"realworldqa","model":"paligemma-mix-3b","score":55.2,"metric":"percent"},{"benchmark":"realworldqa","model":"phi-3.5-vision-4b","score":53.6,"metric":"percent"},{"benchmark":"realworldqa","model":"pixtral-12b","score":65.4,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2-vl-72b","score":77.8,"metric":"percent"},{"benchmark":"realworldqa","model":"dots-vlm1","score":79.1,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2-vl-7b","score":70.1,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-235b-a22b-thinking","score":81.3,"metric":"percent"},{"benchmark":"realworldqa","model":"xgen-mm-interleave-4b","score":61.2,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2.5-vl-72b","score":75.9,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-2.5-pro","score":78.43,"metric":"percent"},{"benchmark":"realworldqa","model":"seed1.5-vl-thinking","score":78.69,"metric":"percent"},{"benchmark":"realworldqa","model":"dots-vlm1","score":79.08,"metric":"percent"},{"benchmark":"realworldqa","model":"minicpm-v-2.0-3b","score":55.8,"metric":"percent"},{"benchmark":"realworldqa","model":"blip-3-4b","score":60.5,"metric":"percent"},{"benchmark":"realworldqa","model":"phi-3-vision-4b","score":59.4,"metric":"percent"},{"benchmark":"realworldqa","model":"mm1.5-3b","score":56.9,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2.5-2b","score":60.1,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2.5-4b","score":64.3,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-2b","score":62,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-4b","score":66.3,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2.5-vl-3b","score":65.4,"metric":"percent"},{"benchmark":"realworldqa","model":"cambrian-34b","score":67.8,"metric":"percent"},{"benchmark":"realworldqa","model":"mm1-30b","score":59.4,"metric":"percent"},{"benchmark":"realworldqa","model":"mm1.5-30b","score":69,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2.5-26b","score":74.5,"metric":"percent"},{"benchmark":"realworldqa","model":"blip-3o-4b","score":60.4,"metric":"percent"},{"benchmark":"realworldqa","model":"emu3-8b","score":57.4,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2.5-omni-7b","score":62.6,"metric":"percent"},{"benchmark":"realworldqa","model":"bagel-14b","score":72.8,"metric":"percent"},{"benchmark":"realworldqa","model":"manzano-3b","score":65.1,"metric":"percent"},{"benchmark":"realworldqa","model":"manzano-30b","score":70.1,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-4o","score":75.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-1.5-pro","score":64.1,"metric":"percent"},{"benchmark":"refcoco","model":"gemma-3-27b-vl","score":2.4,"metric":"percent"},{"benchmark":"refcoco","model":"glm-4.1v","score":85.3,"metric":"percent"},{"benchmark":"refcoco","model":"glm-4.5v","score":91.3,"metric":"percent"},{"benchmark":"refcoco","model":"internvl-8b","score":90.1,"metric":"percent"},{"benchmark":"refcoco","model":"internvl3.5-4b","score":92.4,"metric":"percent"},{"benchmark":"refcoco","model":"kimi-vl-a3b-thinking-2506","score":33.6,"metric":"percent"},{"benchmark":"refcoco","model":"mimo-vl-7b-rl","score":89.6,"metric":"percent"},{"benchmark":"refcoco","model":"mimo-vl-7b-sft","score":85.7,"metric":"percent"},{"benchmark":"refcoco","model":"qwen2.5-vl-7b","score":87.1,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-235b-a22b-thinking","score":92.4,"metric":"percent"},{"benchmark":"refcoco","model":"gemini-2.5-pro","score":74.6,"metric":"percent"},{"benchmark":"refcoco","model":"gpt-5","score":66.8,"metric":"percent"},{"benchmark":"refcoco","model":"step-3","score":20.2,"metric":"percent"},{"benchmark":"refcoco","model":"moondream-9b-a2b","score":91.1,"metric":"percent"},{"benchmark":"refcoco","model":"gemini-2.5-flash","score":75.8,"metric":"percent"},{"benchmark":"refcoco","model":"claude-sonnet-4","score":30.1,"metric":"percent"},{"benchmark":"refcoco","model":"qwen2.5-vl-72b","score":90.3,"metric":"percent"},{"benchmark":"refcoco","model":"seed1.5-vl-thinking","score":91.3,"metric":"percent"},{"benchmark":"refcoco","model":"dots-vlm1","score":90.45,"metric":"percent"},{"benchmark":"refcocog","model":"moondream-9b-a2b","score":88.6,"metric":"percent"},{"benchmark":"refcocog","model":"gpt-5","score":49.8,"metric":"percent"},{"benchmark":"refcocog","model":"gemini-2.5-flash","score":75.1,"metric":"percent"},{"benchmark":"refcocog","model":"claude-sonnet-4","score":26.2,"metric":"percent"},{"benchmark":"refcocoplus","model":"moondream-9b-a2b","score":81.8,"metric":"percent"},{"benchmark":"refcocoplus","model":"gpt-5","score":46.3,"metric":"percent"},{"benchmark":"refcocoplus","model":"gemini-2.5-flash","score":70.2,"metric":"percent"},{"benchmark":"refcocoplus","model":"claude-sonnet-4","score":23.4,"metric":"percent"},{"benchmark":"refusal-suppression","model":"k2-think","score":76,"metric":"percent"},{"benchmark":"refusalbench","model":"hermes-4-70b","score":59.5,"metric":"percent"},{"benchmark":"repobench","model":"codestral-22b","score":34,"metric":"percent"},{"benchmark":"repobench","model":"claude-sonnet-4.5","score":83.82,"metric":"percent"},{"benchmark":"repobench","model":"gpt-5-codex-medium","score":67.65,"metric":"percent"},{"benchmark":"repobench","model":"gemini-2.5-pro","score":67.35,"metric":"percent"},{"benchmark":"repobench","model":"gpt-5-codex-high","score":66.18,"metric":"percent"},{"benchmark":"repobench","model":"gpt-5-codex-low","score":64.71,"metric":"percent"},{"benchmark":"repobench","model":"gpt-5-mini","score":64.71,"metric":"percent"},{"benchmark":"repobench","model":"gpt-5-medium","score":63.24,"metric":"percent"},{"benchmark":"repobench","model":"gpt-5-codex","score":61.47,"metric":"percent"},{"benchmark":"repobench","model":"gpt-5-high","score":61.18,"metric":"percent"},{"benchmark":"repobench","model":"gpt-4.1","score":60.29,"metric":"percent"},{"benchmark":"repobench","model":"deepseek-v3.2-exp-thinking","score":59.41,"metric":"percent"},{"benchmark":"repobench","model":"claude-opus-4.1","score":59.12,"metric":"percent"},{"benchmark":"rewardbench","model":"gemini-2.5-pro","score":79.5,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gpt-5-mini","score":99,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-opus-4.1","score":98,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gpt-5-medium","score":98,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gemini-2.5-pro","score":96,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gpt-5-low","score":95,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-3.7-sonnet","score":95,"metric":"percent"},{"benchmark":"roo-code-evals","model":"kimi-k2-instruct-0905-groq","score":94,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-opus-4","score":94,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gpt-4.1","score":91,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gpt-5-minimal","score":90,"metric":"percent"},{"benchmark":"roo-code-evals","model":"grok-code-fast-1","score":90,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gemini-2.5-flash","score":90,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-3.5-sonnet","score":90,"metric":"percent"},{"benchmark":"roo-code-evals","model":"grok-3","score":89,"metric":"percent"},{"benchmark":"roo-code-evals","model":"kimi-k2-instruct-0905","score":89,"metric":"percent"},{"benchmark":"roo-code-evals","model":"sonoma-sky","score":86,"metric":"percent"},{"benchmark":"roo-code-evals","model":"qwen3-max-instruct-preview","score":86,"metric":"percent"},{"benchmark":"roo-code-evals","model":"glm-4.5","score":86,"metric":"percent"},{"benchmark":"roo-code-evals","model":"kimi-k2-instruct-0711","score":83,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gpt-4.1-mini","score":83,"metric":"percent"},{"benchmark":"roo-code-evals","model":"o4-mini-high","score":79,"metric":"percent"},{"benchmark":"roo-code-evals","model":"sonoma-dusk","score":78,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gpt-5-nano","score":78,"metric":"percent"},{"benchmark":"roo-code-evals","model":"deepseek-v3","score":77,"metric":"percent"},{"benchmark":"roo-code-evals","model":"o3-mini-high","score":75,"metric":"percent"},{"benchmark":"roo-code-evals","model":"qwen3-next","score":73,"metric":"percent"},{"benchmark":"roo-code-evals","model":"grok-4","score":72,"metric":"percent"},{"benchmark":"roo-code-evals","model":"glm-4.5-air","score":54,"metric":"percent"},{"benchmark":"roo-code-evals","model":"llama-4-maverick","score":52,"metric":"percent"},{"benchmark":"ruler-128k","model":"llama3-3.2b","score":71.3,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen-2.5-7.6b","score":92.2,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen-2.5-7.6b","score":90.2,"metric":"percent"},{"benchmark":"ruler-4k","model":"ministral-8b","score":96,"metric":"percent"},{"benchmark":"ruler-64k","model":"llama-3.1-8b-base","score":84.7,"metric":"percent"},{"benchmark":"ruler-8k","model":"llama-3.1-8b-base","score":93.8,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-r1","score":36.7,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v3.1-thinking","score":38.2,"metric":"percent"},{"benchmark":"scicode","model":"gemini-2.5-pro","score":42.8,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5-high","score":42.9,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-120b","score":38.8,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-20b","score":37.9,"metric":"percent"},{"benchmark":"scicode","model":"grok-4","score":45.7,"metric":"percent"},{"benchmark":"scicode","model":"grok-4-fast","score":44.2,"metric":"percent"},{"benchmark":"scicode","model":"k2-think","score":39.2,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-32b","score":37.1,"metric":"percent"},{"benchmark":"scicode","model":"o3-high","score":41.7,"metric":"percent"},{"benchmark":"scicode","model":"openreasoning-nemotron-1.5b","score":1,"metric":"percent"},{"benchmark":"scicode","model":"openreasoning-nemotron-14b","score":32.4,"metric":"percent"},{"benchmark":"scicode","model":"openreasoning-nemotron-32b","score":39.6,"metric":"percent"},{"benchmark":"scicode","model":"openreasoning-nemotron-7b","score":20.3,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-235b-a22b","score":39.3,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-235b-a22b-instruct-2507","score":42.4,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-30b-a3b","score":28.5,"metric":"percent"},{"benchmark":"scicode","model":"qwq-32b","score":36.9,"metric":"percent"},{"benchmark":"scicode-main","model":"deepseek-r1","score":11.5,"metric":"percent"},{"benchmark":"scicode-main","model":"deepseek-v3.1-thinking","score":11.7,"metric":"percent"},{"benchmark":"scicode-main","model":"gemini-2.5-pro","score":15.4,"metric":"percent"},{"benchmark":"scicode-main","model":"gpt-5-high","score":12.4,"metric":"percent"},{"benchmark":"scicode-main","model":"gpt-oss-120b","score":11,"metric":"percent"},{"benchmark":"scicode-main","model":"gpt-oss-20b","score":9,"metric":"percent"},{"benchmark":"scicode-main","model":"k2-think","score":12,"metric":"percent"},{"benchmark":"scicode-main","model":"nemotron-32b","score":11.4,"metric":"percent"},{"benchmark":"scicode-main","model":"o3-high","score":11.9,"metric":"percent"},{"benchmark":"scicode-main","model":"qwen3-235b-a22b","score":10.9,"metric":"percent"},{"benchmark":"scicode-main","model":"qwen3-30b-a3b","score":4.8,"metric":"percent"},{"benchmark":"scicode-main","model":"qwq-32b","score":11.5,"metric":"percent"},{"benchmark":"scienceqa","model":"fastvlm-0.5b","score":85.2,"metric":"percent"},{"benchmark":"scienceqa","model":"fastvlm-1.5b","score":94.4,"metric":"percent"},{"benchmark":"scienceqa","model":"fastvlm-7b","score":96.7,"metric":"percent"},{"benchmark":"screenqa-complex","model":"claude-sonnet-4","score":75.7,"metric":"percent"},{"benchmark":"screenqa-complex","model":"holo1-3b","score":53.5,"metric":"percent"},{"benchmark":"screenqa-complex","model":"holo1-7b","score":65.1,"metric":"percent"},{"benchmark":"screenqa-complex","model":"holo1.5-3b","score":81.4,"metric":"percent"},{"benchmark":"screenqa-complex","model":"holo1.5-72b","score":87.1,"metric":"percent"},{"benchmark":"screenqa-complex","model":"holo1.5-7b","score":83.2,"metric":"percent"},{"benchmark":"screenqa-complex","model":"qwen2.5-vl-3b","score":76,"metric":"percent"},{"benchmark":"screenqa-complex","model":"qwen2.5-vl-72b","score":83.2,"metric":"percent"},{"benchmark":"screenqa-complex","model":"qwen2.5-vl-7b","score":81.1,"metric":"percent"},{"benchmark":"screenqa-complex","model":"ui-tars-1.5-7b","score":79.2,"metric":"percent"},{"benchmark":"screenqa-complex","model":"ui-venus-72b","score":83.3,"metric":"percent"},{"benchmark":"screenqa-complex","model":"ui-venus-7b","score":82.3,"metric":"percent"},{"benchmark":"screenqa-short","model":"claude-sonnet-4","score":87,"metric":"percent"},{"benchmark":"screenqa-short","model":"holo1-3b","score":78.3,"metric":"percent"},{"benchmark":"screenqa-short","model":"holo1-7b","score":83.3,"metric":"percent"},{"benchmark":"screenqa-short","model":"holo1.5-3b","score":87.9,"metric":"percent"},{"benchmark":"screenqa-short","model":"holo1.5-72b","score":91.9,"metric":"percent"},{"benchmark":"screenqa-short","model":"holo1.5-7b","score":91,"metric":"percent"},{"benchmark":"screenqa-short","model":"qwen2.5-vl-3b","score":86,"metric":"percent"},{"benchmark":"screenqa-short","model":"qwen2.5-vl-72b","score":87.9,"metric":"percent"},{"benchmark":"screenqa-short","model":"qwen2.5-vl-7b","score":87,"metric":"percent"},{"benchmark":"screenqa-short","model":"ui-tars-1.5-7b","score":88.7,"metric":"percent"},{"benchmark":"screenqa-short","model":"ui-venus-72b","score":88.6,"metric":"percent"},{"benchmark":"screenqa-short","model":"ui-venus-7b","score":86.3,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3-vl-235b-a22b-thinking","score":95.4,"metric":"percent"},{"benchmark":"screenspot","model":"seed1.5-vl-thinking","score":95.2,"metric":"percent"},{"benchmark":"screenspot","model":"internvl-8b","score":79.5,"metric":"percent"},{"benchmark":"screenspot","model":"mimo-vl-7b-rl","score":87.2,"metric":"percent"},{"benchmark":"screenspot","model":"mimo-vl-7b-sft","score":87.3,"metric":"percent"},{"benchmark":"screenspot","model":"qwen2.5-vl-7b","score":84.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-sonnet-4","score":19.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gta1-32b","score":53.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gta1-72b","score":58.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo1-3b","score":23.66,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo1-7b","score":26.06,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo1.5-3b","score":51.49,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo1.5-72b","score":63.25,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo1.5-7b","score":57.94,"metric":"percent"},{"benchmark":"screenspot-pro","model":"kimi-vl-a3b-thinking-2506","score":51,"metric":"percent"},{"benchmark":"screenspot-pro","model":"mimo-vl-7b-rl","score":41.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"mimo-vl-7b-sft","score":39.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2.5-vl-3b","score":29.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2.5-vl-72b","score":55.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2.5-vl-72b-instruct","score":53.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2.5-vl-7b","score":29,"metric":"percent"},{"benchmark":"screenspot-pro","model":"seed-1.5-vl","score":60.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"tianxi-action-7b","score":51.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-tars-1.5","score":61.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-tars-1.5-7b","score":39,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-venus-72b","score":61.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-venus-7b","score":50.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"v2p-7b","score":50.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-235b-a22b-thinking","score":61.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"seed1.5-vl-thinking","score":60.9,"metric":"percent"},{"benchmark":"screenspot-v2","model":"claude-sonnet-4","score":93,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo1-3b","score":88.91,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo1-7b","score":89.85,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo1.5-3b","score":91.66,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo1.5-72b","score":94.41,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo1.5-7b","score":93.31,"metric":"percent"},{"benchmark":"screenspot-v2","model":"internvl-8b","score":81.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"mimo-vl-7b-rl","score":90.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"mimo-vl-7b-sft","score":89.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen2.5-vl-3b","score":80,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen2.5-vl-72b","score":93.3,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen2.5-vl-7b","score":88,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-tars-1.5-7b","score":94,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-venus-72b","score":95.3,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-venus-7b","score":94.1,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"claude-3.7-sonnet","score":72.9,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"gemma-3-27b-it","score":66.3,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"gpt-4o","score":71.1,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl-8b","score":69.7,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"mimo-vl-7b-rl","score":72.4,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"mimo-vl-7b-sft","score":71.9,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"qwen2.5-vl-7b","score":70.7,"metric":"percent"},{"benchmark":"seed-bench-img","model":"fastvlm-0.5b","score":71,"metric":"percent"},{"benchmark":"seed-bench-img","model":"fastvlm-1.5b","score":74.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"fastvlm-7b","score":75.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"minicpm-v-2.0-3b","score":67.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"vila1.5-3b","score":67.9,"metric":"percent"},{"benchmark":"seed-bench-img","model":"bunny-4b","score":72.5,"metric":"percent"},{"benchmark":"seed-bench-img","model":"blip-3-4b","score":72.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"phi-3-vision-4b","score":71.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"mm1.5-3b","score":72.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"llava-next-34b","score":75.9,"metric":"percent"},{"benchmark":"seed-bench-img","model":"cambrian-34b","score":75.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"mm1-30b","score":72.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"mm1.5-30b","score":75,"metric":"percent"},{"benchmark":"seed-bench-img","model":"janus-pro-1.5b","score":68.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"harmon-1.5b","score":67.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"blip-3o-4b","score":73.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"emu3-8b","score":68.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"janus-pro-7b","score":72.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen2.5-omni-7b","score":74.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"bagel-14b","score":78.5,"metric":"percent"},{"benchmark":"seed-bench-img","model":"manzano-3b","score":74.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"manzano-30b","score":76,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gpt-4o","score":77.1,"metric":"percent"},{"benchmark":"showdown","model":"claude-sonnet-4","score":72,"metric":"percent"},{"benchmark":"showdown","model":"holo1-3b","score":59.96,"metric":"percent"},{"benchmark":"showdown","model":"holo1-7b","score":64.27,"metric":"percent"},{"benchmark":"showdown","model":"holo1.5-3b","score":67.5,"metric":"percent"},{"benchmark":"showdown","model":"holo1.5-72b","score":76.84,"metric":"percent"},{"benchmark":"showdown","model":"holo1.5-7b","score":72.17,"metric":"percent"},{"benchmark":"showdown","model":"qwen2.5-vl-3b","score":50.3,"metric":"percent"},{"benchmark":"showdown","model":"qwen2.5-vl-72b","score":41,"metric":"percent"},{"benchmark":"showdown","model":"qwen2.5-vl-7b","score":52,"metric":"percent"},{"benchmark":"showdown","model":"ui-tars-1.5-7b","score":58,"metric":"percent"},{"benchmark":"showdown","model":"ui-venus-72b","score":75.58,"metric":"percent"},{"benchmark":"showdown","model":"ui-venus-7b","score":67.32,"metric":"percent"},{"benchmark":"simple-safety-tests","model":"k2-think","score":95,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3","score":27.3,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3-base","score":26.6,"metric":"percent"},{"benchmark":"simpleqa-search","model":"deepseek-v3.1","score":93.4,"metric":"percent"},{"benchmark":"simpleqa-search","model":"deepseek-v3.1-terminus","score":96.8,"metric":"percent"},{"benchmark":"simpleqa-search","model":"deepseek-v3.2-exp","score":97.1,"metric":"percent"},{"benchmark":"simpleqa-search","model":"deepseek-v3.1-thinking","score":93.4,"metric":"percent"},{"benchmark":"simpleqa","model":"ernie-4.5","score":45.9,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-12b-it","score":6.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-1b-it","score":2.2,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-4b-it","score":4,"metric":"percent"},{"benchmark":"simpleqa","model":"glm-4.5-base","score":30,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-4.1","score":40.2,"metric":"percent"},{"benchmark":"simpleqa-search","model":"jan-nano","score":80.7,"metric":"percent"},{"benchmark":"simpleqa-search","model":"jan-nano-128k","score":83.2,"metric":"percent"},{"benchmark":"simpleqa-search","model":"jan-nano-yarn","score":79.7,"metric":"percent"},{"benchmark":"simpleqa-search","model":"jan-v1","score":91.1,"metric":"percent"},{"benchmark":"simpleqa-search","model":"jan-v1-2509","score":90.7,"metric":"percent"},{"benchmark":"simpleqa-search","model":"jan-v1-edge","score":83,"metric":"percent"},{"benchmark":"simpleqa","model":"kimi-k2-base","score":35.3,"metric":"percent"},{"benchmark":"simpleqa-search","model":"perplexity-pro","score":90.6,"metric":"percent"},{"benchmark":"simpleqa-search","model":"qwen-1.7b-thinking","score":69.14,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-235b-a22b","score":12.4,"metric":"percent"},{"benchmark":"simpleqa-search","model":"qwen3-4b-instruct-2507","score":86.5,"metric":"percent"},{"benchmark":"skatebench","model":"gpt-5","score":98.6,"metric":"percent"},{"benchmark":"socialiqa","model":"gemma-2-2b","score":49.7,"metric":"percent"},{"benchmark":"socialiqa","model":"gemma-2-7b","score":51.8,"metric":"percent"},{"benchmark":"socialiqa","model":"gemma-3-pt-27b","score":54.9,"metric":"percent"},{"benchmark":"spider","model":"llama-3-70b-base","score":67.1,"metric":"percent"},{"benchmark":"spiral-bench","model":"claude-3.5-sonnet","score":47.7,"metric":"percent"},{"benchmark":"spiral-bench","model":"gemini-2.5-flash","score":49.1,"metric":"percent"},{"benchmark":"spiral-bench","model":"gemini-2.5-pro","score":43.5,"metric":"percent"},{"benchmark":"spiral-bench","model":"gpt-4o","score":42.3,"metric":"percent"},{"benchmark":"spiral-bench","model":"gpt-5","score":87,"metric":"percent"},{"benchmark":"spiral-bench","model":"gpt-oss-120b","score":81.4,"metric":"percent"},{"benchmark":"spiral-bench","model":"kimi-k2","score":73,"metric":"percent"},{"benchmark":"spiral-bench","model":"llama-4-maverick","score":48.1,"metric":"percent"},{"benchmark":"spiral-bench","model":"o3","score":86.1,"metric":"percent"},{"benchmark":"spiral-bench","model":"o4-mini","score":73.3,"metric":"percent"},{"benchmark":"squad-v1.1","model":"llama-3-70b-base","score":85.6,"metric":"em"},{"benchmark":"squad-v1.1","model":"llama-3-8b-base","score":76.4,"metric":"em"},{"benchmark":"squad-v1.1","model":"llama-3.1-405b-base","score":89.3,"metric":"em"},{"benchmark":"squad-v1.1","model":"llama-3.1-70b-base","score":81.8,"metric":"em"},{"benchmark":"squad-v1.1","model":"llama-3.1-8b-base","score":77,"metric":"em"},{"benchmark":"superglue","model":"hairuo","score":91.4,"metric":"percent"},{"benchmark":"supergpqa","model":"claude-3.7-sonnet","score":54.4,"metric":"percent"},{"benchmark":"supergpqa","model":"claude-opus-4","score":56.5,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3.1-thinking","score":59.8,"metric":"percent"},{"benchmark":"supergpqa","model":"gemini-2.5-flash-thinking","score":57.8,"metric":"percent"},{"benchmark":"supergpqa","model":"gemma-3-27b-it","score":29.3,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-4o","score":31.6,"metric":"percent"},{"benchmark":"supergpqa","model":"internvl-8b","score":29.4,"metric":"percent"},{"benchmark":"supergpqa","model":"kimi-k2","score":57.2,"metric":"percent"},{"benchmark":"supergpqa","model":"kimi-k2-instruct","score":57.2,"metric":"percent"},{"benchmark":"supergpqa","model":"mimo-vl-7b-rl","score":44.3,"metric":"percent"},{"benchmark":"supergpqa","model":"mimo-vl-7b-sft","score":42.6,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen2.5-vl-7b","score":25.4,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-235b-a22b","score":62.6,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-235b-a22b-thinking-2507","score":64.9,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-30b-a3b","score":53.4,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-30b-a3b-thinking-2507","score":56.8,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-32b-nothinking","score":43.2,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-32b-thinking","score":54.1,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-max-instruct-preview","score":64.6,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-next-80b-a3b-instruct","score":58.8,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-next-80b-a3b-thinking","score":60.8,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-5-codex","score":74.5,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-5-high","score":72.8,"metric":"percent"},{"benchmark":"swe-bench","model":"kimi-k2-instruct-0905","score":69.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-sonnet-4","score":53.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v3.1-thinking","score":54.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v3.1","score":54.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v3.1-terminus","score":57.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v3.2-exp","score":57.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-4.5","score":52.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2-instruct-0711","score":47.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2-instruct-0905","score":55.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3-coder-480b-a35b","score":54.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kat-dev-32b","score":62.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kat-coder","score":73.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4","score":72.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4","score":72.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.1-thinking","score":66,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.1","score":66,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.1-terminus","score":68.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.2-exp","score":67.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.5","score":64.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.6","score":68,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-4o","score":30.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5","score":74.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-codex","score":74.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-high","score":74.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-instruct-0711","score":65.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-instruct-0905","score":69.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"o3","score":69.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-480b-a35b","score":69.6,"metric":"percent"},{"benchmark":"swe-dev","model":"claude-sonnet-4","score":67.1,"metric":"percent"},{"benchmark":"swe-dev","model":"deepseek-v3.1-thinking","score":53.3,"metric":"percent"},{"benchmark":"swe-dev","model":"glm-4.5","score":63.2,"metric":"percent"},{"benchmark":"swe-dev","model":"kimi-k2-instruct-0711","score":61.9,"metric":"percent"},{"benchmark":"swe-dev","model":"kimi-k2-instruct-0905","score":66.6,"metric":"percent"},{"benchmark":"swe-dev","model":"qwen3-coder-480b-a35b","score":64.7,"metric":"percent"},{"benchmark":"swe-lancer","model":"gpt-4.5","score":37.3,"metric":"percent"},{"benchmark":"switzerland-qa","model":"llama-3.3-70b","score":74.3,"metric":"percent"},{"benchmark":"sysbench","model":"deepseek-v3","score":71.3,"metric":"percent"},{"benchmark":"sysbench","model":"ernie-4.5","score":69.8,"metric":"percent"},{"benchmark":"sysbench","model":"gpt-4.1","score":74.1,"metric":"percent"},{"benchmark":"sysbench","model":"hunyuan-7b-instruct","score":72.7,"metric":"percent"},{"benchmark":"sysbench","model":"qwen3-235b-a22b","score":51.3,"metric":"percent"},{"benchmark":"tau1-airline","model":"gemini-2.5-flash-thinking","score":54,"metric":"percent"},{"benchmark":"tau1-airline","model":"qwen3-235b-a22b","score":44,"metric":"percent"},{"benchmark":"tau1-airline","model":"qwen3-235b-a22b-thinking-2507","score":46,"metric":"percent"},{"benchmark":"tau1-airline","model":"qwen3-30b-a3b","score":40,"metric":"percent"},{"benchmark":"tau1-airline","model":"qwen3-30b-a3b-thinking-2507","score":48,"metric":"percent"},{"benchmark":"tau1-airline","model":"qwen3-32b-nothinking","score":17,"metric":"percent"},{"benchmark":"tau1-airline","model":"qwen3-32b-thinking","score":29,"metric":"percent"},{"benchmark":"tau1-airline","model":"qwen3-next-80b-a3b-instruct","score":44,"metric":"percent"},{"benchmark":"tau1-airline","model":"qwen3-next-80b-a3b-thinking","score":49,"metric":"percent"},{"benchmark":"tau1-retail","model":"gemini-2.5-flash-thinking","score":65.2,"metric":"percent"},{"benchmark":"tau1-retail","model":"qwen3-235b-a22b","score":71.3,"metric":"percent"},{"benchmark":"tau1-retail","model":"qwen3-235b-a22b-thinking-2507","score":67.8,"metric":"percent"},{"benchmark":"tau1-retail","model":"qwen3-30b-a3b","score":59.1,"metric":"percent"},{"benchmark":"tau1-retail","model":"qwen3-30b-a3b-thinking-2507","score":67.8,"metric":"percent"},{"benchmark":"tau1-retail","model":"qwen3-32b-nothinking","score":40.1,"metric":"percent"},{"benchmark":"tau1-retail","model":"qwen3-32b-thinking","score":52.8,"metric":"percent"},{"benchmark":"tau1-retail","model":"qwen3-next-80b-a3b-instruct","score":60.9,"metric":"percent"},{"benchmark":"tau1-retail","model":"qwen3-next-80b-a3b-thinking","score":69.6,"metric":"percent"},{"benchmark":"tau2-airline","model":"gemini-2.5-flash-thinking","score":52,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-235b-a22b","score":50,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-235b-a22b-thinking-2507","score":58,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-30b-a3b","score":38,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-30b-a3b-thinking-2507","score":58,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-32b-nothinking","score":24,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-32b-thinking","score":45.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-next-80b-a3b-instruct","score":45.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-next-80b-a3b-thinking","score":60.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-opus-4.1","score":63,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-sonnet-4","score":63,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemini-2.5-flash-thinking","score":66.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-235b-a22b","score":74.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-235b-a22b-thinking-2507","score":71.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-30b-a3b","score":57,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-30b-a3b-thinking-2507","score":58.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-32b-nothinking","score":48.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-32b-thinking","score":49.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-next-80b-a3b-instruct","score":57.3,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-next-80b-a3b-thinking","score":67.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4.1","score":86.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-sonnet-4","score":83.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash-thinking","score":31.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-235b-a22b","score":32.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-235b-a22b-thinking-2507","score":45.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-30b-a3b","score":12.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-30b-a3b-thinking-2507","score":26.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-32b-nothinking","score":24.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-32b-thinking","score":27.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-next-80b-a3b-instruct","score":13.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-next-80b-a3b-thinking","score":43.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.1","score":71.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-sonnet-4","score":49.6,"metric":"percent"},{"benchmark":"tense-change","model":"k2-think","score":84,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-3.7-sonnet","score":35.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4","score":39.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4.1","score":43.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-sonnet-4","score":35.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.1-thinking","score":31.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.1","score":31.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.1-terminus","score":36.7,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.2-exp","score":37.7,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-pro","score":25.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"glaive-swe-v1","score":35.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"glm-4.5","score":39.9,"metric":"percent"},{"benchmark":"terminal-bench","model":"glm-4.6","score":40.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-4.1","score":30.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5","score":49,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-instruct-0711","score":37.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-instruct-0905","score":44.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"o4-mini","score":27.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-coder-480b-a35b","score":37.5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-opus-4.1","score":32.1,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-sonnet-4","score":29.8,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-v3.1-thinking","score":24.1,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gemini-2.5-pro","score":24.8,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"glm-4.5","score":21.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5","score":30.5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-oss-120b","score":22,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"grok-4","score":37.6,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"kimi-k2-instruct","score":22.7,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"o3","score":34.8,"metric":"percent"},{"benchmark":"textvqa","model":"cambrian-1-34b","score":76.7,"metric":"percent"},{"benchmark":"textvqa","model":"cambrian-1-8b","score":71.7,"metric":"percent"},{"benchmark":"textvqa","model":"claude-3-haiku","score":67.3,"metric":"percent"},{"benchmark":"textvqa","model":"claude-3-opus","score":67.5,"metric":"percent"},{"benchmark":"textvqa","model":"claude-3.5-sonnet","score":74.1,"metric":"percent"},{"benchmark":"textvqa","model":"fastvlm-0.5b","score":64.5,"metric":"percent"},{"benchmark":"textvqa","model":"fastvlm-1.5b","score":70.4,"metric":"percent"},{"benchmark":"textvqa","model":"fastvlm-7b","score":74.9,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-1.5-flash","score":78.7,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-1.5-pro","score":78.7,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-4o-0513","score":77.4,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-4v","score":78,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2-8b","score":77.4,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2-llama-3-76b","score":84.4,"metric":"percent"},{"benchmark":"textvqa","model":"llama-3.2v-11b-instruct","score":79.7,"metric":"percent"},{"benchmark":"textvqa","model":"llama-3.2v-90b-instruct","score":82.3,"metric":"percent"},{"benchmark":"textvqa","model":"llava-1.5-13b","score":61.3,"metric":"percent"},{"benchmark":"textvqa","model":"llava-1.5-7b","score":58.2,"metric":"percent"},{"benchmark":"textvqa","model":"llava-onevision-72b","score":80.5,"metric":"percent"},{"benchmark":"textvqa","model":"llava-onevision-7b","score":78.3,"metric":"percent"},{"benchmark":"textvqa","model":"molmo-72b","score":83.1,"metric":"percent"},{"benchmark":"textvqa","model":"molmo-7b-d","score":81.7,"metric":"percent"},{"benchmark":"textvqa","model":"molmo-7b-o","score":80.4,"metric":"percent"},{"benchmark":"textvqa","model":"molmoe-1b","score":78.8,"metric":"percent"},{"benchmark":"textvqa","model":"paligemma-mix-3b","score":56,"metric":"percent"},{"benchmark":"textvqa","model":"phi-3.5-vision-4b","score":72,"metric":"percent"},{"benchmark":"textvqa","model":"pixtral-12b","score":75.7,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2-vl-72b","score":85.5,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2-vl-7b","score":84.3,"metric":"percent"},{"benchmark":"textvqa","model":"xgen-mm-interleave-4b","score":71,"metric":"percent"},{"benchmark":"toxigen","model":"k2-think","score":97,"metric":"percent"},{"benchmark":"treebench","model":"gemma-3-27b-vl","score":33.8,"metric":"percent"},{"benchmark":"treebench","model":"glm-4.1v","score":37.5,"metric":"percent"},{"benchmark":"treebench","model":"glm-4.5v","score":50.1,"metric":"percent"},{"benchmark":"treebench","model":"kimi-vl-a3b-thinking-2506","score":41.5,"metric":"percent"},{"benchmark":"treebench","model":"step-3","score":41.3,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v3-base","score":82.9,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-2-2b","score":53.2,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-2-7b","score":63.4,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-pt-270m","score":15.4,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-pt-27b","score":85.5,"metric":"percent"},{"benchmark":"triviaqa","model":"glm-4.5-base","score":80,"metric":"percent"},{"benchmark":"triviaqa","model":"kimi-k2-base","score":85.1,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-1b-pretrained","score":28.1,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen2.5-1.5b-pretrained","score":20.9,"metric":"percent"},{"benchmark":"triviaqa","model":"smollm1-1.7b-pretrained","score":22.5,"metric":"percent"},{"benchmark":"triviaqa","model":"smollm2-1.7b-pretrained","score":36.7,"metric":"percent"},{"benchmark":"triviaqa","model":"smollm2-135m-base","score":4.3,"metric":"percent"},{"benchmark":"triviaqa","model":"smollm2-135m-pretrained","score":4.3,"metric":"percent"},{"benchmark":"triviaqa-wiki","model":"llama-3-70b-base","score":89.7,"metric":"em"},{"benchmark":"triviaqa-wiki","model":"llama-3-8b-base","score":78.5,"metric":"em"},{"benchmark":"triviaqa-wiki","model":"llama-3.1-405b-base","score":91.8,"metric":"percent"},{"benchmark":"triviaqa-wiki","model":"llama-3.1-405b-base","score":91.8,"metric":"em"},{"benchmark":"triviaqa-wiki","model":"llama-3.1-70b-base","score":89.8,"metric":"em"},{"benchmark":"triviaqa-wiki","model":"llama-3.1-8b-base","score":77.6,"metric":"em"},{"benchmark":"triviaqa","model":"afm-4.5b","score":47.66,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-4b-it","score":42.1,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3-4b","score":44.32,"metric":"percent"},{"benchmark":"triviaqa","model":"smollm3-3b","score":35.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon-h1-0.5b-instruct","score":44.12,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon-h1-1.5b","score":45.98,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon-h1-1.5b-deep","score":50.48,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon-h1-34b-instruct","score":65.27,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon-h1-3b","score":53.19,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon-h1-7b","score":59.91,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon3-10b","score":55.05,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon3-1b","score":42.31,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon3-3b","score":50.06,"metric":"percent"},{"benchmark":"truthfulqa","model":"falcon3-7b","score":55.58,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-3","score":68.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-3-12b-it","score":61.02,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-3-1b-it","score":42.17,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-3-27b-it","score":64.26,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-3-4b-it","score":51.68,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-8b-base","score":52.99,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.2-1.24b-base","score":42.08,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.2-3b-base","score":50.27,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.3-70b","score":66.15,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-4-scout-17b","score":62.74,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-0.5b","score":46.19,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-1.5b","score":47.05,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-32b-instruct","score":70.28,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-3b","score":58.11,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-72b-instruct","score":69.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-7b","score":62.41,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen3-0.8b","score":51.65,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen3-1.7b","score":49.39,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen3-32b","score":58.58,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen3-4b","score":51.75,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen3-8b","score":53.19,"metric":"percent"},{"benchmark":"truthqa","model":"olmo-2-0325-32b-instruct","score":73.2,"metric":"percent"},{"benchmark":"truthqa-multilingual","model":"qwen2.5-72b-instruct","score":58.6,"metric":"percent"},{"benchmark":"tydiqa","model":"llama-3.1-405b-base","score":34.3,"metric":"average/f1"},{"benchmark":"tydiqa","model":"llama-3.1-70b-base","score":29.9,"metric":"average/f1"},{"benchmark":"tydiqa","model":"llama-4-maverick-17b-128e-base","score":31.7,"metric":"average/f1"},{"benchmark":"tydiqa","model":"llama-4-maverick-base","score":31.7,"metric":"average/f1"},{"benchmark":"tydiqa","model":"llama-4-scout-17b-16e-base","score":31.5,"metric":"average/f1"},{"benchmark":"tydiqa","model":"llama-4-scout-17b-base","score":31.5,"metric":"average/f1"},{"benchmark":"v-star","model":"gemma-3-27b-it","score":50.8,"metric":"percent"},{"benchmark":"v-star","model":"gpt-4o","score":73.9,"metric":"percent"},{"benchmark":"v-star","model":"internvl-8b","score":72.8,"metric":"percent"},{"benchmark":"v-star","model":"mimo-vl-7b-rl","score":81.7,"metric":"percent"},{"benchmark":"v-star","model":"mimo-vl-7b-sft","score":80.6,"metric":"percent"},{"benchmark":"v-star","model":"qwen2.5-vl-7b","score":73.8,"metric":"percent"},{"benchmark":"vct","model":"claude-3.7-sonnet","score":30.8,"metric":"percent"},{"benchmark":"vct","model":"gpt-4.5","score":28.3,"metric":"percent"},{"benchmark":"vct","model":"gpt-4o","score":18.8,"metric":"percent"},{"benchmark":"vct","model":"o1","score":35.4,"metric":"percent"},{"benchmark":"vct","model":"o3","score":43.8,"metric":"percent"},{"benchmark":"vct","model":"o4-mini","score":37,"metric":"percent"},{"benchmark":"vct","model":"claude-sonnet-4","score":36,"metric":"percent"},{"benchmark":"vct","model":"claude-opus-4","score":41.1,"metric":"percent"},{"benchmark":"vct","model":"claude-opus-4.1","score":42.9,"metric":"percent"},{"benchmark":"vct","model":"claude-sonnet-4.5","score":39.7,"metric":"percent"},{"benchmark":"vibe-eval-reka","model":"gemini-2.5-pro","score":67.2,"metric":"percent"},{"benchmark":"vibeval","model":"claude-3.7-sonnet","score":39,"metric":"percent"},{"benchmark":"vibeval","model":"gemma-3-27b-it","score":44,"metric":"percent"},{"benchmark":"vibeval","model":"gpt-4o","score":64.7,"metric":"percent"},{"benchmark":"vibeval","model":"internvl-8b","score":43.6,"metric":"percent"},{"benchmark":"vibeval","model":"mimo-vl-7b-rl","score":54.7,"metric":"percent"},{"benchmark":"vibeval","model":"mimo-vl-7b-sft","score":47.2,"metric":"percent"},{"benchmark":"vibeval","model":"qwen2.5-vl-7b","score":47.7,"metric":"percent"},{"benchmark":"video-mme","model":"glm-4.5v","score":70,"metric":"percent"},{"benchmark":"video-mme","model":"gpt-4.1","score":72,"metric":"percent"},{"benchmark":"video-mme","model":"smolvlm2-0.256b","score":33.7,"metric":"percent"},{"benchmark":"video-mme","model":"smolvlm2-0.5b","score":42.2,"metric":"percent"},{"benchmark":"video-mme","model":"smolvlm2-2.2b","score":52.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl-8b","score":66.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"mimo-vl-7b-rl","score":67.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"mimo-vl-7b-sft","score":66.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen2.5-vl-7b","score":65.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemma-3-27b-vl","score":58.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"glm-4.1v","score":68.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"glm-4.5v","score":74.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"kimi-vl-a3b-thinking-2506","score":67.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-235b-a22b-thinking","score":79,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-2.5-pro","score":85.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-5","score":84.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"claude-opus-4.1","score":75.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"seed1.5-vl-thinking","score":77.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemma-3-27b-vl","score":68.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"glm-4.1v","score":73.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"glm-4.5v","score":80.7,"metric":"percent"},{"benchmark":"videomme-sub","model":"kimi-vl-a3b-thinking-2506","score":71.9,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-235b-a22b-thinking","score":80,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-2.5-pro","score":83.6,"metric":"percent"},{"benchmark":"videommmu","model":"seed1.5-vl-thinking","score":81.4,"metric":"percent"},{"benchmark":"videommmu","model":"claude-opus-4.1","score":76.2,"metric":"percent"},{"benchmark":"videommmu","model":"gemma-3-27b-vl","score":54.5,"metric":"percent"},{"benchmark":"videommmu","model":"glm-4.1v","score":61,"metric":"percent"},{"benchmark":"videommmu","model":"glm-4.5v","score":62.4,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-4o","score":61.2,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5","score":84.6,"metric":"percent"},{"benchmark":"videommmu","model":"internvl-8b","score":48.9,"metric":"percent"},{"benchmark":"videommmu","model":"kimi-vl-a3b-thinking-2506","score":65.2,"metric":"percent"},{"benchmark":"videommmu","model":"mimo-vl-7b-rl","score":43.3,"metric":"percent"},{"benchmark":"videommmu","model":"mimo-vl-7b-sft","score":53.1,"metric":"percent"},{"benchmark":"videommmu","model":"o3","score":83.3,"metric":"percent"},{"benchmark":"videommmu","model":"qwen2.5-vl-7b","score":47.4,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"claude-3-sonnet","score":65.8,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"claude-3.7-sonnet","score":79.3,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"claude-3-opus","score":58.5,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"claude-sonnet-4","score":58.9,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"deepseek-vl-7b","score":28.1,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"gemini-1.0-pro","score":48,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"gemini-1.5-pro","score":64.8,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"gemma-3-27b-it","score":49.7,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"gpt-4o","score":80.2,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"gpt-4v","score":64.6,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"holo1-3b","score":54.1,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"holo1-7b","score":38.1,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"holo1.5-3b","score":78.5,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"holo1.5-72b","score":83.8,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"holo1.5-7b","score":82.6,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"internvl-8b","score":62.7,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"llava-1.6-13b","score":39.4,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"llava-1.6-34b","score":50.5,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"llava-1.6-7b","score":36,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"mimo-vl-7b-rl","score":80.2,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"mimo-vl-7b-sft","score":80.2,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"qwen2.5-vl-3b","score":58,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"qwen2.5-vl-72b","score":76.3,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"qwen2.5-vl-7b","score":69,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"ui-tars-1.5-7b","score":79.7,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"ui-venus-72b","score":74.1,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"ui-venus-7b","score":60.9,"metric":"percent"},{"benchmark":"visualwebbench-avg","model":"vila-13b","score":27.3,"metric":"percent"},{"benchmark":"visulogic","model":"dots-vlm1","score":32.2,"metric":"percent"},{"benchmark":"visulogic","model":"doubao-1.5-vision-pro","score":28.1,"metric":"percent"},{"benchmark":"visulogic","model":"ernie-4.5-vl-424b-a47b","score":27.3,"metric":"percent"},{"benchmark":"visulogic","model":"gemini-2.0-pro","score":28,"metric":"percent"},{"benchmark":"visulogic","model":"internvl2.5-38b-rl","score":31.1,"metric":"percent"},{"benchmark":"visulogic","model":"internvl3-78b","score":27.7,"metric":"percent"},{"benchmark":"visulogic","model":"o3","score":29.5,"metric":"percent"},{"benchmark":"visulogic","model":"qwen2.5-vl-7b-instruct-rl","score":28,"metric":"percent"},{"benchmark":"visulogic","model":"seed1.5-vl-thinking","score":35,"metric":"percent"},{"benchmark":"visulogic","model":"qwen3-vl-235b-a22b-thinking","score":34.4,"metric":"percent"},{"benchmark":"visulogic","model":"gemini-2.5-pro","score":31.6,"metric":"percent"},{"benchmark":"visulogic","model":"gpt-5","score":28.5,"metric":"percent"},{"benchmark":"visulogic","model":"claude-opus-4.1","score":27.9,"metric":"percent"},{"benchmark":"visulogic","model":"skywork-r1v3-38b","score":28.5,"metric":"percent"},{"benchmark":"visulogic","model":"qwen2.5-vl-72b","score":25.6,"metric":"percent"},{"benchmark":"visulogic","model":"gemini-2.5-pro","score":29.8,"metric":"percent"},{"benchmark":"visulogic","model":"seed1.5-vl-thinking","score":35.9,"metric":"percent"},{"benchmark":"vitabench","model":"longcat-flash","score":24.3,"metric":"percent"},{"benchmark":"vitabench","model":"longcat-flash-thinking","score":29.5,"metric":"percent"},{"benchmark":"vitabench","model":"deepseek-v3.1-thinking","score":13.5,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3-235b-a22b-thinking-2507","score":21.5,"metric":"percent"},{"benchmark":"vitabench","model":"glm-4.5","score":26.8,"metric":"percent"},{"benchmark":"vitabench","model":"o3","score":35.3,"metric":"percent"},{"benchmark":"vitabench","model":"gemini-2.5-pro","score":24.3,"metric":"percent"},{"benchmark":"vitabench","model":"gpt-5-thinking","score":29.3,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"claude-3.7-sonnet","score":67.4,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"gemma-3-27b-it","score":51.9,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"gpt-4o","score":62.4,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"internvl-8b","score":49.7,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"mimo-vl-7b-rl","score":62.7,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"mimo-vl-7b-sft","score":61.9,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"qwen2.5-vl-7b","score":47.3,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"claude-3.7-sonnet","score":16.59,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"gemini-2.5-pro","score":16.02,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"gpt-4.1","score":13.88,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"o3","score":18.5,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"o4-mini","score":20.25,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"claude-3.5-sonnet","score":45.89,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"claude-3.7-sonnet","score":72.1,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"gemini-1.5-pro","score":65,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"gemma-3-27b-it","score":18.6,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"gpt-4o","score":49.8,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"internvl-8b","score":36.8,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"keye-vl-8b","score":61,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"mimo-vl-7b-rl","score":79.4,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"mimo-vl-7b-sft","score":78,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"qwen2.5-vl-7b","score":37.4,"metric":"percent"},{"benchmark":"vqav2","model":"cambrian-1-34b","score":83.8,"metric":"percent"},{"benchmark":"vqav2","model":"cambrian-1-8b","score":81.2,"metric":"percent"},{"benchmark":"vqav2","model":"claude-3-haiku","score":68.4,"metric":"percent"},{"benchmark":"vqav2","model":"claude-3-opus","score":66.3,"metric":"percent"},{"benchmark":"vqav2","model":"claude-3.5-sonnet","score":70.7,"metric":"percent"},{"benchmark":"vqav2","model":"fastvlm-0.5b","score":76.3,"metric":"percent"},{"benchmark":"vqav2","model":"fastvlm-1.5b","score":79.1,"metric":"percent"},{"benchmark":"vqav2","model":"fastvlm-7b","score":80.8,"metric":"percent"},{"benchmark":"vqav2","model":"gemini-1.5-flash","score":80.1,"metric":"percent"},{"benchmark":"vqav2","model":"gemini-1.5-pro","score":80.2,"metric":"percent"},{"benchmark":"vqav2","model":"gpt-4o-0513","score":78.7,"metric":"percent"},{"benchmark":"vqav2","model":"gpt-4v","score":77.2,"metric":"percent"},{"benchmark":"vqav2","model":"internvl2-8b","score":76.7,"metric":"percent"},{"benchmark":"vqav2","model":"internvl2-llama-3-76b","score":85.6,"metric":"percent"},{"benchmark":"vqav2","model":"llama-3.2v-11b-instruct","score":75.2,"metric":"percent"},{"benchmark":"vqav2","model":"llama-3.2v-90b-instruct","score":78.1,"metric":"percent"},{"benchmark":"vqav2","model":"llava-1.5-13b","score":80,"metric":"percent"},{"benchmark":"vqav2","model":"llava-1.5-7b","score":78.5,"metric":"percent"},{"benchmark":"vqav2","model":"llava-onevision-72b","score":85.2,"metric":"percent"},{"benchmark":"vqav2","model":"llava-onevision-7b","score":84,"metric":"percent"},{"benchmark":"vqav2","model":"molmo-72b","score":86.5,"metric":"percent"},{"benchmark":"vqav2","model":"molmo-7b-d","score":85.6,"metric":"percent"},{"benchmark":"vqav2","model":"molmo-7b-o","score":85.3,"metric":"percent"},{"benchmark":"vqav2","model":"molmoe-1b","score":83.9,"metric":"percent"},{"benchmark":"vqav2","model":"paligemma-mix-3b","score":76.3,"metric":"percent"},{"benchmark":"vqav2","model":"phi-3.5-vision-4b","score":75.7,"metric":"percent"},{"benchmark":"vqav2","model":"pixtral-12b","score":78.6,"metric":"percent"},{"benchmark":"vqav2","model":"qwen2-vl-72b","score":81.9,"metric":"percent"},{"benchmark":"vqav2","model":"qwen2-vl-7b","score":82.9,"metric":"percent"},{"benchmark":"vqav2","model":"xgen-mm-interleave-4b","score":81.5,"metric":"percent"},{"benchmark":"webclick","model":"claude-sonnet-4","score":93,"metric":"percent"},{"benchmark":"webclick","model":"holo1-3b","score":79.35,"metric":"percent"},{"benchmark":"webclick","model":"holo1-7b","score":84.04,"metric":"percent"},{"benchmark":"webclick","model":"holo1.5-3b","score":81.45,"metric":"percent"},{"benchmark":"webclick","model":"holo1.5-72b","score":92.43,"metric":"percent"},{"benchmark":"webclick","model":"holo1.5-7b","score":90.24,"metric":"percent"},{"benchmark":"webclick","model":"qwen2.5-vl-3b","score":71.2,"metric":"percent"},{"benchmark":"webclick","model":"qwen2.5-vl-72b","score":88.29,"metric":"percent"},{"benchmark":"webclick","model":"qwen2.5-vl-7b","score":76.51,"metric":"percent"},{"benchmark":"webclick","model":"ui-tars-1.5-7b","score":86.1,"metric":"percent"},{"benchmark":"webclick","model":"ui-venus-72b","score":77,"metric":"percent"},{"benchmark":"webclick","model":"ui-venus-7b","score":84.44,"metric":"percent"},{"benchmark":"webdev-arena","model":"claude-opus-4","score":1383,"metric":"score"},{"benchmark":"webdev-arena","model":"claude-opus-4.1","score":1476,"metric":"score"},{"benchmark":"webdev-arena","model":"claude-sonnet-4","score":1360,"metric":"score"},{"benchmark":"webdev-arena","model":"deepseek-r1","score":1393,"metric":"score"},{"benchmark":"webdev-arena","model":"deepseek-v3.1-thinking","score":1364,"metric":"score"},{"benchmark":"webdev-arena","model":"gemini-2.5-pro","score":1405,"metric":"score"},{"benchmark":"webdev-arena","model":"glm-4.5","score":1371,"metric":"score"},{"benchmark":"webdev-arena","model":"glm-4.5-air","score":1366,"metric":"score"},{"benchmark":"webdev-arena","model":"gpt-5","score":1483,"metric":"score"},{"benchmark":"webdev-arena","model":"qwen3-coder-480b-a35b","score":1367,"metric":"score"},{"benchmark":"webquest-multiqa","model":"gemma-3-27b-vl","score":36.5,"metric":"percent"},{"benchmark":"webquest-multiqa","model":"glm-4.1v","score":54.7,"metric":"percent"},{"benchmark":"webquest-multiqa","model":"glm-4.5v","score":60.6,"metric":"percent"},{"benchmark":"webquest-multiqa","model":"kimi-vl-a3b-thinking-2506","score":11.1,"metric":"percent"},{"benchmark":"webquest-multiqa","model":"step-3","score":52.8,"metric":"percent"},{"benchmark":"webquest-singleqa","model":"gemma-3-27b-vl","score":31.2,"metric":"percent"},{"benchmark":"webquest-singleqa","model":"glm-4.1v","score":72.1,"metric":"percent"},{"benchmark":"webquest-singleqa","model":"glm-4.5v","score":76.9,"metric":"percent"},{"benchmark":"webquest-singleqa","model":"kimi-vl-a3b-thinking-2506","score":35.6,"metric":"percent"},{"benchmark":"webquest-singleqa","model":"step-3","score":58.7,"metric":"percent"},{"benchmark":"websrc","model":"claude-3.7-sonnet","score":91.1,"metric":"percent"},{"benchmark":"websrc","model":"claude-sonnet-4","score":96,"metric":"percent"},{"benchmark":"websrc","model":"gemma-3-27b-it","score":89,"metric":"percent"},{"benchmark":"websrc","model":"gpt-4o","score":89.1,"metric":"percent"},{"benchmark":"websrc","model":"holo1-3b","score":93.9,"metric":"percent"},{"benchmark":"websrc","model":"holo1-7b","score":95.3,"metric":"percent"},{"benchmark":"websrc","model":"holo1.5-3b","score":94.8,"metric":"percent"},{"benchmark":"websrc","model":"holo1.5-72b","score":97.2,"metric":"percent"},{"benchmark":"websrc","model":"holo1.5-7b","score":95.9,"metric":"percent"},{"benchmark":"websrc","model":"internvl-8b","score":91.1,"metric":"percent"},{"benchmark":"websrc","model":"mimo-vl-7b-rl","score":95.3,"metric":"percent"},{"benchmark":"websrc","model":"mimo-vl-7b-sft","score":96.5,"metric":"percent"},{"benchmark":"websrc","model":"qwen2.5-vl-3b","score":93,"metric":"percent"},{"benchmark":"websrc","model":"qwen2.5-vl-72b","score":97,"metric":"percent"},{"benchmark":"websrc","model":"qwen2.5-vl-7b","score":95,"metric":"percent"},{"benchmark":"websrc","model":"ui-tars-1.5-7b","score":92.9,"metric":"percent"},{"benchmark":"websrc","model":"ui-venus-72b","score":96.7,"metric":"percent"},{"benchmark":"websrc","model":"ui-venus-7b","score":96.6,"metric":"percent"},{"benchmark":"webvoyager2","model":"gemma-3-27b-vl","score":34.8,"metric":"percent"},{"benchmark":"webvoyager2","model":"glm-4.1v","score":69,"metric":"percent"},{"benchmark":"webvoyager2","model":"glm-4.5v","score":84.4,"metric":"percent"},{"benchmark":"webwalker-qa","model":"deepseek-v3.1","score":61.2,"metric":"avg@3"},{"benchmark":"webwalker-qa","model":"glm-4.5","score":65.6,"metric":"avg@3"},{"benchmark":"webwalker-qa","model":"kimi-k2","score":63,"metric":"avg@3"},{"benchmark":"webwalker-qa","model":"o3","score":71.7,"metric":"avg@3"},{"benchmark":"webwalker-qa","model":"tongyi-deepresearch","score":72.2,"metric":"avg@3"},{"benchmark":"wemath","model":"gemma-3-27b-vl","score":37.9,"metric":"percent"},{"benchmark":"wemath","model":"glm-4.1v","score":63.8,"metric":"percent"},{"benchmark":"wemath","model":"glm-4.5v","score":68.8,"metric":"percent"},{"benchmark":"wemath","model":"kimi-vl-a3b-thinking-2506","score":42,"metric":"percent"},{"benchmark":"wemath","model":"step-3","score":59.8,"metric":"percent"},{"benchmark":"werewolf","model":"gpt-5","score":97.1,"metric":"percent"},{"benchmark":"winogender","model":"tfree-hat-pretrained-7b-base","score":67.1,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-2-2b","score":65.4,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-2-7b","score":72.3,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-270m-it","score":52.3,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-pt-270m","score":52,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1b-pretrained","score":57.8,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.1-405b-base","score":86.7,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.1-405b-base","score":86.7,"metric":"acc_char"},{"benchmark":"winogrande","model":"llama-3.1-70b-base","score":83.3,"metric":"acc_char"},{"benchmark":"winogrande","model":"llama-3.1-8b-base","score":60.5,"metric":"acc_char"},{"benchmark":"winogrande","model":"qwen2.5-1.5b-pretrained","score":59.3,"metric":"percent"},{"benchmark":"winogrande","model":"smollm1-1.7b-pretrained","score":54.7,"metric":"percent"},{"benchmark":"winogrande","model":"smollm2-1.7b-pretrained","score":59.4,"metric":"percent"},{"benchmark":"winogrande","model":"smollm2-135m-base","score":51.3,"metric":"percent"},{"benchmark":"winogrande","model":"smollm2-135m-pretrained","score":51.3,"metric":"percent"},{"benchmark":"wmdp-bio","model":"zephyr-7b","score":63.7,"metric":"percent"},{"benchmark":"wmdp-chem","model":"zephyr-7b","score":45.8,"metric":"percent"},{"benchmark":"wmdp-cyber","model":"zephyr-7b","score":44,"metric":"percent"},{"benchmark":"wmt23-ende","model":"gpt-4","score":89,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gemma-3-27b-it","score":53.4,"metric":"percent"},{"benchmark":"writingbench","model":"gemini-2.5-flash-thinking","score":83.9,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-235b-a22b","score":85.2,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-235b-a22b-thinking-2507","score":88.3,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-30b-a3b","score":85.5,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-30b-a3b-thinking-2507","score":85,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-32b-nothinking","score":75.4,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-32b-thinking","score":79,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-next-80b-a3b-instruct","score":87.3,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-next-80b-a3b-thinking","score":84.6,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"claude-sonnet-4","score":65,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"deepseek-v3.1","score":71,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"glm-4.5","score":70,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"kimi-k2","score":50,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"kimi-researcher","score":69,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"o3","score":67,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"tongyi-deepresearch","score":75,"metric":"avg@3"},{"benchmark":"zebralogic","model":"deepseek-v3","score":81.8,"metric":"percent"},{"benchmark":"zebralogic","model":"ernie-4.5","score":58.1,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4.1","score":56.3,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-235b-a22b","score":37.7,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-moe-2507","score":94.2,"metric":"percent"},{"benchmark":"zerobench","model":"gemma-3-27b-vl","score":17.7,"metric":"percent"},{"benchmark":"zerobench","model":"glm-4.1v","score":19.2,"metric":"percent"},{"benchmark":"zerobench","model":"glm-4.5v","score":23.4,"metric":"percent"},{"benchmark":"zerobench","model":"kimi-vl-a3b-thinking-2506","score":16.2,"metric":"percent"},{"benchmark":"zerobench","model":"seed1.5-vl-thinking","score":2,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3-vl-235b-a22b-thinking","score":4,"metric":"percent"},{"benchmark":"zerobench","model":"gemini-2.5-pro","score":3,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5","score":2,"metric":"percent"},{"benchmark":"zerobench","model":"claude-opus-4.1","score":1,"metric":"percent"},{"benchmark":"zerobench","model":"step-3","score":23,"metric":"percent"},{"benchmark":"zerobench","model":"qwen2.5-vl-72b","score":2,"metric":"percent"},{"benchmark":"zerobench","model":"gemini-2.5-pro","score":5,"metric":"percent"},{"benchmark":"zerobench","model":"dots-vlm1","score":4,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-235b-a22b-thinking","score":27.7,"metric":"percent"},{"benchmark":"zerobench-sub","model":"seed1.5-vl-thinking","score":30.8,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemini-2.5-pro","score":33.8,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gpt-5","score":24.6,"metric":"percent"},{"benchmark":"zerobench-sub","model":"claude-opus-4.1","score":26.3,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen2.5-vl-72b","score":20,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemini-2.5-pro","score":30.24,"metric":"percent"},{"benchmark":"zerobench-sub","model":"seed1.5-vl-thinking","score":25.75,"metric":"percent"},{"benchmark":"zerobench-sub","model":"dots-vlm1","score":26.65,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-medium-1.2","score":91.82,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-medium-1.2","score":83.48,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-medium-1.2","score":76.26,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-medium-1.2","score":75,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-medium-1.1","score":72.03,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-medium-1.1","score":60.99,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-medium-1.1","score":71.46,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-medium-1.1","score":59.35,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-flash-2.0","score":51.38,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b-nothinking","score":31.5,"metric":"percent"},{"benchmark":"livecodebench","model":"seed-oss-36b-instruct","score":30.7,"metric":"percent"},{"benchmark":"livecodebench","model":"hunyuan-80b-a13b-instruct","score":25.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":42.7,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-medium-1.0","score":73.59,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-medium-1.0","score":64.95,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-medium-1.0","score":70.83,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-medium-1.0","score":59.36,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-small-1.2","score":86.14,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-small-1.2","score":77.34,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-small-1.2","score":70.07,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-small-1.2","score":70.88,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-small-1.1","score":70.52,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-small-1.1","score":62.03,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-small-1.1","score":65.78,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-small-1.1","score":59.17,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-small-1.0","score":70.68,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-small-1.0","score":62.76,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-small-1.0","score":68.18,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-small-1.0","score":55.84,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-3.1-2b-instruct","score":23.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-3.1-2b-instruct","score":27.17,"metric":"percent"},{"benchmark":"mmlu","model":"granite-3.1-2b-instruct","score":57.11,"metric":"percent"},{"benchmark":"pope","model":"moondream-9b-a2b","score":89,"metric":"percent"},{"benchmark":"pope","model":"gpt-5","score":88.4,"metric":"percent"},{"benchmark":"pope","model":"gemini-2.5-flash","score":88.1,"metric":"percent"},{"benchmark":"pope","model":"claude-sonnet-4","score":84.6,"metric":"percent"},{"benchmark":"popqa","model":"granite-3.1-2b-instruct","score":20.55,"metric":"percent"},{"benchmark":"truthfulqa","model":"granite-3.1-2b-instruct","score":59.79,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.1-2b-instruct","score":61.82,"metric":"percent"},{"benchmark":"drop","model":"granite-3.1-2b-instruct","score":20.99,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-3.1-2b-instruct","score":67.55,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-3.1-2b-instruct","score":75.26,"metric":"percent"},{"benchmark":"ifeval","model":"granite-3.1-2b-instruct","score":63.59,"metric":"percent"},{"benchmark":"attaq","model":"granite-3.1-2b-instruct","score":84.7,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-3.2-2b-instruct","score":24.86,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-3.2-2b-instruct","score":34.51,"metric":"percent"},{"benchmark":"mmlu","model":"granite-3.2-2b-instruct","score":57.18,"metric":"percent"},{"benchmark":"popqa","model":"granite-3.2-2b-instruct","score":20.56,"metric":"percent"},{"benchmark":"truthfulqa","model":"granite-3.2-2b-instruct","score":59.8,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.2-2b-instruct","score":61.39,"metric":"percent"},{"benchmark":"drop","model":"granite-3.2-2b-instruct","score":23.84,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-3.2-2b-instruct","score":67.02,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-3.2-2b-instruct","score":73.39,"metric":"percent"},{"benchmark":"ifeval","model":"granite-3.2-2b-instruct","score":61.55,"metric":"percent"},{"benchmark":"attaq","model":"granite-3.2-2b-instruct","score":83.23,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-3.3-2b-instruct","score":28.86,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-3.3-2b-instruct","score":43.45,"metric":"percent"},{"benchmark":"mmlu","model":"granite-3.3-2b-instruct","score":55.88,"metric":"percent"},{"benchmark":"popqa","model":"granite-3.3-2b-instruct","score":18.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"granite-3.3-2b-instruct","score":58.97,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.3-2b-instruct","score":63.91,"metric":"percent"},{"benchmark":"drop","model":"granite-3.3-2b-instruct","score":44.33,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-3.3-2b-instruct","score":72.48,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-3.3-2b-instruct","score":75.68,"metric":"percent"},{"benchmark":"ifeval","model":"granite-3.3-2b-instruct","score":65.88,"metric":"percent"},{"benchmark":"attaq","model":"granite-3.3-2b-instruct","score":87.47,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3.1-8b-instruct","score":36.43,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-8b-instruct","score":24.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-8b-instruct","score":71.2,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-8b-instruct","score":20.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-8b-instruct","score":55.1,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-8b-instruct","score":62.8,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-8b-instruct","score":61.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b-instruct","score":83.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-8b-instruct","score":82.9,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-8b-instruct","score":80.6,"metric":"percent"},{"benchmark":"attaq","model":"llama-3.1-8b-instruct","score":83.43,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-r1-distill-llama-8b","score":17.17,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-r1-distill-llama-8b","score":21.85,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-r1-distill-llama-8b","score":45.8,"metric":"percent"},{"benchmark":"popqa","model":"deepseek-r1-distill-llama-8b","score":13.25,"metric":"percent"},{"benchmark":"truthfulqa","model":"deepseek-r1-distill-llama-8b","score":47.43,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-r1-distill-llama-8b","score":67.39,"metric":"percent"},{"benchmark":"drop","model":"deepseek-r1-distill-llama-8b","score":49.73,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-r1-distill-llama-8b","score":72.18,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-r1-distill-llama-8b","score":62.91,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-r1-distill-llama-8b","score":66.5,"metric":"percent"},{"benchmark":"attaq","model":"deepseek-r1-distill-llama-8b","score":42.87,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2.5-7b-instruct","score":25.44,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen2.5-7b-instruct","score":29,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-7b-instruct","score":76.6,"metric":"percent"},{"benchmark":"popqa","model":"qwen2.5-7b-instruct","score":18.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-7b-instruct","score":63.1,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-7b-instruct","score":21.7,"metric":"percent"},{"benchmark":"drop","model":"qwen2.5-7b-instruct","score":54.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-7b-instruct","score":83.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-7b-instruct","score":89.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-7b-instruct","score":74.7,"metric":"percent"},{"benchmark":"attaq","model":"qwen2.5-7b-instruct","score":81.9,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-r1-distill-qwen-7b","score":10.36,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-r1-distill-qwen-7b","score":15.35,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-r1-distill-qwen-7b","score":50.72,"metric":"percent"},{"benchmark":"popqa","model":"deepseek-r1-distill-qwen-7b","score":9.94,"metric":"percent"},{"benchmark":"truthfulqa","model":"deepseek-r1-distill-qwen-7b","score":47.14,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-r1-distill-qwen-7b","score":67.38,"metric":"percent"},{"benchmark":"drop","model":"deepseek-r1-distill-qwen-7b","score":51.78,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-r1-distill-qwen-7b","score":78.47,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-r1-distill-qwen-7b","score":78.43,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-r1-distill-qwen-7b","score":59.1,"metric":"percent"},{"benchmark":"attaq","model":"deepseek-r1-distill-qwen-7b","score":42.45,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-3.1-8b-instruct","score":37.58,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-3.1-8b-instruct","score":30.34,"metric":"percent"},{"benchmark":"mmlu","model":"granite-3.1-8b-instruct","score":66.77,"metric":"percent"},{"benchmark":"popqa","model":"granite-3.1-8b-instruct","score":28.76,"metric":"percent"},{"benchmark":"truthfulqa","model":"granite-3.1-8b-instruct","score":65.84,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.1-8b-instruct","score":69.87,"metric":"percent"},{"benchmark":"drop","model":"granite-3.1-8b-instruct","score":58.57,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-3.1-8b-instruct","score":79.15,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-3.1-8b-instruct","score":85.79,"metric":"percent"},{"benchmark":"ifeval","model":"granite-3.1-8b-instruct","score":73.2,"metric":"percent"},{"benchmark":"attaq","model":"granite-3.1-8b-instruct","score":85.73,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-3.2-8b-instruct","score":55.25,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-3.2-8b-instruct","score":61.19,"metric":"percent"},{"benchmark":"mmlu","model":"granite-3.2-8b-instruct","score":66.79,"metric":"percent"},{"benchmark":"popqa","model":"granite-3.2-8b-instruct","score":28.04,"metric":"percent"},{"benchmark":"truthfulqa","model":"granite-3.2-8b-instruct","score":66.92,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.2-8b-instruct","score":71.86,"metric":"percent"},{"benchmark":"drop","model":"granite-3.2-8b-instruct","score":58.29,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-3.2-8b-instruct","score":81.65,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-3.2-8b-instruct","score":85.72,"metric":"percent"},{"benchmark":"ifeval","model":"granite-3.2-8b-instruct","score":74.31,"metric":"percent"},{"benchmark":"attaq","model":"granite-3.2-8b-instruct","score":84.7,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-3.3-8b-instruct","score":57.56,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-3.3-8b-instruct","score":62.68,"metric":"percent"},{"benchmark":"mmlu","model":"granite-3.3-8b-instruct","score":65.54,"metric":"percent"},{"benchmark":"popqa","model":"granite-3.3-8b-instruct","score":26.17,"metric":"percent"},{"benchmark":"truthfulqa","model":"granite-3.3-8b-instruct","score":66.86,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.3-8b-instruct","score":69.13,"metric":"percent"},{"benchmark":"bbh","model":"trlm-135m","score":36.8,"metric":"percent"},{"benchmark":"drop","model":"granite-3.3-8b-instruct","score":59.36,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-3.3-8b-instruct","score":80.89,"metric":"percent"},{"benchmark":"gsm8k","model":"trlm-135m","score":2.59,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-3.3-8b-instruct","score":86.09,"metric":"percent"},{"benchmark":"ifeval","model":"granite-3.3-8b-instruct","score":74.82,"metric":"percent"},{"benchmark":"attaq","model":"granite-3.3-8b-instruct","score":88.5,"metric":"percent"},{"benchmark":"aime-2024","model":"granite-3.1-2b-instruct","score":0.89,"metric":"percent"},{"benchmark":"math500","model":"granite-3.1-2b-instruct","score":35.07,"metric":"percent"},{"benchmark":"aime-2024","model":"granite-3.2-2b-instruct","score":0.89,"metric":"percent"},{"benchmark":"math500","model":"granite-3.2-2b-instruct","score":35.54,"metric":"percent"},{"benchmark":"aime-2024","model":"granite-3.3-2b-instruct","score":3.28,"metric":"percent"},{"benchmark":"math500","model":"granite-3.3-2b-instruct","score":58.09,"metric":"percent"},{"benchmark":"aime-2024","model":"granite-3.1-8b-instruct","score":1.97,"metric":"percent"},{"benchmark":"math500","model":"granite-3.1-8b-instruct","score":48.73,"metric":"percent"},{"benchmark":"aime-2024","model":"granite-3.2-8b-instruct","score":2.43,"metric":"percent"},{"benchmark":"math500","model":"granite-3.2-8b-instruct","score":52.8,"metric":"percent"},{"benchmark":"aime-2024","model":"granite-3.3-8b-instruct","score":8.12,"metric":"percent"},{"benchmark":"math500","model":"granite-3.3-8b-instruct","score":69.02,"metric":"percent"},{"benchmark":"mmstar","model":"smoldocling-256m-preview","score":17,"metric":"percent"},{"benchmark":"mmstar","model":"granite-docling-258m","score":30,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2.5-vl-72b","score":71.13,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-pro","score":78.73,"metric":"percent"},{"benchmark":"mmstar","model":"seed1.5-vl-thinking","score":78.33,"metric":"percent"},{"benchmark":"mmstar","model":"dots-vlm1","score":76.67,"metric":"percent"},{"benchmark":"wildbench-v2","model":"mistral-small-3.1-24b-instruct","score":55.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"mistral-small-3.1-24b-instruct","score":19.56,"metric":"percent"},{"benchmark":"ifbench","model":"mistral-small-3.1-24b-instruct","score":82.75,"metric":"percent"},{"benchmark":"wildbench-v2","model":"mistral-small-3.2-24b-instruct","score":65.33,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"mistral-small-3.2-24b-instruct","score":43.1,"metric":"percent"},{"benchmark":"ifbench","model":"mistral-small-3.2-24b-instruct","score":84.78,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-small-3.1-24b-instruct","score":80.62,"metric":"percent"},{"benchmark":"math","model":"mistral-small-3.1-24b-instruct","score":69.3,"metric":"percent"},{"benchmark":"simpleqa","model":"mistral-small-3.1-24b-instruct","score":10.43,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-small-3.2-24b-instruct","score":80.5,"metric":"percent"},{"benchmark":"math","model":"mistral-small-3.2-24b-instruct","score":69.42,"metric":"percent"},{"benchmark":"simpleqa","model":"mistral-small-3.2-24b-instruct","score":12.1,"metric":"percent"},{"benchmark":"mmmu","model":"mistral-small-3.1-24b-instruct","score":64,"metric":"percent"},{"benchmark":"mathvista","model":"mistral-small-3.1-24b-instruct","score":68.91,"metric":"percent"},{"benchmark":"chartqa","model":"mistral-small-3.1-24b-instruct","score":86.24,"metric":"percent"},{"benchmark":"docvqa","model":"mistral-small-3.1-24b-instruct","score":94.08,"metric":"percent"},{"benchmark":"mmmu","model":"mistral-small-3.2-24b-instruct","score":62.5,"metric":"percent"},{"benchmark":"mmmu","model":"claude-sonnet-4","score":74.4,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-pro","score":82,"metric":"percent"},{"benchmark":"mathvista","model":"mistral-small-3.2-24b-instruct","score":67.09,"metric":"percent"},{"benchmark":"chartqa","model":"mistral-small-3.2-24b-instruct","score":87.4,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2.5-vl-72b","score":86.1,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-pro","score":86.16,"metric":"percent"},{"benchmark":"chartqa","model":"seed1.5-vl-thinking","score":86.88,"metric":"percent"},{"benchmark":"chartqa","model":"dots-vlm1","score":87.68,"metric":"percent"},{"benchmark":"docvqa","model":"mistral-small-3.2-24b-instruct","score":94.86,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2.5-vl-72b","score":96.23,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-pro","score":95.42,"metric":"percent"},{"benchmark":"docvqa","model":"seed1.5-vl-thinking","score":93.65,"metric":"percent"},{"benchmark":"docvqa","model":"dots-vlm1","score":96.52,"metric":"percent"},{"benchmark":"ai2d","model":"mistral-small-3.2-24b-instruct","score":92.91,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2.5-vl-72b","score":88.3,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-pro","score":91.03,"metric":"percent"},{"benchmark":"ai2d","model":"seed1.5-vl-thinking","score":89.05,"metric":"percent"},{"benchmark":"ai2d","model":"dots-vlm1","score":88.37,"metric":"percent"},{"benchmark":"humaneval-plus","model":"o1-preview","score":89,"metric":"percent"},{"benchmark":"humaneval-plus","model":"o1-mini","score":89,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-32b-instruct","score":87.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4o-2024-08-06","score":87.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4-turbo-2024-04-09","score":86.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v2.5","score":83.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4o-mini-2024-07-18","score":83.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-v2-instruct","score":82.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3.5-sonnet","score":81.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4-turbo","score":81.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"grok-3-beta","score":80.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-1.5-pro","score":79.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4","score":79.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codeqwen1.5-7b-chat","score":78.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"opencoder-8b-instruct","score":77.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3-opus","score":77.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-1.5-flash","score":75.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-33b-instruct","score":75,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codestral-22b-v0.1","score":73.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"opencodeinterpreter-ds-33b","score":73.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"wizardcoder-33b-v1.1","score":73.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"artigenz-coder-ds-6.7b","score":72.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mixtral-8x22b-instruct-v0.1","score":72,"metric":"percent"},{"benchmark":"humaneval-plus","model":"opencodeinterpreter-ds-6.7b","score":72,"metric":"percent"},{"benchmark":"humaneval-plus","model":"speechless-codellama-34b-v2.0","score":72,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-6.7b-instruct","score":71.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-7b-instruct-v1.5","score":71.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"magicoder-s-ds-6.7b","score":71.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starchat2-15b-v0.1","score":71.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-3.5-turbo-nov-2023","score":70.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"code-millenials-34b","score":70.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"databricks-dbrx-instruct","score":70.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"wavecoder-ultra-6.7b","score":69.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"xwincoder-34b","score":69.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3-haiku-mar-2024","score":68.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"magicoder-s-cl-7b","score":67.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"openchat-3.5-7b-0106","score":67.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"phind-codellama-34b-v2","score":67.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-3.5-may-2023","score":66.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-70b-instruct","score":65.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"whiterabbitneo-33b-v1","score":65.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"speechless-coder-ds-6.7b","score":65.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"wizardcoder-python-34b-v1.0","score":64.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3-sonnet-mar-2024","score":64,"metric":"percent"},{"benchmark":"humaneval-plus","model":"speechless-starcoder2-15b","score":62.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-large","score":62.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-2","score":61.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-1.5-pro","score":61,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-1.3b-instruct","score":60.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starcoder2-15b-instruct-v0.1","score":60.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"code-290k-6.7b-instruct","score":59.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen1.5-72b-chat","score":59.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"phi-3-mini-4k-instruct","score":59.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"dolphin-2.6-mixtral-8x7b","score":57.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"command-r","score":56.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-1.0-pro","score":55.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"code-13b","score":52.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegemma-7b-it","score":51.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"speechless-starcoder2-7b","score":51.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-70b","score":50.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"wizardcoder-15b-v1.0","score":50.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-instant-1-mar-2024","score":50.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"speechless-coding-7b-16k-tora","score":50.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"code-33b","score":49.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"openhermes-2.5-code-290k-13b","score":48.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codeqwen1.5-7b","score":45.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"wizardcoder-python-7b-v1.0","score":45.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"phi-2-2.7b","score":45.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-33b-base","score":44.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-34b","score":43.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-codealpaca-7b","score":42.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistralhermes-codepro-7b-v1","score":42.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegemma-7b","score":41.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"speechless-code-mistral-7b-v1.0","score":41.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-6.7b-base","score":39.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mixtral-8x7b-instruct-v0.1","score":39.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-13b","score":38.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starcoder2-15b","score":37.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"solar-10.7b-instruct-v1.0","score":37.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-7b-instruct-v0.2","score":36,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-7b","score":35.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-1.1-7b-it","score":35.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"xdan-l1-chat-rl-v1-7b","score":32.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"python-code-13b","score":30.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starcoder2-7b","score":29.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starcoder-15b","score":29.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-7b","score":28.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegen-16b","score":28,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starcoder2-3b","score":27.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codet5-16b","score":26.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegen-6b","score":25.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-1.3b-base","score":25.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-7b-it","score":25,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codet5-6b","score":24.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-7b","score":23.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"zephyr-7b-beta","score":23.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegen-2b","score":22.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codet5-2b","score":22,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starcoderbase-7b","score":21.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegemma-2b","score":20.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-2b","score":20.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegen2-7b","score":17.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-1.1-2b-it","score":17.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegen2-16b","score":16.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starcoderbase-3b","score":15.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"vicuna-13b","score":15.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-2b-it","score":15.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"santacoder-1.1b","score":14,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegen2-3b","score":12.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"incoder-6.7b","score":12.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"starcoderbase-1b","score":12.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"vicuna-7b","score":11.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-j-6b","score":11,"metric":"percent"},{"benchmark":"humaneval-plus","model":"incoder-1.3b","score":11,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codegen2-1b","score":9.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-neo-2.7b","score":6.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"polycoder-2.7b","score":6.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"stablelm-7b","score":2.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"zyte-1b","score":1.8,"metric":"percent"},{"benchmark":"humaneval","model":"o1-preview","score":96.3,"metric":"percent"},{"benchmark":"humaneval","model":"o1-mini","score":96.3,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-2024-08-06","score":92.7,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-32b-instruct","score":92.1,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v3","score":91.5,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2.5","score":90.2,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4-turbo-2024-04-09","score":90.2,"metric":"percent"},{"benchmark":"humaneval","model":"grok-3-beta","score":88.4,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-mini-2024-07-18","score":88.4,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4","score":88.4,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3.5-sonnet","score":87.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-v2-instruct","score":85.4,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4-turbo","score":85.4,"metric":"percent"},{"benchmark":"humaneval","model":"codeqwen1.5-7b-chat","score":83.5,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3-opus","score":82.9,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-1.5-flash","score":82.3,"metric":"percent"},{"benchmark":"humaneval","model":"opencoder-8b-instruct","score":81.7,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-33b-instruct","score":81.1,"metric":"percent"},{"benchmark":"humaneval","model":"codestral-22b","score":81.1,"metric":"percent"},{"benchmark":"humaneval","model":"wizardcoder-33b-v1.1","score":79.9,"metric":"percent"},{"benchmark":"humaneval","model":"opencodeinterpreter-ds-33b","score":79.3,"metric":"percent"},{"benchmark":"humaneval","model":"opencodeinterpreter-ds-6.7b","score":77.4,"metric":"percent"},{"benchmark":"humaneval","model":"speechless-codellama-34b-v2.0","score":77.4,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5-turbo","score":76.8,"metric":"percent"},{"benchmark":"humaneval","model":"magicoder-s-ds-6.7b","score":76.8,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3-haiku","score":76.8,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x22b-instruct-v0.1","score":76.2,"metric":"percent"},{"benchmark":"humaneval","model":"artigenz-coder-ds-6.7b","score":75.6,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-7b-instruct-v1.5","score":75.6,"metric":"percent"},{"benchmark":"humaneval","model":"xwincoder-34b","score":75.6,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-6.7b-instruct","score":74.4,"metric":"percent"},{"benchmark":"humaneval","model":"code-millenials-34b","score":74.4,"metric":"percent"},{"benchmark":"humaneval","model":"starchat2-15b-v0.1","score":73.8,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5","score":73.2,"metric":"percent"},{"benchmark":"humaneval","model":"wizardcoder-python-34b-v1.0","score":73.2,"metric":"percent"},{"benchmark":"humaneval","model":"openchat-3.5-7b-0106","score":72.6,"metric":"percent"},{"benchmark":"humaneval","model":"phind-codellama-34b-v2","score":71.3,"metric":"percent"},{"benchmark":"humaneval","model":"speechless-coder-ds-6.7b","score":71.3,"metric":"percent"},{"benchmark":"humaneval","model":"magicoder-s-cl-7b","score":70.7,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3-sonnet","score":70.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-8b-instruct","score":86.3,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-large","score":69.5,"metric":"percent"},{"benchmark":"humaneval","model":"claude-2","score":69.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-72b-chat","score":68.3,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-1.5-pro","score":68.3,"metric":"percent"},{"benchmark":"humaneval","model":"starcoder2-15b-instruct-v0.1","score":67.7,"metric":"percent"},{"benchmark":"humaneval","model":"speechless-starcoder2-15b","score":67.1,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-1.3b-instruct","score":65.9,"metric":"percent"},{"benchmark":"humaneval","model":"code-290k-6.7b-instruct","score":64.6,"metric":"percent"},{"benchmark":"humaneval","model":"phi-3-mini-4k-instruct","score":64.6,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-1.0-pro","score":63.4,"metric":"percent"},{"benchmark":"humaneval","model":"codegemma-7b-it","score":60.4,"metric":"percent"},{"benchmark":"humaneval","model":"claude-instant-1-mar-2024","score":57.3,"metric":"percent"},{"benchmark":"humaneval","model":"wizardcoder-15b-v1.0","score":56.7,"metric":"percent"},{"benchmark":"humaneval","model":"code-13b","score":56.1,"metric":"percent"},{"benchmark":"humaneval","model":"speechless-starcoder2-7b","score":56.1,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-70b","score":67.1,"metric":"percent"},{"benchmark":"humaneval","model":"code-33b","score":54.9,"metric":"percent"},{"benchmark":"humaneval","model":"speechless-coding-7b-16k-tora","score":54.9,"metric":"percent"},{"benchmark":"humaneval","model":"openhermes-2.5-code-290k-13b","score":54.3,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-34b","score":51.8,"metric":"percent"},{"benchmark":"humaneval","model":"codeqwen1.5-7b","score":51.8,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-33b-base","score":51.2,"metric":"percent"},{"benchmark":"humaneval","model":"wizardcoder-python-7b-v1.0","score":50.6,"metric":"percent"},{"benchmark":"humaneval","model":"phi-2-2.7b","score":49.4,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-codealpaca-7b","score":48.2,"metric":"percent"},{"benchmark":"humaneval","model":"speechless-code-mistral-7b-v1.0","score":48.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-6.7b-base","score":47.6,"metric":"percent"},{"benchmark":"humaneval","model":"mistralhermes-codepro-7b-v1","score":47.6,"metric":"percent"},{"benchmark":"humaneval","model":"starcoder2-15b","score":46.3,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x7b-instruct-v0.1","score":45.1,"metric":"percent"},{"benchmark":"humaneval","model":"codegemma-7b","score":44.5,"metric":"percent"},{"benchmark":"humaneval","model":"solar-10.7b-instruct-v1.0","score":43.3,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-13b","score":42.7,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-1.1-7b-it","score":42.7,"metric":"percent"},{"benchmark":"humaneval","model":"xdan-l1-chat-rl-v1-7b","score":40.2,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-7b","score":37.8,"metric":"percent"},{"benchmark":"humaneval","model":"starcoder2-7b","score":35.4,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-7b","score":35.4,"metric":"percent"},{"benchmark":"humaneval","model":"starcoder-15b","score":34.1,"metric":"percent"},{"benchmark":"humaneval","model":"codegen-16b","score":32.9,"metric":"percent"},{"benchmark":"humaneval","model":"python-code-13b","score":32.9,"metric":"percent"},{"benchmark":"humaneval","model":"codet5plus-16b","score":31.7,"metric":"percent"},{"benchmark":"humaneval","model":"starcoder2-3b","score":31.7,"metric":"percent"},{"benchmark":"humaneval","model":"codegen-6b","score":29.3,"metric":"percent"},{"benchmark":"humaneval","model":"codet5plus-6b","score":29.3,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-1.3b-base","score":28.7,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b","score":28.7,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-7b-it","score":28.7,"metric":"percent"},{"benchmark":"humaneval","model":"codegemma-2b","score":26.8,"metric":"percent"},{"benchmark":"humaneval","model":"codegen-2b","score":24.4,"metric":"percent"},{"benchmark":"humaneval","model":"starcoderbase-7b","score":24.4,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-1.1-2b-it","score":22.6,"metric":"percent"},{"benchmark":"humaneval","model":"codegen2-16b","score":19.5,"metric":"percent"},{"benchmark":"humaneval","model":"codegen2-7b","score":18.3,"metric":"percent"},{"benchmark":"humaneval","model":"starcoderbase-3b","score":17.7,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2b-it","score":17.7,"metric":"percent"},{"benchmark":"humaneval","model":"vicuna-13b","score":17.1,"metric":"percent"},{"benchmark":"humaneval","model":"codegen2-3b","score":15.9,"metric":"percent"},{"benchmark":"humaneval","model":"incoder-6.7b","score":15.9,"metric":"percent"},{"benchmark":"humaneval","model":"santacoder-1.1b","score":14.6,"metric":"percent"},{"benchmark":"humaneval","model":"starcoderbase-1b","score":14.6,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-j-6b","score":12.2,"metric":"percent"},{"benchmark":"humaneval","model":"incoder-1.3b","score":12.2,"metric":"percent"},{"benchmark":"humaneval","model":"vicuna-7b","score":11.6,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-neo-2.7b","score":7.9,"metric":"percent"},{"benchmark":"humaneval","model":"polycoder-2.7b","score":6.1,"metric":"percent"},{"benchmark":"humaneval","model":"stablelm-7b","score":2.4,"metric":"percent"},{"benchmark":"humaneval","model":"zyte-1b","score":2.4,"metric":"percent"},{"benchmark":"humaneval","model":"coda-1.7b-base","score":29.3,"metric":"percent"},{"benchmark":"humaneval","model":"coda-1.7b-instruct","score":54.3,"metric":"percent"},{"benchmark":"humaneval","model":"dream-7b-base","score":56.7,"metric":"percent"},{"benchmark":"humaneval","model":"dream-7b-instruct","score":57.9,"metric":"percent"},{"benchmark":"humaneval","model":"llada-8b-instruct","score":35.4,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-5-2025-08-07","score":93.5,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-4.1-20250805","score":93.4,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-4-20250514","score":92.8,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-2.5-pro-preview-06-05","score":92.4,"metric":"percent"},{"benchmark":"mmlu","model":"o3-2025-04-16","score":92.3,"metric":"percent"},{"benchmark":"mmlu","model":"o1-2024-12-17","score":91.9,"metric":"percent"},{"benchmark":"mmlu","model":"grok-4-0709","score":91.6,"metric":"percent"},{"benchmark":"mmlu","model":"claude-sonnet-4-20250514","score":91.4,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4.1-2025-04-14","score":90.3,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-r1-0528","score":90.3,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3.7-sonnet-20250219","score":90.2,"metric":"percent"},{"benchmark":"mmlu","model":"grok-3","score":90.1,"metric":"percent"},{"benchmark":"mmlu","model":"o4-mini-2025-04-16","score":90,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3","score":89.5,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3.5-sonnet-20241022","score":89.5,"metric":"percent"},{"benchmark":"mmlu","model":"grok-3-mini","score":89.2,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4o-2024-08-06","score":88.1,"metric":"percent"},{"benchmark":"mmlu","model":"grok-2-1212","score":88,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-120b-2025-08-05","score":87.7,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-2.0-flash-001","score":87.7,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-1.5-pro-002","score":86.9,"metric":"percent"},{"benchmark":"mmlu","model":"o3-mini-2025-01-31","score":85.9,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-large-2411","score":85.1,"metric":"percent"},{"benchmark":"mmlu","model":"o1-mini-2024-09-12","score":84,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-20b-2025-08-05","score":82.2,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b-it","score":81.5,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-1.5-flash-002","score":81.4,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4o-mini-2024-07-18","score":81.4,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3.5-haiku-20241022","score":81,"metric":"percent"},{"benchmark":"mmlu","model":"open-mixtral-8x22b-2404","score":77.5,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-12b-it","score":77.1,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-1.5-flash-8b-001","score":75,"metric":"percent"},{"benchmark":"mmlu","model":"codestral-2501","score":67.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-235b-a22b-thinking-2507","score":66.7,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-3.5-turbo-1106","score":66.4,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-4b-it","score":62.7,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-3b-2410","score":57.6,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-8b-2410","score":57.3,"metric":"percent"},{"benchmark":"mmlu","model":"trlm-135m","score":34.95,"metric":"percent"},{"benchmark":"mmlu-redux","model":"exaone-4.0-1.2b","score":71.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-4.0-1.2b","score":59.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"exaone-4.0-1.2b","score":52,"metric":"percent"},{"benchmark":"aime-2025","model":"exaone-4.0-1.2b","score":45.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"exaone-4.0-1.2b","score":34,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"exaone-4.0-1.2b","score":44.6,"metric":"percent"},{"benchmark":"livecodebench","model":"exaone-4.0-1.2b","score":45.3,"metric":"percent"},{"benchmark":"ifeval","model":"exaone-4.0-1.2b","score":67.8,"metric":"percent"},{"benchmark":"multi-ifeval","model":"exaone-4.0-1.2b","score":53.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"exaone-4.0-1.2b","score":52.9,"metric":"percent"},{"benchmark":"kor-bench","model":"ling-1t","score":76,"metric":"percent"},{"benchmark":"kor-bench","model":"deepseek-v3.1-terminus","score":73.76,"metric":"percent"},{"benchmark":"kor-bench","model":"kimi-k2-0905","score":73.2,"metric":"percent"},{"benchmark":"kor-bench","model":"gpt-5","score":70.56,"metric":"percent"},{"benchmark":"kor-bench","model":"gemini-2.5-pro","score":59.68,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"exaone-4.0-1.2b","score":37.48,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"exaone-4.0-1.2b","score":40.43,"metric":"percent"},{"benchmark":"ksm","model":"exaone-4.0-1.2b","score":60.6,"metric":"percent"},{"benchmark":"mmmlu-es","model":"exaone-4.0-1.2b","score":62.4,"metric":"percent"},{"benchmark":"math500-es","model":"exaone-4.0-1.2b","score":88.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"exaone-deep-2.4b","score":68.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-deep-2.4b","score":56.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"exaone-deep-2.4b","score":54.3,"metric":"percent"},{"benchmark":"aime-2025","model":"exaone-deep-2.4b","score":47.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"exaone-deep-2.4b","score":27.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"exaone-deep-2.4b","score":47.2,"metric":"percent"},{"benchmark":"livecodebench","model":"exaone-deep-2.4b","score":43.1,"metric":"percent"},{"benchmark":"ifeval","model":"exaone-deep-2.4b","score":71,"metric":"percent"},{"benchmark":"multi-ifeval","model":"exaone-deep-2.4b","score":54.5,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"exaone-deep-2.4b","score":24.6,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"exaone-deep-2.4b","score":25,"metric":"percent"},{"benchmark":"ksm","model":"exaone-deep-2.4b","score":60.9,"metric":"percent"},{"benchmark":"mmmlu-es","model":"exaone-deep-2.4b","score":51.4,"metric":"percent"},{"benchmark":"math500-es","model":"exaone-deep-2.4b","score":84.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-0.6b","score":55.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-0.6b","score":38.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-0.6b","score":27.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-0.6b","score":15.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-0.6b","score":7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-0.6b","score":12.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-0.6b","score":16.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-0.6b","score":59.2,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-0.6b","score":37.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-0.6b","score":46.4,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-0.6b","score":21.6,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-0.6b","score":24.5,"metric":"percent"},{"benchmark":"ksm","model":"qwen3-0.6b","score":22.8,"metric":"percent"},{"benchmark":"mmmlu-es","model":"qwen3-0.6b","score":48.8,"metric":"percent"},{"benchmark":"math500-es","model":"qwen3-0.6b","score":70.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-1.7b","score":73.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":57.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-1.7b","score":40.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-1.7b","score":21.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-1.7b","score":33.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-1.7b","score":29.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-1.7b","score":72.5,"metric":"percent"},{"benchmark":"multi-ifeval","model":"qwen3-1.7b","score":53.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-1.7b","score":56.6,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-1.7b","score":38.3,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-1.7b","score":38,"metric":"percent"},{"benchmark":"ksm","model":"qwen3-1.7b","score":52.9,"metric":"percent"},{"benchmark":"mmmlu-es","model":"qwen3-1.7b","score":64.5,"metric":"percent"},{"benchmark":"math500-es","model":"qwen3-1.7b","score":87.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"smollm3-3b","score":74.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm3-3b","score":57.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"smollm3-3b","score":26,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"smollm3-3b","score":27.6,"metric":"percent"},{"benchmark":"multi-ifeval","model":"smollm3-3b","score":47.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"smollm3-3b","score":37.1,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"smollm3-3b","score":30.5,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"smollm3-3b","score":33.7,"metric":"percent"},{"benchmark":"ksm","model":"smollm3-3b","score":49.7,"metric":"percent"},{"benchmark":"mmmlu-es","model":"smollm3-3b","score":64.7,"metric":"percent"},{"benchmark":"math500-es","model":"smollm3-3b","score":87.5,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"aya-expanse-32b","score":33.05,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"aya-expanse-32b","score":28.46,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"gemma-3-12b-it","score":46.7,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"gemma-3-12b-it","score":41.06,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"phi-4-14b","score":49.75,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"phi-4-14b","score":44.33,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"mistral-small-3.1-24b-instruct","score":52.92,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"mistral-small-3.1-24b-instruct","score":50.91,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"gemma-3-27b-it","score":54.04,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"gemma-3-27b-it","score":53.02,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"llama-3.3-70b-instruct","score":56.17,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"llama-3.3-70b-instruct","score":54.63,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-14b","score":57.25,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-14b","score":56.39,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-30b-a3b","score":58.41,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-30b-a3b","score":58.4,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"command-a","score":62.93,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"command-a","score":61.46,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-32b","score":64.98,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-32b","score":61.97,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"exaone-4.0-32b","score":64.79,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"exaone-4.0-32b","score":62.24,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"llama-4-scout-17b-16e","score":67.49,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"llama-4-scout-17b-16e","score":63.01,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-30b-a3b-thinking-2507","score":65.25,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-30b-a3b-thinking-2507","score":63.86,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-14b-thinking","score":65.71,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-14b-thinking","score":64.01,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"deepseek-v3","score":65.64,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"deepseek-v3","score":64.32,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-32b-thinking","score":68.77,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-32b-thinking","score":64.75,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwq-32b","score":67.34,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwq-32b","score":64.55,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-235b-a22b","score":69.54,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-235b-a22b","score":66.45,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"exaone-4.0-32b-thinking","score":72.71,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"exaone-4.0-32b-thinking","score":66.03,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-235b-a22b-thinking-2507","score":74.49,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-235b-a22b-thinking-2507","score":69.42,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"llama-4-maverick-17b-128e-instruct","score":77.58,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"llama-4-maverick-17b-128e-instruct","score":70.54,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"deepseek-r1","score":78.51,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"deepseek-r1","score":72.35,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"gpt-4.1-mini-2025-04-14","score":67.03,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"gpt-4.1-mini-2025-04-14","score":60.15,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"o3-mini-2025-01-31","score":67.84,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"o3-mini-2025-01-31","score":62.06,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"grok-3-mini-beta","score":71.47,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"grok-3-mini-beta","score":65.89,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"grok-3-beta","score":72.9,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"grok-3-beta","score":68.03,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"o4-mini-2025-04-16","score":75.8,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"o4-mini-2025-04-16","score":72.73,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"gpt-4.1-2025-04-14","score":75.86,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"gpt-4.1-2025-04-14","score":72.81,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"claude-3.7-sonnet","score":76.88,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"claude-3.7-sonnet","score":73.33,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"o3-2025-04-16","score":79.92,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"o3-2025-04-16","score":75.98,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"claude-3.7-sonnet-thinking","score":79.36,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"claude-3.7-sonnet-thinking","score":75.51,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"o1","score":81.14,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"o1","score":77.54,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"grok-4-fast","score":85.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.1","score":81,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-sonnet-4","score":77.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5","score":85.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-pro","score":86.4,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4-fast","score":92,"metric":"percent"},{"benchmark":"hmmt-2025","model":"grok-4-fast","score":93.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"ring-1t-preview","score":84.53,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-2.5-pro","score":82.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.1-terminus-thinking","score":86.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-5-thinking","score":93.3,"metric":"percent"},{"benchmark":"hle","model":"grok-4-fast","score":20,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-4-fast","score":80,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-0528","score":73.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b","score":70.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b-thinking-2507","score":78.4,"metric":"percent"},{"benchmark":"livecodebench","model":"dots-vlm1","score":72.94,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini","score":86.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-codex","score":84.7,"metric":"percent"},{"benchmark":"livecodebench","model":"o3","score":83.9,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-4","score":83.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":83.2,"metric":"percent"},{"benchmark":"livecodebench","model":"o4-mini","score":82.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b","score":80.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro-preview-06-05","score":79.2,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-4-fast-thinking","score":79,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5","score":77.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":70.65,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.1-terminus-thinking","score":75.33,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b-thinking-2507","score":75.72,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5","score":80.6,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-flash-linear-2.0","score":69.82,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-flash-2.0","score":70.76,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b-thinking-2504","score":62.33,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash","score":61.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b-medium","score":66.45,"metric":"percent"},{"benchmark":"livecodebench","model":"seed-oss-36b-instruct","score":69.01,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b-thinking","score":71.97,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-3-mini-fast-high-reasoning","score":76.2,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-medium-1.2","score":74.9,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-4.5-sonnet-thinking","score":73,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-small-1.2","score":72.1,"metric":"percent"},{"benchmark":"livecodebench","model":"o3-mini","score":71.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b","score":70.6,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-instruct","score":70.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-max","score":70.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1","score":70.2,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4-thinking","score":70.2,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5","score":67.3,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.6","score":82.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-max-instruct-preview","score":66.9,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4-1-20250805-thinking","score":66.5,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-3-mini-fast-low-reasoning","score":66.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3-0324","score":65.5,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.1-20250805","score":64.6,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4","score":62.6,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4-thinking","score":62.4,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-code-fast","score":62,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.7-sonnet-thinking","score":60.4,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4","score":59.7,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.3-nemotron-super-thinking","score":58.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4.1-mini","score":58.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-preview-05-20","score":56.9,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.7-sonnet","score":56.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4.1","score":54.7,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-3","score":52.9,"metric":"percent"},{"benchmark":"livecodebench","model":"o1","score":50.3,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.5-sonnet-20241022","score":49.6,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-4-maverick","score":47.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-preview-05-20-thinking","score":46.9,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-4-fast","score":46.1,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-medium-3.1","score":44.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.0-flash-001","score":43.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o-2024-11-20","score":43.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4.1-nano","score":42.7,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.5-haiku-20241022","score":41.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-1.5-pro-002","score":41.7,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-2","score":38.7,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-4-scout-17b","score":38.5,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-large-2411","score":37.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-1.5-flash-002","score":36.9,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.3-instruct-turbo-70b","score":36.3,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.3-nemotron-super-4","score":36.3,"metric":"percent"},{"benchmark":"livecodebench","model":"command-a","score":35.1,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-small-3.1-24b-instruct","score":31.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o-mini","score":26.4,"metric":"percent"},{"benchmark":"livecodebench","model":"jamba-1.6-large","score":22.3,"metric":"percent"},{"benchmark":"livecodebench","model":"command-r-plus","score":18.2,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-small-1.0","score":15.8,"metric":"percent"},{"benchmark":"livecodebench","model":"jamba-mini-1.6","score":9.9,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4-0709","score":93.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-2025-08-07","score":90.8,"metric":"percent"},{"benchmark":"aime-2025","model":"o3-2025-04-16","score":87.5,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0528","score":84.2,"metric":"percent"},{"benchmark":"aime-2025","model":"o4-mini-2025-04-16","score":82.5,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-pro-preview-06-05","score":78.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b-2025-08-05","score":78.3,"metric":"percent"},{"benchmark":"aime-2025","model":"o3-mini-2025-01-31","score":77.5,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash-05-20","score":75.8,"metric":"percent"},{"benchmark":"aime-2025","model":"o1-2024-12-17","score":70,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-3-mini","score":67.5,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-3","score":53.3,"metric":"percent"},{"benchmark":"aime-2025","model":"o1-mini-2024-09-12","score":51.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4.1-2025-04-14","score":36.7,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4-20250514","score":35.8,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4-20250514","score":33.3,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.1-20250805","score":33.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.0-flash-001","score":29.2,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-27b-it","score":25.8,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-3.7-sonnet-20250219","score":20.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-12b-it","score":20,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-1.5-pro-002","score":12.5,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b-2025-08-05","score":11.7,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-2-1212","score":10.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-4b-it","score":10.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-1.5-flash-002","score":10,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4o-mini-2024-07-18","score":8.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-1.5-flash-8b-001","score":7.5,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4o-2024-08-06","score":5.8,"metric":"percent"},{"benchmark":"aime-2025","model":"mistral-large-2411","score":4.2,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-3.5-sonnet-20241022","score":2.5,"metric":"percent"},{"benchmark":"aime-2025","model":"codestral-2501","score":2.5,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-3b-2410","score":0.8,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-8b-2410","score":0.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-3.5-turbo-1106","score":0,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-3.5-haiku-20241022","score":0,"metric":"percent"},{"benchmark":"aime-2025","model":"open-mixtral-8x22b-2404","score":0,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"deepseek-r1-distill-qwen-1.5b","score":21.3,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"llama-3.2-3b-instruct","score":17.59,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"gemma-3-4b-it","score":25.09,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen-2.5-3b-instruct","score":24.74,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-1.7b","score":28.99,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"kanana-nano-2.1b-instruct","score":27.25,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"aya-expanse-8b","score":28.3,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"hyperclovax-seed-text-instruct-1.5b","score":33.94,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"llama-3.1-8b-instruct","score":31.89,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-1.7b-thinking","score":37.8,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"ko-r1-7b-v2.1","score":41.94,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"exaone-4.0-1.2b-thinking","score":46.85,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-8b","score":49.25,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"qwen3-8b-thinking","score":58.79,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"deepseek-r1-distill-qwen-1.5b","score":20.55,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"llama-3.2-3b-instruct","score":25.53,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"gemma-3-4b-it","score":32.86,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen-2.5-3b-instruct","score":33.27,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-1.7b","score":30.42,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"kanana-nano-2.1b-instruct","score":32.6,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"aya-expanse-8b","score":31.65,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"hyperclovax-seed-text-instruct-1.5b","score":38.1,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"llama-3.1-8b-instruct","score":33.81,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-1.7b-thinking","score":38.27,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"ko-r1-7b-v2.1","score":38.7,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"exaone-4.0-1.2b-thinking","score":42.69,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-8b","score":46.92,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-8b-thinking","score":55.27,"metric":"percent"},{"benchmark":"minif2f-test","model":"longcat-flash-thinking","score":81.6,"metric":"percent"},{"benchmark":"minif2f-test","model":"deepseek-v3.1-thinking","score":79.5,"metric":"percent"},{"benchmark":"minif2f-test","model":"qwen3-235b-a22b-thinking-2507","score":26.6,"metric":"percent"},{"benchmark":"minif2f-test","model":"glm-4.5","score":27,"metric":"percent"},{"benchmark":"minif2f-test","model":"o3","score":37.7,"metric":"percent"},{"benchmark":"minif2f-test","model":"gemini-2.5-pro","score":41.8,"metric":"percent"},{"benchmark":"minif2f-test","model":"gpt-5-thinking","score":51.2,"metric":"percent"},{"benchmark":"ojbench","model":"longcat-flash-thinking","score":40.7,"metric":"percent"},{"benchmark":"ojbench","model":"deepseek-v3.1-thinking","score":33.6,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-235b-a22b-thinking-2507","score":32.1,"metric":"percent"},{"benchmark":"ojbench","model":"glm-4.5","score":19,"metric":"percent"},{"benchmark":"ojbench","model":"o3","score":38.4,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-2.5-pro","score":41.6,"metric":"percent"},{"benchmark":"ojbench","model":"gpt-5-thinking","score":34.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"grok-4","score":68,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-256b","score":67,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-4","score":66.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-1.5-pro","score":66,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-sonnet-4","score":64.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"grok-4-fast","score":64.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-1.5-flash","score":61.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-3","score":61,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-r1-preview","score":54.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v3","score":53.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k20895","score":52.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-o3","score":50.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"grok-core-poset","score":48.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-4-flash","score":48.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"llama-4-memonet","score":46,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v3.1","score":45,"metric":"percent"},{"benchmark":"aa-lcr","model":"llama-4","score":34,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-super-105-turbo","score":25,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5-minimal","score":19.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"mistral-medium","score":18.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-2","score":18.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"exaone-4.0-32b","score":14,"metric":"percent"},{"benchmark":"agentdojo","model":"claude-3.7-sonnet-20250219","score":88.66,"metric":"percent"},{"benchmark":"agentdojo","model":"gemini-2.0-flash-001","score":43.3,"metric":"percent"},{"benchmark":"agentdojo","model":"gemini-2.0-flash-exp","score":46.39,"metric":"percent"},{"benchmark":"agentdojo","model":"claude-3.5-sonnet-20241022","score":79.38,"metric":"percent"},{"benchmark":"agentdojo","model":"gemini-1.5-flash-002","score":38.14,"metric":"percent"},{"benchmark":"agentdojo","model":"gemini-1.5-pro-002","score":61.86,"metric":"percent"},{"benchmark":"agentdojo","model":"gpt-4o-mini-2024-07-18","score":68.04,"metric":"percent"},{"benchmark":"agentdojo","model":"claude-3.5-sonnet-20240620","score":79.38,"metric":"percent"},{"benchmark":"agentdojo","model":"claude-3-haiku-20240307","score":39.18,"metric":"percent"},{"benchmark":"agentdojo","model":"claude-3-opus-20240229","score":68.04,"metric":"percent"},{"benchmark":"agentdojo","model":"claude-3-sonnet-20240229","score":53.61,"metric":"percent"},{"benchmark":"agentdojo","model":"command-r","score":26.8,"metric":"percent"},{"benchmark":"agentdojo","model":"command-r-plus","score":24.74,"metric":"percent"},{"benchmark":"agentdojo","model":"gemini-1.5-flash-001","score":38.14,"metric":"percent"},{"benchmark":"agentdojo","model":"gemini-1.5-pro-001","score":46.39,"metric":"percent"},{"benchmark":"agentdojo","model":"gpt-3.5-turbo-0125","score":35.05,"metric":"percent"},{"benchmark":"agentdojo","model":"gpt-4-0125-preview","score":65.98,"metric":"percent"},{"benchmark":"agentdojo","model":"gpt-4-turbo-2024-04-09","score":64.95,"metric":"percent"},{"benchmark":"agentdojo","model":"gpt-4o-2024-05-13","score":69.07,"metric":"percent"},{"benchmark":"agentdojo","model":"llama-3-70b","score":34.02,"metric":"percent"},{"benchmark":"bigcodebench","model":"gpt-4o-2024-05-13","score":56.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v3","score":56.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-4-maverick","score":55.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"quasar-alpha","score":55.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemini-exp-1206","score":54.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemini-exp-1114","score":54.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v2-chat","score":54.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-32b-instruct","score":53.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gpt-4o-2024-11-20","score":53.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gpt-4-turbo-2024-04-09","score":53.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemini-2.0-flash-exp","score":52.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"claude-3.5-sonnet-20240620","score":52.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"claude-3.5-haiku-20241022","score":52.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-14b-instruct","score":52.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3.3-70b-instruct","score":52.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gpt-4o-mini-2024-07-18","score":51.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemini-exp-1121","score":51.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gpt-4-0613","score":51.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"claude-3-opus-20240229","score":51.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"athene-v2-agent","score":51.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v2.5-1210","score":50.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-72b-instruct","score":50.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemini-1.5-pro-api-0514","score":50.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"hermes-2-theta-llama-3-70b","score":50.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3.1-70b-instruct","score":50.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"phi-4","score":50.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwq-32b-preview","score":49.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-r1-distill-qwen-32b","score":49.4,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemini-1.5-flash-api-0514","score":49.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-32b-instruct","score":48.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3-70b-synthia-v3.5","score":48.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"claude-3-sonnet-20240229","score":48.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"sky-t1-32b-flash","score":48.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"mistral-small-24b-instruct-2501","score":47.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"reflectioncoder-ds-33b","score":47.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemma-2-27b-it","score":47.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"whiterabbitneo-33b-v1","score":47.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codestral-22b-v0.1","score":47.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"autocoder","score":46.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-coder-33b-instruct","score":46.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2-72b-chat","score":46.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"hermes-2-pro-llama-3-70b","score":45.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"mixtral-8x22b-instruct","score":45.4,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codellama-70b-instruct","score":45.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gpt-3.5-turbo-0125","score":44.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"claude-3-haiku-20240307","score":44.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v2-chat","score":44.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-7b-instruct","score":44.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codegeex4-all-9b","score":44.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepcoder-14b-preview","score":43.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"yi-coder-9b-chat","score":43.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3.1-nemotron-70b-instruct","score":43.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-r1-distill-qwen-14b","score":43.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"phi-3-medium-128k-instruct","score":43.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"phind-codellama-34b-v2","score":42.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-r1-distill-llama-70b","score":42.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"artigenz-coder-ds-6.7b","score":42.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"yi-large","score":42.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"reflectioncoder-ds-6.7b","score":42.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"reflectioncoder-cl-34b","score":42.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-coder-v2-lite-instruct","score":42.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"athene-70b","score":42.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"nxcode-cq-7b-orpo","score":42.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"magicoder-s-ds-6.7b","score":41.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-7b-instruct","score":41.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codeqwen1.5-7b-chat","score":41.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"tess-v2.5.2-qwen2-72b","score":41.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.57b-a14b","score":41.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"phi-3.1-mini-128k-instruct","score":41.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"starcoder2-15b-instruct-v0.1","score":41.4,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"mistral-small-instruct-2409","score":41.4,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"autocoder-s-6.7b","score":41.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"c4ai-command-r-08-2024","score":41.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"opencodeinterpreter-ds-6.7b","score":40.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"granite-code-34b-instruct","score":40.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codestral-mamba","score":40.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen1.5-110b-chat","score":39.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-coder-6.7b-instruct","score":39.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"yi-1.5-34b-chat","score":38.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"wavecoder-ultra-6.7b","score":38.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"yi-1.5-9b-chat","score":38.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"command-r-plus","score":37.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemma-2-9b-it","score":37.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen1.5-32b-chat","score":37.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen1.5-72b-chat","score":36.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"mistral-small-2402","score":36.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3.1-8b-instruct","score":36.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codegemma-7b-it","score":35.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2-7b-instruct","score":35.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"phi-3.5-mini-instruct","score":35.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"phi-3-small-128k-instruct","score":35.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"phi-3-mini-128k-instruct","score":35.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"reflectioncoder-cl-7b","score":34.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"mistral-large-2402","score":34.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"granite-3.0-8b-instruct","score":32.4,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codellama-34b-instruct","score":32.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codellama-13b-instruct","score":30.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-1.5b-instruct","score":29.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"yi-1.5-6b-chat","score":29.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"internlm2.5-7b-chat","score":29.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"opencodeinterpreter-ds-1.3b","score":27.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-coder-1.3b-instruct","score":26.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3.2-3b-instruct","score":25.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codellama-7b-instruct","score":23.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"mistral-7b-instruct-v0.3","score":23.4,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-r1-distill-qwen-7b","score":21.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-r1-distill-llama-8b","score":12.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-0.5b-instruct","score":10.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-r1-distill-qwen-1.5b","score":7.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-coder-v2-instruct","score":54,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3.7-sonnet-20250219","score":35.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-2024-12-17","score":35.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o3-mini-2025-01-31","score":35.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-r1","score":35.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o3-mini-2025-01-31","score":35.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"quasar-alpha","score":34.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-2024-12-17","score":34.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-v3","score":34.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o3-mini-2025-01-31","score":34.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-exp-1206","score":34.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-2.5-pro-exp-03.25","score":33.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"grok-3-beta","score":33.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-2024-12-17","score":32.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3.7-sonnet-20250219","score":32.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"optimus-alpha","score":32.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4.1-2025-04-14","score":32.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-max","score":32.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4-turbo-2024-04-09","score":32.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"athene-v2-chat","score":32.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-2.0-pro-exp-02-05","score":31.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-v3-0324","score":31.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4.1-mini-2025-04-14","score":31.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"athene-v2-agent","score":31.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4o-2024-11-20","score":31.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"grok-3-mini-beta","score":31.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4o-2024-08-06","score":30.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-32b-instruct","score":30.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3.5-sonnet-20241022","score":30.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3.5-haiku-20241022","score":30.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4.1-nano-2025-04-14","score":30.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3.5-sonnet-20240620","score":29.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-instruct","score":29.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-1.5-pro-exp-0827","score":29.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-exp-1114","score":29.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"chatgpt-4o-latest-20250129","score":29.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-preview-2024-09-12","score":28.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-v2-chat","score":28.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-2.0-flash-001","score":28.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3.3-70b-instruct","score":28.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-2.0-flash-exp","score":28.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-4-maverick","score":28.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-1.5-pro-exp-0801","score":27.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-mini-2024-09-12","score":27.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-exp-1121","score":27.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-2.0-flash-thinking-exp-1219","score":27.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"phi-4","score":27.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4o-2024-05-13","score":27.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"sky-t1-32b-flash","score":26.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwq-32b-preview","score":26.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-1.5-pro-002","score":26.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"grok-3-beta","score":26.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-14b-instruct","score":26.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"grok-3-mini-beta","score":26.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3.1-405b-instruct","score":26.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-r1-distill-qwen-32b","score":26.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-v2.5","score":26.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-1.5-pro-api-0514","score":25.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3.1-70b-instruct","score":25.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-72b-instruct","score":25.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-2.0-flash-lite-preview-02-05","score":25.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4o-mini-2024-07-18","score":25.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3-70b-instruct","score":24.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-32b-instruct","score":24.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3.1-nemotron-70b-instruct","score":24.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"dracarys-llama-3.1-70b-instruct","score":24.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-1.5-flash-api-0514","score":23.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3-70b-synthia-v3.5","score":23.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3-sonnet-20240229","score":23.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"dracarys-72b-instruct","score":22.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"hermes-2-pro-llama-3-70b","score":21.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-1.5-flash-exp-0827","score":21.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-14b-instruct","score":20.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-r1-distill-qwen-14b","score":20.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2-72b-chat","score":20.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codestral-22b-v0.1","score":20.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-small-24b-instruct-2501","score":20.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-7b-instruct","score":20.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-r1-distill-llama-70b","score":20.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepcoder-14b-preview","score":20.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-3.5-turbo-0125","score":19.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mixtral-8x22b-instruct","score":19.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"athene-70b","score":19.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepcoder-14b-preview","score":19.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-33b-instruct","score":19.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"whiterabbitneo-33b-v1","score":19.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"reflectioncoder-ds-33b","score":18.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-v2-chat","score":18.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"opencoder-8b-instruct","score":18.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3-haiku-20240307","score":18.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"yi-large","score":17.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codeqwen1.5-7b-chat","score":17.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-lite-instruct","score":17.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codegeex4-all-9b","score":17.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"nxcode-cq-7b-orpo","score":17.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"autocoder","score":16.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-4-scout","score":16.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-nemo-12b-instruct","score":16.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen1.5-110b-chat","score":15.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"opencodeinterpreter-ds-6.7b","score":15.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"reflectioncoder-ds-6.7b","score":15.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"granite-code-34b-instruct","score":14.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"wavecoder-ultra-6.7b","score":14.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"phi-3.5-mini-instruct","score":14.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-small-instruct-2409","score":14.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"yi-coder-9b-chat","score":14.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"artigenz-coder-ds-6.7b","score":14.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"phind-codellama-34b-v2","score":14.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-7b-instruct","score":14.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-small-2402","score":13.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codestral-mamba","score":13.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"inversecoder-cl-13b","score":13.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"command-r-plus","score":13.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"starcoder2-15b-instruct-v0.1","score":13.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-70b-instruct","score":13.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3.1-8b-instruct","score":13.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"inversecoder-cl-7b","score":13.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"magicoder-s-ds-6.7b","score":13.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"phi-3-medium-128k-instruct","score":13.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"reflectioncoder-cl-34b","score":13.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"c4ai-command-r-plus-08.2024","score":13.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"inversecoder-ds-6.7b","score":12.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-6.7b-instruct","score":12.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.57b-a14b","score":12.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"phi-3-small-128k-instruct","score":12.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen1.5-72b-chat","score":12.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2-7b-instruct","score":11.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"openchat-3.6-8b-20240522","score":11.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen1.5-32b-chat","score":11.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"yi-1.5-9b-chat","score":11.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"granite-code-20b-instruct","score":10.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"autocoder-qw-7b","score":10.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"phi-3-mini-128k-instruct","score":10.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"autocoder-s-6.7b","score":10.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codegemma-7b-it","score":10.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemma-2-9b-it","score":10.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-34b-instruct","score":9.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"reflectioncoder-cl-7b","score":9.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"yi-1.5-34b-chat","score":9.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"opencoder-1.5b-instruct","score":9.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-large-2402","score":8.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"granite-3.0-8b-instruct","score":8.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-13b-instruct","score":8.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-1.5b-instruct","score":5.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"yi-1.5-6b-chat","score":5.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-7b-instruct-v0.3","score":5.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3.2-3b-instruct","score":5.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-r1-distill-qwen-7b","score":4.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"opencodeinterpreter-ds-1.3b","score":4.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-7b-instruct","score":3.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-1.3b-instruct","score":2.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-r1-distill-llama-8b","score":2.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-0.5b-instruct","score":1.4,"metric":"pass@1"},{"benchmark":"bob-hvr","model":"gemini-3-pro","score":18.25,"metric":"index"},{"benchmark":"bob-hvr","model":"gpt-5.2","score":18.04,"metric":"index"},{"benchmark":"bob-hvr","model":"kimi-k2.5","score":16.23,"metric":"index"},{"benchmark":"bob-hvr","model":"gemini-2.5-pro","score":16.09,"metric":"index"},{"benchmark":"bob-hvr","model":"claude-opus-4.5","score":15.63,"metric":"index"},{"benchmark":"bob-hvr","model":"qwen3.5-397b-a17b","score":14.4,"metric":"index"},{"benchmark":"bob-hvr","model":"gpt-5","score":12.13,"metric":"index"},{"benchmark":"bob-hvr","model":"qwen3-235b-a22b","score":8.07,"metric":"index"},{"benchmark":"bob-hvr","model":"qwen3-max","score":8.07,"metric":"index"},{"benchmark":"bob-hvr","model":"deepseek-v3.2","score":7.52,"metric":"index"},{"benchmark":"bob-hvr","model":"kimi-k2","score":7.09,"metric":"index"},{"benchmark":"bob-hvr","model":"gpt-o3","score":7,"metric":"index"},{"benchmark":"bob-hvr","model":"gemini-2.5-flash","score":6.09,"metric":"index"},{"benchmark":"bob-hvr","model":"deepseek-r1","score":5.03,"metric":"index"},{"benchmark":"mmlu-redux","model":"gpt-4o-0327","score":91.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen-3-235b-a22b-nonthinking","score":89.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-30b-a3b-instruct-2507","score":89.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-omni-30b-a3b-instruct","score":86.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-omni-flash-instruct","score":86.8,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4o-0327","score":66.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen-3-235b-a22b-nonthinking","score":62.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-30b-a3b-instruct-2507","score":70.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-omni-30b-a3b-instruct","score":69.6,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-omni-flash-instruct","score":69.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4o-0327","score":26.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen-3-235b-a22b-nonthinking","score":24.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-instruct-2507","score":61.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-omni-30b-a3b-instruct","score":65,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-omni-flash-instruct","score":65.9,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4o-0327","score":52.6,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen-3-235b-a22b-nonthinking","score":37.7,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-30b-a3b-instruct-2507","score":90,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-omni-30b-a3b-instruct","score":76,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-omni-flash-instruct","score":76.1,"metric":"percent"},{"benchmark":"multipl-e","model":"gpt-4o-0327","score":82.7,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen-3-235b-a22b-nonthinking","score":79.3,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-30b-a3b-instruct-2507","score":83.8,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-omni-30b-a3b-instruct","score":81.4,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-omni-flash-instruct","score":81.5,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4o-0327","score":83.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen-3-235b-a22b-nonthinking","score":83.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-instruct-2507","score":84.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-omni-30b-a3b-instruct","score":81,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-omni-flash-instruct","score":81.7,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gpt-4o-0327","score":84.9,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen-3-235b-a22b-nonthinking","score":80.4,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-30b-a3b-instruct-2507","score":86,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-omni-30b-a3b-instruct","score":80.6,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-omni-flash-instruct","score":81.8,"metric":"percent"},{"benchmark":"writingbench","model":"gpt-4o-0327","score":75.5,"metric":"percent"},{"benchmark":"writingbench","model":"qwen-3-235b-a22b-nonthinking","score":77,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-30b-a3b-instruct-2507","score":85.5,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-omni-30b-a3b-instruct","score":82.6,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-omni-flash-instruct","score":83,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gpt-4o-0327","score":66.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen-3-235b-a22b-nonthinking","score":68,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-30b-a3b-instruct-2507","score":65.1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-omni-30b-a3b-instruct","score":64.4,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-omni-flash-instruct","score":65,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-4o-0327","score":70.4,"metric":"percent"},{"benchmark":"multi-if","model":"qwen-3-235b-a22b-nonthinking","score":70.2,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-30b-a3b-instruct-2507","score":67.9,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-omni-30b-a3b-instruct","score":64,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-omni-flash-instruct","score":64.7,"metric":"percent"},{"benchmark":"polymath","model":"gpt-4o-0327","score":25.5,"metric":"percent"},{"benchmark":"polymath","model":"qwen-3-235b-a22b-nonthinking","score":27,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-30b-a3b-instruct-2507","score":43.1,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-omni-30b-a3b-instruct","score":37.9,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-omni-flash-instruct","score":39.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen-3-235b-a22b-thinking","score":92.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-omni-30b-a3b-thinking","score":88.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-omni-flash-thinking","score":89.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"rnd1-base-0910","score":72.6,"metric":"percent"},{"benchmark":"gpqa","model":"qwen-3-235b-a22b-thinking","score":71.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-omni-30b-a3b-thinking","score":73.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-omni-flash-thinking","score":73.1,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-r1-0528","score":81,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-235b-a22b","score":70.7,"metric":"percent"},{"benchmark":"gpqa","model":"dots-vlm1","score":72.78,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4.6","score":81,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4.5","score":79.9,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v3.2-exp","score":79.9,"metric":"percent"},{"benchmark":"gpqa","model":"claude-sonnet-4","score":77.7,"metric":"percent"},{"benchmark":"gpqa","model":"claude-sonnet-4.5","score":83.4,"metric":"percent"},{"benchmark":"gpqa","model":"ring-flash-linear-2.0","score":72.85,"metric":"percent"},{"benchmark":"gpqa","model":"ring-flash-2.0","score":75.25,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b-thinking-2504","score":68.4,"metric":"percent"},{"benchmark":"gpqa","model":"gemini-2.5-flash","score":82.8,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-oss-120b-medium","score":73.1,"metric":"percent"},{"benchmark":"gpqa","model":"seed-oss-36b-instruct","score":71.4,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen-3-235b-a22b-thinking","score":81.5,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-omni-30b-a3b-thinking","score":73.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-omni-flash-thinking","score":74,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-235b-a22b","score":82.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-235b-a22b-thinking-2507","score":92.3,"metric":"percent"},{"benchmark":"aime-2025","model":"dots-vlm1","score":85.83,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.1","score":78,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4","score":74.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5","score":94.6,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.6","score":93.9,"metric":"percent"},{"benchmark":"aime-2025","model":"ring-1t-preview","score":92.6,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.1-terminus-thinking","score":89.06,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-thinking","score":94.6,"metric":"percent"},{"benchmark":"aime-2025","model":"ring-flash-linear-2.0","score":85.1,"metric":"percent"},{"benchmark":"aime-2025","model":"ring-flash-2.0","score":86.98,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b-thinking-2504","score":75.47,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash","score":72,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b-medium","score":80,"metric":"percent"},{"benchmark":"aime-2025","model":"seed-oss-36b-instruct","score":84.7,"metric":"percent"},{"benchmark":"livebench","model":"qwen-3-235b-a22b-thinking","score":77.1,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-omni-30b-a3b-thinking","score":71.8,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-omni-flash-thinking","score":70.3,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-235b-a22b","score":77.1,"metric":"percent"},{"benchmark":"livebench","model":"o1-2024-12-17","score":75.7,"metric":"percent"},{"benchmark":"multipl-e","model":"gemini-2.5-flash-thinking","score":84.5,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen-3-235b-a22b-thinking","score":79.9,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-30b-a3b-thinking-2507","score":81.3,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-omni-30b-a3b-thinking","score":80.6,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-omni-flash-thinking","score":81,"metric":"percent"},{"benchmark":"ifeval","model":"qwen-3-235b-a22b-thinking","score":83.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-omni-30b-a3b-thinking","score":85.1,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-omni-flash-thinking","score":85.2,"metric":"percent"},{"benchmark":"ifeval","model":"trlm-135m","score":35.49,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen-3-235b-a22b-thinking","score":61.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-omni-30b-a3b-thinking","score":55.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-omni-flash-thinking","score":57.8,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gemini-2.5-flash-thinking","score":85,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen-3-235b-a22b-thinking","score":84.6,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-30b-a3b-thinking-2507","score":84.4,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-omni-30b-a3b-thinking","score":82.5,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-omni-flash-thinking","score":83.6,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"ring-flash-linear-2.0","score":84.51,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"ring-flash-2.0","score":83.58,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-32b-thinking-2504","score":81,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gemini-2.5-flash","score":83.54,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gpt-oss-120b-medium","score":80.3,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"seed-oss-36b-instruct","score":83.46,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-next-80b-a3b-thinking","score":72.57,"metric":"percent"},{"benchmark":"writingbench","model":"qwen-3-235b-a22b-thinking","score":80.3,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-omni-30b-a3b-thinking","score":85.5,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-omni-flash-thinking","score":85.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen-3-235b-a22b-thinking","score":70.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-omni-30b-a3b-thinking","score":63.2,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-omni-flash-thinking","score":64.5,"metric":"percent"},{"benchmark":"multi-if","model":"gemini-2.5-flash-thinking","score":74.4,"metric":"percent"},{"benchmark":"multi-if","model":"qwen-3-235b-a22b-thinking","score":71.9,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-30b-a3b-thinking-2507","score":76.4,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-omni-30b-a3b-thinking","score":72.9,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-omni-flash-thinking","score":73.2,"metric":"percent"},{"benchmark":"polymath","model":"qwen-3-235b-a22b-thinking","score":54.7,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-omni-30b-a3b-thinking","score":47.1,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-omni-flash-thinking","score":48.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5","score":23.26,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-opus-4.1","score":22.71,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-sonnet-4","score":17.65,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-2.5-pro-preview-06-05","score":13.54,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"swesmith-32b","score":6.84,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-4o","score":4.92,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3-32b","score":3.42,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"gpt-4o-audio","score":95.6,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"gpt-4o-audio","score":89.8,"metric":"percent"},{"benchmark":"voicebench-wildvoice","model":"gpt-4o-audio","score":91.6,"metric":"percent"},{"benchmark":"voicebench-sd-qa","model":"gpt-4o-audio","score":75.5,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"gpt-4o-audio","score":80.3,"metric":"percent"},{"benchmark":"voicebench-openbookqa","model":"gpt-4o-audio","score":89.2,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"gpt-4o-audio","score":84.1,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"gpt-4o-audio","score":76,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"gpt-4o-audio","score":98.7,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"gpt-4o-audio","score":62.5,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"gpt-4o-audio","score":56.4,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"gemini-2.5-flash","score":96.1,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"gemini-2.5-flash","score":88.3,"metric":"percent"},{"benchmark":"voicebench-wildvoice","model":"gemini-2.5-flash","score":92.1,"metric":"percent"},{"benchmark":"voicebench-sd-qa","model":"gemini-2.5-flash","score":84.5,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"gemini-2.5-flash","score":66.1,"metric":"percent"},{"benchmark":"voicebench-openbookqa","model":"gemini-2.5-flash","score":56.9,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"gemini-2.5-flash","score":83,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"gemini-2.5-flash","score":83.8,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"gemini-2.5-flash","score":96.9,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"gemini-2.5-flash","score":71.8,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"gemini-2.5-flash","score":70.2,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"gemini-2.5-pro","score":94.3,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"gemini-2.5-pro","score":88.4,"metric":"percent"},{"benchmark":"voicebench-wildvoice","model":"gemini-2.5-pro","score":93.4,"metric":"percent"},{"benchmark":"voicebench-sd-qa","model":"gemini-2.5-pro","score":90.1,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"gemini-2.5-pro","score":71.1,"metric":"percent"},{"benchmark":"voicebench-openbookqa","model":"gemini-2.5-pro","score":92.3,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"gemini-2.5-pro","score":92.6,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"gemini-2.5-pro","score":85.7,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"gemini-2.5-pro","score":98.1,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"gemini-2.5-pro","score":77.4,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"gemini-2.5-pro","score":77.7,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"qwen2.5-omni","score":89.9,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"qwen2.5-omni","score":76.7,"metric":"percent"},{"benchmark":"voicebench-wildvoice","model":"qwen2.5-omni","score":77.7,"metric":"percent"},{"benchmark":"voicebench-sd-qa","model":"qwen2.5-omni","score":56.4,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"qwen2.5-omni","score":61.7,"metric":"percent"},{"benchmark":"voicebench-openbookqa","model":"qwen2.5-omni","score":89,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"qwen2.5-omni","score":66.7,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"qwen2.5-omni","score":53.5,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"qwen2.5-omni","score":99.2,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"qwen2.5-omni","score":65.5,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"qwen2.5-omni","score":62.6,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"qwen3-omni-30b-a3b-instruct","score":94.8,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"qwen3-omni-30b-a3b-instruct","score":90.8,"metric":"percent"},{"benchmark":"voicebench-wildvoice","model":"qwen3-omni-30b-a3b-instruct","score":91.6,"metric":"percent"},{"benchmark":"voicebench-sd-qa","model":"qwen3-omni-30b-a3b-instruct","score":76.9,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"qwen3-omni-30b-a3b-instruct","score":68.1,"metric":"percent"},{"benchmark":"voicebench-openbookqa","model":"qwen3-omni-30b-a3b-instruct","score":89.7,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"qwen3-omni-30b-a3b-instruct","score":80.4,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"qwen3-omni-30b-a3b-instruct","score":77.8,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"qwen3-omni-30b-a3b-instruct","score":97.2,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"qwen3-omni-30b-a3b-instruct","score":77.5,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"qwen3-omni-30b-a3b-instruct","score":69,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"qwen3-omni-30b-a3b-thinking","score":96.4,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"qwen3-omni-30b-a3b-thinking","score":90.5,"metric":"percent"},{"benchmark":"voicebench-wildvoice","model":"qwen3-omni-30b-a3b-thinking","score":90.5,"metric":"percent"},{"benchmark":"voicebench-sd-qa","model":"qwen3-omni-30b-a3b-thinking","score":78.1,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"qwen3-omni-30b-a3b-thinking","score":83,"metric":"percent"},{"benchmark":"voicebench-openbookqa","model":"qwen3-omni-30b-a3b-thinking","score":94.3,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"qwen3-omni-30b-a3b-thinking","score":88.9,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"qwen3-omni-30b-a3b-thinking","score":80.6,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"qwen3-omni-30b-a3b-thinking","score":99.4,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"qwen3-omni-30b-a3b-thinking","score":75.4,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"qwen3-omni-30b-a3b-thinking","score":70.2,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"qwen3-omni-flash-instruct","score":95.4,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"qwen3-omni-flash-instruct","score":91,"metric":"percent"},{"benchmark":"voicebench-wildvoice","model":"qwen3-omni-flash-instruct","score":92.3,"metric":"percent"},{"benchmark":"voicebench-sd-qa","model":"qwen3-omni-flash-instruct","score":76.8,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"qwen3-omni-flash-instruct","score":68.4,"metric":"percent"},{"benchmark":"voicebench-openbookqa","model":"qwen3-omni-flash-instruct","score":91.4,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"qwen3-omni-flash-instruct","score":80.6,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"qwen3-omni-flash-instruct","score":75.2,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"qwen3-omni-flash-instruct","score":98.9,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"qwen3-omni-flash-instruct","score":77.6,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"qwen3-omni-flash-instruct","score":69.1,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"qwen3-omni-flash-thinking","score":96.8,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"qwen3-omni-flash-thinking","score":90.9,"metric":"percent"},{"benchmark":"voicebench-wildvoice","model":"qwen3-omni-flash-thinking","score":90.9,"metric":"percent"},{"benchmark":"voicebench-sd-qa","model":"qwen3-omni-flash-thinking","score":78.5,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"qwen3-omni-flash-thinking","score":84.3,"metric":"percent"},{"benchmark":"voicebench-openbookqa","model":"qwen3-omni-flash-thinking","score":95,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"qwen3-omni-flash-thinking","score":89.6,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"qwen3-omni-flash-thinking","score":80.8,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"qwen3-omni-flash-thinking","score":98.9,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"qwen3-omni-flash-thinking","score":76.5,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"qwen3-omni-flash-thinking","score":71.3,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-4o","score":12.4,"metric":"percent"},{"benchmark":"gdpval","model":"grok-4","score":24.3,"metric":"percent"},{"benchmark":"gdpval","model":"gemini-2.5-pro","score":25.5,"metric":"percent"},{"benchmark":"gdpval","model":"o4-mini-high","score":27.9,"metric":"percent"},{"benchmark":"gdpval","model":"o3-high","score":34.1,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5-high","score":38.8,"metric":"percent"},{"benchmark":"gdpval","model":"claude-opus-4.1","score":47.6,"metric":"percent"},{"benchmark":"vibeval","model":"qwen2.5-vl-72b","score":60.13,"metric":"percent"},{"benchmark":"vibeval","model":"gemini-2.5-pro","score":76.39,"metric":"percent"},{"benchmark":"vibeval","model":"seed1.5-vl-thinking","score":68.59,"metric":"percent"},{"benchmark":"vibeval","model":"dots-vlm1","score":69.24,"metric":"percent"},{"benchmark":"m3gia-cn","model":"qwen2.5-vl-72b","score":88.24,"metric":"percent"},{"benchmark":"m3gia-cn","model":"gemini-2.5-pro","score":89.54,"metric":"percent"},{"benchmark":"m3gia-cn","model":"seed1.5-vl-thinking","score":91.2,"metric":"percent"},{"benchmark":"m3gia-cn","model":"dots-vlm1","score":90.85,"metric":"percent"},{"benchmark":"simplevqa-ds","model":"qwen2.5-vl-72b","score":52.19,"metric":"percent"},{"benchmark":"simplevqa-ds","model":"gemini-2.5-pro","score":57.09,"metric":"percent"},{"benchmark":"simplevqa-ds","model":"seed1.5-vl-thinking","score":61.34,"metric":"percent"},{"benchmark":"simplevqa-ds","model":"dots-vlm1","score":55.8,"metric":"percent"},{"benchmark":"ocrreasoning","model":"qwen2.5-vl-72b","score":38.02,"metric":"percent"},{"benchmark":"ocrreasoning","model":"gemini-2.5-pro","score":70.81,"metric":"percent"},{"benchmark":"ocrreasoning","model":"seed1.5-vl-thinking","score":63.42,"metric":"percent"},{"benchmark":"ocrreasoning","model":"dots-vlm1","score":66.23,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2.5-vl-72b","score":87.1,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-pro","score":86.6,"metric":"percent"},{"benchmark":"ocrbench","model":"seed1.5-vl-thinking","score":86.7,"metric":"percent"},{"benchmark":"ocrbench","model":"dots-vlm1","score":82.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-5-high","score":88,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-5-medium","score":86.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3-pro-high","score":84.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-pro-preview-06-05","score":83.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-5-low","score":81.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3-high","score":81.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"grok-4-high","score":79.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-pro-preview-06-05","score":79.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3-high-plus-gpt-4.1","score":78.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3","score":76.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-pro-preview-05-06","score":76.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-pro-preview-03-25","score":72.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-opus-4-20250514","score":72,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o4-mini-high","score":72,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-r1-0528","score":71.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-opus-4-20250514","score":70.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-3.7-sonnet-20250219","score":64.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-r1-plus-claude-3-5-sonnet-20241022","score":64,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o1-2024-12-17-high","score":61.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-sonnet-4-20250514","score":61.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-3.7-sonnet-20250219","score":60.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3-mini-high","score":60.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-235b-a22b","score":59.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"kimi-k2","score":59.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-sonnet-4-20250514","score":56.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-flash-preview-05-20","score":55.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3-0324","score":55.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"quasar-alpha","score":54.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o3-mini-medium","score":53.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"grok-3-beta","score":53.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"optimus-alpha","score":52.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4.1","score":52.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"grok-3-mini-beta-high","score":49.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-chat-v3-prev","score":48.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-flash-preview-04-17","score":47.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"chatgpt-4o-latest-20250329","score":45.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4.5-preview","score":44.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-flash-preview-05-20","score":44,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-oss-120b-high","score":41.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-32b","score":40,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-exp-1206","score":38.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.0-pro-exp-02-05","score":35.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"grok-3-mini-beta-low","score":34.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"o1-mini-2024-09-12","score":32.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4.1-mini","score":32.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"chatgpt-4o-latest-20250215","score":27.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwq-32b-plus-qwen2.5-coder-32b-instruct","score":26.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4o-2024-08-06","score":23.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.0-flash-exp","score":22.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen-max-2025-01-25","score":21.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwq-32b","score":20.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.0-flash-thinking-exp-01-21","score":18.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4o-2024-11-20","score":18.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-chat-v2.5","score":17.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen2.5-coder-32b-instruct","score":16.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"llama-4-maverick-17b-128e-instruct","score":15.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"yi-lightning","score":12.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"command-a-03-2025-quality","score":12,"metric":"percent"},{"benchmark":"aider-polyglot","model":"codestral-2501","score":11.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"openhands-lm-32b-v0.1","score":10.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4.1-nano","score":8.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen2.5-coder-32b-instruct-hyperbolic","score":8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemma-3-27b-it","score":4.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4o-mini-2024-07-18","score":3.6,"metric":"percent"},{"benchmark":"evalperf","model":"gpt-4o-2024-08-06","score":100,"metric":"percent"},{"benchmark":"evalperf","model":"deepseek-chat-v2.5","score":97,"metric":"percent"},{"benchmark":"evalperf","model":"o1-preview-2024-09-12","score":90.9,"metric":"percent"},{"benchmark":"evalperf","model":"mistral-large-instruct-2407","score":87.9,"metric":"percent"},{"benchmark":"evalperf","model":"o1-mini-2024-09-12-high","score":84.8,"metric":"percent"},{"benchmark":"evalperf","model":"o1-mini-2024-09-12","score":81.8,"metric":"percent"},{"benchmark":"evalperf","model":"gpt-4o-mini-2024-07-18","score":78.8,"metric":"percent"},{"benchmark":"evalperf","model":"deepseek-chat-v3","score":75.8,"metric":"percent"},{"benchmark":"evalperf","model":"qwen2.5-7b-instruct","score":72.7,"metric":"percent"},{"benchmark":"evalperf","model":"gemma-2-27b-it","score":69.7,"metric":"percent"},{"benchmark":"evalperf","model":"qwen2.5-72b-instruct","score":66.7,"metric":"percent"},{"benchmark":"evalperf","model":"qwen2.5-32b-instruct","score":60.6,"metric":"percent"},{"benchmark":"evalperf","model":"yi-coder-9b-chat","score":57.6,"metric":"percent"},{"benchmark":"evalperf","model":"magicoder-s-ds-6.7b","score":57.6,"metric":"percent"},{"benchmark":"evalperf","model":"qwq-32b-preview","score":54.5,"metric":"percent"},{"benchmark":"evalperf","model":"deepseek-coder-6.7b-instruct","score":54.5,"metric":"percent"},{"benchmark":"evalperf","model":"deepseek-coder-v2-lite-instruct","score":51.5,"metric":"percent"},{"benchmark":"evalperf","model":"mistral-small-instruct-2409","score":42.4,"metric":"percent"},{"benchmark":"evalperf","model":"codestral-22b-v0.1","score":39.4,"metric":"percent"},{"benchmark":"evalperf","model":"deepseek-coder-33b-instruct","score":39.4,"metric":"percent"},{"benchmark":"evalperf","model":"qwen2.5-14b-instruct","score":36.4,"metric":"percent"},{"benchmark":"evalperf","model":"grok-beta","score":33.3,"metric":"percent"},{"benchmark":"evalperf","model":"opencoder-8b-instruct","score":30.3,"metric":"percent"},{"benchmark":"evalperf","model":"llama-3.1-70b-instruct","score":27.3,"metric":"percent"},{"benchmark":"evalperf","model":"gemma-2-9b-it","score":24.2,"metric":"percent"},{"benchmark":"evalperf","model":"gemini-1.5-flash-002","score":24.2,"metric":"percent"},{"benchmark":"evalperf","model":"mistral-nemo-instruct-2407","score":21.2,"metric":"percent"},{"benchmark":"evalperf","model":"llama-3.1-8b-instruct","score":15.2,"metric":"percent"},{"benchmark":"evalperf","model":"codeqwen1.5-7b-chat","score":12.1,"metric":"percent"},{"benchmark":"evalperf","model":"phi-3-medium-4k-instruct","score":9.1,"metric":"percent"},{"benchmark":"evalperf","model":"llama-3.1-nemotron-70b-instruct-hf","score":6.1,"metric":"percent"},{"benchmark":"evalperf","model":"gemini-1.5-pro-002","score":3,"metric":"percent"},{"benchmark":"evalperf","model":"meta-llama-3-8b-instruct","score":0,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"devstral","score":46.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-4.1-mini","score":23.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-3-5-haiku-20240620","score":40.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"swe-smith-lm-32b","score":40.2,"metric":"percent"},{"benchmark":"mbpp","model":"codestral-22b","score":78.2,"metric":"percent"},{"benchmark":"crux-o","model":"codestral-22b","score":51.3,"metric":"percent"},{"benchmark":"spider","model":"codestral-22b","score":63.5,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-70b","score":70.8,"metric":"percent"},{"benchmark":"crux-o","model":"codellama-70b","score":47.3,"metric":"percent"},{"benchmark":"repobench","model":"codellama-70b","score":11.4,"metric":"percent"},{"benchmark":"spider","model":"codellama-70b","score":37,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-33b","score":77.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-33b","score":80.2,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-33b","score":49.5,"metric":"percent"},{"benchmark":"repobench","model":"deepseek-coder-33b","score":28.4,"metric":"percent"},{"benchmark":"spider","model":"deepseek-coder-33b","score":60,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b","score":76.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-70b","score":76.7,"metric":"percent"},{"benchmark":"crux-o","model":"llama-3-70b","score":26,"metric":"percent"},{"benchmark":"repobench","model":"llama-3-70b","score":18.4,"metric":"percent"},{"benchmark":"spider","model":"llama-3-70b","score":67.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-3.7-sonnet","score":62.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.1","score":74.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5","score":72.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-2.5-pro","score":67.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"o3","score":30.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4.1","score":46.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-sonnet-4","score":36.4,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5","score":43.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-4.5-sonnet-thinking","score":61.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5-codex","score":58.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5","score":48.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-sonnet-4-thinking","score":45,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.1","score":41.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-pro","score":41.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"glm-4.5","score":41.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-4","score":38.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-instruct-0905","score":37.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-max-instruct-preview","score":36.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-max","score":36.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-flash","score":31.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5-mini","score":30,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-4-fast-thinking","score":26.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-flash-thinking","score":26.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-oss-120b","score":22.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-flash-thinking","score":21.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-code-fast","score":20,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-4-fast","score":18.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"llama-4-maverick","score":17.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-r1","score":13.8,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4-turbo-2024-04-09-cot","score":75.7,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4-turbo-2024-04-09","score":68.5,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4o-cot","score":75.6,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4o","score":65.1,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4-0613-cot","score":75.5,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4-0613","score":69.8,"metric":"percent"},{"benchmark":"crux-i","model":"claude-opus-4-cot","score":73.4,"metric":"percent"},{"benchmark":"crux-i","model":"claude-opus-4","score":64.2,"metric":"percent"},{"benchmark":"crux-i","model":"semcoder-s-6.7b-cot","score":63.1,"metric":"percent"},{"benchmark":"crux-i","model":"semcoder-6.7b-cot","score":62.5,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-3.5-turbo-0613-cot","score":50.3,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-34b-cot","score":50.1,"metric":"percent"},{"benchmark":"crux-i","model":"codetulu-2-34b","score":49.3,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-3.5-turbo-0613","score":49,"metric":"percent"},{"benchmark":"crux-i","model":"starcoder2-15b","score":48.1,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-13b-cot","score":47.4,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-34b","score":47.2,"metric":"percent"},{"benchmark":"crux-i","model":"phind-base","score":47.2,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-base-33b","score":46.5,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-instruct-33b","score":46.5,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-python-34b","score":43.9,"metric":"percent"},{"benchmark":"crux-i","model":"wizard-34b","score":42.7,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-13b","score":42.5,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-base-6.7b","score":41.9,"metric":"percent"},{"benchmark":"crux-i","model":"magicoder-s-ds-6.7b","score":41.7,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-7b-cot","score":40.4,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-python-13b","score":39.7,"metric":"percent"},{"benchmark":"crux-i","model":"mixtral-8x7b","score":39.3,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-instruct-6.7b","score":37.4,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-python-7b","score":37.3,"metric":"percent"},{"benchmark":"crux-i","model":"wizardlm-13b","score":36.5,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-7b","score":35.9,"metric":"percent"},{"benchmark":"crux-i","model":"mistral-7b","score":35,"metric":"percent"},{"benchmark":"crux-i","model":"starcoder2-7b","score":34.6,"metric":"percent"},{"benchmark":"crux-i","model":"stablecode-3b","score":33.5,"metric":"percent"},{"benchmark":"crux-i","model":"starcoder2-3b","score":32.7,"metric":"percent"},{"benchmark":"crux-i","model":"phi-2","score":31.6,"metric":"percent"},{"benchmark":"crux-i","model":"starcoderbase-16b","score":31.3,"metric":"percent"},{"benchmark":"crux-i","model":"starcoderbase-7b","score":29.7,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-base-1.3b","score":27.8,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-instruct-1.3b","score":27.2,"metric":"percent"},{"benchmark":"crux-i","model":"phi-1.5","score":23.2,"metric":"percent"},{"benchmark":"crux-i","model":"phi-1","score":13.1,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-4-turbo-2024-04-09-cot","score":82,"metric":"pass@1"},{"benchmark":"crux-o","model":"claude-opus-4-cot","score":82,"metric":"pass@1"},{"benchmark":"crux-o","model":"gpt-4-0613-cot","score":77.1,"metric":"pass@1"},{"benchmark":"crux-o","model":"gpt-4-0613-cot","score":88.2,"metric":"pass@5"},{"benchmark":"crux-o","model":"gpt-4o-cot","score":76,"metric":"pass@1"},{"benchmark":"crux-o","model":"gpt-4o","score":70,"metric":"pass@1"},{"benchmark":"crux-o","model":"gpt-4-0613","score":68.7,"metric":"pass@1"},{"benchmark":"crux-o","model":"gpt-4-0613","score":73,"metric":"pass@5"},{"benchmark":"crux-o","model":"gpt-4-turbo-2024-04-09","score":67.7,"metric":"pass@1"},{"benchmark":"crux-o","model":"claude-opus-4","score":65.8,"metric":"pass@1"},{"benchmark":"crux-o","model":"semcoder-6.7b-cot","score":64.4,"metric":"pass@1"},{"benchmark":"crux-o","model":"semcoder-6.7b-cot","score":79.1,"metric":"pass@5"},{"benchmark":"crux-o","model":"semcoder-s-6.7b-cot","score":64.1,"metric":"pass@1"},{"benchmark":"crux-o","model":"semcoder-s-6.7b-cot","score":78.3,"metric":"pass@5"},{"benchmark":"crux-o","model":"gpt-3.5-turbo-0613-cot","score":59,"metric":"pass@1"},{"benchmark":"crux-o","model":"gpt-3.5-turbo-0613-cot","score":76.7,"metric":"pass@5"},{"benchmark":"crux-o","model":"deepseek-instruct-33b","score":49.9,"metric":"pass@1"},{"benchmark":"crux-o","model":"deepseek-instruct-33b","score":61.8,"metric":"pass@5"},{"benchmark":"crux-o","model":"gpt-3.5-turbo-0613","score":49.4,"metric":"pass@1"},{"benchmark":"crux-o","model":"gpt-3.5-turbo-0613","score":59.3,"metric":"pass@5"},{"benchmark":"crux-o","model":"deepseek-base-33b","score":48.6,"metric":"pass@1"},{"benchmark":"crux-o","model":"deepseek-base-33b","score":61.6,"metric":"pass@5"},{"benchmark":"crux-o","model":"starcoder2-15b","score":47.1,"metric":"pass@1"},{"benchmark":"crux-o","model":"starcoder2-15b","score":59.5,"metric":"pass@5"},{"benchmark":"crux-o","model":"codetulu-2-34b","score":45.8,"metric":"pass@1"},{"benchmark":"crux-o","model":"codetulu-2-34b","score":58.9,"metric":"pass@5"},{"benchmark":"crux-o","model":"magicoder-s-ds-6.7b","score":44.4,"metric":"pass@1"},{"benchmark":"crux-o","model":"magicoder-s-ds-6.7b","score":57.5,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-34b-cot","score":43.6,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-34b-cot","score":69.4,"metric":"pass@5"},{"benchmark":"crux-o","model":"deepseek-base-6.7b","score":43.5,"metric":"pass@1"},{"benchmark":"crux-o","model":"deepseek-base-6.7b","score":54.8,"metric":"pass@5"},{"benchmark":"crux-o","model":"wizard-34b","score":43.4,"metric":"pass@1"},{"benchmark":"crux-o","model":"wizard-34b","score":53.8,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-34b","score":42.4,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-34b","score":55.9,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-python-34b","score":41.4,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-python-34b","score":52.9,"metric":"pass@5"},{"benchmark":"crux-o","model":"wizardlm-13b","score":41.3,"metric":"pass@1"},{"benchmark":"crux-o","model":"wizardlm-13b","score":52.4,"metric":"pass@5"},{"benchmark":"crux-o","model":"deepseek-instruct-6.7b","score":41.2,"metric":"pass@1"},{"benchmark":"crux-o","model":"deepseek-instruct-6.7b","score":52.8,"metric":"pass@5"},{"benchmark":"crux-o","model":"mixtral-8x7b","score":40.5,"metric":"pass@1"},{"benchmark":"crux-o","model":"mixtral-8x7b","score":54,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-python-13b","score":39.8,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-python-13b","score":52.5,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-13b","score":39.7,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-13b","score":53.9,"metric":"pass@5"},{"benchmark":"crux-o","model":"phind-base","score":39.7,"metric":"pass@1"},{"benchmark":"crux-o","model":"phind-base","score":52.8,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-13b-cot","score":36,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-13b-cot","score":61.8,"metric":"pass@5"},{"benchmark":"crux-o","model":"starcoder2-7b","score":36,"metric":"pass@1"},{"benchmark":"crux-o","model":"starcoder2-7b","score":52,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-python-7b","score":35.9,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-python-7b","score":48.8,"metric":"pass@5"},{"benchmark":"crux-o","model":"mistral-7b","score":34.3,"metric":"pass@1"},{"benchmark":"crux-o","model":"mistral-7b","score":48.6,"metric":"pass@5"},{"benchmark":"crux-o","model":"starcoderbase-16b","score":34.2,"metric":"pass@1"},{"benchmark":"crux-o","model":"starcoderbase-16b","score":47.1,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-7b","score":34.2,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-7b","score":48.4,"metric":"pass@5"},{"benchmark":"crux-o","model":"starcoder2-3b","score":34.2,"metric":"pass@1"},{"benchmark":"crux-o","model":"starcoder2-3b","score":48.4,"metric":"pass@5"},{"benchmark":"crux-o","model":"phi-2","score":33.5,"metric":"pass@1"},{"benchmark":"crux-o","model":"phi-2","score":46.6,"metric":"pass@5"},{"benchmark":"crux-o","model":"starcoderbase-7b","score":32.2,"metric":"pass@1"},{"benchmark":"crux-o","model":"starcoderbase-7b","score":44.9,"metric":"pass@5"},{"benchmark":"crux-o","model":"deepseek-base-1.3b","score":31,"metric":"pass@1"},{"benchmark":"crux-o","model":"deepseek-base-1.3b","score":43.4,"metric":"pass@5"},{"benchmark":"crux-o","model":"codellama-7b-cot","score":29.9,"metric":"pass@1"},{"benchmark":"crux-o","model":"codellama-7b-cot","score":55.4,"metric":"pass@5"},{"benchmark":"crux-o","model":"deepseek-instruct-1.3b","score":28.7,"metric":"pass@1"},{"benchmark":"crux-o","model":"deepseek-instruct-1.3b","score":40,"metric":"pass@5"},{"benchmark":"crux-o","model":"phi-1.5","score":27.5,"metric":"pass@1"},{"benchmark":"crux-o","model":"phi-1.5","score":39.1,"metric":"pass@5"},{"benchmark":"crux-o","model":"stablecode-3b","score":26.7,"metric":"pass@1"},{"benchmark":"crux-o","model":"stablecode-3b","score":43.5,"metric":"pass@5"},{"benchmark":"crux-o","model":"phi-1","score":21.7,"metric":"pass@1"},{"benchmark":"crux-o","model":"phi-1","score":32,"metric":"pass@5"},{"benchmark":"financeagent","model":"claude-sonnet-4.5","score":55.3,"metric":"percent"},{"benchmark":"financeagent","model":"claude-opus-4.1","score":50.9,"metric":"percent"},{"benchmark":"financeagent","model":"claude-sonnet-4","score":44.5,"metric":"percent"},{"benchmark":"financeagent","model":"gpt-5","score":46.9,"metric":"percent"},{"benchmark":"financeagent","model":"gemini-2.5-pro","score":29.4,"metric":"percent"},{"benchmark":"ai2d","model":"minicpm-v-2.0-3b","score":62.9,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-nano-2","score":51,"metric":"percent"},{"benchmark":"ai2d","model":"phi-3-vision-4b","score":76.7,"metric":"percent"},{"benchmark":"ai2d","model":"mm1.5-3b","score":65.7,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2.5-2b","score":74.9,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2.5-4b","score":81.4,"metric":"percent"},{"benchmark":"ai2d","model":"internvl3.5-2b","score":78.7,"metric":"percent"},{"benchmark":"ai2d","model":"internvl3.5-4b","score":82.6,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2.5-vl-3b","score":81.6,"metric":"percent"},{"benchmark":"ai2d","model":"cambrian-34b","score":79.7,"metric":"percent"},{"benchmark":"ai2d","model":"mm1-30b","score":73.3,"metric":"percent"},{"benchmark":"ai2d","model":"mm1.5-30b","score":77.2,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2.5-26b","score":86.4,"metric":"percent"},{"benchmark":"ai2d","model":"janus-pro-1.5b","score":67,"metric":"percent"},{"benchmark":"ai2d","model":"emu3-8b","score":70,"metric":"percent"},{"benchmark":"ai2d","model":"janus-pro-7b","score":68.1,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2.5-omni-7b","score":76.8,"metric":"percent"},{"benchmark":"ai2d","model":"bagel-14b","score":89.2,"metric":"percent"},{"benchmark":"ai2d","model":"manzano-3b","score":82.2,"metric":"percent"},{"benchmark":"ai2d","model":"manzano-30b","score":86,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4o","score":84.6,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-1.5-pro","score":79.1,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-pro","score":89.5,"metric":"percent"},{"benchmark":"scienceqa","model":"minicpm-v-2.0-3b","score":80.7,"metric":"percent"},{"benchmark":"scienceqa","model":"vila1.5-3b","score":69,"metric":"percent"},{"benchmark":"scienceqa","model":"bunny-4b","score":78.3,"metric":"percent"},{"benchmark":"scienceqa","model":"blip-3-4b","score":88.3,"metric":"percent"},{"benchmark":"scienceqa","model":"phi-3-vision-4b","score":90.8,"metric":"percent"},{"benchmark":"scienceqa","model":"mm1.5-3b","score":85.8,"metric":"percent"},{"benchmark":"scienceqa","model":"llava-next-34b","score":81.8,"metric":"percent"},{"benchmark":"scienceqa","model":"cambrian-34b","score":85.6,"metric":"percent"},{"benchmark":"scienceqa","model":"mm1-30b","score":81,"metric":"percent"},{"benchmark":"scienceqa","model":"mm1.5-30b","score":91.9,"metric":"percent"},{"benchmark":"scienceqa","model":"manzano-3b","score":92.9,"metric":"percent"},{"benchmark":"scienceqa","model":"manzano-30b","score":96.2,"metric":"percent"},{"benchmark":"scienceqa","model":"gpt-4o","score":90.7,"metric":"percent"},{"benchmark":"scienceqa","model":"gemini-1.5-pro","score":85.7,"metric":"percent"},{"benchmark":"scienceqa","model":"gemini-2.5-pro","score":88.4,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v-2.0-3b","score":38.2,"metric":"percent"},{"benchmark":"mmmu","model":"vila1.5-3b","score":33.3,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-nano-2","score":32.6,"metric":"percent"},{"benchmark":"mmmu","model":"bunny-4b","score":41.4,"metric":"percent"},{"benchmark":"mmmu","model":"blip-3-4b","score":41.1,"metric":"percent"},{"benchmark":"mmmu","model":"phi-3-vision-4b","score":40.4,"metric":"percent"},{"benchmark":"mmmu","model":"mm1.5-3b","score":37.1,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2.5-2b","score":43.6,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2.5-4b","score":52.3,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-2b","score":59,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2.5-vl-3b","score":53.1,"metric":"percent"},{"benchmark":"mmmu","model":"llava-next-34b","score":51.1,"metric":"percent"},{"benchmark":"mmmu","model":"cambrian-34b","score":49.7,"metric":"percent"},{"benchmark":"mmmu","model":"mm1-30b","score":44.7,"metric":"percent"},{"benchmark":"mmmu","model":"mm1.5-30b","score":47.4,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2.5-26b","score":51.8,"metric":"percent"},{"benchmark":"mmmu","model":"janus-pro-1.5b","score":36.3,"metric":"percent"},{"benchmark":"mmmu","model":"harmon-1.5b","score":38.9,"metric":"percent"},{"benchmark":"mmmu","model":"blip-3o-4b","score":46.6,"metric":"percent"},{"benchmark":"mmmu","model":"emu3-8b","score":31.6,"metric":"percent"},{"benchmark":"mmmu","model":"janus-pro-7b","score":41,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2.5-omni-7b","score":47.2,"metric":"percent"},{"benchmark":"mmmu","model":"bagel-14b","score":55.3,"metric":"percent"},{"benchmark":"mmmu","model":"manzano-3b","score":51.4,"metric":"percent"},{"benchmark":"mmmu","model":"manzano-30b","score":57.8,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4o","score":69.2,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.5-pro","score":60.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"minicpm-v-2.0-3b","score":38.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-nano-2","score":30.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"blip-3-4b","score":39.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"phi-3-vision-4b","score":44.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"mm1.5-3b","score":44.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2.5-2b","score":51.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2.5-4b","score":60.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl3.5-2b","score":71.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl3.5-4b","score":77.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2.5-vl-3b","score":62.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-next-34b","score":46.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"cambrian-34b","score":53.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"mm1-30b","score":39.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"mm1.5-30b","score":55.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2.5-26b","score":67.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"janus-pro-1.5b","score":36.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"emu3-8b","score":47.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"janus-pro-7b","score":42.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2.5-omni-7b","score":54.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"bagel-14b","score":73.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"manzano-3b","score":69.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"manzano-30b","score":73.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4o","score":61.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-1.5-pro","score":57.7,"metric":"percent"},{"benchmark":"chartqa","model":"minicpm-v-2.0-3b","score":59.8,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-nano-2","score":51.9,"metric":"percent"},{"benchmark":"chartqa","model":"phi-3-vision-4b","score":81.4,"metric":"percent"},{"benchmark":"chartqa","model":"mm1.5-3b","score":74.2,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2.5-2b","score":79.2,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2.5-4b","score":84,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-2b","score":80.7,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-4b","score":86,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2.5-vl-3b","score":84,"metric":"percent"},{"benchmark":"chartqa","model":"cambrian-34b","score":75.6,"metric":"percent"},{"benchmark":"chartqa","model":"mm1-30b","score":76.9,"metric":"percent"},{"benchmark":"chartqa","model":"mm1.5-30b","score":83.6,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2.5-26b","score":87.2,"metric":"percent"},{"benchmark":"chartqa","model":"janus-pro-1.5b","score":23.4,"metric":"percent"},{"benchmark":"chartqa","model":"janus-pro-7b","score":25.8,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2.5-omni-7b","score":81.5,"metric":"percent"},{"benchmark":"chartqa","model":"bagel-14b","score":78.5,"metric":"percent"},{"benchmark":"chartqa","model":"manzano-3b","score":88.2,"metric":"percent"},{"benchmark":"chartqa","model":"manzano-30b","score":89,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-4o","score":85.7,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-pro","score":83.3,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-v-2.0-3b","score":74.1,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-nano-2","score":65.9,"metric":"percent"},{"benchmark":"textvqa","model":"phi-3-vision-4b","score":70.1,"metric":"percent"},{"benchmark":"textvqa","model":"mm1.5-3b","score":76.5,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2.5-2b","score":74.3,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2.5-4b","score":76.8,"metric":"percent"},{"benchmark":"textvqa","model":"internvl3.5-2b","score":76.5,"metric":"percent"},{"benchmark":"textvqa","model":"internvl3.5-4b","score":77.9,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2.5-vl-3b","score":79.3,"metric":"percent"},{"benchmark":"textvqa","model":"llava-next-34b","score":69.5,"metric":"percent"},{"benchmark":"textvqa","model":"cambrian-34b","score":76.7,"metric":"percent"},{"benchmark":"textvqa","model":"mm1-30b","score":73.5,"metric":"percent"},{"benchmark":"textvqa","model":"mm1.5-30b","score":79.2,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2.5-26b","score":82.4,"metric":"percent"},{"benchmark":"textvqa","model":"janus-pro-1.5b","score":41.9,"metric":"percent"},{"benchmark":"textvqa","model":"blip-3o-4b","score":78,"metric":"percent"},{"benchmark":"textvqa","model":"emu3-8b","score":64.7,"metric":"percent"},{"benchmark":"textvqa","model":"janus-pro-7b","score":45.6,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2.5-omni-7b","score":77.4,"metric":"percent"},{"benchmark":"textvqa","model":"bagel-14b","score":80,"metric":"percent"},{"benchmark":"textvqa","model":"manzano-3b","score":80.1,"metric":"percent"},{"benchmark":"textvqa","model":"manzano-30b","score":84.4,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-2.5-pro","score":76.8,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-v-2.0-3b","score":71.9,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-nano-2","score":74.3,"metric":"percent"},{"benchmark":"docvqa","model":"phi-3-vision-4b","score":83.3,"metric":"percent"},{"benchmark":"docvqa","model":"mm1.5-3b","score":87.7,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2.5-2b","score":88.7,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2.5-4b","score":91.6,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-2b","score":89.4,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-4b","score":92.4,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2.5-vl-3b","score":93.9,"metric":"percent"},{"benchmark":"docvqa","model":"cambrian-34b","score":75.5,"metric":"percent"},{"benchmark":"docvqa","model":"mm1-30b","score":75.8,"metric":"percent"},{"benchmark":"docvqa","model":"mm1.5-30b","score":91.4,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2.5-26b","score":94,"metric":"percent"},{"benchmark":"docvqa","model":"janus-pro-1.5b","score":35.5,"metric":"percent"},{"benchmark":"docvqa","model":"emu3-8b","score":76.3,"metric":"percent"},{"benchmark":"docvqa","model":"janus-pro-7b","score":40.8,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2.5-omni-7b","score":88.6,"metric":"percent"},{"benchmark":"docvqa","model":"bagel-14b","score":88.1,"metric":"percent"},{"benchmark":"docvqa","model":"manzano-3b","score":93.5,"metric":"percent"},{"benchmark":"docvqa","model":"manzano-30b","score":94.3,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4o","score":92.8,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-pro","score":94,"metric":"percent"},{"benchmark":"infovqa","model":"minicpm-v-2.0-3b","score":37.6,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-nano-2","score":54.5,"metric":"percent"},{"benchmark":"infovqa","model":"phi-3-vision-4b","score":49,"metric":"percent"},{"benchmark":"infovqa","model":"mm1.5-3b","score":58.5,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2.5-2b","score":60.9,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2.5-4b","score":72.1,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-2b","score":70.8,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-4b","score":78,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2.5-vl-3b","score":77.1,"metric":"percent"},{"benchmark":"infovqa","model":"mm1-30b","score":47.3,"metric":"percent"},{"benchmark":"infovqa","model":"mm1.5-30b","score":67.3,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2.5-26b","score":79.8,"metric":"percent"},{"benchmark":"infovqa","model":"janus-pro-1.5b","score":14.1,"metric":"percent"},{"benchmark":"infovqa","model":"janus-pro-7b","score":21.3,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2.5-omni-7b","score":46.9,"metric":"percent"},{"benchmark":"infovqa","model":"bagel-14b","score":51,"metric":"percent"},{"benchmark":"infovqa","model":"manzano-3b","score":75,"metric":"percent"},{"benchmark":"infovqa","model":"manzano-30b","score":81.9,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-1.5-pro","score":81,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-2.5-pro","score":84.3,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-v-2.0-3b","score":60.5,"metric":"percent"},{"benchmark":"ocrbench","model":"phi-3-vision-4b","score":63.7,"metric":"percent"},{"benchmark":"ocrbench","model":"mm1.5-3b","score":65.7,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2.5-2b","score":80.4,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2.5-4b","score":82.8,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3.5-2b","score":83.6,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3.5-4b","score":82.2,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2.5-vl-3b","score":79.7,"metric":"percent"},{"benchmark":"ocrbench","model":"cambrian-34b","score":60,"metric":"percent"},{"benchmark":"ocrbench","model":"mm1-30b","score":60.6,"metric":"percent"},{"benchmark":"ocrbench","model":"mm1.5-30b","score":65.8,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2.5-26b","score":85.2,"metric":"percent"},{"benchmark":"ocrbench","model":"janus-pro-1.5b","score":48.7,"metric":"percent"},{"benchmark":"ocrbench","model":"emu3-8b","score":68.7,"metric":"percent"},{"benchmark":"ocrbench","model":"janus-pro-7b","score":59,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2.5-omni-7b","score":70.4,"metric":"percent"},{"benchmark":"ocrbench","model":"bagel-14b","score":73.3,"metric":"percent"},{"benchmark":"ocrbench","model":"manzano-3b","score":85.7,"metric":"percent"},{"benchmark":"ocrbench","model":"manzano-30b","score":86.3,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4o","score":73.6,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-1.5-pro","score":75.4,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-pro","score":86.2,"metric":"percent"},{"benchmark":"financeagent","model":"grok-4-fast","score":54.7,"metric":"percent"},{"benchmark":"corpfin","model":"grok-4-fast","score":73.3,"metric":"percent"},{"benchmark":"caselaw","model":"grok-4-fast","score":71.4,"metric":"percent"},{"benchmark":"taxeval","model":"grok-4-fast","score":68.2,"metric":"percent"},{"benchmark":"mortgagetax","model":"grok-4-fast","score":55.1,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4-fast","score":91.2,"metric":"percent"},{"benchmark":"mgsm","model":"grok-4-fast","score":90.9,"metric":"percent"},{"benchmark":"legalbench","model":"grok-4-fast","score":81.7,"metric":"percent"},{"benchmark":"medqa","model":"grok-4-fast","score":92.1,"metric":"percent"},{"benchmark":"gpqa","model":"grok-4-fast","score":85.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-4-fast","score":79.7,"metric":"percent"},{"benchmark":"mmmu","model":"grok-4-fast","score":72.8,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-4-fast","score":79,"metric":"percent"},{"benchmark":"ioi","model":"grok-4-fast","score":11.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-4-fast","score":26.3,"metric":"percent"},{"benchmark":"mbpp","model":"apriel-nemotron-15b-thinker","score":85.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-nemotron-nano-8b-v1","score":73.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwq-32b","score":88.2,"metric":"percent"},{"benchmark":"mbpp","model":"lg-exaone-32b","score":76.8,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"apriel-nemotron-15b-thinker","score":75.4,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"llama-3.1-nemotron-nano-8b-v1","score":54.1,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"qwq-32b","score":79,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"o1-mini","score":81,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"lg-exaone-32b","score":75.4,"metric":"percent"},{"benchmark":"enterprise-rag","model":"apriel-nemotron-15b-thinker","score":69.2,"metric":"percent"},{"benchmark":"enterprise-rag","model":"llama-3.1-nemotron-nano-8b-v1","score":11.1,"metric":"percent"},{"benchmark":"enterprise-rag","model":"qwq-32b","score":65.2,"metric":"percent"},{"benchmark":"enterprise-rag","model":"o1-mini","score":66.5,"metric":"percent"},{"benchmark":"enterprise-rag","model":"lg-exaone-32b","score":52.1,"metric":"percent"},{"benchmark":"mt-bench","model":"apriel-nemotron-15b-thinker","score":85.7,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.1-nemotron-nano-8b-v1","score":74.2,"metric":"percent"},{"benchmark":"mt-bench","model":"qwq-32b","score":83.1,"metric":"percent"},{"benchmark":"mt-bench","model":"o1-mini","score":83.8,"metric":"percent"},{"benchmark":"mt-bench","model":"lg-exaone-32b","score":83.9,"metric":"percent"},{"benchmark":"mixeval","model":"apriel-nemotron-15b-thinker","score":82.8,"metric":"percent"},{"benchmark":"mixeval","model":"llama-3.1-nemotron-nano-8b-v1","score":62.1,"metric":"percent"},{"benchmark":"mixeval","model":"qwq-32b","score":77.3,"metric":"percent"},{"benchmark":"mixeval","model":"o1-mini","score":82.9,"metric":"percent"},{"benchmark":"mixeval","model":"lg-exaone-32b","score":80.6,"metric":"percent"},{"benchmark":"ifeval","model":"apriel-nemotron-15b-thinker","score":84.6,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-nemotron-nano-8b-v1","score":69.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwq-32b","score":82.8,"metric":"percent"},{"benchmark":"ifeval","model":"o1-mini","score":79.5,"metric":"percent"},{"benchmark":"ifeval","model":"lg-exaone-32b","score":83.1,"metric":"percent"},{"benchmark":"multichallenge","model":"apriel-nemotron-15b-thinker","score":36.6,"metric":"percent"},{"benchmark":"multichallenge","model":"llama-3.1-nemotron-nano-8b-v1","score":16.1,"metric":"percent"},{"benchmark":"multichallenge","model":"qwq-32b","score":37.7,"metric":"percent"},{"benchmark":"multichallenge","model":"o1-mini","score":30.8,"metric":"percent"},{"benchmark":"multichallenge","model":"lg-exaone-32b","score":38.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apriel-nemotron-15b-thinker","score":57.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-nemotron-nano-8b-v1","score":54,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwq-32b","score":66.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o1-mini","score":60,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lg-exaone-32b","score":65.2,"metric":"percent"},{"benchmark":"math500","model":"apriel-nemotron-15b-thinker","score":91.6,"metric":"percent"},{"benchmark":"math500","model":"llama-3.1-nemotron-nano-8b-v1","score":89.6,"metric":"percent"},{"benchmark":"math500","model":"qwq-32b","score":90.8,"metric":"percent"},{"benchmark":"math500","model":"o1-mini","score":90,"metric":"percent"},{"benchmark":"math500","model":"lg-exaone-32b","score":91.6,"metric":"percent"},{"benchmark":"aime-2024","model":"apriel-nemotron-15b-thinker","score":73.3,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.1-nemotron-nano-8b-v1","score":62,"metric":"percent"},{"benchmark":"aime-2024","model":"qwq-32b","score":79.5,"metric":"percent"},{"benchmark":"aime-2024","model":"o1-mini","score":63.6,"metric":"percent"},{"benchmark":"aime-2024","model":"lg-exaone-32b","score":76,"metric":"percent"},{"benchmark":"aime-2025","model":"apriel-nemotron-15b-thinker","score":60,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.1-nemotron-nano-8b-v1","score":48.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwq-32b","score":68.7,"metric":"percent"},{"benchmark":"aime-2025","model":"o1-mini","score":54.8,"metric":"percent"},{"benchmark":"aime-2025","model":"lg-exaone-32b","score":64.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apriel-nemotron-15b-thinker","score":73.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-nemotron-nano-8b-v1","score":61.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwq-32b","score":79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"o1-mini","score":80.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lg-exaone-32b","score":73.9,"metric":"percent"},{"benchmark":"amc-23","model":"apriel-nemotron-15b-thinker","score":95,"metric":"percent"},{"benchmark":"amc-23","model":"llama-3.1-nemotron-nano-8b-v1","score":93.5,"metric":"percent"},{"benchmark":"amc-23","model":"qwq-32b","score":98.5,"metric":"percent"},{"benchmark":"amc-23","model":"o1-mini","score":92.5,"metric":"percent"},{"benchmark":"amc-23","model":"lg-exaone-32b","score":95,"metric":"percent"},{"benchmark":"lmarena-text","model":"gemini-2.5-pro","score":1453,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4-1-20250805-thinking-16k","score":1448,"metric":"elo"},{"benchmark":"lmarena-text","model":"o3-2025-04-16","score":1440,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4.5-preview-2025-02-27","score":1440,"metric":"elo"},{"benchmark":"lmarena-text","model":"chatgpt-4o-latest-20250326","score":1440,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5-high","score":1439,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.1-20250805","score":1439,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-max-preview","score":1433,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4-fast","score":1425,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5-chat","score":1426,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-vl-235b-a22b-instruct","score":1421,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-max-2025-09-23","score":1418,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4-20250514-thinking-16k","score":1420,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4-0709","score":1418,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-235b-a22b-instruct-2507","score":1418,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-r1-0528","score":1417,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k2-0905-preview","score":1416,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.1-thinking","score":1415,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.1-terminus","score":1415,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.1","score":1415,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.1-terminus-thinking","score":1414,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k2-0711-preview","score":1415,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.5-flash-preview-09-2025","score":1410,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4-20250514","score":1411,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-3-preview-02-24","score":1410,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4.1-2025-04-14","score":1409,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-medium-2508","score":1408,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.5-flash","score":1407,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.5","score":1407,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-next-80b-a3b-instruct","score":1402,"metric":"elo"},{"benchmark":"lmarena-text","model":"longcat-flash-chat","score":1399,"metric":"elo"},{"benchmark":"lmarena-text","model":"o1-2024-12-17","score":1399,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-235b-a22b-thinking-2507","score":1397,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-sonnet-4-20250514-thinking-32k","score":1398,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-235b-a22b-no-thinking","score":1398,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-r1","score":1394,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5-mini-high","score":1393,"metric":"elo"},{"benchmark":"lmarena-text","model":"mai-1-preview","score":1392,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-vl-235b-a22b-thinking","score":1387,"metric":"elo"},{"benchmark":"lmarena-text","model":"o4-mini-2025-04-16","score":1391,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3-0324","score":1391,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-sonnet-4-20250514","score":1388,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-t1-20250711","score":1385,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.5-flash-lite-preview-09-2025","score":1383,"metric":"elo"},{"benchmark":"lmarena-text","model":"o1-preview","score":1386,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3-7-sonnet-20250219-thinking-32k","score":1385,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-30b-a3b-instruct-2507","score":1383,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-coder-480b-a35b-instruct","score":1381,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-medium-2505","score":1380,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-turbos-20250416","score":1379,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4.1-mini-2025-04-14","score":1377,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-235b-a22b","score":1372,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-next-80b-a3b-thinking","score":1370,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2.5-max","score":1371,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.5-air","score":1369,"metric":"elo"},{"benchmark":"lmarena-text","model":"minimax-m1","score":1369,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3.5-sonnet-20241022","score":1369,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-3-mini-high","score":1362,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-3-27b-it","score":1362,"metric":"elo"},{"benchmark":"lmarena-text","model":"o3-mini-high","score":1361,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-3-mini-beta","score":1357,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3","score":1356,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-small-2506","score":1351,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.5v","score":1346,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.0-flash-lite-preview-02-05","score":1351,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-pro-002","score":1350,"metric":"elo"},{"benchmark":"lmarena-text","model":"step-3","score":1346,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-turbos-20250226","score":1344,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-nemotron-ultra-253b-v1","score":1344,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-32b","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"o3-mini","score":1347,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-oss-120b","score":1346,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen-plus-0125","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"command-a-03-2025","score":1347,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4-plus-0111","score":1342,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5-nano-high","score":1341,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-3-12b-it","score":1339,"metric":"elo"},{"benchmark":"lmarena-text","model":"nvidia-llama-3.3-nemotron-super-49b-v1.5","score":1339,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-turbo-0110","score":1337,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4o-2024-05-13","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3.5-sonnet-20240620","score":1340,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-405b-instruct-bf16","score":1334,"metric":"elo"},{"benchmark":"lmarena-text","model":"o1-mini","score":1333,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwq-32b","score":1333,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-advanced-0514","score":1332,"metric":"elo"},{"benchmark":"lmarena-text","model":"step-2-16k-exp-202412","score":1331,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4o-2024-08-06","score":1332,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-405b-instruct-fp8","score":1332,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-2-2024-08-13","score":1332,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.3-nemotron-49b-super-v1","score":1323,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-large-2025-02-10","score":1323,"metric":"elo"},{"benchmark":"lmarena-text","model":"yi-lightning","score":1327,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-4-maverick-17b-128e-instruct","score":1325,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-30b-a3b","score":1324,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v2.5-1210","score":1320,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-oss-20b","score":1320,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-turbo-2024-04-09","score":1322,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-4-scout-17b-16e-instruct","score":1320,"metric":"elo"},{"benchmark":"lmarena-text","model":"step-1o-turbo-202506","score":1319,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4.1-nano-2025-04-14","score":1318,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3-opus-20240229","score":1320,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-pro-001","score":1320,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-experimental-chat-05-14","score":1318,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-3n-e4b-it","score":1318,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3.5-haiku-20241022","score":1318,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4-plus","score":1316,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.3-70b-instruct","score":1317,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen-max-0919","score":1315,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2.5-plus-1127","score":1312,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4o-mini-2024-07-18","score":1314,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-standard-2025-02-10","score":1308,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-1106-preview","score":1313,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-0125-preview","score":1312,"metric":"elo"},{"benchmark":"lmarena-text","model":"athene-v2-chat","score":1311,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-large-2407","score":1311,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-flash-002","score":1310,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-3-4b-it","score":1302,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-2-mini-2024-08-13","score":1305,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v2.5","score":1304,"metric":"elo"},{"benchmark":"lmarena-text","model":"athene-70b-0725","score":1303,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-large-2411","score":1303,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2.5-72b-instruct","score":1300,"metric":"elo"},{"benchmark":"lmarena-text","model":"magistral-medium-2506","score":1297,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-small-3.1-24b-instruct-2503","score":1297,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-nemotron-70b-instruct","score":1296,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-large-vision","score":1292,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-70b-instruct","score":1292,"metric":"elo"},{"benchmark":"lmarena-text","model":"jamba-1.5-large","score":1286,"metric":"elo"},{"benchmark":"lmarena-text","model":"reka-core-20240904","score":1286,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-tulu-3-70b","score":1285,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-nemotron-51b-instruct","score":1284,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-pro-v1.0","score":1286,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-0314","score":1285,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2-27b-it","score":1285,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-flash-001","score":1282,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3-sonnet-20240229","score":1280,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2-9b-it-simpo","score":1277,"metric":"elo"},{"benchmark":"lmarena-text","model":"nemotron-4-340b-instruct","score":1277,"metric":"elo"},{"benchmark":"lmarena-text","model":"command-r-plus-08-2024","score":1276,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4-0520","score":1272,"metric":"elo"},{"benchmark":"lmarena-text","model":"reka-flash-20240904","score":1271,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3-70b-instruct","score":1274,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-0613","score":1273,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-small-24b-instruct-2501","score":1271,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2.5-coder-32b-instruct","score":1267,"metric":"elo"},{"benchmark":"lmarena-text","model":"c4ai-aya-expanse-32b","score":1265,"metric":"elo"},{"benchmark":"lmarena-text","model":"command-r-plus","score":1262,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-coder-v2","score":1261,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2-9b-it","score":1262,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2-72b-instruct","score":1261,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3-haiku-20240307","score":1259,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-flash-8b-001","score":1258,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-lite-v1.0","score":1258,"metric":"elo"},{"benchmark":"lmarena-text","model":"olmo-2-0325-32b-instruct","score":1252,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-4","score":1253,"metric":"elo"},{"benchmark":"lmarena-text","model":"command-r-08-2024","score":1250,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-large-2402","score":1241,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-micro-v1.0","score":1240,"metric":"elo"},{"benchmark":"lmarena-text","model":"jamba-1.5-mini","score":1237,"metric":"elo"},{"benchmark":"lmarena-text","model":"ministral-8b-2410","score":1235,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-standard-256k","score":1231,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-110b-chat","score":1233,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-72b-chat","score":1232,"metric":"elo"},{"benchmark":"lmarena-text","model":"reka-flash-21b-20240226-online","score":1232,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-pro-dev-api","score":1232,"metric":"elo"},{"benchmark":"lmarena-text","model":"mixtral-8x22b-instruct-v0.1","score":1229,"metric":"elo"},{"benchmark":"lmarena-text","model":"command-r","score":1227,"metric":"elo"},{"benchmark":"lmarena-text","model":"reka-flash-21b-20240226","score":1225,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-tulu-3-8b","score":1221,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-pro","score":1219,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-medium","score":1223,"metric":"elo"},{"benchmark":"lmarena-text","model":"c4ai-aya-expanse-8b","score":1222,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-3.5-turbo-0125","score":1222,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3-8b-instruct","score":1222,"metric":"elo"},{"benchmark":"lmarena-text","model":"zephyr-orpo-141b-a35b-v0.1","score":1212,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-3.1-8b-instruct","score":1209,"metric":"elo"},{"benchmark":"lmarena-text","model":"yi-1.5-34b-chat","score":1213,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-8b-instruct","score":1210,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-32b-chat","score":1204,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-3.5-turbo-1106","score":1199,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-3-medium-4k-instruct","score":1197,"metric":"elo"},{"benchmark":"lmarena-text","model":"mixtral-8x7b-instruct-v0.1","score":1197,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2-2b-it","score":1196,"metric":"elo"},{"benchmark":"lmarena-text","model":"dbrx-instruct-preview","score":1194,"metric":"elo"},{"benchmark":"lmarena-text","model":"internlm2_5-20b-chat","score":1192,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-14b-chat","score":1192,"metric":"elo"},{"benchmark":"lmarena-text","model":"wizardlm-70b","score":1184,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-llm-67b-chat","score":1183,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-3.1-2b-instruct","score":1180,"metric":"elo"},{"benchmark":"lmarena-text","model":"yi-34b-chat","score":1183,"metric":"elo"},{"benchmark":"lmarena-text","model":"openchat-3.5-0106","score":1181,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-3.0-8b-instruct","score":1181,"metric":"elo"},{"benchmark":"lmarena-text","model":"openchat-3.5","score":1180,"metric":"elo"},{"benchmark":"lmarena-text","model":"tulu-2-dpo-70b","score":1178,"metric":"elo"},{"benchmark":"lmarena-text","model":"openhermes-2.5-mistral-7b","score":1175,"metric":"elo"},{"benchmark":"lmarena-text","model":"snowflake-arctic-instruct","score":1179,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-1.1-7b-it","score":1177,"metric":"elo"},{"benchmark":"lmarena-text","model":"vicuna-33b","score":1172,"metric":"elo"},{"benchmark":"lmarena-text","model":"starling-lm-7b-beta","score":1172,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-3-small-8k-instruct","score":1171,"metric":"elo"},{"benchmark":"lmarena-text","model":"nous-hermes-2-mixtral-8x7b-dpo","score":1165,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-2-70b-chat","score":1171,"metric":"elo"},{"benchmark":"lmarena-text","model":"starling-lm-7b-alpha","score":1167,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.2-3b-instruct","score":1166,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwq-32b-preview","score":1161,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama2-70b-steerlm-chat","score":1157,"metric":"elo"},{"benchmark":"lmarena-text","model":"solar-10.7b-instruct-v1.0","score":1153,"metric":"elo"},{"benchmark":"lmarena-text","model":"dolphin-2.2.1-mistral-7b","score":1151,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-3.0-2b-instruct","score":1155,"metric":"elo"},{"benchmark":"lmarena-text","model":"mpt-30b-chat","score":1149,"metric":"elo"},{"benchmark":"lmarena-text","model":"falcon-180b-chat","score":1145,"metric":"elo"},{"benchmark":"lmarena-text","model":"wizardlm-13b","score":1149,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-7b-instruct-v0.2","score":1150,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-7b-chat","score":1143,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-3-mini-4k-instruct-june-2024","score":1142,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-2-13b-chat","score":1142,"metric":"elo"},{"benchmark":"lmarena-text","model":"vicuna-13b","score":1140,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen-14b-chat","score":1137,"metric":"elo"},{"benchmark":"lmarena-text","model":"codellama-34b-instruct","score":1136,"metric":"elo"},{"benchmark":"lmarena-text","model":"palm-2","score":1134,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-7b-it","score":1132,"metric":"elo"},{"benchmark":"lmarena-text","model":"zephyr-7b-beta","score":1131,"metric":"elo"},{"benchmark":"lmarena-text","model":"zephyr-7b-alpha","score":1128,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-3-mini-128k-instruct","score":1130,"metric":"elo"},{"benchmark":"lmarena-text","model":"guanaco-33b","score":1127,"metric":"elo"},{"benchmark":"lmarena-text","model":"codellama-70b-instruct","score":1118,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-3-mini-4k-instruct","score":1128,"metric":"elo"},{"benchmark":"lmarena-text","model":"stripedhyena-nous-7b","score":1119,"metric":"elo"},{"benchmark":"lmarena-text","model":"smollm2-1.7b-instruct","score":1117,"metric":"elo"},{"benchmark":"lmarena-text","model":"vicuna-7b","score":1114,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.2-1b-instruct","score":1112,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-1.1-2b-it","score":1111,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-7b-instruct","score":1109,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-2-7b-chat","score":1108,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2b-it","score":1088,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-4b-chat","score":1089,"metric":"elo"},{"benchmark":"lmarena-text","model":"olmo-7b-instruct","score":1075,"metric":"elo"},{"benchmark":"lmarena-text","model":"koala-13b","score":1069,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt4all-13b-snoozy","score":1062,"metric":"elo"},{"benchmark":"lmarena-text","model":"alpaca-13b","score":1063,"metric":"elo"},{"benchmark":"lmarena-text","model":"mpt-7b-chat","score":1059,"metric":"elo"},{"benchmark":"lmarena-text","model":"chatglm3-6b","score":1056,"metric":"elo"},{"benchmark":"lmarena-text","model":"rwkv-4-raven-14b","score":1040,"metric":"elo"},{"benchmark":"lmarena-text","model":"chatglm2-6b","score":1024,"metric":"elo"},{"benchmark":"lmarena-text","model":"oasst-pythia-12b","score":1019,"metric":"elo"},{"benchmark":"lmarena-text","model":"chatglm-6b","score":994,"metric":"elo"},{"benchmark":"lmarena-text","model":"fastchat-t5-3b","score":989,"metric":"elo"},{"benchmark":"lmarena-text","model":"dolly-v2-12b","score":975,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-1-13b","score":966,"metric":"elo"},{"benchmark":"lmarena-text","model":"stablelm-tuned-alpha-7b","score":950,"metric":"elo"},{"benchmark":"lmarena-vision","model":"gemini-2.5-pro","score":1242,"metric":"score"},{"benchmark":"lmarena-vision","model":"chatgpt-4o-latest-20250326","score":1235,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4.5-preview-2025-02-27","score":1222,"metric":"score"},{"benchmark":"lmarena-vision","model":"o3-2025-04-16","score":1217,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3-vl-235b-a22b-instruct","score":1210,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.5-flash-preview-09-2025","score":1207,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5-chat","score":1213,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4.1-2025-04-14","score":1208,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.5-flash","score":1205,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4-20250514-thinking-16k","score":1204,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-sonnet-4-20250514-thinking-32k","score":1200,"metric":"score"},{"benchmark":"lmarena-vision","model":"o4-mini-2025-04-16","score":1196,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5-high","score":1195,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4.1-mini-2025-04-14","score":1193,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3-7-sonnet-20250219-thinking-32k","score":1191,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3-vl-235b-a22b-thinking","score":1185,"metric":"score"},{"benchmark":"lmarena-vision","model":"o1-2024-12-17","score":1189,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4-20250514","score":1184,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-sonnet-4-20250514","score":1182,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.5-flash-lite-preview-09-2025","score":1175,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4-0709","score":1179,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen-vl-max-2025-08-13","score":1173,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5-mini-high","score":1174,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-pro-002","score":1174,"metric":"score"},{"benchmark":"lmarena-vision","model":"glm-4.5v","score":1156,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4o-2024-05-13","score":1158,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3.5-sonnet-20241022","score":1157,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-1o-turbo-202506","score":1149,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemma-3-27b-it","score":1149,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-medium-2505","score":1148,"metric":"score"},{"benchmark":"lmarena-vision","model":"hunyuan-large-vision","score":1141,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5-nano-high","score":1144,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3.5-sonnet-20240620","score":1143,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-3","score":1139,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-medium-2508","score":1138,"metric":"score"},{"benchmark":"lmarena-vision","model":"llama-4-maverick-17b-128e-instruct","score":1138,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-flash-002","score":1134,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-small-2506","score":1132,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3.5-haiku-20241022","score":1129,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.0-flash-lite-preview-02-05","score":1129,"metric":"score"},{"benchmark":"lmarena-vision","model":"llama-4-scout-17b-16e-instruct","score":1122,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-1o-vision-32k-highres","score":1119,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-small-3.1-24b-instruct-2503","score":1118,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen2.5-vl-72b-instruct","score":1117,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4o-2024-08-06","score":1115,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen2.5-vl-32b-instruct","score":1111,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-pro-001","score":1113,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4-turbo-2024-04-09","score":1109,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4o-mini-2024-07-18","score":1093,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4.1-nano-2025-04-14","score":1085,"metric":"score"},{"benchmark":"lmarena-vision","model":"pixtral-large-2411","score":1089,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen-vl-max-1119","score":1081,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen2-vl-72b","score":1081,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-flash-8b-001","score":1066,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3-opus-20240229","score":1060,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-1v-32k","score":1057,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-flash-001","score":1056,"metric":"score"},{"benchmark":"lmarena-vision","model":"molmo-72b-0924","score":1044,"metric":"score"},{"benchmark":"lmarena-vision","model":"hunyuan-standard-vision-2024-12-31","score":1040,"metric":"score"},{"benchmark":"lmarena-vision","model":"llama-3.2-vision-90b-instruct","score":1028,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen2-vl-7b-instruct","score":1028,"metric":"score"},{"benchmark":"lmarena-vision","model":"pixtral-12b-2409","score":1020,"metric":"score"},{"benchmark":"lmarena-vision","model":"internvl2-26b","score":1020,"metric":"score"},{"benchmark":"lmarena-vision","model":"amazon-nova-lite-v1.0","score":1017,"metric":"score"},{"benchmark":"lmarena-vision","model":"amazon-nova-pro-v1.0","score":1016,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3-sonnet-20240229","score":1016,"metric":"score"},{"benchmark":"lmarena-vision","model":"yi-vision","score":1000,"metric":"score"},{"benchmark":"lmarena-vision","model":"c4ai-aya-vision-32b","score":996,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3-haiku-20240307","score":999,"metric":"score"},{"benchmark":"lmarena-vision","model":"molmo-7b-d-0924","score":992,"metric":"score"},{"benchmark":"lmarena-vision","model":"nvila-internal-15b-v1","score":984,"metric":"score"},{"benchmark":"lmarena-vision","model":"llama-3.2-vision-11b-instruct","score":987,"metric":"score"},{"benchmark":"lmarena-vision","model":"llava-onevision-qwen2-72b-ov","score":977,"metric":"score"},{"benchmark":"lmarena-vision","model":"llava-1.6-34b","score":963,"metric":"score"},{"benchmark":"lmarena-vision","model":"minicpm-v-2_6","score":961,"metric":"score"},{"benchmark":"lmarena-vision","model":"cogvlm2-llama3-chat-19b","score":960,"metric":"score"},{"benchmark":"lmarena-vision","model":"internvl2-4b","score":953,"metric":"score"},{"benchmark":"lmarena-vision","model":"phi-3.5-vision-instruct","score":919,"metric":"score"},{"benchmark":"lmarena-vision","model":"phi-3-vision-128k-instruct","score":881,"metric":"score"},{"benchmark":"webdev-arena","model":"gpt-5-high","score":1480,"metric":"elo"},{"benchmark":"webdev-arena","model":"claude-opus-4-1-20250805-thinking-16k","score":1468,"metric":"elo"},{"benchmark":"webdev-arena","model":"claude-opus-4.1-20250805","score":1458,"metric":"elo"},{"benchmark":"webdev-arena","model":"gemini-2.5-pro","score":1403,"metric":"elo"},{"benchmark":"webdev-arena","model":"deepseek-r1-0528","score":1393,"metric":"elo"},{"benchmark":"webdev-arena","model":"claude-opus-4-20250514","score":1383,"metric":"elo"},{"benchmark":"webdev-arena","model":"glm-4.5","score":1375,"metric":"elo"},{"benchmark":"webdev-arena","model":"glm-4.5-air","score":1367,"metric":"elo"},{"benchmark":"webdev-arena","model":"deepseek-v3.1-thinking","score":1362,"metric":"elo"},{"benchmark":"webdev-arena","model":"qwen3-coder","score":1366,"metric":"elo"},{"benchmark":"webdev-arena","model":"claude-sonnet-4-20250514","score":1362,"metric":"elo"},{"benchmark":"webdev-arena","model":"claude-3.7-sonnet-20250219","score":1358,"metric":"elo"},{"benchmark":"webdev-arena","model":"deepseek-v3.1","score":1340,"metric":"elo"},{"benchmark":"webdev-arena","model":"qwen3-coder-plus-2025-09-23","score":1332,"metric":"elo"},{"benchmark":"webdev-arena","model":"kimi-k2-instruct","score":1316,"metric":"elo"},{"benchmark":"webdev-arena","model":"gemini-2.5-flash","score":1289,"metric":"elo"},{"benchmark":"webdev-arena","model":"gpt-4.1-2025-04-14","score":1253,"metric":"elo"},{"benchmark":"webdev-arena","model":"claude-3.5-sonnet-20241022","score":1238,"metric":"elo"},{"benchmark":"webdev-arena","model":"deepseek-v3-0324","score":1208,"metric":"elo"},{"benchmark":"webdev-arena","model":"deepseek-r1","score":1199,"metric":"elo"},{"benchmark":"webdev-arena","model":"gpt-4.1-mini-2025-04-14","score":1193,"metric":"elo"},{"benchmark":"webdev-arena","model":"qwen3-235b-a22b","score":1189,"metric":"elo"},{"benchmark":"webdev-arena","model":"o3-2025-04-16","score":1186,"metric":"elo"},{"benchmark":"webdev-arena","model":"mistral-medium-3","score":1181,"metric":"elo"},{"benchmark":"webdev-arena","model":"grok-4-0709","score":1174,"metric":"elo"},{"benchmark":"webdev-arena","model":"grok-code-fast-1","score":1150,"metric":"elo"},{"benchmark":"webdev-arena","model":"grok-3-preview-02-24","score":1143,"metric":"elo"},{"benchmark":"webdev-arena","model":"o3-mini-high","score":1137,"metric":"elo"},{"benchmark":"webdev-arena","model":"claude-3.5-haiku-20241022","score":1133,"metric":"elo"},{"benchmark":"webdev-arena","model":"minimax-m1","score":1129,"metric":"elo"},{"benchmark":"webdev-arena","model":"o4-mini-2025-04-16","score":1118,"metric":"elo"},{"benchmark":"webdev-arena","model":"gpt-oss-120b","score":1094,"metric":"elo"},{"benchmark":"webdev-arena","model":"o3-mini","score":1092,"metric":"elo"},{"benchmark":"webdev-arena","model":"gemini-2.0-pro-exp-02-05","score":1090,"metric":"elo"},{"benchmark":"webdev-arena","model":"o1-2024-12-17","score":1045,"metric":"elo"},{"benchmark":"webdev-arena","model":"o1-mini","score":1043,"metric":"elo"},{"benchmark":"webdev-arena","model":"gemini-2.0-flash-001","score":1040,"metric":"elo"},{"benchmark":"webdev-arena","model":"gemini-2.0-flash-thinking-01-21","score":1030,"metric":"elo"},{"benchmark":"webdev-arena","model":"llama-4-maverick-17b-128e-instruct","score":1027,"metric":"elo"},{"benchmark":"webdev-arena","model":"gemini-2.0-flash-exp","score":980,"metric":"elo"},{"benchmark":"webdev-arena","model":"qwen2.5-max","score":976,"metric":"elo"},{"benchmark":"webdev-arena","model":"gpt-4o-2024-11-20","score":964,"metric":"elo"},{"benchmark":"webdev-arena","model":"deepseek-v3","score":960,"metric":"elo"},{"benchmark":"webdev-arena","model":"qwen2.5-coder-32b-instruct","score":902,"metric":"elo"},{"benchmark":"webdev-arena","model":"llama-4-scout-17b-16e-instruct","score":901,"metric":"elo"},{"benchmark":"webdev-arena","model":"gemini-1.5-pro-002","score":893,"metric":"elo"},{"benchmark":"webdev-arena","model":"llama-3.1-405b-instruct","score":810,"metric":"elo"},{"benchmark":"mmlu-pro","model":"gpt-5-high","score":87.5,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5-high","score":73.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5-high","score":75.6,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5-high","score":30.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-4","score":86.6,"metric":"percent"},{"benchmark":"hle","model":"grok-4","score":23.9,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4","score":92.7,"metric":"percent"},{"benchmark":"ifbench","model":"grok-4","score":53.7,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4.5","score":77.7,"metric":"percent"},{"benchmark":"scicode","model":"claude-sonnet-4.5","score":44.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-sonnet-4.5","score":65.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-4-fast","score":85,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"grok-4-fast","score":84.7,"metric":"percent"},{"benchmark":"hle","model":"grok-4-fast","score":17,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-4-fast","score":83.2,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4-fast","score":89.7,"metric":"percent"},{"benchmark":"ifbench","model":"grok-4-fast","score":50.5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"grok-4-fast","score":17.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"grok-4-fast","score":65.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-pro","score":86.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-pro","score":84.4,"metric":"percent"},{"benchmark":"hle","model":"gemini-2.5-pro","score":21.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":80.1,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-pro","score":87.7,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-2.5-pro","score":48.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-2.5-pro","score":66,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.1","score":89,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.1","score":11.9,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.1","score":65.4,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.1","score":40,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.1","score":80.3,"metric":"percent"},{"benchmark":"ifbench","model":"claude-opus-4.1","score":55.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-opus-4.1","score":66.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-sonnet-4","score":84.2,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4","score":9.6,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4","score":65.5,"metric":"percent"},{"benchmark":"scicode","model":"claude-sonnet-4","score":40,"metric":"percent"},{"benchmark":"ifbench","model":"claude-sonnet-4","score":54.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"magistral-medium-1.2","score":81.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-medium-1.2","score":73.9,"metric":"percent"},{"benchmark":"hle","model":"magistral-medium-1.2","score":9.6,"metric":"percent"},{"benchmark":"scicode","model":"magistral-medium-1.2","score":39.2,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-medium-1.2","score":82,"metric":"percent"},{"benchmark":"ifbench","model":"magistral-medium-1.2","score":43,"metric":"percent"},{"benchmark":"aa-lcr","model":"magistral-medium-1.2","score":51.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"magistral-medium-1.2","score":12.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"magistral-medium-1.2","score":52,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-flash","score":83.2,"metric":"percent"},{"benchmark":"hle","model":"gemini-2.5-flash","score":11.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash","score":69.5,"metric":"percent"},{"benchmark":"scicode","model":"gemini-2.5-flash","score":39.4,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash","score":73.3,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-2.5-flash","score":50.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-2.5-flash","score":61.7,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gemini-2.5-flash","score":12.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash","score":31.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5-minimal","score":80.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-minimal","score":67.3,"metric":"percent"},{"benchmark":"hle","model":"gpt-5-minimal","score":5.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-minimal","score":55.8,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5-minimal","score":38.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-minimal","score":31.7,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5-minimal","score":45.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5-minimal","score":25,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5-minimal","score":17.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b","score":80.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b","score":78.2,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-120b","score":18.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":65.3,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-120b","score":36.2,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":93.4,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-120b","score":69,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-120b","score":50.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.1-terminus","score":85.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.1-terminus","score":79.2,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.1-terminus","score":15.2,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.1-terminus","score":79.8,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v3.1-terminus","score":40.6,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.1-terminus","score":89.7,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v3.1-terminus","score":57,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v3.1-terminus","score":65,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-v3.1-terminus","score":28.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v3.1-terminus","score":37.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-2507","score":84.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-235b-2507","score":79,"metric":"percent"},{"benchmark":"hle","model":"qwen3-235b-2507","score":15,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-2507","score":78.8,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-235b-2507","score":42.4,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-235b-2507","score":91,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-235b-2507","score":51.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-235b-2507","score":67,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"qwen3-235b-2507","score":12.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-235b-2507","score":53.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-0528","score":84.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-0528","score":81.3,"metric":"percent"},{"benchmark":"hle","model":"deepseek-r1-0528","score":14.9,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-0528","score":77,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-r1-0528","score":40.3,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0528","score":76.8,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-r1-0528","score":39.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-r1-0528","score":54.7,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-r1-0528","score":14.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-r1-0528","score":36.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2-0905","score":81.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2-0905","score":76.7,"metric":"percent"},{"benchmark":"hle","model":"kimi-k2-0905","score":6.3,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-0905","score":61,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k2-0905","score":30.7,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2-0905","score":57.3,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2-0905","score":41.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2-0905","score":52.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"kimi-k2-0905","score":22.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2-0905","score":73.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5","score":83.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.5","score":78.2,"metric":"percent"},{"benchmark":"hle","model":"glm-4.5","score":12.2,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5","score":73.8,"metric":"percent"},{"benchmark":"scicode","model":"glm-4.5","score":34.8,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.5","score":73.7,"metric":"percent"},{"benchmark":"ifbench","model":"glm-4.5","score":44.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-4.5","score":48.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-4.5","score":24.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-air","score":81.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.5-air","score":73.3,"metric":"percent"},{"benchmark":"hle","model":"glm-4.5-air","score":6.8,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-air","score":68.4,"metric":"percent"},{"benchmark":"scicode","model":"glm-4.5-air","score":30.6,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.5-air","score":80.7,"metric":"percent"},{"benchmark":"ifbench","model":"glm-4.5-air","score":37.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-4.5-air","score":43.7,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"glm-4.5-air","score":19.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-4.5-air","score":46.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-maverick","score":80.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-4-maverick","score":67.1,"metric":"percent"},{"benchmark":"hle","model":"llama-4-maverick","score":4.8,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-4-maverick","score":39.7,"metric":"percent"},{"benchmark":"scicode","model":"llama-4-maverick","score":33.1,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-4-maverick","score":19.3,"metric":"percent"},{"benchmark":"ifbench","model":"llama-4-maverick","score":43,"metric":"percent"},{"benchmark":"aa-lcr","model":"llama-4-maverick","score":46,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"llama-4-maverick","score":6.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"llama-4-maverick","score":17.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-next-80b-a3b","score":82.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-next-80b-a3b","score":75.9,"metric":"percent"},{"benchmark":"hle","model":"qwen3-next-80b-a3b","score":11.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b","score":78.4,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-next-80b-a3b","score":38.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-next-80b-a3b","score":84.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-next-80b-a3b","score":60.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-next-80b-a3b","score":60.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"qwen3-next-80b-a3b","score":9.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-next-80b-a3b","score":41.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b","score":73.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b","score":61.7,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-20b","score":8.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b","score":57.2,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-20b","score":35.4,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b","score":61.7,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b","score":60.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-20b","score":18.7,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-oss-20b","score":5.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-20b","score":49.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-nemotron-super-49b-v1.5","score":82.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-nemotron-super-49b-v1.5","score":74.8,"metric":"percent"},{"benchmark":"hle","model":"llama-nemotron-super-49b-v1.5","score":6.8,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-nemotron-super-49b-v1.5","score":77,"metric":"percent"},{"benchmark":"scicode","model":"llama-nemotron-super-49b-v1.5","score":34,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-nemotron-super-49b-v1.5","score":76.7,"metric":"percent"},{"benchmark":"ifbench","model":"llama-nemotron-super-49b-v1.5","score":37,"metric":"percent"},{"benchmark":"aa-lcr","model":"llama-nemotron-super-49b-v1.5","score":34,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"llama-nemotron-super-49b-v1.5","score":5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"llama-nemotron-super-49b-v1.5","score":28.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b-2507","score":74.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b-2507","score":66.7,"metric":"percent"},{"benchmark":"hle","model":"qwen3-4b-2507","score":5.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-2507","score":64.1,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-4b-2507","score":25.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-2507","score":82.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-4b-2507","score":49.8,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-4b-2507","score":37.7,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"qwen3-4b-2507","score":1.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-4b-2507","score":25.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"magistral-small-1.2","score":76.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-small-1.2","score":66.3,"metric":"percent"},{"benchmark":"hle","model":"magistral-small-1.2","score":6.1,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-small-1.2","score":72.3,"metric":"percent"},{"benchmark":"scicode","model":"magistral-small-1.2","score":35.2,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-small-1.2","score":80.3,"metric":"percent"},{"benchmark":"ifbench","model":"magistral-small-1.2","score":44.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"magistral-small-1.2","score":16.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"magistral-small-1.2","score":4.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"magistral-small-1.2","score":27.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-4.0-32b","score":81.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"exaone-4.0-32b","score":73.9,"metric":"percent"},{"benchmark":"hle","model":"exaone-4.0-32b","score":10.5,"metric":"percent"},{"benchmark":"livecodebench","model":"exaone-4.0-32b","score":74.7,"metric":"percent"},{"benchmark":"scicode","model":"exaone-4.0-32b","score":34.4,"metric":"percent"},{"benchmark":"aime-2025","model":"exaone-4.0-32b","score":80,"metric":"percent"},{"benchmark":"ifbench","model":"exaone-4.0-32b","score":36.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"exaone-4.0-32b","score":3.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"exaone-4.0-32b","score":31.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apriel-1.5-15b-thinker","score":77.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apriel-1.5-15b-thinker","score":71.3,"metric":"percent"},{"benchmark":"hle","model":"apriel-1.5-15b-thinker","score":12,"metric":"percent"},{"benchmark":"livecodebench","model":"apriel-1.5-15b-thinker","score":72.8,"metric":"percent"},{"benchmark":"scicode","model":"apriel-1.5-15b-thinker","score":34.8,"metric":"percent"},{"benchmark":"aime-2025","model":"apriel-1.5-15b-thinker","score":87.5,"metric":"percent"},{"benchmark":"ifbench","model":"apriel-1.5-15b-thinker","score":61.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"apriel-1.5-15b-thinker","score":20,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"apriel-1.5-15b-thinker","score":9.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"apriel-1.5-15b-thinker","score":68.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apriel-1.5-15b-thinker-self-reported","score":76.48,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apriel-1.5-15b-thinker-self-reported","score":70.61,"metric":"percent"},{"benchmark":"hle","model":"apriel-1.5-15b-thinker-self-reported","score":11,"metric":"percent"},{"benchmark":"livecodebench","model":"apriel-1.5-15b-thinker-self-reported","score":71.6,"metric":"percent"},{"benchmark":"scicode","model":"apriel-1.5-15b-thinker-self-reported","score":36.46,"metric":"percent"},{"benchmark":"aime-2025","model":"apriel-1.5-15b-thinker-self-reported","score":83.67,"metric":"percent"},{"benchmark":"ifbench","model":"apriel-1.5-15b-thinker-self-reported","score":60.45,"metric":"percent"},{"benchmark":"aa-lcr","model":"apriel-1.5-15b-thinker-self-reported","score":26.33,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"apriel-1.5-15b-thinker-self-reported","score":5.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"apriel-1.5-15b-thinker-self-reported","score":57.8,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-1.7b","score":48.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-1.7b","score":36.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-1.7b","score":22.19,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen3-1.7b","score":56.13,"metric":"percent"},{"benchmark":"brumo25","model":"qwen3-1.7b","score":44.06,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-120b","score":96.6,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-20b","score":96,"metric":"percent"},{"benchmark":"aime-2024","model":"o4-mini","score":93.4,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-235b-a22b","score":85.7,"metric":"percent"},{"benchmark":"aime-2024","model":"o1","score":83.3,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-3.7-sonnet","score":80,"metric":"percent"},{"benchmark":"aime-2024","model":"kimi-k2","score":69.6,"metric":"percent"},{"benchmark":"aime-2024","model":"grok-3","score":52.2,"metric":"percent"},{"benchmark":"aime-2024","model":"nemotron-1.5b","score":61.77,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-1.5b","score":49.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"nemotron-1.5b","score":31.56,"metric":"percent"},{"benchmark":"olympiadbench","model":"nemotron-1.5b","score":64.62,"metric":"percent"},{"benchmark":"brumo25","model":"nemotron-1.5b","score":58.23,"metric":"percent"},{"benchmark":"aime-2024","model":"questa-nemotron-1.5b","score":72.5,"metric":"percent"},{"benchmark":"aime-2025","model":"questa-nemotron-1.5b","score":62.29,"metric":"percent"},{"benchmark":"hmmt-2025","model":"questa-nemotron-1.5b","score":41.67,"metric":"percent"},{"benchmark":"olympiadbench","model":"questa-nemotron-1.5b","score":70.36,"metric":"percent"},{"benchmark":"brumo25","model":"questa-nemotron-1.5b","score":69.48,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-distill-32b","score":72.6,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-distill-32b","score":51.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-r1-distill-32b","score":33,"metric":"percent"},{"benchmark":"olympiadbench","model":"deepseek-r1-distill-32b","score":65,"metric":"percent"},{"benchmark":"brumo25","model":"deepseek-r1-distill-32b","score":68,"metric":"percent"},{"benchmark":"math500","model":"llama-3.1-nemotron-nano-8b-v1","score":95.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-nemotron-nano-8b-v1","score":54.1,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"llama-3.1-nemotron-nano-8b-v1","score":63.9,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-nemotron-nano-8b-v1","score":84.6,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-h-small","score":78.44,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-h-small","score":55.47,"metric":"percent"},{"benchmark":"bbh","model":"granite-4.0-h-small","score":81.62,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.0-h-small","score":70.63,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.0-h-small","score":40.63,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-4.0-h-small","score":42.48,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-small","score":89.87,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-small","score":85.22,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-small","score":87.55,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-4.0-h-small","score":46.48,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-h-small","score":87.27,"metric":"percent"},{"benchmark":"gsm-symbolic","model":"granite-4.0-h-small","score":87.38,"metric":"percent"},{"benchmark":"minerva-math","model":"granite-4.0-h-small","score":74,"metric":"percent"},{"benchmark":"deepmind-math","model":"granite-4.0-h-small","score":59.33,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.0-h-small","score":88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.0-h-small","score":83,"metric":"percent"},{"benchmark":"mbpp","model":"granite-4.0-h-small","score":84,"metric":"percent"},{"benchmark":"mbpp-plus","model":"granite-4.0-h-small","score":71,"metric":"percent"},{"benchmark":"crux-o","model":"granite-4.0-h-small","score":50.25,"metric":"percent"},{"benchmark":"bigcodebench","model":"granite-4.0-h-small","score":46.23,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.0-h-small","score":64.69,"metric":"percent"},{"benchmark":"multipl-e","model":"granite-4.0-h-small","score":57.37,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.0-h-small","score":69.69,"metric":"percent"},{"benchmark":"include","model":"granite-4.0-h-small","score":63.97,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.0-h-small","score":38.72,"metric":"percent"},{"benchmark":"salad-bench","model":"granite-4.0-h-small","score":97.3,"metric":"percent"},{"benchmark":"attaq","model":"granite-4.0-h-small","score":86.64,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-micro","score":65.98,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-micro","score":44.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-micro","score":44.7,"metric":"percent"},{"benchmark":"bbh","model":"granite-4.0-micro","score":72.48,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.0-micro","score":64.29,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.0-micro","score":30.14,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-4.0-micro","score":29.49,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-micro","score":85.5,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-micro","score":79.12,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-micro","score":82.31,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-4.0-micro","score":25.84,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-micro","score":85.45,"metric":"percent"},{"benchmark":"gsm-symbolic","model":"granite-4.0-micro","score":79.82,"metric":"percent"},{"benchmark":"minerva-math","model":"granite-4.0-micro","score":62.06,"metric":"percent"},{"benchmark":"deepmind-math","model":"granite-4.0-micro","score":44.56,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.0-micro","score":80,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.0-micro","score":72,"metric":"percent"},{"benchmark":"mbpp","model":"granite-4.0-micro","score":72,"metric":"percent"},{"benchmark":"mbpp-plus","model":"granite-4.0-micro","score":64,"metric":"percent"},{"benchmark":"crux-o","model":"granite-4.0-micro","score":41.5,"metric":"percent"},{"benchmark":"bigcodebench","model":"granite-4.0-micro","score":39.21,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.0-micro","score":59.98,"metric":"percent"},{"benchmark":"multipl-e","model":"granite-4.0-micro","score":49.21,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.0-micro","score":55.14,"metric":"percent"},{"benchmark":"include","model":"granite-4.0-micro","score":51.62,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.0-micro","score":28.56,"metric":"percent"},{"benchmark":"salad-bench","model":"granite-4.0-micro","score":97.06,"metric":"percent"},{"benchmark":"attaq","model":"granite-4.0-micro","score":86.05,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-h-micro","score":67.43,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-h-micro","score":43.48,"metric":"percent"},{"benchmark":"bbh","model":"granite-4.0-h-micro","score":69.36,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.0-h-micro","score":59,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.0-h-micro","score":32.15,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-4.0-h-micro","score":30.23,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-micro","score":82.72,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-micro","score":76.09,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-micro","score":79.41,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-4.0-h-micro","score":24.19,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-h-micro","score":86.92,"metric":"percent"},{"benchmark":"gsm-symbolic","model":"granite-4.0-h-micro","score":82.27,"metric":"percent"},{"benchmark":"minerva-math","model":"granite-4.0-h-micro","score":64.06,"metric":"percent"},{"benchmark":"deepmind-math","model":"granite-4.0-h-micro","score":46.44,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.0-h-micro","score":82,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.0-h-micro","score":75,"metric":"percent"},{"benchmark":"mbpp","model":"granite-4.0-h-micro","score":74,"metric":"percent"},{"benchmark":"mbpp-plus","model":"granite-4.0-h-micro","score":66,"metric":"percent"},{"benchmark":"crux-o","model":"granite-4.0-h-micro","score":45.5,"metric":"percent"},{"benchmark":"bigcodebench","model":"granite-4.0-h-micro","score":40.84,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.0-h-micro","score":58.21,"metric":"percent"},{"benchmark":"multipl-e","model":"granite-4.0-h-micro","score":48.91,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.0-h-micro","score":57.37,"metric":"percent"},{"benchmark":"include","model":"granite-4.0-h-micro","score":51.1,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.0-h-micro","score":28.76,"metric":"percent"},{"benchmark":"salad-bench","model":"granite-4.0-h-micro","score":96.77,"metric":"percent"},{"benchmark":"attaq","model":"granite-4.0-h-micro","score":83.72,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-h-tiny","score":68.65,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-h-tiny","score":44.94,"metric":"percent"},{"benchmark":"bbh","model":"granite-4.0-h-tiny","score":66.34,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.0-h-tiny","score":62.15,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.0-h-tiny","score":32.59,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-4.0-h-tiny","score":30.47,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-tiny","score":81.38,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-tiny","score":75.52,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-tiny","score":78.45,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-4.0-h-tiny","score":25.52,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-h-tiny","score":84.69,"metric":"percent"},{"benchmark":"gsm-symbolic","model":"granite-4.0-h-tiny","score":81.45,"metric":"percent"},{"benchmark":"minerva-math","model":"granite-4.0-h-tiny","score":63.32,"metric":"percent"},{"benchmark":"deepmind-math","model":"granite-4.0-h-tiny","score":46,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.0-h-tiny","score":80,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.0-h-tiny","score":74,"metric":"percent"},{"benchmark":"mbpp","model":"granite-4.0-h-tiny","score":73,"metric":"percent"},{"benchmark":"mbpp","model":"rnd1-base-0910","score":65.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-30b-a3b","score":74.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"granite-4.0-h-tiny","score":66,"metric":"percent"},{"benchmark":"crux-o","model":"granite-4.0-h-tiny","score":43,"metric":"percent"},{"benchmark":"bigcodebench","model":"granite-4.0-h-tiny","score":40.92,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.0-h-tiny","score":55.93,"metric":"percent"},{"benchmark":"multipl-e","model":"granite-4.0-h-tiny","score":47.26,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.0-h-tiny","score":56.59,"metric":"percent"},{"benchmark":"include","model":"granite-4.0-h-tiny","score":51.06,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.0-h-tiny","score":28.64,"metric":"percent"},{"benchmark":"salad-bench","model":"granite-4.0-h-tiny","score":96.77,"metric":"percent"},{"benchmark":"attaq","model":"granite-4.0-h-tiny","score":83.72,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.3-2b-instruct","score":52.51,"metric":"percent"},{"benchmark":"drop","model":"granite-3.3-2b-instruct","score":35.98,"metric":"percent"},{"benchmark":"humaneval","model":"granite-3.3-2b-instruct","score":80.51,"metric":"percent"},{"benchmark":"ifeval","model":"granite-3.3-2b-instruct","score":65.8,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.3-8b-instruct","score":59.01,"metric":"percent"},{"benchmark":"drop","model":"granite-3.3-8b-instruct","score":41.53,"metric":"percent"},{"benchmark":"humaneval","model":"granite-3.3-8b-instruct","score":89.73,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-4.0-tiny-preview","score":26.7,"metric":"percent"},{"benchmark":"arena-hard","model":"jamba-mini-1.6","score":51.2,"metric":"percent"},{"benchmark":"arena-hard","model":"ministral-8b","score":41.35,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3.1-8b","score":28.17,"metric":"percent"},{"benchmark":"arena-hard","model":"command-r7b","score":27.95,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-4.0-tiny-preview","score":35.16,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-tiny-preview","score":60.4,"metric":"percent"},{"benchmark":"popqa","model":"granite-4.0-tiny-preview","score":22.93,"metric":"percent"},{"benchmark":"truthfulqa","model":"granite-4.0-tiny-preview","score":58.07,"metric":"percent"},{"benchmark":"bbh","model":"granite-4.0-tiny-preview","score":55.71,"metric":"percent"},{"benchmark":"bbh","model":"rnd1-base-0910","score":67.5,"metric":"percent"},{"benchmark":"bbh","model":"dream-7b-instruct","score":57.9,"metric":"percent"},{"benchmark":"bbh","model":"llada-8b-instruct","score":47.4,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-30b-a3b","score":81.5,"metric":"percent"},{"benchmark":"drop","model":"granite-4.0-tiny-preview","score":46.22,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-tiny-preview","score":70.05,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.0-tiny-preview","score":82.41,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.0-tiny-preview","score":78.33,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-tiny-preview","score":63.03,"metric":"percent"},{"benchmark":"attaq","model":"granite-4.0-tiny-preview","score":86.1,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2.5-vl-72b-instruct","score":70.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2.5-vl-72b-instruct","score":51.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2.5-vl-72b-instruct","score":74.8,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2.5-vl-72b-instruct","score":38.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen2.5-vl-72b-instruct","score":57.6,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen2.5-vl-72b-instruct","score":18,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen2.5-vl-72b-instruct","score":88.6,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2.5-vl-72b-instruct","score":75.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2.5-vl-72b-instruct","score":70.8,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen2.5-vl-72b-instruct","score":58.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2.5-vl-72b-instruct","score":58.1,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"qwen2.5-vl-72b-instruct","score":7.6,"metric":"score"},{"benchmark":"miabench","model":"qwen2.5-vl-72b-instruct","score":90.7,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2.5-vl-72b-instruct","score":96.4,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2.5-vl-72b-instruct","score":87.3,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2.5-vl-72b-instruct","score":88.7,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2.5-vl-72b-instruct","score":88.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen2.5-vl-72b-instruct","score":61.5,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen2.5-vl-72b-instruct","score":63.7,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen2.5-vl-72b-instruct","score":79.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2.5-vl-72b-instruct","score":87.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2.5-vl-72b-instruct","score":49.7,"metric":"percent"},{"benchmark":"countbench","model":"qwen2.5-vl-72b-instruct","score":93.6,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen2.5-vl-72b-instruct","score":43.1,"metric":"percent"},{"benchmark":"arkitscenes","model":"qwen2.5-vl-72b-instruct","score":61.5,"metric":"percent"},{"benchmark":"hypersim","model":"qwen2.5-vl-72b-instruct","score":34.7,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen2.5-vl-72b-instruct","score":41,"metric":"percent"},{"benchmark":"blink","model":"qwen2.5-vl-72b-instruct","score":64.4,"metric":"percent"},{"benchmark":"muirbench","model":"qwen2.5-vl-72b-instruct","score":70.7,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen2.5-vl-72b-instruct","score":30.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen2.5-vl-72b-instruct","score":72.1,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen2.5-vl-72b-instruct","score":72.1,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen2.5-vl-72b-instruct","score":44.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen2.5-vl-72b-instruct","score":70.4,"metric":"percent"},{"benchmark":"video-mme","model":"qwen2.5-vl-72b-instruct","score":73.3,"metric":"percent"},{"benchmark":"mlvu","model":"qwen2.5-vl-72b-instruct","score":71.4,"metric":"percent"},{"benchmark":"lvbench","model":"qwen2.5-vl-72b-instruct","score":47.3,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen2.5-vl-72b-instruct","score":50.9,"metric":"percent"},{"benchmark":"videommmu","model":"qwen2.5-vl-72b-instruct","score":60.2,"metric":"percent"},{"benchmark":"screenspot","model":"qwen2.5-vl-72b-instruct","score":87.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2.5-vl-72b-instruct","score":43.6,"metric":"percent"},{"benchmark":"osworld","model":"qwen2.5-vl-72b-instruct","score":35,"metric":"percent"},{"benchmark":"androidworld","model":"qwen2.5-vl-72b-instruct","score":35,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen2.5-vl-72b-instruct","score":8.8,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen2.5-vl-72b-instruct","score":69.1,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen2.5-vl-72b-instruct","score":68,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-mini-minimal","score":67.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-mini-minimal","score":53.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-5-mini-minimal","score":59.6,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-mini-minimal","score":46.6,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gpt-5-mini-minimal","score":36.5,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gpt-5-mini-minimal","score":24.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gpt-5-mini-minimal","score":78.5,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5-mini-minimal","score":73.3,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-mini-minimal","score":64.1,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5-mini-minimal","score":53,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5-mini-minimal","score":55.9,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"gpt-5-mini-minimal","score":7.4,"metric":"score"},{"benchmark":"miabench","model":"gpt-5-mini-minimal","score":92.3,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5-mini-minimal","score":91,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-5-mini-minimal","score":73,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-mini-minimal","score":80.7,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5-mini-minimal","score":80.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gpt-5-mini-minimal","score":61.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gpt-5-mini-minimal","score":61.6,"metric":"percent"},{"benchmark":"cc-ocr","model":"gpt-5-mini-minimal","score":61.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5-mini-minimal","score":78.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5-mini-minimal","score":48.9,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5-mini-minimal","score":84.1,"metric":"percent"},{"benchmark":"odinw-13","model":"gpt-5-mini-minimal","score":43.6,"metric":"percent"},{"benchmark":"arkitscenes","model":"gpt-5-mini-minimal","score":45.8,"metric":"percent"},{"benchmark":"hypersim","model":"gpt-5-mini-minimal","score":39.3,"metric":"percent"},{"benchmark":"sunrgbd","model":"gpt-5-mini-minimal","score":45.8,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-mini-minimal","score":56.7,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-5-mini-minimal","score":57.5,"metric":"percent"},{"benchmark":"vsi-bench","model":"gpt-5-mini-minimal","score":45.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5-mini-minimal","score":72.1,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5-mini-minimal","score":27.7,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-5-mini-minimal","score":44.6,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-5-mini-minimal","score":71,"metric":"percent"},{"benchmark":"video-mme","model":"gpt-5-mini-minimal","score":71.1,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5-mini-minimal","score":71.7,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-5-mini-minimal","score":68,"metric":"percent"},{"benchmark":"charades-sta","model":"gpt-5-mini-minimal","score":50.9,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5-mini-minimal","score":56.7,"metric":"percent"},{"benchmark":"screenspot","model":"gpt-5-mini-minimal","score":66.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5-mini-minimal","score":43.6,"metric":"percent"},{"benchmark":"osworld","model":"gpt-5-mini-minimal","score":30.5,"metric":"percent"},{"benchmark":"androidworld","model":"gpt-5-mini-minimal","score":30.5,"metric":"percent"},{"benchmark":"osworld-g","model":"gpt-5-mini-minimal","score":37.7,"metric":"percent"},{"benchmark":"hrbench4k","model":"gpt-5-mini-minimal","score":67.6,"metric":"percent"},{"benchmark":"hrbench8k","model":"gpt-5-mini-minimal","score":66.3,"metric":"percent"},{"benchmark":"mmmu","model":"claude-sonnet-4","score":75.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-sonnet-4","score":56.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-sonnet-4","score":72.4,"metric":"percent"},{"benchmark":"mathvision","model":"claude-sonnet-4","score":52.7,"metric":"percent"},{"benchmark":"mathverse-mini","model":"claude-sonnet-4","score":65.9,"metric":"percent"},{"benchmark":"zerobench-sub","model":"claude-sonnet-4","score":24.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"claude-sonnet-4","score":82.4,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-sonnet-4","score":68.1,"metric":"percent"},{"benchmark":"mmstar","model":"claude-sonnet-4","score":67.4,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-sonnet-4","score":52.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-sonnet-4","score":54.5,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"claude-sonnet-4","score":7.5,"metric":"score"},{"benchmark":"miabench","model":"claude-sonnet-4","score":89.4,"metric":"percent"},{"benchmark":"docvqa","model":"claude-sonnet-4","score":54,"metric":"percent"},{"benchmark":"infovqa","model":"claude-sonnet-4","score":30,"metric":"percent"},{"benchmark":"ai2d","model":"claude-sonnet-4","score":82.4,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-sonnet-4","score":74.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"claude-sonnet-4","score":44.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"claude-sonnet-4","score":36.2,"metric":"percent"},{"benchmark":"cc-ocr","model":"claude-sonnet-4","score":67.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-sonnet-4","score":87.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-sonnet-4","score":60.9,"metric":"percent"},{"benchmark":"countbench","model":"claude-sonnet-4","score":91.5,"metric":"percent"},{"benchmark":"odinw-13","model":"claude-sonnet-4","score":44.6,"metric":"percent"},{"benchmark":"arkitscenes","model":"claude-sonnet-4","score":36.2,"metric":"percent"},{"benchmark":"hypersim","model":"claude-sonnet-4","score":39.3,"metric":"percent"},{"benchmark":"sunrgbd","model":"claude-sonnet-4","score":42.2,"metric":"percent"},{"benchmark":"blink","model":"claude-sonnet-4","score":59.9,"metric":"percent"},{"benchmark":"muirbench","model":"claude-sonnet-4","score":66.6,"metric":"percent"},{"benchmark":"vsi-bench","model":"claude-sonnet-4","score":37.7,"metric":"percent"},{"benchmark":"embspatialbench","model":"claude-sonnet-4","score":67.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"claude-sonnet-4","score":67.5,"metric":"percent"},{"benchmark":"robospatialhome","model":"claude-sonnet-4","score":70.2,"metric":"percent"},{"benchmark":"mvbench","model":"claude-sonnet-4","score":71.6,"metric":"percent"},{"benchmark":"video-mme","model":"claude-sonnet-4","score":71.6,"metric":"percent"},{"benchmark":"mlvu","model":"claude-sonnet-4","score":68,"metric":"percent"},{"benchmark":"lvbench","model":"claude-sonnet-4","score":50.6,"metric":"percent"},{"benchmark":"charades-sta","model":"claude-sonnet-4","score":50.6,"metric":"percent"},{"benchmark":"videommmu","model":"claude-sonnet-4","score":67.3,"metric":"percent"},{"benchmark":"screenspot","model":"claude-sonnet-4","score":70.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-sonnet-4","score":44.6,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2-8b-a1b","score":64.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2-8b-a1b","score":37.42,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2-8b-a1b","score":29.29,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-8b-a1b","score":77.58,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-8b-a1b","score":25.85,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2-8b-a1b","score":58.19,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2-2.6b","score":64.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2-2.6b","score":25.96,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-distill-qwen-1.5b","score":27,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2-2.6b","score":26.57,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-2.6b","score":79.56,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2-2.6b","score":60.26,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.2-3b-instruct","score":60.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-3b-instruct","score":22.25,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-3b","score":35,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.2-3b-instruct","score":30.6,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.2-3b-instruct","score":71.43,"metric":"percent"},{"benchmark":"multi-if","model":"llama-3.2-3b-instruct","score":50.91,"metric":"percent"},{"benchmark":"mmlu","model":"smollm3-3b","score":59.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm3-3b","score":23.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-4-mini","score":47,"metric":"percent"},{"benchmark":"gpqa","model":"smollm3-3b","score":26.31,"metric":"percent"},{"benchmark":"ifeval","model":"smollm3-3b","score":72.44,"metric":"percent"},{"benchmark":"multi-if","model":"smollm3-3b","score":58.86,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-4b-it","score":58.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-4b-it","score":34.76,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-4b","score":42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"jamba-reasoning-3b","score":61,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3-4b-it","score":29.51,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-4b-it","score":76.85,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-3-4b-it","score":23.53,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-3-4b-it","score":66.61,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-4b-instruct-2507","score":72.25,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b-instruct-2507","score":52.31,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-4b-instruct-2507","score":34.85,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b-instruct-2507","score":85.62,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-4b-instruct-2507","score":30.28,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-4b-instruct-2507","score":75.54,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-h-tiny","score":66.79,"metric":"percent"},{"benchmark":"mmlu","model":"rnd1-base-0910","score":69.6,"metric":"percent"},{"benchmark":"mmlu","model":"dream-7b-instruct","score":69.5,"metric":"percent"},{"benchmark":"mmlu","model":"llada-8b-instruct","score":65.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b","score":79.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-h-tiny","score":32.03,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.0-h-tiny","score":26.46,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-tiny","score":81.06,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.0-h-tiny","score":18.37,"metric":"percent"},{"benchmark":"multi-if","model":"granite-4.0-h-tiny","score":52.99,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2-8b-a1b","score":84.38,"metric":"percent"},{"benchmark":"gsm-plus","model":"lfm2-8b-a1b","score":64.76,"metric":"percent"},{"benchmark":"math500","model":"lfm2-8b-a1b","score":74.2,"metric":"percent"},{"benchmark":"math-lvl5","model":"lfm2-8b-a1b","score":62.38,"metric":"percent"},{"benchmark":"mgsm","model":"lfm2-8b-a1b","score":72.4,"metric":"percent"},{"benchmark":"mmmlu","model":"lfm2-8b-a1b","score":55.26,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2-2.6b","score":82.41,"metric":"percent"},{"benchmark":"gsm-plus","model":"lfm2-2.6b","score":60.75,"metric":"percent"},{"benchmark":"math500","model":"lfm2-2.6b","score":63.6,"metric":"percent"},{"benchmark":"math-lvl5","model":"lfm2-2.6b","score":54.38,"metric":"percent"},{"benchmark":"mgsm","model":"lfm2-2.6b","score":74.32,"metric":"percent"},{"benchmark":"mmmlu","model":"lfm2-2.6b","score":55.39,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-3b-instruct","score":75.21,"metric":"percent"},{"benchmark":"gsm-plus","model":"llama-3.2-3b-instruct","score":38.68,"metric":"percent"},{"benchmark":"math500","model":"llama-3.2-3b-instruct","score":41.2,"metric":"percent"},{"benchmark":"math-lvl5","model":"llama-3.2-3b-instruct","score":24.06,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.2-3b-instruct","score":61.68,"metric":"percent"},{"benchmark":"mmmlu","model":"llama-3.2-3b-instruct","score":47.92,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm3-3b","score":81.12,"metric":"percent"},{"benchmark":"gsm-plus","model":"smollm3-3b","score":58.91,"metric":"percent"},{"benchmark":"math500","model":"smollm3-3b","score":73.6,"metric":"percent"},{"benchmark":"math-lvl5","model":"smollm3-3b","score":51.93,"metric":"percent"},{"benchmark":"mgsm","model":"smollm3-3b","score":68.72,"metric":"percent"},{"benchmark":"mmmlu","model":"smollm3-3b","score":50.02,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-4b-it","score":89.92,"metric":"percent"},{"benchmark":"gsm-plus","model":"gemma-3-4b-it","score":68.38,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-4b-it","score":73.2,"metric":"percent"},{"benchmark":"math-lvl5","model":"gemma-3-4b-it","score":52.18,"metric":"percent"},{"benchmark":"mgsm","model":"gemma-3-4b-it","score":87.28,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-3-4b-it","score":50.14,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-4b-instruct-2507","score":68.46,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3-4b-instruct-2507","score":56.16,"metric":"percent"},{"benchmark":"math500","model":"qwen3-4b-instruct-2507","score":85.6,"metric":"percent"},{"benchmark":"math-lvl5","model":"qwen3-4b-instruct-2507","score":73.62,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-4b-instruct-2507","score":81.76,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-4b-instruct-2507","score":60.67,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-h-tiny","score":82.64,"metric":"percent"},{"benchmark":"gsm8k","model":"rnd1-base-0910","score":80,"metric":"percent"},{"benchmark":"gsm8k","model":"dream-7b-instruct","score":77.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llada-8b-instruct","score":70.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b","score":85.2,"metric":"percent"},{"benchmark":"gsm-plus","model":"granite-4.0-h-tiny","score":59.14,"metric":"percent"},{"benchmark":"math500","model":"granite-4.0-h-tiny","score":58.2,"metric":"percent"},{"benchmark":"math-lvl5","model":"granite-4.0-h-tiny","score":36.11,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.0-h-tiny","score":73.68,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.0-h-tiny","score":56.13,"metric":"percent"},{"benchmark":"livecodebench","model":"lfm2-8b-a1b","score":21.04,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"lfm2-8b-a1b","score":21.36,"metric":"percent"},{"benchmark":"humaneval-plus","model":"lfm2-8b-a1b","score":69.51,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"lfm2-8b-a1b","score":44.22,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-1b-it","score":4.27,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemma-3-1b-it","score":4.43,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gemma-3-1b-it","score":41.67,"metric":"percent"},{"benchmark":"livecodebench","model":"granite-4.0-h-tiny","score":26.73,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"granite-4.0-h-tiny","score":27.27,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.0-h-tiny","score":73.78,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"granite-4.0-h-tiny","score":32.6,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.2-1b-instruct","score":4.08,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"llama-3.2-1b-instruct","score":3.64,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.2-1b-instruct","score":23.17,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"llama-3.2-1b-instruct","score":31.43,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-1.5b-instruct","score":11.18,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen2.5-1.5b-instruct","score":10.57,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-1.5b-instruct","score":48.78,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen2.5-1.5b-instruct","score":22.18,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-1.7b","score":24.07,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-1.7b","score":26.48,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-1.7b","score":60.98,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-1.7b","score":31.56,"metric":"percent"},{"benchmark":"livecodebench","model":"lfm2-2.6b","score":14.41,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"lfm2-2.6b","score":14.43,"metric":"percent"},{"benchmark":"humaneval-plus","model":"lfm2-2.6b","score":57.93,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"lfm2-2.6b","score":38.79,"metric":"percent"},{"benchmark":"livecodebench","model":"smollm3-3b","score":19.05,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"smollm3-3b","score":19.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"smollm3-3b","score":60.37,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"smollm3-3b","score":36.44,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.2-3b-instruct","score":11.47,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"llama-3.2-3b-instruct","score":11.48,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.2-3b-instruct","score":24.06,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"llama-3.2-3b-instruct","score":38.84,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b","score":36.11,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-4b","score":38.64,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-4b","score":71.95,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-4b","score":37.49,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-instruct-2507","score":48.72,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-4b-instruct-2507","score":50.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-4b-instruct-2507","score":82.32,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-4b-instruct-2507","score":51.71,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-4b-it","score":18.86,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemma-3-4b-it","score":19.09,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-4b-it","score":62.8,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gemma-3-4b-it","score":68.56,"metric":"percent"},{"benchmark":"race","model":"rnd1-base-0910","score":57.6,"metric":"percent"},{"benchmark":"race","model":"dream-7b-instruct","score":44.7,"metric":"percent"},{"benchmark":"race","model":"llada-8b-instruct","score":38.7,"metric":"percent"},{"benchmark":"race","model":"qwen3-30b-a3b","score":40.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-tfree-hat-pretrained-7b-dpo","score":65.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-tfree-hat-pretrained-7b-dpo","score":65.5,"metric":"percent"},{"benchmark":"winogrande","model":"llama-tfree-hat-pretrained-7b-dpo","score":71.3,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3_1-70b-tfree-hat-sft","score":36,"metric":"percent"},{"benchmark":"winogender","model":"llama-3_1-70b-tfree-hat-sft","score":67.9,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3_1-70b-tfree-hat-sft","score":77.3,"metric":"norm_log_acc"},{"benchmark":"mmlu","model":"llama-3.3-70b-instruct","score":81.8,"metric":"norm_log_acc"},{"benchmark":"mmlu-fulltext","model":"llama-3_1-70b-tfree-hat-sft","score":78.6,"metric":"norm_log_acc"},{"benchmark":"mmlu-fulltext","model":"llama-3.3-70b-instruct","score":83,"metric":"norm_log_acc"},{"benchmark":"mmlu-pro","model":"llama-3_1-70b-tfree-hat-sft","score":51.3,"metric":"norm_log_acc"},{"benchmark":"mmlu-pro","model":"llama-3.3-70b-instruct","score":57.3,"metric":"norm_log_acc"},{"benchmark":"gpqa","model":"llama-3_1-70b-tfree-hat-sft","score":36,"metric":"log_acc"},{"benchmark":"gpqa","model":"llama-3.3-70b-instruct","score":54.5,"metric":"log_acc"},{"benchmark":"bbh","model":"llama-3_1-70b-tfree-hat-sft","score":0.652,"metric":"norm_log_acc"},{"benchmark":"bbh","model":"llama-3.3-70b-instruct","score":0.706,"metric":"norm_log_acc"},{"benchmark":"openbookqa","model":"llama-3_1-70b-tfree-hat-sft","score":0.526,"metric":"norm_log_acc"},{"benchmark":"openbookqa","model":"llama-3.3-70b-instruct","score":0.556,"metric":"norm_log_acc"},{"benchmark":"triviaqa","model":"llama-3_1-70b-tfree-hat-sft","score":0.582,"metric":"comp_acc"},{"benchmark":"triviaqa","model":"llama-3.3-70b-instruct","score":0.757,"metric":"comp_acc"},{"benchmark":"truthfulqa","model":"llama-3_1-70b-tfree-hat-sft","score":0.176,"metric":"norm_prob_mass"},{"benchmark":"truthfulqa","model":"llama-3.3-70b-instruct","score":0.191,"metric":"norm_prob_mass"},{"benchmark":"arc-easy","model":"llama-3_1-70b-tfree-hat-sft","score":0.92,"metric":"norm_log_acc"},{"benchmark":"arc-easy","model":"llama-3.3-70b-instruct","score":0.911,"metric":"norm_log_acc"},{"benchmark":"arc-challenge","model":"llama-3_1-70b-tfree-hat-sft","score":0.739,"metric":"norm_log_acc"},{"benchmark":"arc-challenge","model":"llama-3.3-70b-instruct","score":0.741,"metric":"norm_log_acc"},{"benchmark":"winogrande","model":"llama-3_1-70b-tfree-hat-sft","score":0.749,"metric":"norm_log_acc"},{"benchmark":"winogrande","model":"llama-3.3-70b-instruct","score":0.697,"metric":"norm_log_acc"},{"benchmark":"hellaswag","model":"llama-3_1-70b-tfree-hat-sft","score":0.809,"metric":"norm_log_acc"},{"benchmark":"hellaswag","model":"llama-3.3-70b-instruct","score":0.665,"metric":"norm_log_acc"},{"benchmark":"mmmlu","model":"llama-3_1-70b-tfree-hat-sft","score":0.715,"metric":"norm_log_acc"},{"benchmark":"mmmlu","model":"llama-3.3-70b-instruct","score":0.783,"metric":"norm_log_acc"},{"benchmark":"arc-easy-de","model":"llama-3_1-70b-tfree-hat-sft","score":0.848,"metric":"norm_log_acc"},{"benchmark":"arc-easy-de","model":"llama-3.3-70b-instruct","score":0.825,"metric":"norm_log_acc"},{"benchmark":"arc-challenge-de","model":"llama-3_1-70b-tfree-hat-sft","score":0.669,"metric":"norm_log_acc"},{"benchmark":"arc-challenge-de","model":"llama-3.3-70b-instruct","score":0.653,"metric":"norm_log_acc"},{"benchmark":"winogrande-de","model":"llama-3_1-70b-tfree-hat-sft","score":0.793,"metric":"norm_log_acc"},{"benchmark":"winogrande-de","model":"llama-3.3-70b-instruct","score":0.761,"metric":"norm_log_acc"},{"benchmark":"hellaswag-de","model":"llama-3_1-70b-tfree-hat-sft","score":0.727,"metric":"norm_log_acc"},{"benchmark":"hellaswag-de","model":"llama-3.3-70b-instruct","score":0.707,"metric":"norm_log_acc"},{"benchmark":"truthfulqa-de","model":"llama-3_1-70b-tfree-hat-sft","score":0.17,"metric":"norm_prob_mass"},{"benchmark":"truthfulqa-de","model":"llama-3.3-70b-instruct","score":0.174,"metric":"norm_prob_mass"},{"benchmark":"gsm8k-de","model":"llama-3_1-70b-tfree-hat-sft","score":0.63,"metric":"comp_acc"},{"benchmark":"gsm8k-de","model":"llama-3.3-70b-instruct","score":0.139,"metric":"comp_acc"},{"benchmark":"wmt16","model":"llama-3_1-70b-tfree-hat-sft","score":37.38,"metric":"bleu"},{"benchmark":"wmt16","model":"llama-3.3-70b-instruct","score":38.841,"metric":"bleu"},{"benchmark":"wmt16-instruct","model":"llama-3_1-70b-tfree-hat-sft","score":37.614,"metric":"bleu"},{"benchmark":"wmt16-instruct","model":"llama-3.3-70b-instruct","score":37.912,"metric":"bleu"},{"benchmark":"alpacaeval","model":"llama-3_1-70b-tfree-hat-sft","score":36.3,"metric":"CS"},{"benchmark":"alpacaeval","model":"llama-3.3-70b-instruct","score":16.8,"metric":"CS"},{"benchmark":"alpacaeval","model":"llama-3_1-70b-tfree-hat-sft","score":94.5,"metric":"IF"},{"benchmark":"alpacaeval","model":"llama-3.3-70b-instruct","score":96.1,"metric":"IF"},{"benchmark":"alpacaeval","model":"llama-3_1-70b-tfree-hat-sft","score":99.4,"metric":"LC"},{"benchmark":"alpacaeval","model":"llama-3.3-70b-instruct","score":99.3,"metric":"LC"},{"benchmark":"quality","model":"llama-3_1-70b-tfree-hat-sft","score":48.8,"metric":"log_acc"},{"benchmark":"quality","model":"llama-3.3-70b-instruct","score":45.9,"metric":"log_acc"},{"benchmark":"zeroscrolls-musique","model":"llama-3_1-70b-tfree-hat-sft","score":45,"metric":"F1"},{"benchmark":"zeroscrolls-musique","model":"llama-3.3-70b-instruct","score":52.2,"metric":"F1"},{"benchmark":"zeroscrolls-spacedigest","model":"llama-3_1-70b-tfree-hat-sft","score":77.9,"metric":"ES"},{"benchmark":"zeroscrolls-spacedigest","model":"llama-3.3-70b-instruct","score":40.4,"metric":"ES"},{"benchmark":"zeroscrolls-squality","model":"llama-3_1-70b-tfree-hat-sft","score":17,"metric":"rouge_gm"},{"benchmark":"zeroscrolls-squality","model":"llama-3.3-70b-instruct","score":15.9,"metric":"rouge_gm"},{"benchmark":"winogender","model":"llama-3_1-70b-tfree-hat-sft","score":67.9,"metric":"norm_log_acc"},{"benchmark":"winogender","model":"llama-3.3-70b-instruct","score":84.3,"metric":"norm_log_acc"},{"benchmark":"aime-2024","model":"mistral-medium-3","score":26.8,"metric":"percent"},{"benchmark":"aime-2025","model":"mistral-medium-3","score":21.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-medium-3","score":57.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"mistral-medium-3","score":29.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"mistral-medium-3","score":28.9,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-medium","score":73.6,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-medium","score":64.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-medium","score":70.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"magistral-medium","score":59.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"magistral-medium","score":47.1,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-medium-3","score":92.1,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-medium-3","score":30.3,"metric":"percent"},{"benchmark":"multipl-e","model":"mistral-medium-3","score":81.4,"metric":"percent"},{"benchmark":"arena-hard","model":"mistral-medium-3","score":97.1,"metric":"percent"},{"benchmark":"ifeval","model":"mistral-medium-3","score":89.4,"metric":"percent"},{"benchmark":"math500","model":"mistral-medium-3","score":91,"metric":"percent"},{"benchmark":"math500","model":"minimax-m1-80k","score":96.8,"metric":"percent"},{"benchmark":"math500","model":"minimax-m1-40k","score":96,"metric":"percent"},{"benchmark":"math500","model":"qwen3-235b-a22b","score":96.2,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1-0528","score":98,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1","score":97.3,"metric":"percent"},{"benchmark":"math500","model":"seed-thinking-v1.5","score":96.7,"metric":"percent"},{"benchmark":"math500","model":"claude-opus-4","score":98.2,"metric":"percent"},{"benchmark":"math500","model":"gemini-2.5-pro","score":98.8,"metric":"percent"},{"benchmark":"math500","model":"o3","score":98.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-medium-3","score":77.2,"metric":"percent"},{"benchmark":"ruler-32k","model":"mistral-medium-3","score":96,"metric":"percent"},{"benchmark":"ruler-128k","model":"mistral-medium-3","score":90.2,"metric":"percent"},{"benchmark":"mmmu","model":"mistral-medium-3","score":66.1,"metric":"percent"},{"benchmark":"docvqa","model":"mistral-medium-3","score":95.3,"metric":"percent"},{"benchmark":"ai2d","model":"mistral-medium-3","score":93.7,"metric":"percent"},{"benchmark":"chartqa","model":"mistral-medium-3","score":82.6,"metric":"percent"},{"benchmark":"mathvista","model":"pixtral-large-2411","score":69.4,"metric":"percent"},{"benchmark":"mmmu","model":"pixtral-large-2411","score":64,"metric":"percent"},{"benchmark":"chartqa","model":"pixtral-large-2411","score":88.1,"metric":"percent"},{"benchmark":"docvqa","model":"pixtral-large-2411","score":93.3,"metric":"percent"},{"benchmark":"vqav2","model":"pixtral-large-2411","score":80.9,"metric":"percent"},{"benchmark":"ai2d","model":"pixtral-large-2411","score":93.8,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"pixtral-large-2411","score":7.4,"metric":"score"},{"benchmark":"lambada","model":"pythia-70m","score":19.2,"metric":"percent"},{"benchmark":"lambada","model":"pythia-160m","score":34.2,"metric":"percent"},{"benchmark":"lambada","model":"pythia-410m","score":52.4,"metric":"percent"},{"benchmark":"lambada","model":"pythia-1b","score":58,"metric":"percent"},{"benchmark":"piqa","model":"pythia-70m","score":59.8,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-70m","score":49.2,"metric":"percent"},{"benchmark":"wsc","model":"pythia-70m","score":36.5,"metric":"percent"},{"benchmark":"arc-easy","model":"pythia-70m","score":38.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-70m","score":16.2,"metric":"percent"},{"benchmark":"sciq","model":"pythia-70m","score":60.6,"metric":"percent"},{"benchmark":"logiqa","model":"pythia-70m","score":23.5,"metric":"percent"},{"benchmark":"piqa","model":"pythia-160m","score":61.8,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-160m","score":49.7,"metric":"percent"},{"benchmark":"wsc","model":"pythia-160m","score":36.5,"metric":"percent"},{"benchmark":"arc-easy","model":"pythia-160m","score":44,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-160m","score":20.1,"metric":"percent"},{"benchmark":"sciq","model":"pythia-160m","score":72,"metric":"percent"},{"benchmark":"logiqa","model":"pythia-160m","score":21,"metric":"percent"},{"benchmark":"piqa","model":"pythia-410m","score":67.5,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-410m","score":53.4,"metric":"percent"},{"benchmark":"wsc","model":"pythia-410m","score":47.1,"metric":"percent"},{"benchmark":"arc-easy","model":"pythia-410m","score":51.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-410m","score":20.2,"metric":"percent"},{"benchmark":"sciq","model":"pythia-410m","score":82.6,"metric":"percent"},{"benchmark":"logiqa","model":"pythia-410m","score":20.9,"metric":"percent"},{"benchmark":"piqa","model":"pythia-1b","score":70,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-1b","score":52.9,"metric":"percent"},{"benchmark":"wsc","model":"pythia-1b","score":36.5,"metric":"percent"},{"benchmark":"arc-easy","model":"pythia-1b","score":58.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-1b","score":24.5,"metric":"percent"},{"benchmark":"sciq","model":"pythia-1b","score":87,"metric":"percent"},{"benchmark":"logiqa","model":"pythia-1b","score":21.2,"metric":"percent"},{"benchmark":"lambada","model":"pythia-1.4b","score":61.9,"metric":"percent"},{"benchmark":"piqa","model":"pythia-1.4b","score":72,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-1.4b","score":56.6,"metric":"percent"},{"benchmark":"wsc","model":"pythia-1.4b","score":44.2,"metric":"percent"},{"benchmark":"arc-easy","model":"pythia-1.4b","score":61.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-1.4b","score":27.2,"metric":"percent"},{"benchmark":"sciq","model":"pythia-1.4b","score":86.5,"metric":"percent"},{"benchmark":"logiqa","model":"pythia-1.4b","score":22.1,"metric":"percent"},{"benchmark":"lambada","model":"pythia-2.8b","score":65.1,"metric":"percent"},{"benchmark":"piqa","model":"pythia-2.8b","score":74.1,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-2.8b","score":58.2,"metric":"percent"},{"benchmark":"wsc","model":"pythia-2.8b","score":38.5,"metric":"percent"},{"benchmark":"arc-easy","model":"pythia-2.8b","score":63.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-2.8b","score":30.1,"metric":"percent"},{"benchmark":"sciq","model":"pythia-2.8b","score":88.2,"metric":"percent"},{"benchmark":"logiqa","model":"pythia-2.8b","score":21.4,"metric":"percent"},{"benchmark":"lambada","model":"pythia-6.9b","score":68.9,"metric":"percent"},{"benchmark":"piqa","model":"pythia-6.9b","score":76,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-6.9b","score":63.1,"metric":"percent"},{"benchmark":"wsc","model":"pythia-6.9b","score":44.2,"metric":"percent"},{"benchmark":"arc-easy","model":"pythia-6.9b","score":68.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-6.9b","score":33.1,"metric":"percent"},{"benchmark":"sciq","model":"pythia-6.9b","score":91.1,"metric":"percent"},{"benchmark":"logiqa","model":"pythia-6.9b","score":21.5,"metric":"percent"},{"benchmark":"lambada","model":"pythia-12b","score":71,"metric":"percent"},{"benchmark":"piqa","model":"pythia-12b","score":76.3,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-12b","score":66,"metric":"percent"},{"benchmark":"wsc","model":"pythia-12b","score":39.4,"metric":"percent"},{"benchmark":"arc-easy","model":"pythia-12b","score":70.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-12b","score":33.2,"metric":"percent"},{"benchmark":"sciq","model":"pythia-12b","score":92.9,"metric":"percent"},{"benchmark":"logiqa","model":"pythia-12b","score":22.4,"metric":"percent"},{"benchmark":"humaneval","model":"bloom-176b","score":15.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-30b-a3b-instruct","score":85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-vl-30b-a3b-instruct","score":77.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-vl-30b-a3b-instruct","score":88.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-vl-30b-a3b-instruct","score":70.4,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-vl-30b-a3b-instruct","score":53.1,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-vl-30b-a3b-instruct","score":27,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-30b-a3b-instruct","score":69.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-vl-30b-a3b-instruct","score":50.6,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-vl-30b-a3b-instruct","score":65.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-30b-a3b-instruct","score":42.6,"metric":"percent"},{"benchmark":"sifo","model":"qwen3-vl-30b-a3b-instruct","score":50.1,"metric":"percent"},{"benchmark":"sifo-multiturn","model":"qwen3-vl-30b-a3b-instruct","score":35.1,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-30b-a3b-instruct","score":85.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-vl-30b-a3b-instruct","score":58.5,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-vl-30b-a3b-instruct","score":84.6,"metric":"ELO"},{"benchmark":"writingbench","model":"qwen3-vl-30b-a3b-instruct","score":82.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-vl-30b-a3b-instruct","score":66.3,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-vl-30b-a3b-instruct","score":66.1,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-vl-30b-a3b-instruct","score":70.9,"metric":"percent"},{"benchmark":"include","model":"qwen3-vl-30b-a3b-instruct","score":71.6,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-vl-30b-a3b-instruct","score":44.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-30b-a3b-thinking","score":87.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-vl-30b-a3b-thinking","score":80.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-vl-30b-a3b-thinking","score":90.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-vl-30b-a3b-thinking","score":74.4,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-vl-30b-a3b-thinking","score":56.4,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-vl-30b-a3b-thinking","score":23.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-30b-a3b-thinking","score":83.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-vl-30b-a3b-thinking","score":67.6,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-vl-30b-a3b-thinking","score":72.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-30b-a3b-thinking","score":64.2,"metric":"percent"},{"benchmark":"sifo","model":"qwen3-vl-30b-a3b-thinking","score":66.9,"metric":"percent"},{"benchmark":"sifo-multiturn","model":"qwen3-vl-30b-a3b-thinking","score":60.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-30b-a3b-thinking","score":81.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-vl-30b-a3b-thinking","score":56.7,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-vl-30b-a3b-thinking","score":82.5,"metric":"elo"},{"benchmark":"writingbench","model":"qwen3-vl-30b-a3b-thinking","score":85.2,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-vl-30b-a3b-thinking","score":68.6,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-vl-30b-a3b-thinking","score":73,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-vl-30b-a3b-thinking","score":76.1,"metric":"percent"},{"benchmark":"include","model":"qwen3-vl-30b-a3b-thinking","score":74.5,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-vl-30b-a3b-thinking","score":51.7,"metric":"percent"},{"benchmark":"mathvista","model":"pixtral-12b","score":58,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"pixtral-12b","score":6.05,"metric":"score"},{"benchmark":"mmmu","model":"claude-3-haiku","score":50.4,"metric":"percent"},{"benchmark":"mathvista","model":"claude-3-haiku","score":44.8,"metric":"percent"},{"benchmark":"chartqa","model":"claude-3-haiku","score":69.6,"metric":"percent"},{"benchmark":"docvqa","model":"claude-3-haiku","score":74.6,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"claude-3-haiku","score":5.46,"metric":"score"},{"benchmark":"mmmu","model":"gemini-1.5-flash-8b-0827","score":50.7,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-1.5-flash-8b-0827","score":56.9,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-1.5-flash-8b-0827","score":78,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-1.5-flash-8b-0827","score":79.5,"metric":"percent"},{"benchmark":"vqav2","model":"gemini-1.5-flash-8b-0827","score":65.5,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"gemini-1.5-flash-8b-0827","score":5.93,"metric":"score"},{"benchmark":"mmmu","model":"llava-onevision-72b","score":54.4,"metric":"percent"},{"benchmark":"mathvista","model":"llava-onevision-72b","score":57.2,"metric":"percent"},{"benchmark":"chartqa","model":"llava-onevision-72b","score":66.9,"metric":"percent"},{"benchmark":"docvqa","model":"llava-onevision-72b","score":91.6,"metric":"percent"},{"benchmark":"vqav2","model":"llava-onevision-72b","score":83.8,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"llava-onevision-72b","score":4.95,"metric":"score"},{"benchmark":"mmmu","model":"gpt-4o","score":68.6,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-4o","score":64.6,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-4o","score":85.1,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4o","score":88.9,"metric":"percent"},{"benchmark":"vqav2","model":"gpt-4o","score":77.8,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"gpt-4o","score":7.72,"metric":"score"},{"benchmark":"mmmu","model":"claude-3.5-sonnet","score":68,"metric":"percent"},{"benchmark":"mathvista","model":"claude-3.5-sonnet","score":64.4,"metric":"percent"},{"benchmark":"chartqa","model":"claude-3.5-sonnet","score":87.6,"metric":"percent"},{"benchmark":"docvqa","model":"claude-3.5-sonnet","score":90.3,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"claude-3.5-sonnet","score":7.5,"metric":"score"},{"benchmark":"mmlu","model":"llama-2-7b","score":44.4,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b","score":77.1,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-7b","score":69.5,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-7b","score":77.9,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-7b","score":68.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-7b","score":43.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b","score":24.7,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-7b","score":63.8,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b","score":11.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b","score":26.1,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b","score":3.9,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b","score":16,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b","score":55.6,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-13b","score":80.7,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-13b","score":72.9,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-13b","score":80.8,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-13b","score":75.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-13b","score":48.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-13b","score":29,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-13b","score":69.6,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b","score":18.9,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-13b","score":35.4,"metric":"percent"},{"benchmark":"math","model":"llama-2-13b","score":6,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b","score":34.3,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b","score":60.1,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b","score":81.3,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b","score":75.3,"metric":"percent"},{"benchmark":"piqa","model":"mistral-7b","score":83,"metric":"percent"},{"benchmark":"arc-easy","model":"mistral-7b","score":80,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b","score":55.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"mistral-7b","score":28.8,"metric":"percent"},{"benchmark":"triviaqa","model":"mistral-7b","score":69.9,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b","score":30.5,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b","score":47.5,"metric":"percent"},{"benchmark":"math","model":"mistral-7b","score":13.1,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b","score":52.1,"metric":"percent"},{"benchmark":"mmlu","model":"codellama-7b","score":36.9,"metric":"percent"},{"benchmark":"hellaswag","model":"codellama-7b","score":62.9,"metric":"percent"},{"benchmark":"winogrande","model":"codellama-7b","score":62.3,"metric":"percent"},{"benchmark":"piqa","model":"codellama-7b","score":72.8,"metric":"percent"},{"benchmark":"arc-easy","model":"codellama-7b","score":59.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"codellama-7b","score":34.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"codellama-7b","score":11,"metric":"percent"},{"benchmark":"triviaqa","model":"codellama-7b","score":34.9,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-7b","score":31.1,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b","score":52.5,"metric":"percent"},{"benchmark":"math","model":"codellama-7b","score":5.2,"metric":"percent"},{"benchmark":"gsm8k","model":"codellama-7b","score":20.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b","score":17.5,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-7b","score":56.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-13b","score":16.7,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-13b","score":64,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-33b","score":56.8,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-1-33b","score":82.8,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1-33b","score":76,"metric":"percent"},{"benchmark":"piqa","model":"llama-1-33b","score":82.3,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-1-33b","score":80,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-1-33b","score":57.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-33b","score":24.1,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-1-33b","score":68.5,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-33b","score":25,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-33b","score":40.9,"metric":"percent"},{"benchmark":"math","model":"llama-1-33b","score":8.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-33b","score":44.1,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b","score":69.9,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-70b","score":85.4,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-70b","score":80.4,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-70b","score":82.6,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-70b","score":79.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-70b","score":56.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-70b","score":25.4,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-70b","score":73,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":29.3,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-70b","score":49.8,"metric":"percent"},{"benchmark":"math","model":"llama-2-70b","score":13.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b","score":69.6,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b","score":62.5,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b","score":81,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b","score":74.2,"metric":"percent"},{"benchmark":"piqa","model":"mistral-7b","score":82.2,"metric":"percent"},{"benchmark":"arc-easy","model":"mistral-7b","score":80.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b","score":54.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"mistral-7b","score":23.2,"metric":"percent"},{"benchmark":"triviaqa","model":"mistral-7b","score":62.5,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b","score":26.2,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b","score":50.2,"metric":"percent"},{"benchmark":"math","model":"mistral-7b","score":12.7,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b","score":50,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x7b","score":70.6,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x7b","score":84.4,"metric":"percent"},{"benchmark":"winogrande","model":"mixtral-8x7b","score":77.2,"metric":"percent"},{"benchmark":"piqa","model":"mixtral-8x7b","score":83.6,"metric":"percent"},{"benchmark":"arc-easy","model":"mixtral-8x7b","score":83.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"mixtral-8x7b","score":59.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"mixtral-8x7b","score":30.6,"metric":"percent"},{"benchmark":"triviaqa","model":"mixtral-8x7b","score":71.5,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x7b","score":40.2,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x7b","score":60.7,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x7b","score":28.4,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x7b","score":74.4,"metric":"percent"},{"benchmark":"bbq","model":"llama-3.3-70b","score":0.6228,"metric":"score"},{"benchmark":"bbq","model":"gemini-2.0-flash","score":0.6026,"metric":"score"},{"benchmark":"bbq","model":"gpt-4o","score":0.5733,"metric":"score"},{"benchmark":"bbq","model":"claude-3-haiku","score":0.6405,"metric":"score"},{"benchmark":"bbq","model":"hcx","score":0.6345,"metric":"score"},{"benchmark":"bbq","model":"gpt-4-turbo","score":0.6362,"metric":"score"},{"benchmark":"bbq","model":"hcx-dash","score":0.5966,"metric":"score"},{"benchmark":"bbq","model":"qwen2.5-72b-instruct","score":0.6866,"metric":"score"},{"benchmark":"bbq","model":"gpt-3.5-turbo","score":0.6362,"metric":"score"},{"benchmark":"bbq","model":"claude-3.5-sonnet","score":0.547,"metric":"score"},{"benchmark":"bbq","model":"llama-2-70b","score":51.5,"metric":"percent"},{"benchmark":"bbq","model":"mixtral-8x7b","score":55.98,"metric":"percent"},{"benchmark":"bold","model":"llama-2-70b","score":0.094,"metric":"score"},{"benchmark":"bold","model":"mixtral-8x7b","score":0.084,"metric":"score"},{"benchmark":"hellaswag","model":"llama-2-70b","score":87.1,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-70b","score":83.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-70b","score":86,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-70b","score":85.1,"metric":"percent"},{"benchmark":"triqa","model":"llama-2-70b","score":77.57,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-70b","score":35.5,"metric":"percent"},{"benchmark":"mmlu","model":"command-r-08-2024","score":68.2,"metric":"percent"},{"benchmark":"hellaswag","model":"command-r-08-2024","score":87,"metric":"percent"},{"benchmark":"winogrande","model":"command-r-08-2024","score":81.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"command-r-08-2024","score":66.5,"metric":"percent"},{"benchmark":"mmlu","model":"command-r-plus-08-2024","score":75.7,"metric":"percent"},{"benchmark":"hellaswag","model":"command-r-plus-08-2024","score":88.6,"metric":"percent"},{"benchmark":"winogrande","model":"command-r-plus-08-2024","score":85.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"command-r-plus-08-2024","score":71,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b","score":62.47,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b","score":83.1,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b","score":78,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b","score":77.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b","score":78.1,"metric":"percent"},{"benchmark":"triqa","model":"mistral-7b","score":68.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"mistral-7b","score":28.1,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x7b","score":70.63,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x7b","score":86.6,"metric":"percent"},{"benchmark":"winogrande","model":"mixtral-8x7b","score":81.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"mixtral-8x7b","score":85.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"mixtral-8x7b","score":85.9,"metric":"percent"},{"benchmark":"triqa","model":"mixtral-8x7b","score":78.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"mixtral-8x7b","score":36.5,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x22b","score":77.75,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x22b","score":88.5,"metric":"percent"},{"benchmark":"winogrande","model":"mixtral-8x22b","score":84.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"mixtral-8x22b","score":91.3,"metric":"percent"},{"benchmark":"triqa","model":"mixtral-8x22b","score":82.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"mixtral-8x22b","score":40.1,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b","score":53.6,"metric":"percent"},{"benchmark":"gsm8k","model":"command-r-08-2024","score":56.6,"metric":"percent"},{"benchmark":"gsm8k","model":"command-r-plus-08-2024","score":70.7,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b","score":26.22,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b","score":36.5,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x7b","score":58.4,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x22b","score":45.1,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x22b","score":71.2,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b","score":78.6,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b","score":88.4,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x22b","score":41.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-saferl","score":18.2,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-saferl-thinking","score":63.5,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b","score":26.4,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-thinking","score":65.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b","score":26.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-saferl","score":27.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-thinking","score":48.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-saferl-thinking","score":47.5,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-4b","score":41.7,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-4b-saferl","score":40.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-4b-thinking","score":55.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-4b-saferl-thinking","score":51.2,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-4b","score":9.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-4b-saferl","score":10.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-4b-thinking","score":13.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-4b-saferl-thinking","score":16.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"o3-2025-04-16","score":87,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"o4-mini-2025-04-16-high","score":81.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"o4-mini-2025-04-16","score":78,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"o3-mini-2025-01-31-high","score":64.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"o1-2024-12-17-high","score":58.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-4.1","score":58.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"o1-2024-12-17","score":50.2,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"o3-mini-2025-01-31","score":50,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemini-2.5","score":49.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-4.1-mini","score":48.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"deepseek-r1","score":48,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"claude-3-7-sonnet-20250219-thinking-16k","score":47,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-235b-a22b","score":46.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemini-2.5-flash","score":45.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-4.5-preview","score":43,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwq-32b","score":36.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-32b","score":35.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-30b-a3b","score":28.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"claude-3.5-sonnet-20241022","score":25.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"s1.1-32b","score":18.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-4.1-nano","score":15.4,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"athene-v2-chat","score":12.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-4b","score":12.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"llama4-maverick-instruct-basic","score":12,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemma-3-27b-it","score":9.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen2.5-72b-instruct","score":8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"llama-3.1-nemotron-70b-instruct-hf","score":6.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"openthinker2-32b","score":2.3,"metric":"percent"},{"benchmark":"math","model":"mathstral-7b","score":56.6,"metric":"percent"},{"benchmark":"gsm8k","model":"mathstral-7b","score":77.1,"metric":"percent"},{"benchmark":"odyssey-math","model":"mathstral-7b","score":37.2,"metric":"percent"},{"benchmark":"gre-math-maj16","model":"mathstral-7b","score":56.9,"metric":"percent"},{"benchmark":"amc-23","model":"mathstral-7b","score":42.4,"metric":"percent"},{"benchmark":"math","model":"deepseek-math-7b","score":44.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-math-7b","score":80.6,"metric":"percent"},{"benchmark":"odyssey-math","model":"deepseek-math-7b","score":27.6,"metric":"percent"},{"benchmark":"gre-math-maj16","model":"deepseek-math-7b","score":44.6,"metric":"percent"},{"benchmark":"amc-23","model":"deepseek-math-7b","score":28,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b","score":28.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b","score":75.4,"metric":"percent"},{"benchmark":"odyssey-math","model":"llama-3-8b","score":24,"metric":"percent"},{"benchmark":"gre-math-maj16","model":"llama-3-8b","score":26.2,"metric":"percent"},{"benchmark":"amc-23","model":"llama-3-8b","score":34.4,"metric":"percent"},{"benchmark":"math","model":"glm4-9b","score":50.2,"metric":"percent"},{"benchmark":"gsm8k","model":"glm4-9b","score":48.8,"metric":"percent"},{"benchmark":"odyssey-math","model":"glm4-9b","score":18.9,"metric":"percent"},{"benchmark":"gre-math-maj16","model":"glm4-9b","score":46.2,"metric":"percent"},{"benchmark":"amc-23","model":"glm4-9b","score":36,"metric":"percent"},{"benchmark":"math","model":"qwen2-7b","score":56.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-7b","score":32.7,"metric":"percent"},{"benchmark":"odyssey-math","model":"qwen2-7b","score":24.8,"metric":"percent"},{"benchmark":"gre-math-maj16","model":"qwen2-7b","score":58.5,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2-7b","score":35.2,"metric":"percent"},{"benchmark":"math","model":"gemma-2-9b","score":48.3,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-9b","score":69.5,"metric":"percent"},{"benchmark":"odyssey-math","model":"gemma-2-9b","score":18.6,"metric":"percent"},{"benchmark":"gre-math-maj16","model":"gemma-2-9b","score":52.3,"metric":"percent"},{"benchmark":"amc-23","model":"gemma-2-9b","score":31.2,"metric":"percent"},{"benchmark":"humaneval","model":"codegemma-1.1-7b","score":61,"metric":"percent"},{"benchmark":"mbpp","model":"codegemma-1.1-7b","score":67.7,"metric":"percent"},{"benchmark":"spider","model":"codegemma-1.1-7b","score":46.3,"metric":"percent"},{"benchmark":"cruxeval","model":"codegemma-1.1-7b","score":50.4,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b","score":48.2,"metric":"percent"},{"benchmark":"spider","model":"codellama-7b","score":29.3,"metric":"percent"},{"benchmark":"cruxeval","model":"codellama-7b","score":50.1,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-math-7b","score":65.9,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-math-7b","score":70.8,"metric":"percent"},{"benchmark":"spider","model":"deepseek-math-7b","score":61.2,"metric":"percent"},{"benchmark":"cruxeval","model":"deepseek-math-7b","score":55.5,"metric":"percent"},{"benchmark":"humaneval","model":"codestral-mamba","score":75,"metric":"percent"},{"benchmark":"mbpp","model":"codestral-mamba","score":68.5,"metric":"percent"},{"benchmark":"spider","model":"codestral-mamba","score":58.8,"metric":"percent"},{"benchmark":"cruxeval","model":"codestral-mamba","score":57.8,"metric":"percent"},{"benchmark":"cruxeval","model":"codestral-22b","score":51.3,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-34b","score":43.3,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-34b","score":75.1,"metric":"percent"},{"benchmark":"spider","model":"codellama-34b","score":50.8,"metric":"percent"},{"benchmark":"cruxeval","model":"codellama-34b","score":55.2,"metric":"percent"},{"benchmark":"aime-2025","model":"ring-1t","score":93.4,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-thinking-high","score":94.6,"metric":"percent"},{"benchmark":"codeforces","model":"ring-1t","score":2088,"metric":"ELO"},{"benchmark":"codeforces","model":"ring-1t-preview","score":2092,"metric":"ELO"},{"benchmark":"codeforces","model":"gemini-2.5-pro","score":1837,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v3.1-terminus-thinking","score":2073,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen3-235b-a22b-thinking-2507","score":2055,"metric":"ELO"},{"benchmark":"codeforces","model":"gpt-5-thinking-high","score":1918,"metric":"ELO"},{"benchmark":"arc-agi-1","model":"ring-1t","score":55.94,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-thinking-high","score":65.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"ring-1t","score":81.59,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"ring-1t-preview","score":73.41,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemini-2.5-pro","score":79.2,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"deepseek-v3.1-terminus-thinking","score":60.27,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-235b-a22b-thinking-2507","score":80.18,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-5-thinking-high","score":82.91,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-1t","score":78.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-thinking-high","score":80.6,"metric":"percent"},{"benchmark":"healthbench","model":"ring-1t","score":57.93,"metric":"percent"},{"benchmark":"healthbench","model":"ring-1t-preview","score":54.44,"metric":"percent"},{"benchmark":"healthbench","model":"gemini-2.5-pro","score":49.39,"metric":"percent"},{"benchmark":"healthbench","model":"deepseek-v3.1-terminus-thinking","score":50.19,"metric":"percent"},{"benchmark":"healthbench","model":"qwen3-235b-a22b-thinking-2507","score":55.56,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-5-thinking-high","score":67.2,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"ring-1t","score":85.4,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"ring-1t-preview","score":85.5,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gemini-2.5-pro","score":85.7,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"deepseek-v3.1-terminus-thinking","score":85.24,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-235b-a22b-thinking-2507","score":85.49,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gpt-5-thinking-high","score":89.69,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-4b-instruct","score":67.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-8b-instruct","score":69.6,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-flash-lite","score":72.7,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-nano-minimal","score":57.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-4b-instruct","score":53.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-8b-instruct","score":55.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-flash-lite","score":55.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-nano-minimal","score":36.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-4b-instruct","score":73.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-8b-instruct","score":77.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-2.5-flash-lite","score":70.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-5-nano-minimal","score":40.9,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-4b-instruct","score":51.6,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-8b-instruct","score":53.9,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.5-flash-lite","score":52.9,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-nano-minimal","score":33.2,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-4b-instruct","score":46.8,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-8b-instruct","score":62.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gemini-2.5-flash-lite","score":65.9,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gpt-5-nano-minimal","score":27,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-4b-instruct","score":21,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-8b-instruct","score":22.8,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemini-2.5-flash-lite","score":15.3,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gpt-5-nano-minimal","score":15.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-4b-instruct","score":85.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-8b-instruct","score":85,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemini-2.5-flash-lite","score":82.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gpt-5-nano-minimal","score":51.6,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-4b-instruct","score":70.9,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-8b-instruct","score":71.5,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-2.5-flash-lite","score":70.6,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5-nano-minimal","score":60.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-4b-instruct","score":69.8,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-8b-instruct","score":70.9,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-flash-lite","score":71.3,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-nano-minimal","score":41.3,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-4b-instruct","score":48,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-8b-instruct","score":50.2,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-2.5-flash-lite","score":52.2,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5-nano-minimal","score":39,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-4b-instruct","score":57.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-8b-instruct","score":61.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.5-flash-lite","score":53.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5-nano-minimal","score":39.3,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-4b-instruct","score":7.5,"metric":"score"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-8b-instruct","score":7.7,"metric":"score"},{"benchmark":"mm-mt-bench","model":"gemini-2.5-flash-lite","score":7.1,"metric":"score"},{"benchmark":"mm-mt-bench","model":"gpt-5-nano-minimal","score":6.2,"metric":"score"},{"benchmark":"miabench","model":"qwen3-vl-4b-instruct","score":89.7,"metric":"percent"},{"benchmark":"miabench","model":"qwen3-vl-8b-instruct","score":91.1,"metric":"percent"},{"benchmark":"miabench","model":"gemini-2.5-flash-lite","score":90.5,"metric":"percent"},{"benchmark":"miabench","model":"gpt-5-nano-minimal","score":89.6,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-4b-instruct","score":43.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-8b-instruct","score":47.9,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen2.5-vl-72b-instruct","score":42.1,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gemini-2.5-flash-lite","score":38.3,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gpt-5-nano-minimal","score":22.1,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-4b-instruct","score":95.3,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-8b-instruct","score":96.1,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-flash-lite","score":92,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5-nano-minimal","score":78.3,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-4b-instruct","score":80.3,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-8b-instruct","score":83.1,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-2.5-flash-lite","score":75,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-5-nano-minimal","score":49.2,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-4b-instruct","score":84.1,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-8b-instruct","score":85.7,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-flash-lite","score":84.8,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-nano-minimal","score":65.7,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-4b-instruct","score":88.1,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-8b-instruct","score":89.6,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-flash-lite","score":81.3,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5-nano-minimal","score":70.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-4b-instruct","score":63.7,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-4b-instruct","score":57.6,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-8b-instruct","score":65.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-8b-instruct","score":61.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemini-2.5-flash-lite","score":48.1,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gemini-2.5-flash-lite","score":34.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gpt-5-nano-minimal","score":37.9,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gpt-5-nano-minimal","score":27.3,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-4b-instruct","score":76.2,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-8b-instruct","score":79.9,"metric":"percent"},{"benchmark":"cc-ocr","model":"gemini-2.5-flash-lite","score":72.1,"metric":"percent"},{"benchmark":"cc-ocr","model":"gpt-5-nano-minimal","score":52.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-4b-instruct","score":76.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-8b-instruct","score":83,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-2.5-flash-lite","score":73.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5-nano-minimal","score":64.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-4b-instruct","score":39.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-8b-instruct","score":46.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-flash-lite","score":44.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5-nano-minimal","score":31.7,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-4b-instruct","score":48.2,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-8b-instruct","score":44.7,"metric":"percent"},{"benchmark":"arkitscenes","model":"qwen3-vl-4b-instruct","score":56.6,"metric":"percent"},{"benchmark":"arkitscenes","model":"qwen3-vl-8b-instruct","score":56.8,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-4b-instruct","score":12.2,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-8b-instruct","score":12.7,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-4b-instruct","score":34.7,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-8b-instruct","score":36.2,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-4b-instruct","score":65.8,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-8b-instruct","score":69.1,"metric":"percent"},{"benchmark":"blink","model":"gemini-2.5-flash-lite","score":62,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-nano-minimal","score":42.2,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3-vl-4b-instruct","score":63.8,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3-vl-8b-instruct","score":64.4,"metric":"percent"},{"benchmark":"muirbench","model":"gemini-2.5-flash-lite","score":67,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-5-nano-minimal","score":45.7,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-4b-instruct","score":41.3,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-8b-instruct","score":45.8,"metric":"percent"},{"benchmark":"erqa","model":"gemini-2.5-flash-lite","score":40.5,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5-nano-minimal","score":45.8,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-4b-instruct","score":58.4,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-8b-instruct","score":59.4,"metric":"percent"},{"benchmark":"vsi-bench","model":"gemini-2.5-flash-lite","score":27,"metric":"percent"},{"benchmark":"vsi-bench","model":"gpt-5-nano-minimal","score":27,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-4b-instruct","score":79.6,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-8b-instruct","score":78.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-2.5-flash-lite","score":66.3,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5-nano-minimal","score":50.7,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-4b-instruct","score":46.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-8b-instruct","score":54.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-2.5-flash-lite","score":12.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5-nano-minimal","score":2.5,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-4b-instruct","score":61.7,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-8b-instruct","score":66.9,"metric":"percent"},{"benchmark":"robospatialhome","model":"gemini-2.5-flash-lite","score":41.2,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-5-nano-minimal","score":44.8,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-4b-instruct","score":68.9,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-8b-instruct","score":68.7,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-2.5-flash-lite","score":65,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-5-nano-minimal","score":49.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-4b-instruct","score":69.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-8b-instruct","score":71.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen2.5-vl-72b-instruct","score":73.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-2.5-flash-lite","score":69.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-5-nano-minimal","score":52.6,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-4b-instruct","score":75.3,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-8b-instruct","score":78.1,"metric":"percent"},{"benchmark":"mlvu","model":"qwen2.5-vl-72b-instruct","score":74.6,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-2.5-flash-lite","score":69.3,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5-nano-minimal","score":52.6,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-4b-instruct","score":56.2,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-8b-instruct","score":58,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen3-vl-4b-instruct","score":55.5,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen3-vl-8b-instruct","score":56,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-4b-instruct","score":56.2,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-8b-instruct","score":65.3,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-2.5-flash-lite","score":63,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5-nano-minimal","score":40.2,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3-vl-4b-instruct","score":94,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3-vl-8b-instruct","score":94.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-4b-instruct","score":59.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-8b-instruct","score":54.6,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-4b-instruct","score":58.2,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-8b-instruct","score":58.2,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3-vl-4b-instruct","score":45.3,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3-vl-8b-instruct","score":47.6,"metric":"percent"},{"benchmark":"osworld","model":"qwen3-vl-4b-instruct","score":26.2,"metric":"percent"},{"benchmark":"osworld","model":"qwen3-vl-8b-instruct","score":33.9,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-4b-instruct","score":80.1,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-8b-instruct","score":86.4,"metric":"percent"},{"benchmark":"v-star","model":"qwen2.5-vl-72b-instruct","score":69.1,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-4b-instruct","score":78.3,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-8b-instruct","score":78.9,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen2.5-vl-72b-instruct","score":67.6,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-4b-instruct","score":72.9,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-8b-instruct","score":74.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-4b-instruct","score":77.2,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-8b-instruct","score":80.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-vl-4b-instruct","score":67.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-vl-8b-instruct","score":71.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-vl-4b-instruct","score":81.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-vl-8b-instruct","score":84.9,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-vl-4b-instruct","score":40.3,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-vl-8b-instruct","score":44.5,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-4b-instruct","score":46.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-8b-instruct","score":45.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-vl-4b-instruct","score":30.7,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-vl-8b-instruct","score":32.5,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-vl-4b-instruct","score":60.9,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-vl-8b-instruct","score":62,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-4b-instruct","score":37.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-8b-instruct","score":39.3,"metric":"percent"},{"benchmark":"sifo","model":"qwen3-vl-4b-instruct","score":42.7,"metric":"percent"},{"benchmark":"sifo","model":"qwen3-vl-8b-instruct","score":47.1,"metric":"percent"},{"benchmark":"sifo-multiturn","model":"qwen3-vl-4b-instruct","score":36.7,"metric":"percent"},{"benchmark":"sifo-multiturn","model":"qwen3-vl-8b-instruct","score":38.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-4b-instruct","score":82.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-8b-instruct","score":83.7,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-vl-4b-instruct","score":82.5,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-vl-8b-instruct","score":83.1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-vl-4b-instruct","score":63.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-vl-8b-instruct","score":66.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-vl-4b-instruct","score":59.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-vl-8b-instruct","score":65.4,"metric":"percent"},{"benchmark":"include","model":"qwen3-vl-4b-instruct","score":61.4,"metric":"percent"},{"benchmark":"include","model":"qwen3-vl-8b-instruct","score":67,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-vl-4b-instruct","score":28.8,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-vl-8b-instruct","score":30.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-4b-instruct-2507","score":78.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b-non-thinking","score":77.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b-instruct-2507","score":69.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b-non-thinking","score":63.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-4b-instruct-2507","score":84.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-8b-non-thinking","score":79.5,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-4b-instruct-2507","score":42.8,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-8b-non-thinking","score":35.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-instruct-2507","score":47.4,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b-non-thinking","score":20.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-4b-instruct-2507","score":31,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-8b-non-thinking","score":11.8,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-4b-instruct-2507","score":63,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-8b-non-thinking","score":53.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-instruct-2507","score":35.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b-non-thinking","score":25.5,"metric":"percent"},{"benchmark":"sifo","model":"qwen3-4b-instruct-2507","score":44.8,"metric":"percent"},{"benchmark":"sifo","model":"qwen3-8b-non-thinking","score":45.7,"metric":"percent"},{"benchmark":"sifo-multiturn","model":"qwen3-4b-instruct-2507","score":35.2,"metric":"percent"},{"benchmark":"sifo-multiturn","model":"qwen3-8b-non-thinking","score":37.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b-instruct-2507","score":83.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-8b-non-thinking","score":83,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-4b-instruct-2507","score":83.4,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3-8b-non-thinking","score":71.4,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-4b-instruct-2507","score":61.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-8b-non-thinking","score":60.2,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-4b-instruct-2507","score":61.6,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-8b-non-thinking","score":58,"metric":"percent"},{"benchmark":"include","model":"qwen3-4b-instruct-2507","score":60.1,"metric":"percent"},{"benchmark":"include","model":"qwen3-8b-non-thinking","score":62.5,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-4b-instruct-2507","score":31.1,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-8b-non-thinking","score":18.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kat-dev-72b-exp","score":74.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-4.5-haiku","score":73.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-4.5-haiku","score":41,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-4.5-haiku","score":83.2,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-4.5-haiku","score":63.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-4.5-haiku","score":83,"metric":"percent"},{"benchmark":"osworld","model":"claude-4.5-haiku","score":50.7,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-4.5-haiku","score":96.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-4.5-haiku","score":73,"metric":"percent"},{"benchmark":"mmlu","model":"claude-4.5-haiku","score":83,"metric":"percent"},{"benchmark":"mmmu","model":"claude-4.5-haiku","score":73.2,"metric":"percent"},{"benchmark":"hellaswag","model":"mobilellm-p1-base","score":67.11,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-1b","score":62.3,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.2-1b","score":65.69,"metric":"percent"},{"benchmark":"boolq","model":"mobilellm-p1-base","score":76.24,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3-1b","score":63.2,"metric":"percent"},{"benchmark":"boolq","model":"llama-3.2-1b","score":62.51,"metric":"percent"},{"benchmark":"piqa","model":"mobilellm-p1-base","score":76.55,"metric":"percent"},{"benchmark":"piqa","model":"gemma-3-1b","score":73.8,"metric":"percent"},{"benchmark":"piqa","model":"llama-3.2-1b","score":75.14,"metric":"percent"},{"benchmark":"socialiqa","model":"mobilellm-p1-base","score":50.87,"metric":"percent"},{"benchmark":"socialiqa","model":"gemma-3-1b","score":48.9,"metric":"percent"},{"benchmark":"socialiqa","model":"llama-3.2-1b","score":45.6,"metric":"percent"},{"benchmark":"triviaqa","model":"mobilellm-p1-base","score":39.85,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-1b","score":39.8,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-3.2-1b","score":23.81,"metric":"percent"},{"benchmark":"naturalquestions","model":"mobilellm-p1-base","score":15.76,"metric":"percent"},{"benchmark":"naturalquestions","model":"gemma-3-1b","score":9.48,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-3.2-1b","score":5.48,"metric":"percent"},{"benchmark":"arc-challenge","model":"mobilellm-p1-base","score":52.62,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-1b","score":38.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-1b","score":38.28,"metric":"percent"},{"benchmark":"arc-easy","model":"mobilellm-p1-base","score":76.28,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-3-1b","score":73,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-3.2-1b","score":63.47,"metric":"percent"},{"benchmark":"winogrande","model":"mobilellm-p1-base","score":62.83,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-1b","score":58.2,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.2-1b","score":61.09,"metric":"percent"},{"benchmark":"openbookqa","model":"mobilellm-p1-base","score":43.6,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-3.2-1b","score":37.2,"metric":"percent"},{"benchmark":"nih","model":"mobilellm-p1-base","score":100,"metric":"percent"},{"benchmark":"nih","model":"gemma-3-1b","score":96.44,"metric":"percent"},{"benchmark":"nih","model":"llama-3.2-1b","score":98.67,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-1.5-flash","score":67.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-1.5-pro","score":75.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.0-flash","score":77.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.0-pro","score":79.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-2b","score":15.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-9b","score":46.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-27b","score":56.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-1b","score":14.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-4b","score":43.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-12b","score":60.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-27b","score":67.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-1.5-flash","score":30.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-1.5-pro","score":34.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.0-flash","score":34.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.0-pro","score":36,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-2-2b","score":1.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-2-9b","score":10.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-2-27b","score":20.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-1b","score":1.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-4b","score":12.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-12b","score":24.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-27b","score":29.7,"metric":"percent"},{"benchmark":"bird-sql","model":"gemini-1.5-flash","score":45.6,"metric":"percent"},{"benchmark":"bird-sql","model":"gemini-1.5-pro","score":54.4,"metric":"percent"},{"benchmark":"bird-sql","model":"gemini-2.0-flash","score":58.7,"metric":"percent"},{"benchmark":"bird-sql","model":"gemini-2.0-pro","score":59.3,"metric":"percent"},{"benchmark":"bird-sql","model":"gemma-2-2b","score":12.2,"metric":"percent"},{"benchmark":"bird-sql","model":"gemma-2-9b","score":33.8,"metric":"percent"},{"benchmark":"bird-sql","model":"gemma-2-27b","score":46.7,"metric":"percent"},{"benchmark":"bird-sql","model":"gemma-3-1b","score":6.4,"metric":"percent"},{"benchmark":"bird-sql","model":"gemma-3-4b","score":36.3,"metric":"percent"},{"benchmark":"bird-sql","model":"gemma-3-12b","score":47.9,"metric":"percent"},{"benchmark":"bird-sql","model":"gemma-3-27b","score":54.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-1.5-flash","score":51,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-1.5-pro","score":59.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.0-flash","score":60.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.0-pro","score":64.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-2-2b","score":24.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-2-9b","score":28.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-2-27b","score":34.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-1b","score":19.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-4b","score":30.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-12b","score":40.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-27b","score":42.4,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-1.5-flash","score":8.6,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-1.5-pro","score":24.9,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-2.0-flash","score":29.9,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-2.0-pro","score":44.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-2-2b","score":2.8,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-2-9b","score":5.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-2-27b","score":9.2,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-1b","score":2.2,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-4b","score":4,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-12b","score":6.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-27b","score":10,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-1.5-flash","score":82.9,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-1.5-pro","score":80,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-2.0-flash","score":84.6,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-2.0-pro","score":82.8,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-2-2b","score":43.8,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-2-9b","score":62,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-2-27b","score":62.4,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-1b","score":36.4,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-4b","score":70.1,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-12b","score":75.8,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-27b","score":74.9,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemini-1.5-flash","score":73.7,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemini-1.5-pro","score":80.8,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemini-2.0-flash","score":83.4,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemini-2.0-pro","score":86.5,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemma-2-2b","score":41.9,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemma-2-9b","score":64.8,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemma-2-27b","score":68.6,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemma-3-1b","score":34.2,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemma-3-4b","score":54.5,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemma-3-12b","score":69.5,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemma-3-27b","score":75.1,"metric":"percent"},{"benchmark":"math","model":"gemini-1.5-flash","score":77.9,"metric":"percent"},{"benchmark":"math","model":"gemini-1.5-pro","score":86.5,"metric":"percent"},{"benchmark":"math","model":"gemini-2.0-flash","score":90.9,"metric":"percent"},{"benchmark":"math","model":"gemini-2.0-pro","score":91.8,"metric":"percent"},{"benchmark":"math","model":"gemma-2-2b","score":27.2,"metric":"percent"},{"benchmark":"math","model":"gemma-2-9b","score":49.4,"metric":"percent"},{"benchmark":"math","model":"gemma-2-27b","score":55.6,"metric":"percent"},{"benchmark":"math","model":"gemma-3-1b","score":48,"metric":"percent"},{"benchmark":"math","model":"gemma-3-4b","score":75.6,"metric":"percent"},{"benchmark":"math","model":"gemma-3-12b","score":83.8,"metric":"percent"},{"benchmark":"math","model":"gemma-3-27b","score":89,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemini-1.5-flash","score":47.2,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemini-1.5-pro","score":52,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemini-2.0-flash","score":63.5,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemma-2-2b","score":1.8,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemma-2-9b","score":10.4,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemma-2-27b","score":14.8,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemma-3-1b","score":15.8,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemma-3-4b","score":43,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemma-3-12b","score":54.5,"metric":"percent"},{"benchmark":"hiddenmath","model":"gemma-3-27b","score":60.3,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.5-flash","score":62.3,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.5-pro","score":65.9,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.0-flash","score":71.7,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.0-pro","score":72.7,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-3-4b","score":48.8,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-3-12b","score":59.6,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-3-27b","score":64.9,"metric":"percent"},{"benchmark":"mmlu","model":"mobilellm-p1","score":44.8,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-1b","score":29.9,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.2-1b","score":49.3,"metric":"percent"},{"benchmark":"ifeval","model":"mobilellm-p1","score":62,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-1b","score":80.2,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.2-1b","score":59.5,"metric":"percent"},{"benchmark":"mbpp","model":"mobilellm-p1","score":46.8,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-1b","score":35.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.2-1b","score":39.6,"metric":"percent"},{"benchmark":"humaneval","model":"mobilellm-p1","score":59.8,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-1b","score":41.5,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.2-1b","score":37.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"mobilellm-p1","score":62.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-1b","score":59.4,"metric":"percent"},{"benchmark":"hellaswag","model":"mobilellm-p1","score":58.4,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.2-1b","score":41.2,"metric":"percent"},{"benchmark":"bfcl-v2","model":"mobilellm-p1","score":29.4,"metric":"percent"},{"benchmark":"bfcl-v2","model":"llama-3.2-1b","score":25.7,"metric":"percent"},{"benchmark":"open-rewrite","model":"mobilellm-p1","score":51,"metric":"percent"},{"benchmark":"open-rewrite","model":"llama-3.2-1b","score":41.6,"metric":"percent"},{"benchmark":"tldr9-plus","model":"mobilellm-p1","score":16.8,"metric":"percent"},{"benchmark":"tldr9-plus","model":"llama-3.2-1b","score":16.8,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"nougat","score":45.2,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"smoldocling","score":49.3,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"internvl2-76b","score":44,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"qwen2.5-vl-7b","score":31.6,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"olmocr","score":32.6,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"got-ocr2.0","score":28.7,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"ocrflux-3b","score":23.8,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"gpt-4o","score":23.3,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"internvl3-78b","score":21.8,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"qwen2.5-vl-72b","score":21.4,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"dots.ocr","score":18.2,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"gemini-2.5-pro","score":14.8,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"mineru2.0","score":13.3,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"dots.ocr","score":12.5,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"deepseek-ocr-tiny","score":38.6,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"deepseek-ocr-small","score":22.1,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"deepseek-ocr-base","score":13.7,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"deepseek-ocr-large","score":13.8,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"gundam","score":12.7,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"gundam-m","score":12.3,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"dolphin","score":35.6,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"marker","score":29.6,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"mathpix","score":19.1,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"mineru-2.1.1","score":16.2,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"monkeyocr-1.2b","score":15.4,"metric":"percent"},{"benchmark":"omnidocbench-edit","model":"pp-structurev3","score":15.2,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"dolphin","score":44,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"marker","score":49.7,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"mathpix","score":36.4,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"mineru-2.1.1","score":24.4,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"monkeyocr-1.2b","score":26.3,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"pp-structurev3","score":13.6,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"nougat","score":97.3,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"smoldocling","score":81.6,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"internvl2-76b","score":44.3,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"qwen2.5-vl-7b","score":39.9,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"olmocr","score":46.9,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"got-ocr2.0","score":41.1,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"ocrflux-3b","score":34.9,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"gpt-4o","score":39.9,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"internvl3-78b","score":29.6,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"qwen2.5-vl-72b","score":26.1,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"dots.ocr","score":26.1,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"gemini-2.5-pro","score":21.2,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"mineru2.0","score":23.8,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"dots.ocr","score":16,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"deepseek-ocr-tiny","score":36.1,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"deepseek-ocr-small","score":28.4,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"deepseek-ocr-base","score":24,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"deepseek-ocr-large","score":20.8,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"gundam","score":18.1,"metric":"percent"},{"benchmark":"omnidocbench-cn","model":"gundam-m","score":15.7,"metric":"percent"},{"benchmark":"fox-page-en","model":"dolphin","score":1.14,"metric":"percent"},{"benchmark":"fox-page-en","model":"dolphin-1.5","score":0.74,"metric":"percent"},{"benchmark":"fox-page-cn","model":"dolphin","score":1.31,"metric":"percent"},{"benchmark":"fox-page-cn","model":"dolphin-1.5","score":0.77,"metric":"percent"},{"benchmark":"dolphin-page","model":"dolphin","score":10.28,"metric":"percent"},{"benchmark":"dolphin-page","model":"dolphin-1.5","score":7.43,"metric":"percent"},{"benchmark":"evg","model":"dolphin","score":4.24,"metric":"percent"},{"benchmark":"evg","model":"dolphin-1.5","score":2.98,"metric":"percent"},{"benchmark":"olmocr-bench","model":"got-ocr","score":48.3,"metric":"percent"},{"benchmark":"olmocr-bench","model":"marker-v1.7.5","score":70.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mineru-1.3.10","score":61.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mistral-ocr-api","score":72,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gpt-4o","score":69.9,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gemini-2.0-flash","score":63.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"qwen2-vl","score":31.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"qwen2.5-vl-7b","score":65.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"olmocr","score":75.5,"metric":"percent"},{"benchmark":"aime-2025","model":"ring-mini-sparse-2.0-exp","score":77.92,"metric":"percent"},{"benchmark":"aime-2024","model":"ring-mini-sparse-2.0-exp","score":84.58,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"ring-mini-sparse-2.0-exp","score":85.77,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-mini-sparse-2.0-exp","score":62.19,"metric":"percent"},{"benchmark":"gpqa","model":"ring-mini-sparse-2.0-exp","score":67.3,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-2b-instruct","score":53.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-2b-instruct","score":36.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-2b-instruct","score":61.3,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-2b-instruct","score":31.6,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-2b-instruct","score":52.1,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-2b-instruct","score":13.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-2b-instruct","score":77.8,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-2b-instruct","score":63.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-2b-instruct","score":58.3,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-2b-instruct","score":40.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-2b-instruct","score":51.4,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-2b-instruct","score":5.9,"metric":"score"},{"benchmark":"miabench","model":"qwen3-vl-2b-instruct","score":83.6,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-2b-instruct","score":31.6,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-2b-instruct","score":93.3,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-2b-instruct","score":72.4,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-2b-instruct","score":76.9,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-2b-instruct","score":85.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-2b-instruct","score":56.3,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-2b-instruct","score":53,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-2b-instruct","score":72.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-2b-instruct","score":62.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-2b-instruct","score":26.8,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-2b-instruct","score":88.4,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-2b-instruct","score":43.4,"metric":"percent"},{"benchmark":"arkitscenes","model":"qwen3-vl-2b-instruct","score":56.2,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-2b-instruct","score":12,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-2b-instruct","score":33.8,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-2b-instruct","score":53.8,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3-vl-2b-instruct","score":47.4,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-2b-instruct","score":28.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-2b-instruct","score":53.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-2b-instruct","score":69.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-2b-instruct","score":30.3,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-2b-instruct","score":49.1,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-2b-instruct","score":61.7,"metric":"percent"},{"benchmark":"video-mme","model":"qwen3-vl-2b-instruct","score":61.9,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-2b-instruct","score":68.3,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-2b-instruct","score":47.4,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen3-vl-2b-instruct","score":54.5,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-2b-instruct","score":41.9,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3-vl-2b-instruct","score":91.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-2b-instruct","score":48.5,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-2b-instruct","score":46.1,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3-vl-2b-instruct","score":36.4,"metric":"percent"},{"benchmark":"osworld","model":"qwen3-vl-2b-instruct","score":34.1,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-2b-instruct","score":74.9,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-2b-instruct","score":74.1,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-2b-instruct","score":68.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-32b-instruct","score":76,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-32b-instruct","score":65.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-32b-instruct","score":83.8,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-32b-instruct","score":63.4,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-32b-instruct","score":76.8,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-32b-instruct","score":25.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-32b-instruct","score":88.9,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-32b-instruct","score":79,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-32b-instruct","score":77.7,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-32b-instruct","score":56.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-32b-instruct","score":63.8,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-32b-instruct","score":8.4,"metric":"score"},{"benchmark":"miabench","model":"qwen3-vl-32b-instruct","score":91.8,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-32b-instruct","score":55.4,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-32b-instruct","score":96.9,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-32b-instruct","score":87,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-32b-instruct","score":89.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-32b-instruct","score":89.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-32b-instruct","score":67.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-32b-instruct","score":59.2,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-32b-instruct","score":80.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-32b-instruct","score":90.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-32b-instruct","score":62.8,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-32b-instruct","score":94.9,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-32b-instruct","score":46.6,"metric":"percent"},{"benchmark":"arkitscenes","model":"qwen3-vl-32b-instruct","score":55.6,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-32b-instruct","score":14,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-32b-instruct","score":37,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-32b-instruct","score":67.3,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3-vl-32b-instruct","score":72.8,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-32b-instruct","score":48.8,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-32b-instruct","score":61.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-32b-instruct","score":81.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-32b-instruct","score":61.4,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-32b-instruct","score":64.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-32b-instruct","score":72.8,"metric":"percent"},{"benchmark":"video-mme","model":"qwen3-vl-32b-instruct","score":76.6,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-32b-instruct","score":82.1,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-32b-instruct","score":63.8,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen3-vl-32b-instruct","score":61.2,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-32b-instruct","score":71.9,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3-vl-32b-instruct","score":95.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-32b-instruct","score":57.9,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-32b-instruct","score":65.1,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3-vl-32b-instruct","score":57.3,"metric":"percent"},{"benchmark":"osworld","model":"qwen3-vl-32b-instruct","score":32.6,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-32b-instruct","score":85.3,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-32b-instruct","score":82.9,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-32b-instruct","score":77.8,"metric":"percent"},{"benchmark":"zerobench-sub","model":"claude-sonnet-4","score":23.1,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-sonnet-4","score":52.8,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"claude-sonnet-4","score":52.6,"metric":"percent"},{"benchmark":"ai2d","model":"claude-sonnet-4","score":82.6,"metric":"percent"},{"benchmark":"erqa","model":"claude-sonnet-4","score":39.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"claude-sonnet-4","score":36.1,"metric":"percent"},{"benchmark":"refspatialbench","model":"claude-sonnet-4","score":4.3,"metric":"percent"},{"benchmark":"v-star","model":"claude-sonnet-4","score":37.7,"metric":"percent"},{"benchmark":"hrbench4k","model":"claude-sonnet-4","score":50.6,"metric":"percent"},{"benchmark":"hrbench8k","model":"claude-sonnet-4","score":40.5,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-2b","score":57.67,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2.5-vl-3b","score":56.13,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3-2b","score":61.1,"metric":"percent"},{"benchmark":"mmstar","model":"smolvlm2-2.2b","score":46,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2-vl-3b","score":57.73,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-2b","score":51.78,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2.5-vl-3b","score":51.67,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3-2b","score":48.7,"metric":"percent"},{"benchmark":"mmmu","model":"smolvlm2-2.2b","score":41.6,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2-vl-3b","score":45.33,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3.5-2b","score":61.6,"metric":"percent"},{"benchmark":"mathvista","model":"qwen2.5-vl-3b","score":62.5,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3-2b","score":57.6,"metric":"percent"},{"benchmark":"mathvista","model":"smolvlm2-2.2b","score":51.5,"metric":"percent"},{"benchmark":"mathvista","model":"lfm2-vl-3b","score":62.2,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-2b","score":50.97,"metric":"percent"},{"benchmark":"blink","model":"qwen2.5-vl-3b","score":48.97,"metric":"percent"},{"benchmark":"blink","model":"internvl3-2b","score":53.1,"metric":"percent"},{"benchmark":"blink","model":"smolvlm2-2.2b","score":42.3,"metric":"percent"},{"benchmark":"blink","model":"lfm2-vl-3b","score":51.03,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-2b","score":69.29,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2.5-vl-3b","score":76.12,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3-2b","score":66.1,"metric":"percent"},{"benchmark":"infovqa","model":"smolvlm2-2.2b","score":37.75,"metric":"percent"},{"benchmark":"infovqa","model":"lfm2-vl-3b","score":67.37,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"internvl3.5-2b","score":78.18,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen2.5-vl-3b","score":80.41,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"internvl3-2b","score":81.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"smolvlm2-2.2b","score":69.24,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"lfm2-vl-3b","score":79.81,"metric":"percent"},{"benchmark":"ocrbench-elo","model":"internvl3.5-2b","score":834,"metric":"points"},{"benchmark":"ocrbench-elo","model":"qwen2.5-vl-3b","score":824,"metric":"points"},{"benchmark":"ocrbench-elo","model":"internvl3-2b","score":831,"metric":"points"},{"benchmark":"ocrbench-elo","model":"smolvlm2-2.2b","score":725,"metric":"points"},{"benchmark":"ocrbench-elo","model":"lfm2-vl-3b","score":822,"metric":"points"},{"benchmark":"pope","model":"internvl3.5-2b","score":87.17,"metric":"percent"},{"benchmark":"pope","model":"qwen2.5-vl-3b","score":86.17,"metric":"percent"},{"benchmark":"pope","model":"internvl3-2b","score":90.1,"metric":"percent"},{"benchmark":"pope","model":"smolvlm2-2.2b","score":85.1,"metric":"percent"},{"benchmark":"pope","model":"lfm2-vl-3b","score":89.01,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-2b","score":60.78,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2.5-vl-3b","score":65.23,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3-2b","score":65.1,"metric":"percent"},{"benchmark":"realworldqa","model":"smolvlm2-2.2b","score":57.5,"metric":"percent"},{"benchmark":"realworldqa","model":"lfm2-vl-3b","score":71.37,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl3.5-2b","score":2128.83,"metric":"points"},{"benchmark":"mme-elo","model":"qwen2.5-vl-3b","score":2163.29,"metric":"points"},{"benchmark":"mme-elo","model":"internvl3-2b","score":2186.4,"metric":"points"},{"benchmark":"mme-elo","model":"smolvlm2-2.2b","score":1792.5,"metric":"points"},{"benchmark":"mme-elo","model":"lfm2-vl-3b","score":2050.9,"metric":"points"},{"benchmark":"mm-ifeval","model":"internvl3.5-2b","score":47.31,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen2.5-vl-3b","score":38.62,"metric":"percent"},{"benchmark":"mm-ifeval","model":"internvl3-2b","score":38.49,"metric":"percent"},{"benchmark":"mm-ifeval","model":"smolvlm2-2.2b","score":19.42,"metric":"percent"},{"benchmark":"mm-ifeval","model":"lfm2-vl-3b","score":51.83,"metric":"percent"},{"benchmark":"seedbench","model":"internvl3.5-2b","score":75.41,"metric":"percent"},{"benchmark":"seedbench","model":"qwen2.5-vl-3b","score":73.88,"metric":"percent"},{"benchmark":"seedbench","model":"internvl3-2b","score":74.95,"metric":"percent"},{"benchmark":"seedbench","model":"smolvlm2-2.2b","score":71.3,"metric":"percent"},{"benchmark":"seedbench","model":"lfm2-vl-3b","score":76.55,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gpt-4o","score":68.9,"metric":"percent"},{"benchmark":"olmocr-bench","model":"qwen2-vl-7b","score":31.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gemini-2.5-flash","score":57.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"nanonets-ocr-s","score":64.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"monkeyocr-pro-3b","score":75.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"infinity-parser-7b","score":82.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"dots.ocr","score":79.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"marker","score":76.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mineru-2.5.4","score":75.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"paddleocr-vl","score":80,"metric":"percent"},{"benchmark":"olmocr-bench","model":"nanonets-ocr2-3b","score":69.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"deepseek-ocr-base","score":75.7,"metric":"percent"},{"benchmark":"olmocr-bench","model":"chandra-ocr-0.1.0","score":83.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"olmocr","score":68.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"olmocr-2-7b-1025","score":82.4,"metric":"percent"},{"benchmark":"livecodebench","model":"minimax-m1-80k","score":65,"metric":"percent"},{"benchmark":"livecodebench","model":"minimax-m1-40k","score":62.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1","score":55.9,"metric":"percent"},{"benchmark":"livecodebench","model":"seed-thinking-v1.5","score":67.5,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4","score":56.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":77.1,"metric":"percent"},{"benchmark":"livecodebench","model":"o3","score":75.8,"metric":"percent"},{"benchmark":"fullstackbench","model":"minimax-m1-80k","score":68.3,"metric":"percent"},{"benchmark":"fullstackbench","model":"minimax-m1-40k","score":67.6,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3-235b-a22b","score":62.9,"metric":"percent"},{"benchmark":"fullstackbench","model":"deepseek-r1-0528","score":69.4,"metric":"percent"},{"benchmark":"fullstackbench","model":"deepseek-r1","score":70.1,"metric":"percent"},{"benchmark":"fullstackbench","model":"seed-thinking-v1.5","score":69.9,"metric":"percent"},{"benchmark":"fullstackbench","model":"claude-opus-4","score":70.3,"metric":"percent"},{"benchmark":"fullstackbench","model":"o3","score":69.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m1-80k","score":70,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m1-40k","score":69.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-235b-a22b","score":71.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-0528","score":81,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1","score":71.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed-thinking-v1.5","score":77.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o3","score":83.3,"metric":"percent"},{"benchmark":"hle","model":"minimax-m1-80k","score":8.4,"metric":"percent"},{"benchmark":"hle","model":"minimax-m1-40k","score":7.2,"metric":"percent"},{"benchmark":"hle","model":"qwen3-235b-a22b","score":7.6,"metric":"percent"},{"benchmark":"hle","model":"deepseek-r1-0528","score":17.7,"metric":"percent"},{"benchmark":"hle","model":"deepseek-r1","score":8.6,"metric":"percent"},{"benchmark":"hle","model":"seed-thinking-v1.5","score":8.2,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4","score":10.7,"metric":"percent"},{"benchmark":"hle","model":"gemini-2.5-pro","score":21.6,"metric":"percent"},{"benchmark":"hle","model":"o3","score":20.3,"metric":"percent"},{"benchmark":"zebralogic","model":"minimax-m1-80k","score":86.8,"metric":"percent"},{"benchmark":"zebralogic","model":"minimax-m1-40k","score":80.1,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-235b-a22b","score":80.3,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-r1-0528","score":95.1,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-r1","score":78.7,"metric":"percent"},{"benchmark":"zebralogic","model":"seed-thinking-v1.5","score":84.4,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-opus-4","score":95.1,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-2.5-pro","score":91.6,"metric":"percent"},{"benchmark":"zebralogic","model":"o3","score":95.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-m1-80k","score":81.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-m1-40k","score":80.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-0528","score":85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1","score":84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed-thinking-v1.5","score":87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4","score":85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"o3","score":85,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m1-80k","score":56,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m1-40k","score":55.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-235b-a22b","score":34.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-r1-0528","score":57.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-r1","score":49.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"seed-thinking-v1.5","score":47,"metric":"percent"},{"benchmark":"mrcr-128k","model":"minimax-m1-80k","score":73.4,"metric":"percent"},{"benchmark":"mrcr-128k","model":"minimax-m1-40k","score":76.1,"metric":"percent"},{"benchmark":"mrcr-128k","model":"qwen3-235b-a22b","score":27.7,"metric":"percent"},{"benchmark":"mrcr-128k","model":"deepseek-r1-0528","score":51.5,"metric":"percent"},{"benchmark":"mrcr-128k","model":"deepseek-r1","score":35.8,"metric":"percent"},{"benchmark":"mrcr-128k","model":"seed-thinking-v1.5","score":54.3,"metric":"percent"},{"benchmark":"mrcr-128k","model":"claude-opus-4","score":48.9,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gemini-2.5-pro","score":76.8,"metric":"percent"},{"benchmark":"mrcr-128k","model":"o3","score":56.5,"metric":"percent"},{"benchmark":"mrcr-1m","model":"minimax-m1-80k","score":56.2,"metric":"percent"},{"benchmark":"mrcr-1m","model":"minimax-m1-40k","score":58.6,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-2.5-pro","score":58.8,"metric":"percent"},{"benchmark":"longbench-v2","model":"minimax-m1-80k","score":61.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"minimax-m1-40k","score":61,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-235b-a22b","score":50.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-r1-0528","score":52.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-r1","score":58.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"seed-thinking-v1.5","score":52.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-opus-4","score":55.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-2.5-pro","score":65,"metric":"percent"},{"benchmark":"longbench-v2","model":"o3","score":58.8,"metric":"percent"},{"benchmark":"tau2-airline","model":"minimax-m1-80k","score":62,"metric":"percent"},{"benchmark":"tau2-airline","model":"minimax-m1-40k","score":60,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-235b-a22b","score":34.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"deepseek-r1-0528","score":53.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"seed-thinking-v1.5","score":44,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-opus-4","score":59.6,"metric":"percent"},{"benchmark":"tau2-airline","model":"gemini-2.5-pro","score":50,"metric":"percent"},{"benchmark":"tau2-airline","model":"o3","score":52,"metric":"percent"},{"benchmark":"tau2-retail","model":"minimax-m1-80k","score":63.5,"metric":"percent"},{"benchmark":"tau2-retail","model":"minimax-m1-40k","score":67.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-235b-a22b","score":58.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"deepseek-r1-0528","score":63.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"seed-thinking-v1.5","score":55.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4","score":81.4,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemini-2.5-pro","score":67,"metric":"percent"},{"benchmark":"tau2-retail","model":"o3","score":73.9,"metric":"percent"},{"benchmark":"simpleqa","model":"minimax-m1-80k","score":18.5,"metric":"percent"},{"benchmark":"simpleqa","model":"minimax-m1-40k","score":17.9,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-235b-a22b","score":11,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-r1-0528","score":27.8,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-r1","score":30.1,"metric":"percent"},{"benchmark":"simpleqa","model":"seed-thinking-v1.5","score":12.9,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-2.5-pro","score":54,"metric":"percent"},{"benchmark":"simpleqa","model":"o3","score":49.4,"metric":"percent"},{"benchmark":"multichallenge","model":"minimax-m1-80k","score":44.7,"metric":"percent"},{"benchmark":"multichallenge","model":"minimax-m1-40k","score":44.7,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-235b-a22b","score":40,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-r1-0528","score":45,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-r1","score":40.7,"metric":"percent"},{"benchmark":"multichallenge","model":"seed-thinking-v1.5","score":43,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-opus-4","score":45.8,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-2.5-pro","score":51.8,"metric":"percent"},{"benchmark":"multichallenge","model":"o3","score":56.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m2","score":69.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-2.5-pro","score":63.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-thinking","score":74.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-0905-preview","score":69.2,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"minimax-m2","score":36.2,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"glm-4.6","score":30,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"kimi-k2-0905-preview","score":33.5,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"deepseek-v3.2-exp","score":30.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"minimax-m2","score":56.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-sonnet-4","score":56.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-4.6","score":53.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2-0905-preview","score":55.9,"metric":"percent"},{"benchmark":"terminal-bench","model":"minimax-m2","score":46.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5-thinking","score":43.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-0905-preview","score":44.5,"metric":"percent"},{"benchmark":"artifactsbench","model":"minimax-m2","score":66.8,"metric":"percent"},{"benchmark":"artifactsbench","model":"claude-sonnet-4","score":57.3,"metric":"percent"},{"benchmark":"artifactsbench","model":"claude-sonnet-4.5","score":61.5,"metric":"percent"},{"benchmark":"artifactsbench","model":"gemini-2.5-pro","score":57.7,"metric":"percent"},{"benchmark":"artifactsbench","model":"gpt-5-thinking","score":73,"metric":"percent"},{"benchmark":"artifactsbench","model":"glm-4.6","score":59.8,"metric":"percent"},{"benchmark":"artifactsbench","model":"kimi-k2-0905-preview","score":54.2,"metric":"percent"},{"benchmark":"artifactsbench","model":"deepseek-v3.2-exp","score":55.8,"metric":"percent"},{"benchmark":"browsecomp","model":"minimax-m2","score":44,"metric":"percent"},{"benchmark":"browsecomp","model":"gemini-2.5-pro","score":9.9,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5-thinking","score":54.9,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2-0905-preview","score":14.1,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v3.2-exp","score":40.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"minimax-m2","score":48.5,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"claude-sonnet-4.5","score":40.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gemini-2.5-pro","score":32.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-5-thinking","score":65,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"glm-4.6","score":49.5,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"kimi-k2-0905-preview","score":28.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepseek-v3.2-exp","score":47.9,"metric":"percent"},{"benchmark":"gaia","model":"minimax-m2","score":75.7,"metric":"percent"},{"benchmark":"gaia","model":"claude-sonnet-4","score":68.3,"metric":"percent"},{"benchmark":"gaia","model":"claude-sonnet-4.5","score":71.2,"metric":"percent"},{"benchmark":"gaia","model":"gemini-2.5-pro","score":60.2,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5-thinking","score":76.4,"metric":"percent"},{"benchmark":"gaia","model":"glm-4.6","score":71.9,"metric":"percent"},{"benchmark":"gaia","model":"kimi-k2-0905-preview","score":60.2,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-v3.2-exp","score":63.5,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"minimax-m2","score":72,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"claude-sonnet-4","score":64.6,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"claude-sonnet-4.5","score":66,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"gemini-2.5-pro","score":56,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"gpt-5-thinking","score":77.8,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"glm-4.6","score":70,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"kimi-k2-0905-preview","score":61,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"deepseek-v3.2-exp","score":71,"metric":"percent"},{"benchmark":"hle","model":"minimax-m2","score":31.8,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4","score":20.3,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4.5","score":24.5,"metric":"percent"},{"benchmark":"hle","model":"gemini-2.5-pro","score":28.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5-thinking","score":35.2,"metric":"percent"},{"benchmark":"hle","model":"kimi-k2-0905-preview","score":26.9,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.2-exp","score":27.2,"metric":"percent"},{"benchmark":"finsearchcomp","model":"minimax-m2","score":65.5,"metric":"percent"},{"benchmark":"finsearchcomp","model":"claude-sonnet-4","score":42,"metric":"percent"},{"benchmark":"finsearchcomp","model":"claude-sonnet-4.5","score":60.8,"metric":"percent"},{"benchmark":"finsearchcomp","model":"glm-4.6","score":29.2,"metric":"percent"},{"benchmark":"finsearchcomp","model":"kimi-k2-0905-preview","score":29.5,"metric":"percent"},{"benchmark":"finsearchcomp","model":"deepseek-v3.2-exp","score":26.2,"metric":"percent"},{"benchmark":"agentcompany","model":"minimax-m2","score":36,"metric":"percent"},{"benchmark":"agentcompany","model":"claude-sonnet-4","score":37,"metric":"percent"},{"benchmark":"agentcompany","model":"claude-sonnet-4.5","score":41,"metric":"percent"},{"benchmark":"agentcompany","model":"gemini-2.5-pro","score":39.3,"metric":"percent"},{"benchmark":"agentcompany","model":"glm-4.6","score":35,"metric":"percent"},{"benchmark":"agentcompany","model":"kimi-k2-0905-preview","score":30,"metric":"percent"},{"benchmark":"agentcompany","model":"deepseek-v3.2-exp","score":34,"metric":"percent"},{"benchmark":"arc-easy","model":"marin-32b-mantis","score":88,"metric":"percent"},{"benchmark":"arc-challenge","model":"marin-32b-mantis","score":65.7,"metric":"percent"},{"benchmark":"boolq","model":"marin-32b-mantis","score":89.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"marin-32b-mantis","score":82.8,"metric":"percent"},{"benchmark":"copa","model":"marin-32b-mantis","score":93,"metric":"percent"},{"benchmark":"hellaswag","model":"marin-32b-mantis","score":86.9,"metric":"percent"},{"benchmark":"lambada","model":"marin-32b-mantis","score":77.2,"metric":"percent"},{"benchmark":"openbookqa","model":"marin-32b-mantis","score":46.4,"metric":"percent"},{"benchmark":"piqa","model":"marin-32b-mantis","score":85.9,"metric":"percent"},{"benchmark":"winogrande","model":"marin-32b-mantis","score":79.3,"metric":"percent"},{"benchmark":"wsc","model":"marin-32b-mantis","score":79.5,"metric":"percent"},{"benchmark":"mmlu","model":"marin-32b-mantis","score":74.7,"metric":"percent"},{"benchmark":"gpqa","model":"marin-32b-mantis","score":34,"metric":"percent"},{"benchmark":"bbh","model":"marin-32b-mantis","score":59.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"marin-32b-mantis","score":45.1,"metric":"percent"},{"benchmark":"humaneval","model":"marin-32b-mantis","score":42.7,"metric":"percent"},{"benchmark":"gsm8k","model":"marin-32b-mantis","score":69.1,"metric":"percent"},{"benchmark":"math","model":"marin-32b-mantis","score":15.3,"metric":"percent"},{"benchmark":"arc-easy","model":"marin-32b-bison","score":87.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"marin-32b-bison","score":65.8,"metric":"percent"},{"benchmark":"boolq","model":"marin-32b-bison","score":88.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"marin-32b-bison","score":82.3,"metric":"percent"},{"benchmark":"copa","model":"marin-32b-bison","score":94,"metric":"percent"},{"benchmark":"hellaswag","model":"marin-32b-bison","score":86.6,"metric":"percent"},{"benchmark":"lambada","model":"marin-32b-bison","score":77.4,"metric":"percent"},{"benchmark":"openbookqa","model":"marin-32b-bison","score":46.6,"metric":"percent"},{"benchmark":"piqa","model":"marin-32b-bison","score":86.1,"metric":"percent"},{"benchmark":"winogrande","model":"marin-32b-bison","score":78.6,"metric":"percent"},{"benchmark":"wsc","model":"marin-32b-bison","score":82.4,"metric":"percent"},{"benchmark":"mmlu","model":"marin-32b-bison","score":72.9,"metric":"percent"},{"benchmark":"gpqa","model":"marin-32b-bison","score":32.1,"metric":"percent"},{"benchmark":"bbh","model":"marin-32b-bison","score":55.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"marin-32b-bison","score":41.9,"metric":"percent"},{"benchmark":"humaneval","model":"marin-32b-bison","score":29.3,"metric":"percent"},{"benchmark":"gsm8k","model":"marin-32b-bison","score":54.7,"metric":"percent"},{"benchmark":"math","model":"marin-32b-bison","score":10.4,"metric":"percent"},{"benchmark":"arc-easy","model":"olmo-2-32b-base","score":85.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-2-32b-base","score":61.9,"metric":"percent"},{"benchmark":"boolq","model":"olmo-2-32b-base","score":83,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-2-32b-base","score":78.6,"metric":"percent"},{"benchmark":"copa","model":"olmo-2-32b-base","score":93,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-2-32b-base","score":85.9,"metric":"percent"},{"benchmark":"lambada","model":"olmo-2-32b-base","score":78.3,"metric":"percent"},{"benchmark":"openbookqa","model":"olmo-2-32b-base","score":47.2,"metric":"percent"},{"benchmark":"piqa","model":"olmo-2-32b-base","score":83.1,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-2-32b-base","score":78.9,"metric":"percent"},{"benchmark":"wsc","model":"olmo-2-32b-base","score":86.8,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-2-32b-base","score":71.9,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-2-32b-base","score":32.2,"metric":"percent"},{"benchmark":"bbh","model":"olmo-2-32b-base","score":56.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-2-32b-base","score":42,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-2-32b-base","score":23.8,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-2-32b-base","score":76.4,"metric":"percent"},{"benchmark":"math","model":"olmo-2-32b-base","score":12.7,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen2.5-32b-base","score":80.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-32b-base","score":55.9,"metric":"percent"},{"benchmark":"boolq","model":"qwen2.5-32b-base","score":87.7,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen2.5-32b-base","score":88.5,"metric":"percent"},{"benchmark":"copa","model":"qwen2.5-32b-base","score":87,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-32b-base","score":84.1,"metric":"percent"},{"benchmark":"lambada","model":"qwen2.5-32b-base","score":77.6,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen2.5-32b-base","score":44.4,"metric":"percent"},{"benchmark":"piqa","model":"qwen2.5-32b-base","score":82.4,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-32b-base","score":75.7,"metric":"percent"},{"benchmark":"wsc","model":"qwen2.5-32b-base","score":81,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-32b-base","score":80.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-32b-base","score":39,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-32b-base","score":67.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-32b-base","score":57.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-32b-base","score":48.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-32b-base","score":89.3,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-32b-base","score":36.3,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-3-pt-27b","score":88.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-pt-27b","score":65.4,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3-pt-27b","score":87.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"gemma-3-pt-27b","score":73.4,"metric":"percent"},{"benchmark":"copa","model":"gemma-3-pt-27b","score":93,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-pt-27b","score":83,"metric":"percent"},{"benchmark":"lambada","model":"gemma-3-pt-27b","score":78.1,"metric":"percent"},{"benchmark":"openbookqa","model":"gemma-3-pt-27b","score":45,"metric":"percent"},{"benchmark":"piqa","model":"gemma-3-pt-27b","score":84.1,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-pt-27b","score":79,"metric":"percent"},{"benchmark":"wsc","model":"gemma-3-pt-27b","score":91.9,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-pt-27b","score":75.3,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3-pt-27b","score":35.7,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-pt-27b","score":61.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-pt-27b","score":49.4,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-pt-27b","score":17.6,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-pt-27b","score":82,"metric":"percent"},{"benchmark":"math","model":"gemma-3-pt-27b","score":25.8,"metric":"percent"},{"benchmark":"arc-easy","model":"nemotron-nano-12b-v2-base","score":83.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-nano-12b-v2-base","score":60.6,"metric":"percent"},{"benchmark":"boolq","model":"nemotron-nano-12b-v2-base","score":84.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"nemotron-nano-12b-v2-base","score":76.1,"metric":"percent"},{"benchmark":"copa","model":"nemotron-nano-12b-v2-base","score":85,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-nano-12b-v2-base","score":81.4,"metric":"percent"},{"benchmark":"lambada","model":"nemotron-nano-12b-v2-base","score":72.9,"metric":"percent"},{"benchmark":"openbookqa","model":"nemotron-nano-12b-v2-base","score":45.8,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-nano-12b-v2-base","score":82.8,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-nano-12b-v2-base","score":74.4,"metric":"percent"},{"benchmark":"wsc","model":"nemotron-nano-12b-v2-base","score":85.4,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-nano-12b-v2-base","score":77.9,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-nano-12b-v2-base","score":36.6,"metric":"percent"},{"benchmark":"bbh","model":"nemotron-nano-12b-v2-base","score":62,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-nano-12b-v2-base","score":53.1,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-nano-12b-v2-base","score":59.2,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-nano-12b-v2-base","score":84.1,"metric":"percent"},{"benchmark":"math","model":"nemotron-nano-12b-v2-base","score":68.3,"metric":"percent"},{"benchmark":"agieval-lsat-ar","model":"marin-32b-mantis","score":24.8,"metric":"percent"},{"benchmark":"agieval-lsat-ar","model":"marin-32b-bison","score":23.4,"metric":"percent"},{"benchmark":"agieval-lsat-ar","model":"olmo-2-32b-base","score":22.6,"metric":"percent"},{"benchmark":"agieval-lsat-ar","model":"qwen2.5-32b-base","score":30.4,"metric":"percent"},{"benchmark":"agieval-lsat-ar","model":"gemma-3-pt-27b","score":22.2,"metric":"percent"},{"benchmark":"agieval-lsat-ar","model":"nemotron-nano-12b-v2-base","score":28.7,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-1b-it","score":39.85,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.2-1b","score":45.46,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-1.5b","score":60.99,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-1.7b","score":62.46,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-3b","score":65.62,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.2-3b","score":59.69,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-4b","score":73.19,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-4b-it","score":58.37,"metric":"percent"},{"benchmark":"mmlu","model":"ouro-1.4b","score":67.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-1b-it","score":11.31,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-1b","score":11.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-1.5b","score":29.11,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":37.27,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-3b","score":37.87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-3b","score":33.34,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b","score":51.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-4b-it","score":34.61,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ouro-1.4b","score":48.62,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-1b-it","score":30.26,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.2-1b","score":30.72,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-1.5b","score":43.66,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-1.7b","score":53.51,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-3b","score":55.37,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.2-3b","score":39.45,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-4b","score":70.95,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-4b-it","score":66.32,"metric":"percent"},{"benchmark":"bbh","model":"ouro-1.4b","score":71.02,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-1b-it","score":39.25,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-1b","score":41.98,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-1.5b","score":54.44,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-1.7b","score":55.72,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-3b","score":55.46,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-3b","score":52.47,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-4b","score":63.65,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-4b-it","score":60.92,"metric":"percent"},{"benchmark":"arc-challenge","model":"ouro-1.4b","score":60.92,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-1b-it","score":56.12,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.2-1b","score":59.35,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-1.5b","score":67.73,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-1.7b","score":67.09,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-3b","score":74.54,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.2-3b","score":73.09,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-4b","score":75.66,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-4b-it","score":75.58,"metric":"percent"},{"benchmark":"hellaswag","model":"ouro-1.4b","score":74.29,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-1b-it","score":58.72,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.2-1b","score":62.75,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-1.5b","score":66.77,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3-1.7b","score":66.3,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-3b","score":70.17,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.2-3b","score":69.14,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3-4b","score":71.19,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-4b-it","score":71.07,"metric":"percent"},{"benchmark":"winogrande","model":"ouro-1.4b","score":72.3,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-1b-it","score":2.05,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-1b","score":7.05,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-1.5b","score":60.73,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-1.7b","score":70.28,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-3b","score":74.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-3b","score":67.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-4b","score":72.86,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-4b-it","score":68.69,"metric":"percent"},{"benchmark":"gsm8k","model":"ouro-1.4b","score":78.92,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-1b-it","score":41,"metric":"percent"},{"benchmark":"math500","model":"llama-3.2-1b","score":7.4,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-1.5b","score":17.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-1.7b","score":25.8,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-3b","score":42.6,"metric":"percent"},{"benchmark":"math500","model":"llama-3.2-3b","score":40.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-4b","score":59.6,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-4b-it","score":68.6,"metric":"percent"},{"benchmark":"math500","model":"ouro-1.4b","score":82.4,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-1b-it","score":6.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.2-1b","score":19.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-1.5b","score":52.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-1.7b","score":66.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-3b","score":68.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.2-3b","score":29.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-4b","score":77.4,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-4b-it","score":34.8,"metric":"percent"},{"benchmark":"humaneval","model":"ouro-1.4b","score":74.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-1b-it","score":5.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.2-1b","score":17.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-1.5b","score":46.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-1.7b","score":59.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-3b","score":62.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.2-3b","score":26.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-4b","score":70.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-4b-it","score":29.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ouro-1.4b","score":67.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-1b-it","score":12.4,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.2-1b","score":35.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-1.5b","score":60.3,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-1.7b","score":68,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-3b","score":63,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.2-3b","score":50.3,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-4b","score":78.8,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-4b-it","score":60.6,"metric":"percent"},{"benchmark":"mbpp","model":"ouro-1.4b","score":73,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-1b-it","score":10.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.2-1b","score":29.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-1.5b","score":50,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-1.7b","score":58.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-3b","score":54.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.2-3b","score":39.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-4b","score":65.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-4b-it","score":51.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ouro-1.4b","score":62.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-7b","score":74.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-8b","score":73.02,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b","score":76.63,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-12b-it","score":72.14,"metric":"percent"},{"benchmark":"mmlu","model":"ouro-2.6b","score":74.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-7b","score":43.55,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b","score":43.24,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b","score":53.72,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-12b-it","score":49.21,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ouro-2.6b","score":55.73,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-7b","score":53.72,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-8b","score":71.56,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-8b","score":77.65,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-12b-it","score":78.41,"metric":"percent"},{"benchmark":"bbh","model":"ouro-2.6b","score":80.46,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-7b","score":63.65,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-8b","score":60.75,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-8b","score":66.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-12b-it","score":72.44,"metric":"percent"},{"benchmark":"arc-challenge","model":"ouro-2.6b","score":66.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-7b","score":79.98,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-8b","score":81.97,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-8b","score":79.6,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-12b-it","score":83.68,"metric":"percent"},{"benchmark":"hellaswag","model":"ouro-2.6b","score":79.69,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-7b","score":76.48,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.1-8b","score":77.11,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3-8b","score":76.8,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-12b-it","score":77.74,"metric":"percent"},{"benchmark":"winogrande","model":"ouro-2.6b","score":75.85,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-7b","score":81.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b","score":78.17,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-8b","score":83.09,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-12b-it","score":77.18,"metric":"percent"},{"benchmark":"gsm8k","model":"ouro-2.6b","score":81.58,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-7b","score":61.2,"metric":"percent"},{"benchmark":"math500","model":"llama-3.1-8b","score":52.9,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b","score":62.3,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-12b-it","score":83.2,"metric":"percent"},{"benchmark":"math500","model":"ouro-2.6b","score":90.85,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-7b","score":79.3,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-8b","score":38.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-8b","score":84.8,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-12b-it","score":46.3,"metric":"percent"},{"benchmark":"humaneval","model":"ouro-2.6b","score":78.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-7b","score":70.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-8b","score":31.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-8b","score":75.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-12b-it","score":37.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ouro-2.6b","score":70.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-7b","score":73.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-8b","score":62.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-8b","score":79,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-12b-it","score":73.5,"metric":"percent"},{"benchmark":"mbpp","model":"ouro-2.6b","score":80.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-7b","score":63.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.1-8b","score":51.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-8b","score":67.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-12b-it","score":66.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ouro-2.6b","score":66.6,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-2.5-pro-preview-06-05","score":55.1,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-5-2025-08-07","score":51.1,"metric":"percent"},{"benchmark":"simpleqa","model":"o3-2025-04-16","score":50.5,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-235b-a22b-thinking-2507","score":50.4,"metric":"percent"},{"benchmark":"simpleqa","model":"grok-4-0709","score":50.3,"metric":"percent"},{"benchmark":"simpleqa","model":"o1-2024-12-17","score":47.2,"metric":"percent"},{"benchmark":"simpleqa","model":"grok-3","score":41.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-4.1-2025-04-14","score":40.9,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-4o-2024-08-06","score":38.4,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-opus-4.1-20250805","score":37.6,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-3.7-sonnet-20250219","score":37.5,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-3.5-sonnet-20241022","score":36.2,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-opus-4-20250514","score":32.3,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-r1-0528","score":31.9,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3","score":29.5,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-2.0-flash-001","score":28.2,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-2.5-flash-preview-05-20","score":27.8,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3.1","score":26.2,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-1.5-pro-002","score":26.1,"metric":"percent"},{"benchmark":"simpleqa","model":"mistral-large-2411","score":24.2,"metric":"percent"},{"benchmark":"simpleqa","model":"grok-2-1212","score":23.6,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-sonnet-4-20250514","score":23.1,"metric":"percent"},{"benchmark":"simpleqa","model":"o4-mini-2025-04-16","score":20.5,"metric":"percent"},{"benchmark":"simpleqa","model":"grok-3-mini","score":20.4,"metric":"percent"},{"benchmark":"simpleqa","model":"open-mixtral-8x22b-2404","score":19.3,"metric":"percent"},{"benchmark":"simpleqa","model":"o3-mini-2025-01-31","score":16.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-oss-120b","score":12.6,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-3.5-haiku-20241022","score":12.2,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-3.5-turbo-1106","score":11.9,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-27b-it","score":10,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-4o-mini-2024-07-18","score":9.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-1.5-flash-002","score":9.2,"metric":"percent"},{"benchmark":"simpleqa","model":"o1-mini-2024-09-12","score":8.9,"metric":"percent"},{"benchmark":"simpleqa","model":"granite-4.0-h-small","score":8.6,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-12b-it","score":6.1,"metric":"percent"},{"benchmark":"simpleqa","model":"ministral-8b-2410","score":5.9,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-oss-20b","score":5.5,"metric":"percent"},{"benchmark":"simpleqa","model":"codestral-2501","score":5.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-1.5-flash-8b-001","score":5,"metric":"percent"},{"benchmark":"simpleqa","model":"ministral-3b-2410","score":4.8,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-3-4b-it","score":3.8,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-instruct","score":53.7,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3-0324","score":46.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b","score":37,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4","score":48.5,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4","score":47.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4.1","score":44.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash","score":44.7,"metric":"percent"},{"benchmark":"ojbench","model":"kimi-k2-instruct","score":27.1,"metric":"percent"},{"benchmark":"ojbench","model":"deepseek-v3-0324","score":24,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-235b-a22b","score":11.3,"metric":"percent"},{"benchmark":"ojbench","model":"claude-sonnet-4","score":15.3,"metric":"percent"},{"benchmark":"ojbench","model":"claude-opus-4","score":19.6,"metric":"percent"},{"benchmark":"ojbench","model":"gpt-4.1","score":19.5,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-2.5-flash","score":19.5,"metric":"percent"},{"benchmark":"multipl-e","model":"kimi-k2-instruct","score":85.7,"metric":"percent"},{"benchmark":"multipl-e","model":"deepseek-v3-0324","score":83.1,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-235b-a22b","score":78.2,"metric":"percent"},{"benchmark":"multipl-e","model":"claude-sonnet-4","score":88.6,"metric":"percent"},{"benchmark":"multipl-e","model":"claude-opus-4","score":89.6,"metric":"percent"},{"benchmark":"multipl-e","model":"gpt-4.1","score":86.7,"metric":"percent"},{"benchmark":"multipl-e","model":"gemini-2.5-flash","score":85.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-instruct","score":65.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3-0324","score":38.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-4.1","score":54.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2-instruct","score":47.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v3-0324","score":25.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3-235b-a22b","score":20.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-sonnet-4","score":51,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-4.1","score":31.5,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"kimi-k2-instruct","score":18.3,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"deepseek-v3-0324","score":8,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"qwen3-235b-a22b","score":9,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"claude-sonnet-4","score":29.2,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"gpt-4.1","score":11.7,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"gemini-2.5-flash","score":14,"metric":"percent"},{"benchmark":"swe-lancer","model":"kimi-k2-instruct","score":39.1,"metric":"percent"},{"benchmark":"swe-lancer","model":"deepseek-v3-0324","score":30.5,"metric":"percent"},{"benchmark":"swe-lancer","model":"qwen3-235b-a22b","score":24.1,"metric":"percent"},{"benchmark":"swe-lancer","model":"claude-sonnet-4","score":40.8,"metric":"percent"},{"benchmark":"swe-lancer","model":"gpt-4.1","score":23,"metric":"percent"},{"benchmark":"swe-lancer","model":"gemini-2.5-flash","score":38.5,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"kimi-k2-instruct","score":27.8,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"deepseek-v3-0324","score":12.2,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"qwen3-235b-a22b","score":13.2,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"claude-sonnet-4","score":43.3,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"gpt-4.1","score":29.9,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"gemini-2.5-flash","score":5.7,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-instruct","score":30,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4","score":43.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-4.1","score":8.3,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"kimi-k2-instruct","score":25,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"deepseek-v3-0324","score":16.3,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"qwen3-235b-a22b","score":6.6,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"gpt-4.1","score":30.3,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"gemini-2.5-flash","score":16.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"kimi-k2-instruct","score":60,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-sonnet-4","score":56.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-opus-4","score":70.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-flash","score":44,"metric":"percent"},{"benchmark":"tau2-retail","model":"kimi-k2-instruct","score":70.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"deepseek-v3-0324","score":69.1,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-235b-a22b","score":57,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-sonnet-4","score":75,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4","score":81.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-4.1","score":74.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemini-2.5-flash","score":64.3,"metric":"percent"},{"benchmark":"tau2-airline","model":"kimi-k2-instruct","score":56.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"deepseek-v3-0324","score":39,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-235b-a22b","score":26.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-sonnet-4","score":55.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-opus-4","score":60,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-4.1","score":54.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"gemini-2.5-flash","score":42.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2-instruct","score":65.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v3-0324","score":32.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-235b-a22b","score":22.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-sonnet-4","score":45.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4","score":57,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-4.1","score":38.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash","score":16.9,"metric":"percent"},{"benchmark":"acebench","model":"kimi-k2-instruct","score":76.5,"metric":"percent"},{"benchmark":"acebench","model":"deepseek-v3-0324","score":72.7,"metric":"percent"},{"benchmark":"acebench","model":"qwen3-235b-a22b","score":70.5,"metric":"percent"},{"benchmark":"acebench","model":"claude-sonnet-4","score":76.2,"metric":"percent"},{"benchmark":"acebench","model":"claude-opus-4","score":75.6,"metric":"percent"},{"benchmark":"acebench","model":"gpt-4.1","score":80.1,"metric":"percent"},{"benchmark":"acebench","model":"gemini-2.5-flash","score":74.5,"metric":"percent"},{"benchmark":"aime-2024","model":"kimi-k2-instruct","score":69.6,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v3-0324","score":59.4,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-sonnet-4","score":43.4,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-opus-4","score":48.2,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4.1","score":46.5,"metric":"percent"},{"benchmark":"aime-2024","model":"gemini-2.5-flash","score":61.3,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2-instruct","score":49.5,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3-0324","score":46.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-235b-a22b","score":24.7,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4","score":33.1,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4.1","score":37,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash","score":46.6,"metric":"percent"},{"benchmark":"math500","model":"kimi-k2-instruct","score":97.4,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v3-0324","score":94,"metric":"percent"},{"benchmark":"math500","model":"claude-sonnet-4","score":94,"metric":"percent"},{"benchmark":"math500","model":"claude-opus-4","score":94.4,"metric":"percent"},{"benchmark":"math500","model":"gpt-4.1","score":92.4,"metric":"percent"},{"benchmark":"math500","model":"gemini-2.5-flash","score":95.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"kimi-k2-instruct","score":38.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3-0324","score":27.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-235b-a22b","score":11.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"claude-sonnet-4","score":15.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"claude-opus-4","score":15.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-4.1","score":19.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-2.5-flash","score":34.7,"metric":"percent"},{"benchmark":"cnmo-2024","model":"kimi-k2-instruct","score":74.3,"metric":"percent"},{"benchmark":"cnmo-2024","model":"deepseek-v3-0324","score":74.7,"metric":"percent"},{"benchmark":"cnmo-2024","model":"qwen3-235b-a22b","score":48.6,"metric":"percent"},{"benchmark":"cnmo-2024","model":"claude-sonnet-4","score":60.4,"metric":"percent"},{"benchmark":"cnmo-2024","model":"claude-opus-4","score":57.6,"metric":"percent"},{"benchmark":"cnmo-2024","model":"gpt-4.1","score":56.6,"metric":"percent"},{"benchmark":"cnmo-2024","model":"gemini-2.5-flash","score":75,"metric":"percent"},{"benchmark":"polymath","model":"kimi-k2-instruct","score":65.1,"metric":"percent"},{"benchmark":"polymath","model":"deepseek-v3-0324","score":59.5,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-235b-a22b","score":51.9,"metric":"percent"},{"benchmark":"polymath","model":"claude-sonnet-4","score":52.8,"metric":"percent"},{"benchmark":"polymath","model":"claude-opus-4","score":49.8,"metric":"percent"},{"benchmark":"polymath","model":"gpt-4.1","score":54,"metric":"percent"},{"benchmark":"polymath","model":"gemini-2.5-flash","score":49.9,"metric":"percent"},{"benchmark":"zebralogic","model":"kimi-k2-instruct","score":89,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-v3-0324","score":84,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-sonnet-4","score":79.7,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-opus-4","score":59.3,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4.1","score":58.5,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-2.5-flash","score":57.9,"metric":"percent"},{"benchmark":"autologi","model":"kimi-k2-instruct","score":89.5,"metric":"percent"},{"benchmark":"autologi","model":"deepseek-v3-0324","score":88.9,"metric":"percent"},{"benchmark":"autologi","model":"qwen3-235b-a22b","score":83.3,"metric":"percent"},{"benchmark":"autologi","model":"claude-sonnet-4","score":89.8,"metric":"percent"},{"benchmark":"autologi","model":"claude-opus-4","score":86.1,"metric":"percent"},{"benchmark":"autologi","model":"gpt-4.1","score":88.2,"metric":"percent"},{"benchmark":"autologi","model":"gemini-2.5-flash","score":84.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2-instruct","score":75.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3-0324","score":68.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-235b-a22b","score":62.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-sonnet-4","score":70,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4","score":74.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-4.1","score":66.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash","score":68.2,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3-0324","score":53.7,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-235b-a22b","score":50.2,"metric":"percent"},{"benchmark":"supergpqa","model":"claude-sonnet-4","score":55.7,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-4.1","score":50.8,"metric":"percent"},{"benchmark":"supergpqa","model":"gemini-2.5-flash","score":49.6,"metric":"percent"},{"benchmark":"hle","model":"kimi-k2-instruct","score":4.7,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3-0324","score":5.2,"metric":"percent"},{"benchmark":"hle","model":"qwen3-235b-a22b","score":5.7,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4","score":5.8,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4","score":7.1,"metric":"percent"},{"benchmark":"hle","model":"gpt-4.1","score":3.7,"metric":"percent"},{"benchmark":"hle","model":"gemini-2.5-flash","score":5.6,"metric":"percent"},{"benchmark":"mmlu","model":"kimi-k2-instruct","score":89.5,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3-0324","score":89.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-235b-a22b","score":87,"metric":"percent"},{"benchmark":"mmlu","model":"claude-sonnet-4","score":91.5,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-4","score":92.9,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4.1","score":90.4,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-2.5-flash","score":90.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-k2-instruct","score":92.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3-0324","score":90.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-235b-a22b","score":89.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-sonnet-4","score":93.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-opus-4","score":94.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4.1","score":92.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemini-2.5-flash","score":90.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2-instruct","score":81.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3-0324","score":81.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-a22b","score":77.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-sonnet-4","score":83.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4","score":86.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4.1","score":81.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-flash","score":79.4,"metric":"percent"},{"benchmark":"ifeval","model":"kimi-k2-instruct","score":89.8,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v3-0324","score":81.1,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-235b-a22b","score":83.2,"metric":"percent"},{"benchmark":"ifeval","model":"claude-sonnet-4","score":87.6,"metric":"percent"},{"benchmark":"ifeval","model":"claude-opus-4","score":87.4,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4.1","score":88,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-2.5-flash","score":84.3,"metric":"percent"},{"benchmark":"multichallenge","model":"kimi-k2-instruct","score":54.1,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v3-0324","score":31.4,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-235b-a22b","score":34,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-sonnet-4","score":46.8,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-opus-4","score":49,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-4.1","score":36.4,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-2.5-flash","score":39.5,"metric":"percent"},{"benchmark":"simpleqa","model":"kimi-k2-instruct","score":31,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3-0324","score":27.7,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-235b-a22b","score":13.2,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-sonnet-4","score":15.9,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-opus-4","score":22.8,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-4.1","score":42.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-2.5-flash","score":23.3,"metric":"percent"},{"benchmark":"livebench","model":"kimi-k2-instruct","score":76.4,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-v3-0324","score":72.4,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-235b-a22b","score":67.6,"metric":"percent"},{"benchmark":"livebench","model":"claude-sonnet-4","score":74.8,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4.1","score":69.8,"metric":"percent"},{"benchmark":"livebench","model":"gemini-2.5-flash","score":67.8,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"kimi-k2-instruct","score":54.5,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"deepseek-v3-0324","score":39.9,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"qwen3-235b-a22b","score":39.9,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"claude-sonnet-4","score":51.6,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"claude-opus-4","score":59.7,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"gpt-4.1","score":51.7,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"gemini-2.5-flash","score":48.7,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"kimi-k2-instruct","score":85,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"deepseek-v3-0324","score":59.3,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"qwen3-235b-a22b","score":59.8,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"claude-sonnet-4","score":54.6,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"claude-opus-4","score":68.5,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"gpt-4.1","score":61.5,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"gemini-2.5-flash","score":72.8,"metric":"percent"},{"benchmark":"facts-grounding","model":"kimi-k2-instruct","score":88.5,"metric":"percent"},{"benchmark":"facts-grounding","model":"deepseek-v3-0324","score":68.3,"metric":"percent"},{"benchmark":"facts-grounding","model":"qwen3-235b-a22b","score":68.5,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-sonnet-4","score":83.6,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-4.1","score":79.2,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-2.5-flash","score":86.6,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"deepseek-v3-0324","score":11.1,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"qwen3-235b-a22b","score":5.5,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"claude-sonnet-4","score":5.5,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"gpt-4.1","score":3.3,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"gemini-2.5-flash","score":2.2,"metric":"percent"},{"benchmark":"faithjudge-1-hallu","model":"kimi-k2-instruct","score":92.6,"metric":"percent"},{"benchmark":"faithjudge-1-hallu","model":"deepseek-v3-0324","score":83.4,"metric":"percent"},{"benchmark":"faithjudge-1-hallu","model":"qwen3-235b-a22b","score":75.7,"metric":"percent"},{"benchmark":"faithjudge-1-hallu","model":"claude-sonnet-4","score":83,"metric":"percent"},{"benchmark":"faithjudge-1-hallu","model":"gpt-4.1","score":91,"metric":"percent"},{"benchmark":"faithjudge-1-hallu","model":"gemini-2.5-flash","score":93.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"kimi-k2-instruct","score":49.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v3-0324","score":51.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-sonnet-4","score":52.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-4.1","score":54.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-2.5-flash","score":55.5,"metric":"percent"},{"benchmark":"frames","model":"kimi-k2-instruct","score":77.1,"metric":"percent"},{"benchmark":"frames","model":"deepseek-v3-0324","score":79.2,"metric":"percent"},{"benchmark":"frames","model":"claude-sonnet-4","score":76.3,"metric":"percent"},{"benchmark":"frames","model":"gpt-4.1","score":87.4,"metric":"percent"},{"benchmark":"frames","model":"gemini-2.5-flash","score":72.9,"metric":"percent"},{"benchmark":"mrcr-v2","model":"kimi-k2-instruct","score":55,"metric":"percent"},{"benchmark":"mrcr-v2","model":"deepseek-v3-0324","score":50.8,"metric":"percent"},{"benchmark":"mrcr-v2","model":"claude-sonnet-4","score":74.4,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gpt-4.1","score":66.9,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gemini-2.5-flash","score":81.7,"metric":"percent"},{"benchmark":"drop","model":"kimi-k2-instruct","score":93.5,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v3-0324","score":91.2,"metric":"percent"},{"benchmark":"drop","model":"qwen3-235b-a22b","score":84.3,"metric":"percent"},{"benchmark":"drop","model":"claude-sonnet-4","score":92,"metric":"percent"},{"benchmark":"drop","model":"gpt-4.1","score":79.1,"metric":"percent"},{"benchmark":"drop","model":"gemini-2.5-flash","score":81.7,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-4.5","score":62.5,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-4o","score":38.2,"metric":"percent"},{"benchmark":"simpleqa","model":"o1","score":47,"metric":"percent"},{"benchmark":"simpleqa","model":"o3-mini","score":15,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4.5","score":71.4,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4.5","score":36.7,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-4.5","score":85.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-4.5","score":38,"metric":"percent"},{"benchmark":"swe-lancer-diamond","model":"gpt-4.5","score":32.6,"metric":"percent"},{"benchmark":"swe-lancer-diamond","model":"gpt-4o","score":23.3,"metric":"percent"},{"benchmark":"swe-lancer-diamond","model":"o3-mini","score":10.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-linear-instruct","score":71.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-linear-instruct","score":86.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-linear-instruct","score":72.7,"metric":"percent"},{"benchmark":"faithjudge-1-hallu","model":"kimi-linear-instruct","score":64.2,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-linear-instruct","score":58.6,"metric":"percent"},{"benchmark":"math500","model":"kimi-linear-instruct","score":94.6,"metric":"percent"},{"benchmark":"hmmt-2025","model":"kimi-linear-instruct","score":44.5,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-linear-instruct","score":45.7,"metric":"percent"},{"benchmark":"ojbench","model":"kimi-linear-instruct","score":14.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kimi-linear-instruct","score":70.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kimi-linear-instruct","score":72.4,"metric":"percent"},{"benchmark":"ruler-128k","model":"kimi-linear-instruct","score":95.4,"metric":"percent"},{"benchmark":"ruler-1m","model":"kimi-linear-instruct","score":94.8,"metric":"percent"},{"benchmark":"triviaqa","model":"kimi-linear-base","score":75.2,"metric":"percent"},{"benchmark":"simpleqa","model":"kimi-linear-base","score":10.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-linear-base","score":54.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-linear-base","score":79.7,"metric":"percent"},{"benchmark":"winogrande","model":"kimi-linear-base","score":81.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-linear-base","score":40.4,"metric":"percent"},{"benchmark":"math","model":"kimi-linear-base","score":58.5,"metric":"percent"},{"benchmark":"gsm8k","model":"kimi-linear-base","score":86.3,"metric":"percent"},{"benchmark":"gsm8k-platinum","model":"kimi-linear-base","score":89.6,"metric":"percent"},{"benchmark":"cmath","model":"kimi-linear-base","score":85.5,"metric":"percent"},{"benchmark":"crux-i","model":"kimi-linear-base","score":61,"metric":"percent"},{"benchmark":"crux-o","model":"kimi-linear-base","score":67,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-linear-base","score":20,"metric":"percent"},{"benchmark":"evalplus","model":"kimi-linear-base","score":64.9,"metric":"percent"},{"benchmark":"c-eval","model":"kimi-linear-base","score":83.3,"metric":"percent"},{"benchmark":"csimpleqa","model":"kimi-linear-base","score":53.5,"metric":"percent"},{"benchmark":"math","model":"moonlight-base","score":45.3,"metric":"percent"},{"benchmark":"gsm8k","model":"moonlight-base","score":77.2,"metric":"percent"},{"benchmark":"gsm8k-platinum","model":"moonlight-base","score":79.4,"metric":"percent"},{"benchmark":"cmath","model":"moonlight-base","score":79.6,"metric":"percent"},{"benchmark":"crux-i","model":"moonlight-base","score":45.9,"metric":"percent"},{"benchmark":"crux-o","model":"moonlight-base","score":46.6,"metric":"percent"},{"benchmark":"livecodebench","model":"moonlight-base","score":14.3,"metric":"percent"},{"benchmark":"evalplus","model":"moonlight-base","score":50.3,"metric":"percent"},{"benchmark":"c-eval","model":"moonlight-base","score":77.6,"metric":"percent"},{"benchmark":"csimpleqa","model":"moonlight-base","score":34.7,"metric":"percent"},{"benchmark":"triviaqa","model":"moonlight-base","score":66.2,"metric":"percent"},{"benchmark":"simpleqa","model":"moonlight-base","score":5.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"moonlight-base","score":42.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"moonlight-base","score":73.8,"metric":"percent"},{"benchmark":"winogrande","model":"moonlight-base","score":74.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"moonlight-base","score":35.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"moonlight-instruct","score":24.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"moonlight-instruct","score":66.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"moonlight-instruct","score":43.8,"metric":"percent"},{"benchmark":"faithjudge-1-hallu","model":"moonlight-instruct","score":56,"metric":"percent"},{"benchmark":"math500","model":"moonlight-instruct","score":58,"metric":"percent"},{"benchmark":"livecodebench","model":"moonlight-instruct","score":11.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"moonlight-instruct","score":46.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"moonlight-instruct","score":56.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5-codex","score":35.5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-v3.2-exp","score":29.1,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-4.5-haiku","score":25.5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"minimax-m2","score":24.1,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"glm-4.6","score":23.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5-2025-08-07","score":26.32,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-2.5-pro-preview-06-05","score":22.06,"metric":"percent"},{"benchmark":"hle-text-only","model":"o3-high","score":20.57,"metric":"percent"},{"benchmark":"hle-text-only","model":"o3-medium","score":19.78,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5-mini-2025-08","score":19.74,"metric":"percent"},{"benchmark":"hle-text-only","model":"o4-mini-2025-04-16-high","score":18.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-2.5-pro-exp-03.25","score":18.38,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-2.5-pro-preview-05-06","score":18.38,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-oss-120b","score":15.48,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-235b-a22b-thinking-2507","score":15.43,"metric":"percent"},{"benchmark":"hle-text-only","model":"o4-mini-2025-04-16","score":14.53,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-4.5-sonnet-thinking","score":14.09,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-r1-0528","score":14.04,"metric":"percent"},{"benchmark":"hle-text-only","model":"o3-mini-2025-01-31-high","score":13.37,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v3.1","score":12.88,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-2.5-flash-04-17","score":12.58,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-235b-a22b","score":11.75,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4-1-20250805-thinking","score":11.26,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4-thinking","score":10.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-2.5-flash-preview-05-20","score":10.72,"metric":"percent"},{"benchmark":"hle-text-only","model":"o3-mini-2025-01-31-med","score":10.31,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-oss-20b","score":9.73,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-4.5","score":9.64,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-4.5-air","score":9.41,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-r1","score":8.54,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-3.7-sonnet-thinking","score":7.89,"metric":"percent"},{"benchmark":"hle-text-only","model":"o1-2024-12-17","score":7.75,"metric":"percent"},{"benchmark":"hle-text-only","model":"o1-pro","score":7.71,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-4.5","score":7.65,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-4-thinking","score":7.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4.1-20250805","score":7.37,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-2.0-flash-thinking-01-21","score":6.55,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4","score":6.26,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-4.5-preview","score":5.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-4","score":5.42,"metric":"percent"},{"benchmark":"hle-text-only","model":"llama-4-maverick","score":5.34,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-4.1","score":4.97,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2-instruct","score":4.68,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v3-0324","score":4.55,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-1.5-pro-002","score":4.55,"metric":"percent"},{"benchmark":"hle-text-only","model":"nova-micro","score":4.41,"metric":"percent"},{"benchmark":"hle-text-only","model":"mistral-medium-3","score":4.36,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-3.5-sonnet-20241022","score":4.32,"metric":"percent"},{"benchmark":"hle-text-only","model":"nova-pro","score":4.32,"metric":"percent"},{"benchmark":"hle-text-only","model":"nova-lite","score":3.76,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-4o-2024-11-20","score":2.32,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2-thinking","score":44.9,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2-thinking","score":60.2,"metric":"percent"},{"benchmark":"seal-0","model":"kimi-k2-thinking","score":56.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2-thinking","score":61.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-thinking","score":71.3,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-thinking","score":83.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5","score":41.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-4.5-sonnet-thinking","score":32,"metric":"percent"},{"benchmark":"hle-text-only","model":"grok-4","score":41,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2-0905","score":21.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v3.2","score":20.3,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-4.5-sonnet-thinking","score":24.1,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2-0905","score":7.4,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v3.2","score":51.4,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2-thinking","score":94.5,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2-0905","score":51,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.2","score":93.1,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4","score":91.7,"metric":"percent"},{"benchmark":"hmmt-2025","model":"kimi-k2-thinking","score":89.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-5","score":93.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"claude-sonnet-4.5","score":74.6,"metric":"percent"},{"benchmark":"hmmt-2025","model":"kimi-k2-0905","score":38.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.2","score":83.6,"metric":"percent"},{"benchmark":"hmmt-2025","model":"grok-4","score":90,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2-thinking","score":78.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5","score":76,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-4.5-sonnet-thinking","score":65.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2-0905","score":45.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v3.2","score":78.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"grok-4","score":73.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2-thinking","score":84.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-4.5-sonnet-thinking","score":83.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2-0905","score":74.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.2","score":82.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"grok-4","score":87.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2-thinking","score":84.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-4.5-sonnet-thinking","score":87.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.2","score":85,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-k2-thinking","score":94.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-5","score":95.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-4.5-sonnet-thinking","score":95.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-k2-0905","score":92.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3.2","score":93.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"kimi-k2-thinking","score":73.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-4.5-sonnet-thinking","score":79.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"kimi-k2-0905","score":62.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v3.2","score":72.5,"metric":"percent"},{"benchmark":"healthbench","model":"kimi-k2-thinking","score":58,"metric":"percent"},{"benchmark":"healthbench","model":"claude-4.5-sonnet-thinking","score":44.2,"metric":"percent"},{"benchmark":"healthbench","model":"kimi-k2-0905","score":43.8,"metric":"percent"},{"benchmark":"healthbench","model":"deepseek-v3.2","score":46.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"kimi-k2-thinking","score":62.3,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-5","score":63,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"claude-4.5-sonnet-thinking","score":42.4,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"kimi-k2-0905","score":22.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepseek-v3.2","score":65,"metric":"percent"},{"benchmark":"seal-0","model":"gpt-5","score":51.4,"metric":"percent"},{"benchmark":"seal-0","model":"claude-4.5-sonnet-thinking","score":53.4,"metric":"percent"},{"benchmark":"seal-0","model":"kimi-k2-0905","score":25.2,"metric":"percent"},{"benchmark":"seal-0","model":"deepseek-v3.2","score":38.5,"metric":"percent"},{"benchmark":"finsearchcomp","model":"kimi-k2-thinking","score":47.4,"metric":"percent"},{"benchmark":"finsearchcomp","model":"gpt-5","score":48.5,"metric":"percent"},{"benchmark":"finsearchcomp","model":"claude-4.5-sonnet-thinking","score":44,"metric":"percent"},{"benchmark":"finsearchcomp","model":"kimi-k2-0905","score":10.4,"metric":"percent"},{"benchmark":"finsearchcomp","model":"deepseek-v3.2","score":27,"metric":"percent"},{"benchmark":"frames","model":"kimi-k2-thinking","score":87,"metric":"percent"},{"benchmark":"frames","model":"gpt-5","score":86,"metric":"percent"},{"benchmark":"frames","model":"claude-4.5-sonnet-thinking","score":85,"metric":"percent"},{"benchmark":"frames","model":"kimi-k2-0905","score":58.1,"metric":"percent"},{"benchmark":"frames","model":"deepseek-v3.2","score":80.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-4.5-sonnet-thinking","score":77.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-0905","score":69.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.2","score":73.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5","score":55.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-4.5-sonnet-thinking","score":68,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2-0905","score":55.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v3.2","score":70.2,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"kimi-k2-thinking","score":41.9,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"gpt-5","score":39.3,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"claude-4.5-sonnet-thinking","score":44.3,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"kimi-k2-0905","score":33.5,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"deepseek-v3.2","score":30.6,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k2-thinking","score":44.8,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5","score":42.9,"metric":"percent"},{"benchmark":"scicode","model":"claude-4.5-sonnet-thinking","score":44.7,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v3.2","score":37.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5","score":87,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-4.5-sonnet-thinking","score":64,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-0905","score":56.1,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2","score":83.3,"metric":"percent"},{"benchmark":"ojbench","model":"kimi-k2-thinking","score":48.7,"metric":"percent"},{"benchmark":"ojbench","model":"gpt-5","score":56.2,"metric":"percent"},{"benchmark":"ojbench","model":"claude-4.5-sonnet-thinking","score":30.4,"metric":"percent"},{"benchmark":"ojbench","model":"kimi-k2-0905","score":25.5,"metric":"percent"},{"benchmark":"ojbench","model":"deepseek-v3.2","score":38.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-thinking","score":47.1,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-4.5-sonnet-thinking","score":51,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-0905","score":44.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.2","score":37.7,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gpt-4-1106-preview","score":97.7,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"mistral-medium","score":96.8,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gpt-4","score":95.3,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"mixtral-8x7b-instruct-v0.1","score":94.8,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gpt-4-0314","score":94.8,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"yi-34b-chat","score":94.1,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gpt-4-0613","score":93.8,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gpt-3.5-turbo-0613","score":93.4,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"mistral-7b-instruct-v0.2","score":92.8,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"llama-2-70b-chat","score":92.7,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"claude","score":91.6,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"claude-2","score":91.4,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"command","score":90.6,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gpt-3.5-turbo-0301","score":89.4,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"vicuna-33b-v1.3","score":89,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"claude-2.1","score":87.1,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gpt-3.5-turbo-1106","score":86.3,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"phi-2-dpo","score":82.3,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"vicuna-13b-v1.3","score":82.1,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"llama-2-13b-chat","score":81.1,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gemini-pro","score":79.7,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"vicuna-7b-v1.3","score":76.8,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"wizardlm-13b","score":75.3,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"guanaco-65b","score":71.8,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"llama-2-7b-chat","score":71.4,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"vicuna-13b","score":70.4,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"phi-2-sft","score":68.5,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"llama-33b-oasst-rlhf","score":66.5,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"guanaco-33b","score":66,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"nous-hermes-13b","score":65.5,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"vicuna-7b","score":64.4,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"llama-33b-oasst-sft","score":55,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"guanaco-13b","score":52.6,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"davinci-003","score":50,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"guanaco-7b","score":46.6,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"falcon-40b-instruct","score":45.7,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"falcon-7b-instruct","score":45.7,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"alpaca-farm-ppo-sim-gpt4-7b","score":44.1,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"pythia-12b-sft","score":41.9,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"alpaca-farm-ppo-human-7b","score":41.2,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"alpaca-7b","score":26.5,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"pythia-12b-oasst-sft","score":26,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"davinci-001","score":15.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2-thinking","score":93,"metric":"percent"},{"benchmark":"tau2-telecom","model":"minimax-m2","score":86.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-4.6","score":70.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-120b-high","score":65.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-20b-high","score":60.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-4.5-haiku","score":54.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-235b-a22b-2507","score":53.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash","score":45.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v3.2-exp","score":33.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"exaone-4.0-32b","score":17.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5","score":95.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-max","score":84.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2","score":65.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"o4-mini-2025-04-16","score":50.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-3.7-sonnet","score":49,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-4.1-mini","score":48.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-4.1","score":34,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5","score":49.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5-codex","score":44.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.1","score":38,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-2.5-pro","score":32.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"minimax-m2","score":30,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-4.5-haiku","score":29.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5-mini","score":31.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2-instruct","score":27.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"grok-4","score":27.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"grok-code-fast-1","score":25.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-coder-480b-a35b","score":25.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-4.6","score":24.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-oss-120b","score":18.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-2.5-flash","score":17.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5-nano","score":11.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-oss-20b","score":3.4,"metric":"percent"},{"benchmark":"aime-2024","model":"vibethinker-1.5b","score":80.3,"metric":"percent"},{"benchmark":"aime-2025","model":"vibethinker-1.5b","score":74.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"vibethinker-1.5b","score":50.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"vibethinker-1.5b","score":55.9,"metric":"percent"},{"benchmark":"livecodebench","model":"vibethinker-1.5b","score":51.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vibethinker-1.5b","score":46.7,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-medium-2506","score":73.6,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-medium-2506","score":64.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"magistral-medium-2506","score":59.4,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-medium-2506","score":50.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-medium-2506","score":70.8,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-opus-4","score":76,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4","score":69.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"claude-opus-4","score":56.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4","score":79.6,"metric":"percent"},{"benchmark":"aime-2024","model":"gemini-2.5-flash","score":80.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-2.5-flash","score":61.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash","score":82.8,"metric":"percent"},{"benchmark":"aime-2024","model":"o3-mini-medium","score":79.6,"metric":"percent"},{"benchmark":"aime-2025","model":"o3-mini-medium","score":74.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"o3-mini-medium","score":53,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o3-mini-medium","score":66.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o3-mini-medium","score":76.8,"metric":"percent"},{"benchmark":"aime-2024","model":"mimo-7b-rl","score":68.2,"metric":"percent"},{"benchmark":"aime-2025","model":"mimo-7b-rl","score":55.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"mimo-7b-rl","score":38.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"mimo-7b-rl","score":57.8,"metric":"percent"},{"benchmark":"livecodebench","model":"mimo-7b-rl","score":49.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-7b-rl","score":54.4,"metric":"percent"},{"benchmark":"aime-2024","model":"skywork-or1-7b","score":70.2,"metric":"percent"},{"benchmark":"aime-2025","model":"skywork-or1-7b","score":54.6,"metric":"percent"},{"benchmark":"hmmt-2025","model":"skywork-or1-7b","score":32,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"skywork-or1-7b","score":47.6,"metric":"percent"},{"benchmark":"livecodebench","model":"skywork-or1-7b","score":42.7,"metric":"percent"},{"benchmark":"aime-2024","model":"acereason-nemotron-1.1","score":72.6,"metric":"percent"},{"benchmark":"aime-2025","model":"acereason-nemotron-1.1","score":64.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"acereason-nemotron-1.1","score":42.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"acereason-nemotron-1.1","score":57.2,"metric":"percent"},{"benchmark":"livecodebench","model":"acereason-nemotron-1.1","score":52.1,"metric":"percent"},{"benchmark":"aime-2024","model":"glm-z1","score":75.6,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-z1","score":55.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"glm-z1","score":49.1,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-z1","score":42.3,"metric":"percent"},{"benchmark":"aime-2024","model":"phi-4-reasoning","score":74.6,"metric":"percent"},{"benchmark":"aime-2025","model":"phi-4-reasoning","score":63.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"phi-4-reasoning","score":43.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"phi-4-reasoning","score":53.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"phi-4-reasoning","score":67.1,"metric":"percent"},{"benchmark":"aime-2024","model":"ring-lite","score":76.6,"metric":"percent"},{"benchmark":"aime-2025","model":"ring-lite","score":69.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"ring-lite","score":60.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ring-lite","score":61.1,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-20b-medium","score":80,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b-medium","score":72.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b-medium","score":66,"metric":"percent"},{"benchmark":"aime-2024","model":"magistral-small-2506","score":70.7,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-small-2506","score":62.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"magistral-small-2506","score":43.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"magistral-small-2506","score":55.8,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-small-2506","score":47.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-small-2506","score":68.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-32b","score":50.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b","score":60.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-32b","score":68.4,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-nemotron-super-v1","score":67.5,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-nemotron-super-v1","score":60,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"llama-nemotron-super-v1","score":45.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-nemotron-super-v1","score":66.7,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-distill-llama-70b","score":70,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepseek-r1-distill-llama-70b","score":57.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-distill-llama-70b","score":65.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"seed-thinking-v1.5","score":64.9,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.1-nemotron-ultra-253b-v1","score":80.8,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.1-nemotron-ultra-253b-v1","score":72.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"llama-3.1-nemotron-ultra-253b-v1","score":66.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-nemotron-ultra-253b-v1","score":76,"metric":"percent"},{"benchmark":"aime-2024","model":"minimax-m1","score":83.3,"metric":"percent"},{"benchmark":"aime-2025","model":"minimax-m1","score":74.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"minimax-m1","score":62.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m1","score":69.2,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-0120","score":79.8,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0120","score":70,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-r1-0120","score":41.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepseek-r1-0120","score":65.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-0120","score":71.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4","score":22.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-sonnet-4","score":23,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v3","score":37,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2-instruct","score":45.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-235b-a22b","score":53.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-r1","score":60.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"o3","score":61.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5","score":65.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"o4-mini-high","score":67.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-2.5-pro","score":68.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-2.5-deep-think","score":71.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-deep-think-imo-gold","score":80,"metric":"percent"},{"benchmark":"mathvista","model":"ernie-4.5-vl-28b-a3b-thinking","score":82.5,"metric":"percent"},{"benchmark":"mathverse-vision","model":"ernie-4.5-vl-28b-a3b-thinking","score":81,"metric":"percent"},{"benchmark":"mathvision","model":"ernie-4.5-vl-28b-a3b-thinking","score":61.9,"metric":"percent"},{"benchmark":"mmmu","model":"ernie-4.5-vl-28b-a3b-thinking","score":72.2,"metric":"percent"},{"benchmark":"mmlu","model":"baguettotron-321m","score":40,"metric":"percent"},{"benchmark":"gsm8k","model":"baguettotron-321m","score":39,"metric":"percent"},{"benchmark":"hotpotqa","model":"baguettotron-321m","score":51,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-270m-it","score":25,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-270m-it","score":3,"metric":"percent"},{"benchmark":"hotpotqa","model":"gemma-3-270m-it","score":23,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2-350m","score":44,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2-350m","score":34,"metric":"percent"},{"benchmark":"hotpotqa","model":"lfm2-350m","score":25,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4-h-300m","score":36,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4-h-300m","score":39,"metric":"percent"},{"benchmark":"hotpotqa","model":"granite-4-h-300m","score":21,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4-300m","score":35,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4-300m","score":31,"metric":"percent"},{"benchmark":"hotpotqa","model":"granite-4-300m","score":25,"metric":"percent"},{"benchmark":"mmlu","model":"smollm2-360m-instruct","score":25,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-360m-instruct","score":11,"metric":"percent"},{"benchmark":"hotpotqa","model":"smollm2-360m-instruct","score":16,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-0.6b","score":44,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-0.6b","score":40,"metric":"percent"},{"benchmark":"hotpotqa","model":"qwen3-0.6b","score":64,"metric":"percent"},{"benchmark":"hle","model":"mirothinker-v1.0-72b","score":37.7,"metric":"avg@3"},{"benchmark":"browsecomp","model":"mirothinker-v1.0-72b","score":47.1,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"mirothinker-v1.0-72b","score":55.6,"metric":"avg@3"},{"benchmark":"gaia","model":"mirothinker-v1.0-72b","score":81.9,"metric":"avg@8"},{"benchmark":"xbench-deepsearch","model":"mirothinker-v1.0-72b","score":77.8,"metric":"avg@8"},{"benchmark":"seal-0","model":"mirothinker-v1.0-72b","score":51,"metric":"avg@8"},{"benchmark":"mmlu","model":"motif-2-12.7b-base","score":78.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-14b","score":81.05,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-32b","score":83.61,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b","score":81.38,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-12b","score":74.5,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b","score":78.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"motif-2-12.7b-base","score":78.68,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-14b","score":79.88,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-32b","score":83.41,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-30b-a3b","score":81.17,"metric":"percent"},{"benchmark":"mmlu-pro","model":"motif-2-12.7b-base","score":66.38,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-14b","score":61.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b","score":65.54,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b","score":61.49,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-12b","score":45.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-27b","score":52.2,"metric":"percent"},{"benchmark":"supergpqa","model":"motif-2-12.7b-base","score":32.68,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-14b","score":34.27,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-32b","score":39.78,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-30b-a3b","score":35.72,"metric":"percent"},{"benchmark":"bbh","model":"motif-2-12.7b-base","score":81.34,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-14b","score":81.07,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-32b","score":87.38,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-30b-a3b","score":81.54,"metric":"percent"},{"benchmark":"gpqa","model":"motif-2-12.7b-base","score":42.18,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-14b","score":39.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b","score":49.49,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-30b-a3b","score":43.94,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"motif-2-12.7b-base","score":42.92,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-12b","score":25.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-27b","score":24.3,"metric":"percent"},{"benchmark":"gsm8k","model":"motif-2-12.7b-base","score":93.85,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-14b","score":92.49,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-32b","score":93.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b","score":91.81,"metric":"percent"},{"benchmark":"gsm8k","model":"motif-2-12.7b-base","score":94.92,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-12b","score":71,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-27b","score":82.6,"metric":"percent"},{"benchmark":"math","model":"motif-2-12.7b-base","score":73.62,"metric":"percent"},{"benchmark":"math","model":"qwen3-14b","score":62.02,"metric":"percent"},{"benchmark":"math","model":"qwen3-32b","score":61.62,"metric":"percent"},{"benchmark":"math","model":"qwen3-30b-a3b","score":59.04,"metric":"percent"},{"benchmark":"math","model":"gemma-3-12b","score":43.3,"metric":"percent"},{"benchmark":"math","model":"gemma-3-27b","score":50,"metric":"percent"},{"benchmark":"evalplus","model":"motif-2-12.7b-base","score":72.22,"metric":"percent"},{"benchmark":"evalplus","model":"qwen3-14b","score":72.23,"metric":"percent"},{"benchmark":"evalplus","model":"qwen3-32b","score":72.05,"metric":"percent"},{"benchmark":"evalplus","model":"qwen3-30b-a3b","score":71.45,"metric":"percent"},{"benchmark":"mbpp","model":"motif-2-12.7b-base","score":81.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-14b","score":73.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-32b","score":78.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-30b-a3b","score":74.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-12b","score":60.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-27b","score":65.6,"metric":"percent"},{"benchmark":"crux-o","model":"motif-2-12.7b-base","score":63.1,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-14b","score":68.6,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-32b","score":72.5,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-30b-a3b","score":67.2,"metric":"percent"},{"benchmark":"humaneval","model":"motif-2-12.7b-base","score":65.9,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-12b","score":45.7,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-27b","score":48.8,"metric":"percent"},{"benchmark":"drop","model":"motif-2-12.7b-base","score":69.9,"metric":"percent"},{"benchmark":"drop","model":"gemma-3-12b","score":72.2,"metric":"percent"},{"benchmark":"drop","model":"gemma-3-27b","score":77.2,"metric":"percent"},{"benchmark":"hellaswag","model":"motif-2-12.7b-base","score":84,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-12b","score":84.2,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-27b","score":85.6,"metric":"percent"},{"benchmark":"boolq","model":"motif-2-12.7b-base","score":78.5,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3-12b","score":78.8,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3-27b","score":82.4,"metric":"percent"},{"benchmark":"piqa","model":"motif-2-12.7b-base","score":81.6,"metric":"percent"},{"benchmark":"piqa","model":"gemma-3-12b","score":81.8,"metric":"percent"},{"benchmark":"piqa","model":"gemma-3-27b","score":83.3,"metric":"percent"},{"benchmark":"siqa","model":"motif-2-12.7b-base","score":53.8,"metric":"percent"},{"benchmark":"siqa","model":"gemma-3-12b","score":53.4,"metric":"percent"},{"benchmark":"siqa","model":"gemma-3-27b","score":54.9,"metric":"percent"},{"benchmark":"triviaqa","model":"motif-2-12.7b-base","score":72.2,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-12b","score":78.2,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-27b","score":85.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"motif-2-12.7b-base","score":29.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"gemma-3-12b","score":31.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"gemma-3-27b","score":36.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"motif-2-12.7b-base","score":69.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-12b","score":68.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-27b","score":70.6,"metric":"percent"},{"benchmark":"arc-easy","model":"motif-2-12.7b-base","score":84.1,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-3-12b","score":88.3,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-3-27b","score":89,"metric":"percent"},{"benchmark":"winogrande","model":"motif-2-12.7b-base","score":79.6,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-12b","score":74.3,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-27b","score":78.8,"metric":"percent"},{"benchmark":"bbh","model":"motif-2-12.7b-base","score":81.3,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-12b","score":72.6,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-27b","score":77.7,"metric":"percent"},{"benchmark":"mmlu","model":"motif-2-12.7b-instruct","score":86.11,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-12b-it","score":71.9,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b-it","score":76.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"motif-2-12.7b-instruct","score":90.02,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-72b-instruct","score":86.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-14b","score":82,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-14b-thinking","score":88.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-30b-a3b","score":84.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-30b-a3b-thinking-2507","score":89.5,"metric":"percent"},{"benchmark":"bbh","model":"motif-2-12.7b-instruct","score":85.78,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"motif-2-12.7b-instruct","score":63.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen2.5-72b-instruct","score":49,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-14b-thinking","score":64,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-32b-nothinking","score":54.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-32b-thinking","score":68.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b","score":54.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-thinking-2507","score":65.8,"metric":"percent"},{"benchmark":"gsm8k","model":"motif-2-12.7b-instruct","score":96.13,"metric":"percent"},{"benchmark":"math","model":"motif-2-12.7b-instruct","score":97,"metric":"percent"},{"benchmark":"math","model":"gemma-3-27b-it","score":89,"metric":"percent"},{"benchmark":"mbpp","model":"motif-2-12.7b-instruct","score":91,"metric":"percent"},{"benchmark":"livebench","model":"motif-2-12.7b-instruct","score":33.8,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-72b-instruct","score":51.4,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-14b","score":59.6,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-14b-thinking","score":71.3,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-30b-a3b","score":59.4,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-30b-a3b-thinking-2507","score":74.3,"metric":"percent"},{"benchmark":"ifeval","model":"motif-2-12.7b-instruct","score":75.78,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-72b-instruct","score":84.1,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-14b","score":84.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-14b-thinking","score":85.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b","score":83.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-thinking-2507","score":86.5,"metric":"percent"},{"benchmark":"ifeval","model":"motif-2-12.7b-instruct","score":76.52,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-27b-it","score":90.4,"metric":"percent"},{"benchmark":"math500","model":"motif-2-12.7b-instruct","score":96.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-14b","score":90,"metric":"percent"},{"benchmark":"math500","model":"qwen3-14b-thinking","score":96.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-32b-nothinking","score":88.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-32b-thinking","score":97.2,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b","score":89.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b-thinking-2507","score":98,"metric":"percent"},{"benchmark":"aime-2024","model":"motif-2-12.7b-instruct","score":72.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-72b-instruct","score":18.9,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-14b","score":31.7,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-14b-thinking","score":79.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-32b-nothinking","score":31,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-32b-thinking","score":81.4,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b","score":32.8,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b-thinking-2507","score":80.4,"metric":"percent"},{"benchmark":"aime-2025","model":"motif-2-12.7b-instruct","score":63.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-72b-instruct","score":15,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-14b","score":23.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-14b-thinking","score":70.4,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b","score":21.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-thinking-2507","score":70.9,"metric":"percent"},{"benchmark":"zebralogic","model":"motif-2-12.7b-instruct","score":69.5,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen2.5-72b-instruct","score":26.6,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-14b","score":33,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-14b-thinking","score":88.5,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-32b-nothinking","score":29.2,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-32b-thinking","score":88.8,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-30b-a3b","score":33.2,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-30b-a3b-thinking-2507","score":89.5,"metric":"percent"},{"benchmark":"bfcl","model":"motif-2-12.7b-instruct","score":55.34,"metric":"percent"},{"benchmark":"bfcl","model":"qwen2.5-72b-instruct","score":63.4,"metric":"percent"},{"benchmark":"bfcl","model":"qwen3-14b","score":61.5,"metric":"percent"},{"benchmark":"bfcl","model":"qwen3-14b-thinking","score":70.4,"metric":"percent"},{"benchmark":"bfcl","model":"qwen3-32b-nothinking","score":63,"metric":"percent"},{"benchmark":"bfcl","model":"qwen3-32b-thinking","score":70.3,"metric":"percent"},{"benchmark":"bfcl","model":"qwen3-30b-a3b","score":58.6,"metric":"percent"},{"benchmark":"bfcl","model":"qwen3-30b-a3b-thinking-2507","score":69.1,"metric":"percent"},{"benchmark":"livecodebench","model":"motif-2-12.7b-instruct","score":50.03,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-72b-instruct","score":30.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-14b-thinking","score":63.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b-nothinking","score":31.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b-thinking","score":65.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b","score":29.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-thinking-2507","score":62.6,"metric":"percent"},{"benchmark":"livecodebench","model":"motif-2-12.7b-instruct","score":61.66,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-12b-it","score":32,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-27b-it","score":39,"metric":"percent"},{"benchmark":"humaneval","model":"motif-2-12.7b-instruct","score":93.2,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"ernie-4.5-vl-28b-a3b-thinking","score":77.3,"metric":"percent"},{"benchmark":"visulogic","model":"ernie-4.5-vl-28b-a3b-thinking","score":52.5,"metric":"percent"},{"benchmark":"chartqa","model":"ernie-4.5-vl-28b-a3b-thinking","score":87.1,"metric":"percent"},{"benchmark":"ai2d","model":"ernie-4.5-vl-28b-a3b-thinking","score":95.3,"metric":"percent"},{"benchmark":"docvqa","model":"ernie-4.5-vl-28b-a3b-thinking","score":93.6,"metric":"percent"},{"benchmark":"ocrbench-elo","model":"ernie-4.5-vl-28b-a3b-thinking","score":858,"metric":"score"},{"benchmark":"charxiv-rq","model":"ernie-4.5-vl-28b-a3b-thinking","score":56.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"ernie-4.5-vl-28b-a3b-thinking","score":90.3,"metric":"percent"},{"benchmark":"simplevqa","model":"ernie-4.5-vl-28b-a3b-thinking","score":53.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"ernie-4.5-vl-28b-a3b-thinking","score":60.4,"metric":"percent"},{"benchmark":"mmstar","model":"ernie-4.5-vl-28b-a3b-thinking","score":71.1,"metric":"percent"},{"benchmark":"blink","model":"ernie-4.5-vl-28b-a3b-thinking","score":62.8,"metric":"percent"},{"benchmark":"cv-bench","model":"ernie-4.5-vl-28b-a3b-thinking","score":83.8,"metric":"percent"},{"benchmark":"countbench","model":"ernie-4.5-vl-28b-a3b-thinking","score":89,"metric":"percent"},{"benchmark":"tempcompass","model":"ernie-4.5-vl-28b-a3b-thinking","score":75.1,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-pro","score":82.7,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5-high","score":81.3,"metric":"percent"},{"benchmark":"mathverse-vision","model":"gemini-2.5-pro","score":82.9,"metric":"percent"},{"benchmark":"mathverse-vision","model":"gpt-5-high","score":84.1,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"gemini-2.5-pro","score":76.5,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"gpt-5-high","score":69.6,"metric":"percent"},{"benchmark":"visulogic","model":"gpt-5-high","score":28.5,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-pro","score":76.3,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5-high","score":78.2,"metric":"percent"},{"benchmark":"visualpuzzle","model":"gemini-2.5-pro","score":55.8,"metric":"percent"},{"benchmark":"visualpuzzle","model":"gpt-5-high","score":57.8,"metric":"percent"},{"benchmark":"visualpuzzle","model":"ernie-4.5-vl-28b-a3b-thinking","score":52.5,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-pro","score":96.4,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-high","score":95.6,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-pro","score":91.2,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5-high","score":94.2,"metric":"percent"},{"benchmark":"ocrbench-elo","model":"gemini-2.5-pro","score":866,"metric":"elo"},{"benchmark":"ocrbench-elo","model":"gpt-5-high","score":810,"metric":"elo"},{"benchmark":"charxiv-rq","model":"gpt-5-high","score":81.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-2.5-pro","score":93.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5-high","score":91.2,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-2.5-pro","score":84.8,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-5-high","score":85,"metric":"percent"},{"benchmark":"tempcompass","model":"gemini-2.5-pro","score":75.8,"metric":"percent"},{"benchmark":"tempcompass","model":"gpt-5-high","score":82.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3-pro","score":37.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-pro","score":31.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3-pro","score":91.9,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3-pro","score":95,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3-pro","score":81,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gemini-3-pro","score":72.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3-pro","score":81.4,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-3-pro","score":87.6,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-3-pro","score":54.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3-pro","score":76.2,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-3-pro","score":72.1,"metric":"percent"},{"benchmark":"mmmlu","model":"gemini-3-pro","score":91.8,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gemini-3-pro","score":77,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-3-pro","score":26.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3-pro","score":45.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"gemini-3-pro","score":23.4,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gemini-3-pro","score":0.115,"metric":"edit_distance"},{"benchmark":"livecodebench-pro","model":"gemini-3-pro","score":2439,"metric":"elo"},{"benchmark":"vending-bench-2","model":"gemini-3-pro","score":5478.16,"metric":"net_worth_mean"},{"benchmark":"facts-benchmark-suite","model":"gemini-3-pro","score":70.5,"metric":"percent"},{"benchmark":"global-piqa","model":"gemini-3-pro","score":93.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-2.5-pro","score":21.6,"metric":"percent"},{"benchmark":"matharena-apex","model":"gemini-2.5-pro","score":0.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-pro","score":68,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gemini-2.5-pro","score":11.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-pro","score":69.6,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gemini-2.5-pro","score":0.145,"metric":"edit_distance"},{"benchmark":"livecodebench-pro","model":"gemini-2.5-pro","score":1775,"metric":"elo"},{"benchmark":"terminal-bench","model":"gemini-2.5-pro","score":32.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-2.5-pro","score":59.6,"metric":"percent"},{"benchmark":"vending-bench-2","model":"gemini-2.5-pro","score":573.64,"metric":"net_worth_mean"},{"benchmark":"facts-benchmark-suite","model":"gemini-2.5-pro","score":63.4,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-2.5-pro","score":54.5,"metric":"percent"},{"benchmark":"mmmlu","model":"gemini-2.5-pro","score":89.5,"metric":"percent"},{"benchmark":"global-piqa","model":"gemini-2.5-pro","score":91.5,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gemini-2.5-pro","score":58,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-2.5-pro","score":16.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-4.5","score":13.7,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4.5","score":100,"metric":"percent"},{"benchmark":"matharena-apex","model":"claude-sonnet-4.5","score":1.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-sonnet-4.5","score":68,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-sonnet-4.5","score":68.5,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"claude-sonnet-4.5","score":0.145,"metric":"edit_distance"},{"benchmark":"videommmu","model":"claude-sonnet-4.5","score":77.8,"metric":"percent"},{"benchmark":"livecodebench-pro","model":"claude-sonnet-4.5","score":1418,"metric":"elo"},{"benchmark":"terminal-bench","model":"claude-sonnet-4.5","score":42.8,"metric":"percent"},{"benchmark":"vending-bench-2","model":"claude-sonnet-4.5","score":3838.74,"metric":"net_worth_mean"},{"benchmark":"facts-benchmark-suite","model":"claude-sonnet-4.5","score":50.4,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-sonnet-4.5","score":29.3,"metric":"percent"},{"benchmark":"global-piqa","model":"claude-sonnet-4.5","score":90.1,"metric":"percent"},{"benchmark":"mrcr-128k","model":"claude-sonnet-4.5","score":47.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.1","score":26.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.1","score":17.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.1","score":88.1,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.1","score":94,"metric":"percent"},{"benchmark":"matharena-apex","model":"gpt-5.1","score":1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.1","score":76,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5.1","score":3.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.1","score":69.5,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.1","score":0.147,"metric":"edit_distance"},{"benchmark":"videommmu","model":"gpt-5.1","score":80.4,"metric":"percent"},{"benchmark":"livecodebench-pro","model":"gpt-5.1","score":2243,"metric":"elo"},{"benchmark":"terminal-bench","model":"gpt-5.1","score":47.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.1","score":76.3,"metric":"percent"},{"benchmark":"vending-bench-2","model":"gpt-5.1","score":1473.43,"metric":"net_worth_mean"},{"benchmark":"facts-benchmark-suite","model":"gpt-5.1","score":50.8,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-5.1","score":34.9,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5.1","score":91,"metric":"percent"},{"benchmark":"global-piqa","model":"gpt-5.1","score":90.9,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gpt-5.1","score":61.6,"metric":"percent"},{"benchmark":"bbh","model":"claude-3.5-sonnet","score":93.1,"metric":"percent"},{"benchmark":"bbh","model":"gemini-1.5-pro","score":89.2,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-27b","score":87.6,"metric":"percent"},{"benchmark":"bbh","model":"claude-3-sonnet","score":82.9,"metric":"percent"},{"benchmark":"bbh","model":"phi-3.5-moe-instruct","score":79.1,"metric":"percent"},{"benchmark":"bbh","model":"claude-3-haiku","score":73.7,"metric":"percent"},{"benchmark":"wmdp-bio","model":"grok-4","score":87,"metric":"percent"},{"benchmark":"wmdp-bio","model":"grok-4.1-thinking","score":87,"metric":"percent"},{"benchmark":"wmdp-chem","model":"grok-4","score":83,"metric":"percent"},{"benchmark":"wmdp-chem","model":"grok-4.1-thinking","score":84,"metric":"percent"},{"benchmark":"wmdp-cyber","model":"grok-4","score":79,"metric":"percent"},{"benchmark":"wmdp-cyber","model":"grok-4.1-thinking","score":84,"metric":"percent"},{"benchmark":"makemesay","model":"grok-4","score":13,"metric":"percent"},{"benchmark":"makemesay","model":"grok-4.1-thinking","score":0,"metric":"percent"},{"benchmark":"vct","model":"grok-4","score":55,"metric":"percent"},{"benchmark":"vct","model":"grok-4.1-thinking","score":61,"metric":"percent"},{"benchmark":"biolp-bench","model":"grok-4","score":47,"metric":"percent"},{"benchmark":"biolp-bench","model":"grok-4.1-thinking","score":37,"metric":"percent"},{"benchmark":"protocolqa","model":"grok-4","score":76,"metric":"percent"},{"benchmark":"protocolqa","model":"grok-4.1-thinking","score":79,"metric":"percent"},{"benchmark":"figqa","model":"grok-4","score":29,"metric":"percent"},{"benchmark":"figqa","model":"grok-4.1-thinking","score":34,"metric":"percent"},{"benchmark":"cloningscenarios","model":"grok-4","score":45,"metric":"percent"},{"benchmark":"cloningscenarios","model":"grok-4.1-thinking","score":46,"metric":"percent"},{"benchmark":"cybench","model":"grok-4","score":43,"metric":"percent"},{"benchmark":"cybench","model":"grok-4.1-thinking","score":39,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"cogito-671b-v2.1","score":42,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"cogito-671b-v2.1","score":77.72,"metric":"percent"},{"benchmark":"mmlu-pro","model":"cogito-671b-v2.1","score":84.69,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"cogito-671b-v2.1","score":86.24,"metric":"percent"},{"benchmark":"hle","model":"cogito-671b-v2.1","score":16.66,"metric":"percent"},{"benchmark":"simpleqa","model":"cogito-671b-v2.1","score":30.94,"metric":"percent"},{"benchmark":"aime-2025","model":"cogito-671b-v2.1","score":89.47,"metric":"percent"},{"benchmark":"math500","model":"cogito-671b-v2.1","score":98.57,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-32b-sft","score":95.6,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-32b-dpo","score":95.9,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-32b","score":96.1,"metric":"percent"},{"benchmark":"math","model":"qwen3-32b","score":95.4,"metric":"percent"},{"benchmark":"math","model":"qwen3-vl-32b-thinking","score":96.7,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-32b-instruct","score":80.2,"metric":"percent"},{"benchmark":"math","model":"gemma-3-27b-it","score":87.4,"metric":"percent"},{"benchmark":"math","model":"gemma-2-27b-it","score":51.5,"metric":"percent"},{"benchmark":"math","model":"olmo-2-0325-32b-instruct","score":49.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-r1-distill-qwen-32b","score":92.6,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-32b-sft","score":73.5,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-32b-dpo","score":76,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-32b","score":76.8,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-32b","score":80.8,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-vl-32b-thinking","score":86.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-32b-instruct","score":15.7,"metric":"percent"},{"benchmark":"aime-2024","model":"gemma-3-27b-it","score":28.9,"metric":"percent"},{"benchmark":"aime-2024","model":"gemma-2-27b-it","score":4.7,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-2-0325-32b-instruct","score":4.6,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-distill-qwen-32b","score":70.3,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-32b-sft","score":66.2,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-32b-dpo","score":70.7,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-32b","score":72.5,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b","score":70.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-32b-thinking","score":78.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-32b-instruct","score":13.4,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-27b-it","score":22.9,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-2-27b-it","score":0.9,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-2-0325-32b-instruct","score":0.9,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-distill-qwen-32b","score":56.3,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-think-32b-sft","score":43.1,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-think-32b-dpo","score":45.2,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-think-32b","score":50.8,"metric":"percent"},{"benchmark":"omega","model":"qwen3-32b","score":47.7,"metric":"percent"},{"benchmark":"omega","model":"qwen3-vl-32b-thinking","score":50.8,"metric":"percent"},{"benchmark":"omega","model":"qwen2.5-32b-instruct","score":19.2,"metric":"percent"},{"benchmark":"omega","model":"gemma-3-27b-it","score":24,"metric":"percent"},{"benchmark":"omega","model":"gemma-2-27b-it","score":9.1,"metric":"percent"},{"benchmark":"omega","model":"olmo-2-0325-32b-instruct","score":9.8,"metric":"percent"},{"benchmark":"omega","model":"deepseek-r1-distill-qwen-32b","score":38.9,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-32b-sft","score":88.8,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-32b-dpo","score":89.1,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-32b","score":89.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-32b","score":90.6,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-vl-32b-thinking","score":91.1,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-32b-instruct","score":80.9,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-27b-it","score":82.4,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-27b-it","score":66,"metric":"percent"},{"benchmark":"bbh","model":"olmo-2-0325-32b-instruct","score":65.6,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-r1-distill-qwen-32b","score":89.7,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-think-32b-sft","score":70.5,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-think-32b-dpo","score":74.5,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-think-32b","score":76,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-32b","score":88.3,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-vl-32b-thinking","score":96.1,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen2.5-32b-instruct","score":24.1,"metric":"percent"},{"benchmark":"zebralogic","model":"gemma-3-27b-it","score":24.8,"metric":"percent"},{"benchmark":"zebralogic","model":"gemma-2-27b-it","score":17.2,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-2-0325-32b-instruct","score":13.3,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-r1-distill-qwen-32b","score":69.4,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-think-32b-sft","score":85.9,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-think-32b-dpo","score":87.8,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-think-32b","score":88.2,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-32b","score":90,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-vl-32b-thinking","score":92.2,"metric":"percent"},{"benchmark":"agieval","model":"qwen2.5-32b-instruct","score":78.9,"metric":"percent"},{"benchmark":"agieval","model":"gemma-3-27b-it","score":76.9,"metric":"percent"},{"benchmark":"agieval","model":"gemma-2-27b-it","score":70.9,"metric":"percent"},{"benchmark":"agieval","model":"olmo-2-0325-32b-instruct","score":68.4,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-r1-distill-qwen-32b","score":88.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-32b-sft","score":90,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-32b-dpo","score":91.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-32b","score":91.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-32b","score":91.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-vl-32b-thinking","score":90.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-32b-instruct","score":82.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-27b-it","score":79.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-2-27b-it","score":67.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-2-0325-32b-instruct","score":44.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-r1-distill-qwen-32b","score":92.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-32b-sft","score":66.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-32b-dpo","score":67.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-32b","score":68,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-32b","score":70.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-vl-32b-thinking","score":66.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-32b-instruct","score":66.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-27b-it","score":65.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-2-27b-it","score":61.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-2-0325-32b-instruct","score":49,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-r1-distill-qwen-32b","score":70.1,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-think-32b-sft","score":75.8,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-think-32b-dpo","score":81.9,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-think-32b","score":83.5,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-32b","score":90.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-vl-32b-thinking","score":84.8,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen2.5-32b-instruct","score":49.9,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"gemma-3-27b-it","score":39,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"gemma-2-27b-it","score":28.7,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-2-0325-32b-instruct","score":10.6,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"deepseek-r1-distill-qwen-32b","score":79.5,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-32b-sft","score":83.9,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-32b-dpo","score":80.6,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-32b","score":89,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-32b","score":86.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-32b-thinking","score":85.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-32b-instruct","score":81.9,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-27b-it","score":85.4,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-2-27b-it","score":62.1,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-2-0325-32b-instruct","score":85.8,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-r1-distill-qwen-32b","score":78.7,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-think-32b-sft","score":37,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-think-32b-dpo","score":34.4,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-think-32b","score":47.6,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-32b","score":37.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-vl-32b-thinking","score":55.1,"metric":"percent"},{"benchmark":"ifbench","model":"qwen2.5-32b-instruct","score":36.7,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-3-27b-it","score":31.3,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-2-27b-it","score":27.8,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-2-0325-32b-instruct","score":36.4,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-r1-distill-qwen-32b","score":23.8,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-32b-sft","score":85.3,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-32b-dpo","score":85.2,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-32b","score":85.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-32b","score":88.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-32b-thinking","score":90.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-32b-instruct","score":84.6,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b-it","score":74.6,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-27b-it","score":76.1,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-2-0325-32b-instruct","score":77.1,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-r1-distill-qwen-32b","score":88,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-think-32b-sft","score":33.1,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-think-32b-dpo","score":37,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-think-32b","score":31.9,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-32b","score":30.7,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-vl-32b-thinking","score":32.2,"metric":"percent"},{"benchmark":"popqa","model":"qwen2.5-32b-instruct","score":28,"metric":"percent"},{"benchmark":"popqa","model":"gemma-3-27b-it","score":30.2,"metric":"percent"},{"benchmark":"popqa","model":"gemma-2-27b-it","score":30.4,"metric":"percent"},{"benchmark":"popqa","model":"olmo-2-0325-32b-instruct","score":37.2,"metric":"percent"},{"benchmark":"popqa","model":"deepseek-r1-distill-qwen-32b","score":26.7,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-32b-sft","score":55.7,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-32b-dpo","score":57.6,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-32b","score":58.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b","score":67.3,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-vl-32b-thinking","score":67.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-32b-instruct","score":44.6,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3-27b-it","score":45,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-27b-it","score":39.9,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-2-0325-32b-instruct","score":36.4,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-r1-distill-qwen-32b","score":61.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-think-32b-sft","score":69.1,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-think-32b-dpo","score":78.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-think-32b","score":74.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-32b","score":75.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-vl-32b-thinking","score":80.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen2.5-32b-instruct","score":81.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"gemma-3-27b-it","score":65.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"gemma-2-27b-it","score":39.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-2-0325-32b-instruct","score":38,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-r1-distill-qwen-32b","score":26.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.5","score":80.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.5","score":59.3,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4.5","score":88.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.5","score":98.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.5","score":62.3,"metric":"percent"},{"benchmark":"osworld","model":"claude-opus-4.5","score":66.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.5","score":37.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.5","score":87,"metric":"percent"},{"benchmark":"mmmu","model":"claude-opus-4.5","score":80.7,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-opus-4.5","score":90.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.1-codex-max","score":77.9,"metric":"percent"},{"benchmark":"swe-lancer","model":"gpt-5.1-codex-max","score":79.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1-codex-max","score":58.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-sonnet-4.5","score":50,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.1","score":46.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-pro","score":54.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1","score":47.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemini-3-pro","score":85.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-3-pro","score":98,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.1","score":40.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3-pro-preview","score":55.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5-2025-08-07","score":44.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"o3-pro-2025-06-10-high","score":43.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.1-20250805","score":40.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-sonnet-4-20250514","score":35.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-4.5-air","score":34,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k2-instruct","score":23.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3-235b-a22b","score":12,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-2.5-pro-preview-06-05","score":8.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-4o-2024-11-20","score":7.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-2.5-flash-preview-05-20","score":3.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"llama-4-maverick","score":0.8,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5.1","score":85.4,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-opus-4.5","score":100,"metric":"percent"},{"benchmark":"faix-agent","model":"holo1.5-72b","score":90.67,"metric":"percent"},{"benchmark":"faix-agent","model":"gemini-3-pro","score":60,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-sonnet-4.5","score":58.8,"metric":"percent"},{"benchmark":"faix-agent","model":"grok-4-thinking","score":58.4,"metric":"percent"},{"benchmark":"faix-agent","model":"holo1.5-7b","score":56,"metric":"percent"},{"benchmark":"faix-agent","model":"gpt-5","score":54.44,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-3.5-sonnet","score":52,"metric":"percent"},{"benchmark":"faix-agent","model":"ui-venus-72b","score":49.33,"metric":"percent"},{"benchmark":"faix-agent","model":"o3-low","score":47.67,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-vl-32b-instruct","score":46.67,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-opus-4.1","score":42.91,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-vl-235b-a22b-instruct","score":42,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-sonnet-4","score":41.68,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-opus-4","score":41.14,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-vl-30b-a3b-instruct","score":40,"metric":"percent"},{"benchmark":"faix-agent","model":"gpt-5.1","score":36,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-4.5-haiku","score":31.43,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-3.7-sonnet","score":29.6,"metric":"percent"},{"benchmark":"faix-agent","model":"minimax-m2","score":24.8,"metric":"percent"},{"benchmark":"faix-agent","model":"holo1.5-3b","score":24,"metric":"percent"},{"benchmark":"faix-agent","model":"seed-1.5-vl","score":24,"metric":"percent"},{"benchmark":"faix-agent","model":"ui-venus-7b","score":21.33,"metric":"percent"},{"benchmark":"faix-agent","model":"grok-code-fast-1","score":20,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen2.5-vl-72b","score":19.2,"metric":"percent"},{"benchmark":"faix-agent","model":"ui-tars-1.5-7b","score":18.67,"metric":"percent"},{"benchmark":"faix-agent","model":"o4-mini","score":18.5,"metric":"percent"},{"benchmark":"faix-agent","model":"claude-3.5-haiku","score":16,"metric":"percent"},{"benchmark":"faix-agent","model":"deepseek-r1","score":16,"metric":"percent"},{"benchmark":"faix-agent","model":"gpt-4o-mini","score":16,"metric":"percent"},{"benchmark":"faix-agent","model":"holo1-7b","score":16,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-vl-8b-instruct","score":16,"metric":"percent"},{"benchmark":"faix-agent","model":"deepseek-v3.2-exp","score":15,"metric":"percent"},{"benchmark":"faix-agent","model":"glm-4.6","score":14.4,"metric":"percent"},{"benchmark":"faix-agent","model":"gpt-4.1","score":13.6,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-vl-4b-instruct","score":13.33,"metric":"percent"},{"benchmark":"faix-agent","model":"gemini-2.5-pro","score":12,"metric":"percent"},{"benchmark":"faix-agent","model":"minimax-m1-80k","score":12,"metric":"percent"},{"benchmark":"faix-agent","model":"chatgpt-4o","score":11.56,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-vl-2b-instruct","score":9.33,"metric":"percent"},{"benchmark":"faix-agent","model":"grok-4-fast","score":9,"metric":"percent"},{"benchmark":"faix-agent","model":"deepseek-v3.1","score":8,"metric":"percent"},{"benchmark":"faix-agent","model":"gemini-1.5-pro","score":8,"metric":"percent"},{"benchmark":"faix-agent","model":"gemini-2.5-flash","score":8,"metric":"percent"},{"benchmark":"faix-agent","model":"holo1-3b","score":8,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-next-80b-a3b-instruct","score":5.33,"metric":"percent"},{"benchmark":"faix-agent","model":"glm-4.5","score":5.14,"metric":"percent"},{"benchmark":"faix-agent","model":"kimi-k2","score":4.92,"metric":"percent"},{"benchmark":"faix-agent","model":"apriel-1.5-15b-thinker","score":4,"metric":"percent"},{"benchmark":"faix-agent","model":"minimax-m1-40k","score":4,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-235b-a22b-instruct-2507","score":4,"metric":"percent"},{"benchmark":"faix-agent","model":"deepseek-v3","score":2.86,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-max","score":2.67,"metric":"percent"},{"benchmark":"faix-agent","model":"deepseek-v3.1-terminus","score":2,"metric":"percent"},{"benchmark":"faix-agent","model":"glm-4.5-air","score":1.6,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen2.5-vl-7b","score":1.33,"metric":"percent"},{"benchmark":"faix-agent","model":"gpt-oss-120b","score":0.8,"metric":"percent"},{"benchmark":"faix-agent","model":"exaone-4.0-32b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"gemini-1.5-flash","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"gpt-4.1-mini","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"gpt-oss-20b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"llama-3.1-8b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"llama-3.3-70b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"llama-4-maverick","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"llama-nemotron-super-v1","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"magistral-medium-1.2","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"magistral-small-1.2","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-30b-a3b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-32b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-coder-480b-a35b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen2.5-72b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen2.5-vl-3b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-4b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-8b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"qwen3-next-80b-a3b","score":0,"metric":"percent"},{"benchmark":"faix-agent","model":"seed-thinking-v1.5","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"claude-opus-4.5","score":100,"metric":"percent"},{"benchmark":"faix-code","model":"claude-sonnet-4.5","score":63.27,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-5","score":57,"metric":"percent"},{"benchmark":"faix-code","model":"gemini-3-pro","score":53.33,"metric":"percent"},{"benchmark":"faix-code","model":"kimi-k2-thinking","score":49.14,"metric":"percent"},{"benchmark":"faix-code","model":"claude-opus-4","score":43.5,"metric":"percent"},{"benchmark":"faix-code","model":"claude-sonnet-4","score":42,"metric":"percent"},{"benchmark":"faix-code","model":"o1","score":40.33,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-5.1","score":40,"metric":"percent"},{"benchmark":"faix-code","model":"o3-low","score":37.6,"metric":"percent"},{"benchmark":"faix-code","model":"o1-mini","score":35.56,"metric":"percent"},{"benchmark":"faix-code","model":"claude-opus-4.1","score":35.2,"metric":"percent"},{"benchmark":"faix-code","model":"ernie-4.5","score":31,"metric":"percent"},{"benchmark":"faix-code","model":"olmo-3-think-32b","score":30.67,"metric":"percent"},{"benchmark":"faix-code","model":"motif-2-12.7b-instruct","score":30,"metric":"percent"},{"benchmark":"faix-code","model":"gemini-2.5-pro","score":29.82,"metric":"percent"},{"benchmark":"faix-code","model":"grok-4-thinking","score":29.6,"metric":"percent"},{"benchmark":"faix-code","model":"olmo-3-think-32b-dpo","score":29.33,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-vl-32b-thinking","score":29.33,"metric":"percent"},{"benchmark":"faix-code","model":"minimax-m2","score":26.67,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-r1","score":26.13,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-next-80b-a3b-instruct","score":24,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3.1-405b","score":23.33,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-r1-distill-qwen-32b","score":22.4,"metric":"percent"},{"benchmark":"faix-code","model":"grok-4-fast","score":22,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3.1-70b","score":20.8,"metric":"percent"},{"benchmark":"faix-code","model":"k2-think","score":20,"metric":"percent"},{"benchmark":"faix-code","model":"seed-thinking-v1.5","score":19,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-4","score":18.67,"metric":"percent"},{"benchmark":"faix-code","model":"chatgpt-4o","score":18.2,"metric":"percent"},{"benchmark":"faix-code","model":"claude-3.7-sonnet","score":17.82,"metric":"percent"},{"benchmark":"faix-code","model":"qwen2.5-coder-32b-instruct","score":17.2,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-v3.1","score":17.09,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-235b-a22b-instruct-2507","score":16.57,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-coder-480b-a35b-instruct","score":16.36,"metric":"percent"},{"benchmark":"faix-code","model":"glm-4.5","score":16,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-vl-30b-a3b-thinking","score":16,"metric":"percent"},{"benchmark":"faix-code","model":"o3-mini-low","score":15,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-4.1","score":14.8,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-v2.5","score":14.5,"metric":"percent"},{"benchmark":"faix-code","model":"smollm3-3b","score":14.4,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-v3.2","score":14.29,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-v3.1-terminus","score":13.6,"metric":"percent"},{"benchmark":"faix-code","model":"olmo-3-think-32b-sft","score":13.33,"metric":"percent"},{"benchmark":"faix-code","model":"qwen2.5-max","score":13.33,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-32b","score":13.07,"metric":"percent"},{"benchmark":"faix-code","model":"glm-4.5-air","score":13,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3-70b","score":12.57,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-v3.2-exp","score":12.44,"metric":"percent"},{"benchmark":"faix-code","model":"minimax-m1-80k","score":10.67,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-v3","score":10.17,"metric":"percent"},{"benchmark":"faix-code","model":"o4-mini","score":9.33,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-4-turbo","score":9.2,"metric":"percent"},{"benchmark":"faix-code","model":"claude-3.5-sonnet","score":9.14,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-4b","score":9.09,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-oss-120b","score":8,"metric":"percent"},{"benchmark":"faix-code","model":"kimi-k2","score":8,"metric":"percent"},{"benchmark":"faix-code","model":"minimax-m1-40k","score":8,"metric":"percent"},{"benchmark":"faix-code","model":"qwq-32b","score":8,"metric":"percent"},{"benchmark":"faix-code","model":"llama-4-maverick","score":7.5,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-30b-a3b","score":7.33,"metric":"percent"},{"benchmark":"faix-code","model":"glm-4.6","score":7,"metric":"percent"},{"benchmark":"faix-code","model":"mistral-medium-3","score":6.67,"metric":"percent"},{"benchmark":"faix-code","model":"gemini-2.5-flash","score":6.5,"metric":"percent"},{"benchmark":"faix-code","model":"claude-3-opus","score":6.4,"metric":"percent"},{"benchmark":"faix-code","model":"ling-1t","score":6,"metric":"percent"},{"benchmark":"faix-code","model":"qwen-1.7b-thinking","score":6,"metric":"percent"},{"benchmark":"faix-code","model":"claude-3.5-haiku","score":4.57,"metric":"percent"},{"benchmark":"faix-code","model":"gemini-1.5-pro","score":4,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-4o-mini","score":4,"metric":"percent"},{"benchmark":"faix-code","model":"qwen2.5-32b-instruct","score":3.43,"metric":"percent"},{"benchmark":"faix-code","model":"codestral-22b","score":2.67,"metric":"percent"},{"benchmark":"faix-code","model":"gemma-3","score":2.29,"metric":"percent"},{"benchmark":"faix-code","model":"gemma-2-27b-it","score":2,"metric":"percent"},{"benchmark":"faix-code","model":"granite-3.3-8b-instruct","score":2,"metric":"percent"},{"benchmark":"faix-code","model":"grok-code-fast-1","score":2,"metric":"percent"},{"benchmark":"faix-code","model":"llama-4-scout-17b","score":2,"metric":"percent"},{"benchmark":"faix-code","model":"qwen2.5-7b-instruct","score":2,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-vl-30b-a3b-instruct","score":2,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-vl-8b-instruct","score":2,"metric":"percent"},{"benchmark":"faix-code","model":"grok-3-beta","score":1.78,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3.1-8b","score":1.78,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-14b","score":1.33,"metric":"percent"},{"benchmark":"faix-code","model":"olmo-2-0325-32b-instruct","score":1,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-coder-33b","score":0.8,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-oss-20b","score":0.67,"metric":"percent"},{"benchmark":"faix-code","model":"qwen2.5-72b-instruct","score":0.44,"metric":"percent"},{"benchmark":"faix-code","model":"apriel-1.5-15b-thinker","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"claude-3-haiku","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"claude-4.5-haiku","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"codellama-7b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-r1-distill-llama-8b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"deepseek-r1-distill-qwen-7b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"dream-7b-base","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"exaone-4.0-1.2b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"exaone-4.0-32b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"exaone-deep-2.4b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon-3-1b-base","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon-h1-0.5b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon-h1-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon-h1-34b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon-h1-3b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon-h1-7b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon3-10b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon3-3b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"falcon3-7b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gemini-1.5-flash","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gemini-2.0-flash","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gemini-2.0-pro","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gemma-3-12b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gemma-3-1b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gemma-3-4b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-3.5-turbo","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-4.1-mini","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-4.1-nano","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-4.5","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"gpt-5-nano-medium","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"granite-3.3-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"granite-4.0-h-micro","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"granite-4.0-h-small","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"granite-4.0-h-tiny","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"granite-4.0-micro","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"granite-4.0-tiny-preview","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"grok-3-mini","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"kimi-k2-base","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"kimi-linear-base","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"lfm2-2.6b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"lfm2-8b-a1b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llada-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-1-33b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-2-13b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-2-70b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-2-7b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3-8b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3.2-1.24b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3.2-1b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3.2-3b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-3.3-70b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-4-maverick-17b-128e-instruct","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"llama-nemotron-super-v1","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"magistral-medium-1.2","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"magistral-small-1.2","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"mistral-7b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"mistral-large","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"mixtral-8x22b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"mixtral-8x7b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"mobilellm-p1","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"moonlight-base","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"motif-2-12.7b-base","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"ouro-1.4b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"ouro-2.6b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen-2.5-3b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen2.5-0.5b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen2.5-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen2.5-7b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-0.6b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-0.8b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-8b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-max","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-next-80b-a3b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-omni-30b-a3b","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-omni-flash-instruct","score":0,"metric":"percent"},{"benchmark":"faix-code","model":"qwen3-vl-4b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-vl-235b-a22b-instruct","score":100,"metric":"percent"},{"benchmark":"faix-math","model":"gpt-5","score":63.33,"metric":"percent"},{"benchmark":"faix-math","model":"seed-1.5-vl","score":61.33,"metric":"percent"},{"benchmark":"faix-math","model":"gemini-2.0-pro","score":54,"metric":"percent"},{"benchmark":"faix-math","model":"claude-sonnet-4.5","score":50,"metric":"percent"},{"benchmark":"faix-math","model":"ling-1t","score":50,"metric":"percent"},{"benchmark":"faix-math","model":"glm-4.5v","score":48,"metric":"percent"},{"benchmark":"faix-math","model":"gemini-2.5-pro","score":44.33,"metric":"percent"},{"benchmark":"faix-math","model":"kimi-k2-thinking","score":44,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-vl-32b-thinking","score":40,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-vl-32b-instruct","score":38.67,"metric":"percent"},{"benchmark":"faix-math","model":"olmo-3-think-32b","score":37,"metric":"percent"},{"benchmark":"faix-math","model":"dots-vlm1","score":36,"metric":"percent"},{"benchmark":"faix-math","model":"deepseek-v3.1-terminus","score":33.33,"metric":"percent"},{"benchmark":"faix-math","model":"grok-4-fast","score":33.33,"metric":"percent"},{"benchmark":"faix-math","model":"o4-mini","score":33.33,"metric":"percent"},{"benchmark":"faix-math","model":"kimi-k2","score":33,"metric":"percent"},{"benchmark":"faix-math","model":"ernie-4.5-vl-28b-a3b-thinking","score":32,"metric":"percent"},{"benchmark":"faix-math","model":"o3-low","score":31.43,"metric":"percent"},{"benchmark":"faix-math","model":"claude-opus-4.1","score":30.4,"metric":"percent"},{"benchmark":"faix-math","model":"gpt-4.5","score":30,"metric":"percent"},{"benchmark":"faix-math","model":"step-3","score":28,"metric":"percent"},{"benchmark":"faix-math","model":"glm-4.1v","score":26,"metric":"percent"},{"benchmark":"faix-math","model":"gpt-oss-120b","score":24.67,"metric":"percent"},{"benchmark":"faix-math","model":"olmo-3-think-32b-dpo","score":22,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-next-80b-a3b-instruct","score":22,"metric":"percent"},{"benchmark":"faix-math","model":"grok-4-thinking","score":21.33,"metric":"percent"},{"benchmark":"faix-math","model":"claude-opus-4","score":20.67,"metric":"percent"},{"benchmark":"faix-math","model":"grok-3-mini","score":20,"metric":"percent"},{"benchmark":"faix-math","model":"o3-mini-low","score":20,"metric":"percent"},{"benchmark":"faix-math","model":"gemini-2.0-flash","score":19,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-235b-a22b-instruct-2507","score":18.67,"metric":"percent"},{"benchmark":"faix-math","model":"apriel-nemotron-15b-thinker","score":18,"metric":"percent"},{"benchmark":"faix-math","model":"lg-exaone-32b","score":18,"metric":"percent"},{"benchmark":"faix-math","model":"o1","score":18,"metric":"percent"},{"benchmark":"faix-math","model":"olmo-3-think-32b-sft","score":18,"metric":"percent"},{"benchmark":"faix-math","model":"qwq-32b","score":17.33,"metric":"percent"},{"benchmark":"faix-math","model":"motif-2-12.7b-instruct","score":16.8,"metric":"percent"},{"benchmark":"faix-math","model":"chatgpt-4o","score":16.67,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.1-405b","score":16,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-3","score":15,"metric":"percent"},{"benchmark":"faix-math","model":"k2-think","score":15,"metric":"percent"},{"benchmark":"faix-math","model":"gpt-oss-20b","score":14.4,"metric":"percent"},{"benchmark":"faix-math","model":"internvl3.5-4b","score":13.33,"metric":"percent"},{"benchmark":"faix-math","model":"deepseek-r1-distill-qwen-32b","score":12,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.1-nemotron-nano-8b-v1","score":12,"metric":"percent"},{"benchmark":"faix-math","model":"qwen-2.5-3b-instruct","score":12,"metric":"percent"},{"benchmark":"faix-math","model":"claude-sonnet-4","score":11.56,"metric":"percent"},{"benchmark":"faix-math","model":"claude-3.5-sonnet","score":11.2,"metric":"percent"},{"benchmark":"faix-math","model":"kimi-vl-a3b-thinking","score":11.2,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-4b","score":11.11,"metric":"percent"},{"benchmark":"faix-math","model":"deepseek-v3","score":10,"metric":"percent"},{"benchmark":"faix-math","model":"ernie-4.5","score":10,"metric":"percent"},{"benchmark":"faix-math","model":"o1-mini","score":10,"metric":"percent"},{"benchmark":"faix-math","model":"smollm3-3b","score":10,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-32b","score":9.2,"metric":"percent"},{"benchmark":"faix-math","model":"deepseek-v3.1","score":9,"metric":"percent"},{"benchmark":"faix-math","model":"deepseek-v3.2","score":8,"metric":"percent"},{"benchmark":"faix-math","model":"deepseek-v3.2-exp","score":8,"metric":"percent"},{"benchmark":"faix-math","model":"gemini-1.5-pro","score":8,"metric":"percent"},{"benchmark":"faix-math","model":"gemini-2.5-flash-lite","score":8,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-3-4b","score":8,"metric":"percent"},{"benchmark":"faix-math","model":"lfm2-8b-a1b","score":8,"metric":"percent"},{"benchmark":"faix-math","model":"deepseek-r1","score":7.33,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-30b-a3b","score":7,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-3-12b","score":6.86,"metric":"percent"},{"benchmark":"faix-math","model":"gpt-4.1","score":6.29,"metric":"percent"},{"benchmark":"faix-math","model":"lfm2-2.6b","score":6,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-vl-30b-a3b-instruct","score":6,"metric":"percent"},{"benchmark":"faix-math","model":"gemini-1.5-flash","score":5.33,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-vl-30b-a3b-thinking","score":5.33,"metric":"percent"},{"benchmark":"faix-math","model":"qwen-1.7b-thinking","score":4.44,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-2-27b","score":4,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-3-27b-vl","score":4,"metric":"percent"},{"benchmark":"faix-math","model":"magistral-medium-1.2","score":4,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-max","score":4,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-vl-8b-instruct","score":4,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-32b-instruct","score":3.43,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-8b","score":3.43,"metric":"percent"},{"benchmark":"faix-math","model":"falcon-h1-34b-instruct","score":3.2,"metric":"percent"},{"benchmark":"faix-math","model":"claude-3.7-sonnet","score":2.67,"metric":"percent"},{"benchmark":"faix-math","model":"llama-4-maverick","score":2.67,"metric":"percent"},{"benchmark":"faix-math","model":"gemini-2.5-flash","score":2.29,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-3-1b","score":2,"metric":"percent"},{"benchmark":"faix-math","model":"granite-4.0-h-tiny","score":2,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-vl-7b","score":2,"metric":"percent"},{"benchmark":"faix-math","model":"olmo-2-0325-32b-instruct","score":1.6,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-2-9b","score":1.33,"metric":"percent"},{"benchmark":"faix-math","model":"minimax-m1-80k","score":1.33,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-2-27b-it","score":1,"metric":"percent"},{"benchmark":"faix-math","model":"llama-4-scout-17b","score":1,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-14b","score":0.8,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.2-3b","score":0.57,"metric":"percent"},{"benchmark":"faix-math","model":"claude-3-haiku","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"claude-3.5-haiku","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"codellama-7b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"exaone-4.0-1.2b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"exaone-deep-2.4b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"falcon-3-1b-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"falcon-h1-0.5b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"falcon-h1-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"falcon-h1-3b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"falcon-h1-7b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"falcon3-10b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"falcon3-3b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"falcon3-7b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-2-2b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-2-7b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"gemma-3-270m-it","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"glm-4.5","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"gpt-4.1-nano","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"gpt-4o-mini","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"gpt-5-nano-medium","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-3.1-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-3.1-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-3.2-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-3.2-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-3.3-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-3.3-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-4.0-h-micro","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-4.0-h-small","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"granite-4.0-micro","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"grok-3-beta","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"internvl3.5-2b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"kimi-k2-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"kimi-linear-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-1-33b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-2-13b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-2-70b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-2-7b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3-70b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3-8b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.1-70b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.1-8b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.2-1.24b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.2-1b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.2-90b-vision","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-3.3-70b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-4-maverick-17b-128e-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llama-nemotron-super-v1","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"llava-onevision-72b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"magistral-small-1.2","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"marin-32b-bison","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"marin-32b-mantis","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"minimax-m1-40k","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"mistral-7b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"mistral-large","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"mistral-medium-3","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"mistral-small-3.1-24b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"mistral-small-3.2-24b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"mixtral-8x22b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"mixtral-8x7b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"moonlight-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"motif-2-12.7b-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"nemotron-nano-12b-v2-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"ouro-1.4b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"ouro-2.6b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"pixtral-12b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-max","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-0.5b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-32b-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-72b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-7b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen2.5-vl-72b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-0.6b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-0.8b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-omni-30b-a3b","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-omni-flash-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-vl-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"qwen3-vl-4b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"seed-thinking-v1.5","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"smollm2-1.7b-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"smollm2-135m-base","score":0,"metric":"percent"},{"benchmark":"faix-math","model":"smollm2-360m-base","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"o3-low","score":80,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen3-vl-235b-a22b-instruct","score":73.5,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen3-vl-32b-instruct","score":44.36,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen2-vl-72b","score":37,"metric":"percent"},{"benchmark":"faix-ocr","model":"seed-1.5-vl","score":34.67,"metric":"percent"},{"benchmark":"faix-ocr","model":"gemini-2.5-pro","score":33.6,"metric":"percent"},{"benchmark":"faix-ocr","model":"gpt-5","score":29.33,"metric":"percent"},{"benchmark":"faix-ocr","model":"molmo-72b","score":28,"metric":"percent"},{"benchmark":"faix-ocr","model":"mimo-vl","score":27.43,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen3-vl-30b-a3b-instruct","score":26.4,"metric":"percent"},{"benchmark":"faix-ocr","model":"dots-vlm1","score":26.29,"metric":"percent"},{"benchmark":"faix-ocr","model":"claude-3.5-sonnet","score":25,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen3-vl-8b-instruct","score":24.73,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen2.5-vl-72b","score":21.71,"metric":"percent"},{"benchmark":"faix-ocr","model":"llama-4-maverick","score":20,"metric":"percent"},{"benchmark":"faix-ocr","model":"llama-4-maverick-17b-128e-instruct","score":20,"metric":"percent"},{"benchmark":"faix-ocr","model":"internvl2-llama-3-76b","score":19,"metric":"percent"},{"benchmark":"faix-ocr","model":"manzano-30b","score":15.33,"metric":"percent"},{"benchmark":"faix-ocr","model":"ernie-4.5-vl-28b-a3b-thinking","score":14,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen2.5-vl-7b","score":12.8,"metric":"percent"},{"benchmark":"faix-ocr","model":"claude-3.7-sonnet","score":12.57,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen3-vl-4b-instruct","score":12,"metric":"percent"},{"benchmark":"faix-ocr","model":"claude-opus-4.1","score":10.5,"metric":"percent"},{"benchmark":"faix-ocr","model":"glm-4.5v","score":10,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen2-vl-7b-instruct","score":9.6,"metric":"percent"},{"benchmark":"faix-ocr","model":"internvl-8b","score":6.86,"metric":"percent"},{"benchmark":"faix-ocr","model":"llama-3.2-90b-vision","score":6,"metric":"percent"},{"benchmark":"faix-ocr","model":"step-3","score":6,"metric":"percent"},{"benchmark":"faix-ocr","model":"gemini-1.5-pro","score":5.33,"metric":"percent"},{"benchmark":"faix-ocr","model":"internvl2.5-26b","score":5.33,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen3-vl-2b-instruct","score":4.36,"metric":"percent"},{"benchmark":"faix-ocr","model":"llama-4-scout-17b","score":4,"metric":"percent"},{"benchmark":"faix-ocr","model":"molmo-7b-d","score":4,"metric":"percent"},{"benchmark":"faix-ocr","model":"pixtral-12b","score":4,"metric":"percent"},{"benchmark":"faix-ocr","model":"chatgpt-4o","score":3.64,"metric":"percent"},{"benchmark":"faix-ocr","model":"claude-sonnet-4","score":3.27,"metric":"percent"},{"benchmark":"faix-ocr","model":"llava-onevision-72b","score":2,"metric":"percent"},{"benchmark":"faix-ocr","model":"kimi-vl-a3b-thinking","score":1.6,"metric":"percent"},{"benchmark":"faix-ocr","model":"mistral-small-3.1-24b-instruct","score":1.33,"metric":"percent"},{"benchmark":"faix-ocr","model":"gemini-2.5-flash-lite","score":0.73,"metric":"percent"},{"benchmark":"faix-ocr","model":"manzano-3b","score":0.67,"metric":"percent"},{"benchmark":"faix-ocr","model":"bagel-14b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"blip-3o-4b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"cambrian-1-34b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"cambrian-1-8b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"cambrian-34b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"claude-3-haiku","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"claude-3-opus","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"emu3-8b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"fastvlm-0.5b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"fastvlm-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"fastvlm-7b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"gemini-1.5-flash","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"gemini-2.5-flash","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"gemma-3","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"gemma-3-27b-vl","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"glm-4.1v","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"gpt-4v","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"gpt-5-nano-medium","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"internvl2-8b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"internvl2.5-2b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"internvl2.5-4b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"internvl3.5-2b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"internvl3.5-4b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"janus-pro-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"llama-3.2v-11b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"llava-1.5-13b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"llava-1.5-7b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"llava-onevision-7b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"minicpm-v-2.0-3b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"mistral-medium-3","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"mistral-small-3.2-24b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"mm1-30b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"mm1.5-30b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"mm1.5-3b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"molmoe-1b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"paligemma-mix-3b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"phi-3-vision-4b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"phi-3.5-vision-4b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen2.5-omni-7b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"qwen2.5-vl-3b","score":0,"metric":"percent"},{"benchmark":"faix-ocr","model":"xgen-mm-interleave-4b","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"granite-3.3-8b-instruct","score":70,"metric":"percent"},{"benchmark":"faix-safety","model":"grok-4-thinking","score":68,"metric":"percent"},{"benchmark":"faix-safety","model":"claude-sonnet-4.5","score":66,"metric":"percent"},{"benchmark":"faix-safety","model":"gpt-oss-120b","score":60,"metric":"percent"},{"benchmark":"faix-safety","model":"gpt-5","score":59,"metric":"percent"},{"benchmark":"faix-safety","model":"o3-low","score":56,"metric":"percent"},{"benchmark":"faix-safety","model":"qwen3-32b","score":50,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-3-70b","score":48,"metric":"percent"},{"benchmark":"faix-safety","model":"claude-opus-4.1","score":45.33,"metric":"percent"},{"benchmark":"faix-safety","model":"granite-3.2-8b-instruct","score":36,"metric":"percent"},{"benchmark":"faix-safety","model":"granite-3.3-2b-instruct","score":36,"metric":"percent"},{"benchmark":"faix-safety","model":"qwen2.5-72b-instruct","score":36,"metric":"percent"},{"benchmark":"faix-safety","model":"claude-sonnet-4","score":33,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-3.1-405b","score":33,"metric":"percent"},{"benchmark":"faix-safety","model":"gemini-2.0-pro","score":30,"metric":"percent"},{"benchmark":"faix-safety","model":"granite-3.1-8b-instruct","score":28,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-3.3-70b","score":26.4,"metric":"percent"},{"benchmark":"faix-safety","model":"gemini-2.0-flash","score":24,"metric":"percent"},{"benchmark":"faix-safety","model":"gpt-4o-mini","score":24,"metric":"percent"},{"benchmark":"faix-safety","model":"granite-4.0-tiny-preview","score":24,"metric":"percent"},{"benchmark":"faix-safety","model":"kimi-k2","score":24,"metric":"percent"},{"benchmark":"faix-safety","model":"chatgpt-4o","score":22.86,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-3.1-70b","score":22.67,"metric":"percent"},{"benchmark":"faix-safety","model":"claude-opus-4","score":22,"metric":"percent"},{"benchmark":"faix-safety","model":"gemini-2.5-pro","score":20.8,"metric":"percent"},{"benchmark":"faix-safety","model":"deepseek-r1","score":20,"metric":"percent"},{"benchmark":"faix-safety","model":"gemini-2.5-flash","score":20,"metric":"percent"},{"benchmark":"faix-safety","model":"mixtral-8x7b","score":20,"metric":"percent"},{"benchmark":"faix-safety","model":"o3-mini-low","score":20,"metric":"percent"},{"benchmark":"faix-safety","model":"codestral-22b","score":18,"metric":"percent"},{"benchmark":"faix-safety","model":"o4-mini","score":16,"metric":"percent"},{"benchmark":"faix-safety","model":"claude-3.7-sonnet","score":13.33,"metric":"percent"},{"benchmark":"faix-safety","model":"claude-3.5-sonnet","score":13,"metric":"percent"},{"benchmark":"faix-safety","model":"granite-3.1-2b-instruct","score":12,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-3-8b","score":12,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-4-maverick","score":12,"metric":"percent"},{"benchmark":"faix-safety","model":"gpt-4.5","score":6,"metric":"percent"},{"benchmark":"faix-safety","model":"o1","score":4,"metric":"percent"},{"benchmark":"faix-safety","model":"qwen2.5-7b-instruct","score":2.67,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-3.1-8b","score":1.6,"metric":"percent"},{"benchmark":"faix-safety","model":"claude-3.5-haiku","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"deepseek-r1-distill-llama-8b","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"deepseek-r1-distill-qwen-7b","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"deepseek-v3","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"gemini-1.5-flash","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"gemini-1.5-pro","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"gpt-4.1","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"granite-3.2-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-2-70b","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"llama-3.2-3b","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"mistral-7b","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"mixtral-8x22b","score":0,"metric":"percent"},{"benchmark":"faix-safety","model":"qwen3-235b-a22b-instruct-2507","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-vl-235b-a22b-instruct","score":100,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-5","score":66.13,"metric":"percent"},{"benchmark":"faix-stem","model":"gemini-2.0-pro","score":54,"metric":"percent"},{"benchmark":"faix-stem","model":"fastvlm-7b","score":50,"metric":"percent"},{"benchmark":"faix-stem","model":"ling-1t","score":50,"metric":"percent"},{"benchmark":"faix-stem","model":"seed-1.5-vl","score":46,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-sonnet-4.5","score":44,"metric":"percent"},{"benchmark":"faix-stem","model":"kimi-k2-thinking","score":44,"metric":"percent"},{"benchmark":"faix-stem","model":"gemini-2.5-pro","score":42.59,"metric":"percent"},{"benchmark":"faix-stem","model":"glm-4.5v","score":40,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-opus-4.1","score":38.86,"metric":"percent"},{"benchmark":"faix-stem","model":"o3-low","score":38,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3_1-70b-tfree-hat-sft","score":37,"metric":"percent"},{"benchmark":"faix-stem","model":"ernie-4.5-vl-28b-a3b-thinking","score":36,"metric":"percent"},{"benchmark":"faix-stem","model":"molmo-72b","score":36,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-v3.1-terminus","score":33.33,"metric":"percent"},{"benchmark":"faix-stem","model":"grok-4-fast","score":33.33,"metric":"percent"},{"benchmark":"faix-stem","model":"grok-4-thinking","score":32,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-vl-32b-thinking","score":32,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-opus-4","score":31.43,"metric":"percent"},{"benchmark":"faix-stem","model":"fastvlm-1.5b","score":30,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.1-405b","score":29.6,"metric":"percent"},{"benchmark":"faix-stem","model":"olmo-3-think-32b","score":29.6,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-vl-32b-instruct","score":29,"metric":"percent"},{"benchmark":"faix-stem","model":"dots-vlm1","score":27,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-4.5-haiku","score":24,"metric":"percent"},{"benchmark":"faix-stem","model":"manzano-30b","score":24,"metric":"percent"},{"benchmark":"faix-stem","model":"o4-mini","score":23.2,"metric":"percent"},{"benchmark":"faix-stem","model":"step-3","score":22.4,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-oss-120b","score":21.14,"metric":"percent"},{"benchmark":"faix-stem","model":"glm-4.1v","score":20.8,"metric":"percent"},{"benchmark":"faix-stem","model":"kimi-k2","score":20.5,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-4.5","score":20,"metric":"percent"},{"benchmark":"faix-stem","model":"apriel-nemotron-15b-thinker","score":18,"metric":"percent"},{"benchmark":"faix-stem","model":"lg-exaone-32b","score":18,"metric":"percent"},{"benchmark":"faix-stem","model":"o1","score":18,"metric":"percent"},{"benchmark":"faix-stem","model":"olmo-3-think-32b-dpo","score":17.6,"metric":"percent"},{"benchmark":"faix-stem","model":"qwq-32b","score":17.33,"metric":"percent"},{"benchmark":"faix-stem","model":"o3-mini-low","score":16.67,"metric":"percent"},{"benchmark":"faix-stem","model":"chatgpt-4o","score":16.4,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-sonnet-4","score":16.33,"metric":"percent"},{"benchmark":"faix-stem","model":"manzano-3b","score":16,"metric":"percent"},{"benchmark":"faix-stem","model":"gemini-2.0-flash","score":15.2,"metric":"percent"},{"benchmark":"faix-stem","model":"grok-3-mini","score":15,"metric":"percent"},{"benchmark":"faix-stem","model":"k2-think","score":15,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.3-70b","score":14.4,"metric":"percent"},{"benchmark":"faix-stem","model":"olmo-3-think-32b-sft","score":14.4,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-3","score":14.15,"metric":"percent"},{"benchmark":"faix-stem","model":"motif-2-12.7b-instruct","score":14,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-3.5-sonnet","score":13.71,"metric":"percent"},{"benchmark":"faix-stem","model":"mm1.5-30b","score":13.33,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-next-80b-a3b-instruct","score":13.33,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-oss-20b","score":12,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.1-70b","score":12,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.1-nemotron-nano-8b-v1","score":12,"metric":"percent"},{"benchmark":"faix-stem","model":"phi-3-vision-4b","score":10.67,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-235b-a22b-instruct-2507","score":10.67,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-2-7b","score":10,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3-70b","score":10,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-4b","score":10,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-r1-distill-qwen-32b","score":9.6,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-3-12b","score":9.6,"metric":"percent"},{"benchmark":"faix-stem","model":"kimi-vl-a3b-thinking","score":9.33,"metric":"percent"},{"benchmark":"faix-stem","model":"marin-32b-bison","score":9.33,"metric":"percent"},{"benchmark":"faix-stem","model":"marin-32b-mantis","score":9.33,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-v3.1","score":9,"metric":"percent"},{"benchmark":"faix-stem","model":"gemini-1.5-pro","score":9,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen-2.5-3b-instruct","score":9,"metric":"percent"},{"benchmark":"faix-stem","model":"smollm3-3b","score":8.57,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-32b","score":8.36,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-3.5-haiku","score":8,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-v3.2","score":8,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-v3.2-exp","score":8,"metric":"percent"},{"benchmark":"faix-stem","model":"ernie-4.5","score":8,"metric":"percent"},{"benchmark":"faix-stem","model":"internvl3.5-4b","score":8,"metric":"percent"},{"benchmark":"faix-stem","model":"o1-mini","score":8,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-4.1","score":7.5,"metric":"percent"},{"benchmark":"faix-stem","model":"olmo-2-0325-32b-instruct","score":7.11,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-r1","score":6.86,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-3-4b","score":6.55,"metric":"percent"},{"benchmark":"faix-stem","model":"lfm2-8b-a1b","score":6.4,"metric":"percent"},{"benchmark":"faix-stem","model":"gemini-2.5-flash","score":6,"metric":"percent"},{"benchmark":"faix-stem","model":"gemini-2.5-flash-lite","score":6,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-2-2b","score":5.71,"metric":"percent"},{"benchmark":"faix-stem","model":"pixtral-12b","score":5.33,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-vl-30b-a3b-instruct","score":5.14,"metric":"percent"},{"benchmark":"faix-stem","model":"lfm2-2.6b","score":4.8,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-3.7-sonnet","score":4.57,"metric":"percent"},{"benchmark":"faix-stem","model":"gemini-1.5-flash","score":4,"metric":"percent"},{"benchmark":"faix-stem","model":"magistral-medium-1.2","score":4,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-max","score":4,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen-1.7b-thinking","score":3.64,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-30b-a3b","score":3.56,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-vl-8b-instruct","score":3.43,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-3-27b-vl","score":3.2,"metric":"percent"},{"benchmark":"faix-stem","model":"motif-2-12.7b-base","score":3.2,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-8b","score":3,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-2-27b","score":2.67,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-4-maverick","score":2.67,"metric":"percent"},{"benchmark":"faix-stem","model":"nemotron-nano-12b-v2-base","score":2.67,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-32b-instruct","score":2.67,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-v3","score":2.5,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon-h1-34b-instruct","score":2.29,"metric":"percent"},{"benchmark":"faix-stem","model":"mixtral-8x22b","score":2,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-4.0-h-tiny","score":1.6,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-3-1b","score":1.45,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-4-scout-17b","score":1.45,"metric":"percent"},{"benchmark":"faix-stem","model":"minimax-m1-80k","score":1.33,"metric":"percent"},{"benchmark":"faix-stem","model":"mm1.5-3b","score":1.33,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-vl-7b","score":1.33,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-2-9b","score":1,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-2-27b-it","score":0.8,"metric":"percent"},{"benchmark":"faix-stem","model":"mixtral-8x7b","score":0.8,"metric":"percent"},{"benchmark":"faix-stem","model":"mistral-small-3.1-24b-instruct","score":0.67,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-14b","score":0.67,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.2-3b","score":0.44,"metric":"percent"},{"benchmark":"faix-stem","model":"bagel-14b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"blip-3o-4b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"cambrian-1-34b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"cambrian-1-8b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"cambrian-34b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-3-haiku","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"claude-3-opus","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"codellama-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"codestral-22b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"command-r","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-r1-distill-llama-8b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"deepseek-r1-distill-qwen-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"dream-7b-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"emu3-8b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"exaone-4.0-1.2b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"exaone-deep-2.4b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon-3-1b-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon-h1-0.5b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon-h1-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon-h1-3b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon-h1-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon3-10b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon3-3b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"falcon3-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"fastvlm-0.5b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"gemma-3-270m-it","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"glm-4.5","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-3.5-turbo","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-4.1-nano","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-4o-mini","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-4v","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"gpt-5-nano-medium","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-3.1-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-3.1-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-3.2-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-3.2-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-3.3-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-3.3-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-4.0-h-micro","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-4.0-h-small","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-4.0-micro","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"granite-4.0-tiny-preview","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"grok-3-beta","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"internvl2-8b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"internvl2-llama-3-76b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"internvl2.5-26b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"internvl2.5-2b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"internvl2.5-4b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"internvl3.5-2b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"janus-pro-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"kimi-k2-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"kimi-linear-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llada-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-1-33b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-1b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-2-13b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-2-70b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-2-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3-8b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.1-8b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.2-1.24b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.2-1b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.2-90b-vision","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-3.2v-11b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-4-maverick-17b-128e-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llama-nemotron-super-v1","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llava-1.5-13b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llava-1.5-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llava-onevision-72b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"llava-onevision-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"magistral-small-1.2","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"minicpm-v-2.0-3b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"minimax-m1-40k","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"ministral-8b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"mistral-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"mistral-large","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"mistral-medium-3","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"mistral-small-3.2-24b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"mm1-30b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"mobilellm-p1","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"molmo-7b-d","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"molmoe-1b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"moonlight-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"ouro-1.4b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"ouro-2.6b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"paligemma-mix-3b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"phi-3.5-vision-4b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-max","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2-vl-72b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2-vl-7b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-0.5b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-32b-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-72b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-7b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-omni-7b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-vl-72b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen2.5-vl-3b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-0.6b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-0.8b","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-vl-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-vl-30b-a3b-thinking","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"qwen3-vl-4b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"seed-thinking-v1.5","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"smollm1-1.7b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"smollm2-1.7b-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"smollm2-135m-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"smollm2-360m-base","score":0,"metric":"percent"},{"benchmark":"faix-stem","model":"xgen-mm-interleave-4b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"claude-opus-4.5","score":85.71,"metric":"percent"},{"benchmark":"faix-text","model":"gemini-3-pro","score":63,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-5","score":58.81,"metric":"percent"},{"benchmark":"faix-text","model":"kimi-k2-thinking","score":48.22,"metric":"percent"},{"benchmark":"faix-text","model":"claude-sonnet-4.5","score":47.03,"metric":"percent"},{"benchmark":"faix-text","model":"grok-4-thinking","score":44.57,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-vl-32b-thinking","score":44,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-5.1","score":42.86,"metric":"percent"},{"benchmark":"faix-text","model":"o3-low","score":42.31,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-vl-235b-a22b-instruct","score":42,"metric":"percent"},{"benchmark":"faix-text","model":"seed-1.5-vl","score":40,"metric":"percent"},{"benchmark":"faix-text","model":"o1","score":38.08,"metric":"percent"},{"benchmark":"faix-text","model":"claude-opus-4.1","score":35.43,"metric":"percent"},{"benchmark":"faix-text","model":"gemini-2.5-pro","score":30.79,"metric":"percent"},{"benchmark":"faix-text","model":"gemini-2.0-pro","score":30.33,"metric":"percent"},{"benchmark":"faix-text","model":"ernie-4.5","score":30.12,"metric":"percent"},{"benchmark":"faix-text","model":"olmo-3-think-32b","score":29.14,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.1-405b","score":28.17,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-next-80b-a3b-instruct","score":28.17,"metric":"percent"},{"benchmark":"faix-text","model":"claude-opus-4","score":27.44,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-4","score":27.43,"metric":"percent"},{"benchmark":"faix-text","model":"minimax-m2","score":27.27,"metric":"percent"},{"benchmark":"faix-text","model":"claude-sonnet-4","score":24.56,"metric":"percent"},{"benchmark":"faix-text","model":"kimi-k2-base","score":24.4,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-max","score":24.4,"metric":"percent"},{"benchmark":"faix-text","model":"olmo-3-think-32b-dpo","score":24.29,"metric":"percent"},{"benchmark":"faix-text","model":"o1-mini","score":23.33,"metric":"percent"},{"benchmark":"faix-text","model":"grok-4-fast","score":21.71,"metric":"percent"},{"benchmark":"faix-text","model":"apriel-nemotron-15b-thinker","score":21.5,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-235b-a22b-instruct-2507","score":21.12,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-coder-32b-instruct","score":20.5,"metric":"percent"},{"benchmark":"faix-text","model":"gemini-2.0-flash","score":20,"metric":"percent"},{"benchmark":"faix-text","model":"k2-think","score":20,"metric":"percent"},{"benchmark":"faix-text","model":"ling-1t","score":20,"metric":"percent"},{"benchmark":"faix-text","model":"mistral-small-3.2-24b-instruct","score":20,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3_1-70b-tfree-hat-sft","score":19.08,"metric":"percent"},{"benchmark":"faix-text","model":"marin-32b-mantis","score":18.75,"metric":"percent"},{"benchmark":"faix-text","model":"o3-mini-low","score":18.17,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.3-70b","score":18.12,"metric":"percent"},{"benchmark":"faix-text","model":"dots-vlm1","score":18,"metric":"percent"},{"benchmark":"faix-text","model":"lg-exaone-32b","score":18,"metric":"percent"},{"benchmark":"faix-text","model":"mixtral-8x22b","score":18,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.1-70b","score":17.68,"metric":"percent"},{"benchmark":"faix-text","model":"claude-3.5-sonnet","score":17.33,"metric":"percent"},{"benchmark":"faix-text","model":"marin-32b-bison","score":17.25,"metric":"percent"},{"benchmark":"faix-text","model":"claude-4.5-haiku","score":17.2,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-3","score":16.49,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-4-turbo","score":16.33,"metric":"percent"},{"benchmark":"faix-text","model":"olmo-3-think-32b-sft","score":16.29,"metric":"percent"},{"benchmark":"faix-text","model":"kimi-k2","score":16.21,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-max","score":16,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-r1","score":15.92,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-v3.2-exp","score":15.78,"metric":"percent"},{"benchmark":"faix-text","model":"gemini-1.5-pro","score":15.67,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-r1-distill-qwen-32b","score":15.47,"metric":"percent"},{"benchmark":"faix-text","model":"o4-mini","score":15.2,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-4.1","score":14.96,"metric":"percent"},{"benchmark":"faix-text","model":"motif-2-12.7b-instruct","score":14.57,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-v2.5","score":14.5,"metric":"percent"},{"benchmark":"faix-text","model":"grok-code-fast-1","score":14.4,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-32b","score":14.07,"metric":"percent"},{"benchmark":"faix-text","model":"claude-3.7-sonnet","score":13.29,"metric":"percent"},{"benchmark":"faix-text","model":"chatgpt-4o","score":13.17,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-30b-a3b","score":13.1,"metric":"percent"},{"benchmark":"faix-text","model":"mistral-medium-3","score":13,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-32b-base","score":13,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3-70b","score":12.95,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-v3.1","score":12.92,"metric":"percent"},{"benchmark":"faix-text","model":"minimax-m1-80k","score":12.33,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-v3","score":12.29,"metric":"percent"},{"benchmark":"faix-text","model":"glm-4.6","score":12,"metric":"percent"},{"benchmark":"faix-text","model":"granite-3.3-8b-instruct","score":12,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-v3.1-terminus","score":11.82,"metric":"percent"},{"benchmark":"faix-text","model":"gemini-2.5-flash","score":11.79,"metric":"percent"},{"benchmark":"faix-text","model":"claude-3-opus","score":11.43,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-32b-instruct","score":11.43,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-v3.2","score":11.29,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-vl-30b-a3b-thinking","score":11.29,"metric":"percent"},{"benchmark":"faix-text","model":"qwq-32b","score":11.29,"metric":"percent"},{"benchmark":"faix-text","model":"olmo-2-0325-32b-instruct","score":11.23,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.1-nemotron-nano-8b-v1","score":11,"metric":"percent"},{"benchmark":"faix-text","model":"mixtral-8x7b","score":10.75,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-4o-mini","score":10,"metric":"percent"},{"benchmark":"faix-text","model":"glm-4.5","score":9.78,"metric":"percent"},{"benchmark":"faix-text","model":"llama-2-70b","score":9.6,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-oss-120b","score":9.33,"metric":"percent"},{"benchmark":"faix-text","model":"seed-thinking-v1.5","score":9.23,"metric":"percent"},{"benchmark":"faix-text","model":"falcon-h1-34b-instruct","score":9.05,"metric":"percent"},{"benchmark":"faix-text","model":"minimax-m1-40k","score":9,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-2-27b","score":8.73,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-coder-480b-a35b-instruct","score":8.44,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-omni-flash-instruct","score":8.36,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-72b-instruct","score":8.29,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-4b","score":7.83,"metric":"percent"},{"benchmark":"faix-text","model":"gemini-1.5-flash","score":7.58,"metric":"percent"},{"benchmark":"faix-text","model":"granite-3.2-8b-instruct","score":7,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-omni-30b-a3b","score":6.91,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-4.5","score":6.77,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-3-12b","score":6.67,"metric":"percent"},{"benchmark":"faix-text","model":"mistral-small-3.1-24b-instruct","score":6.55,"metric":"percent"},{"benchmark":"faix-text","model":"nemotron-nano-12b-v2-base","score":6.5,"metric":"percent"},{"benchmark":"faix-text","model":"command-r","score":6,"metric":"percent"},{"benchmark":"faix-text","model":"codestral-22b","score":5.78,"metric":"percent"},{"benchmark":"faix-text","model":"smollm3-3b","score":5.76,"metric":"percent"},{"benchmark":"faix-text","model":"granite-3.3-2b-instruct","score":5.54,"metric":"percent"},{"benchmark":"faix-text","model":"apriel-1.5-15b-thinker","score":5.33,"metric":"percent"},{"benchmark":"faix-text","model":"granite-3.1-8b-instruct","score":5,"metric":"percent"},{"benchmark":"faix-text","model":"granite-4.0-h-small","score":4.95,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-2-7b","score":4.86,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-oss-20b","score":4.84,"metric":"percent"},{"benchmark":"faix-text","model":"llama-4-maverick-17b-128e-instruct","score":4.57,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-3-4b","score":4.51,"metric":"percent"},{"benchmark":"faix-text","model":"claude-3.5-haiku","score":4,"metric":"percent"},{"benchmark":"faix-text","model":"granite-4.0-tiny-preview","score":4,"metric":"percent"},{"benchmark":"faix-text","model":"grok-3-beta","score":4,"metric":"percent"},{"benchmark":"faix-text","model":"kimi-linear-base","score":4,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-vl-72b","score":4,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-next-80b-a3b","score":4,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-vl-30b-a3b-instruct","score":3.11,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-2-9b","score":3,"metric":"percent"},{"benchmark":"faix-text","model":"motif-2-12.7b-base","score":2.91,"metric":"percent"},{"benchmark":"faix-text","model":"qwen-2.5-3b-instruct","score":2.88,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-4.1-mini","score":2.86,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-vl-8b-instruct","score":2.86,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-2-27b-it","score":2.67,"metric":"percent"},{"benchmark":"faix-text","model":"qwen-1.7b-thinking","score":2.63,"metric":"percent"},{"benchmark":"faix-text","model":"exaone-deep-2.4b","score":2.4,"metric":"percent"},{"benchmark":"faix-text","model":"llama-4-scout-17b","score":2.33,"metric":"percent"},{"benchmark":"faix-text","model":"lfm2-8b-a1b","score":2.29,"metric":"percent"},{"benchmark":"faix-text","model":"falcon-h1-7b","score":2.11,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-2-2b","score":2,"metric":"percent"},{"benchmark":"faix-text","model":"granite-3.1-2b-instruct","score":2,"metric":"percent"},{"benchmark":"faix-text","model":"llama-4-maverick","score":2,"metric":"percent"},{"benchmark":"faix-text","model":"granite-4.0-micro","score":1.9,"metric":"percent"},{"benchmark":"faix-text","model":"llama-2-13b","score":1.85,"metric":"percent"},{"benchmark":"faix-text","model":"mistral-7b","score":1.78,"metric":"percent"},{"benchmark":"faix-text","model":"lfm2-2.6b","score":1.71,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-3.5-turbo","score":1.6,"metric":"percent"},{"benchmark":"faix-text","model":"mimo-vl","score":1.6,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3-8b","score":1.5,"metric":"percent"},{"benchmark":"faix-text","model":"exaone-4.0-1.2b","score":1.45,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-7b-instruct","score":1.33,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.1-8b","score":1.03,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-coder-33b","score":1,"metric":"percent"},{"benchmark":"faix-text","model":"glm-4.5-air","score":0.86,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-14b","score":0.76,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-8b","score":0.67,"metric":"percent"},{"benchmark":"faix-text","model":"granite-4.0-h-tiny","score":0.62,"metric":"percent"},{"benchmark":"faix-text","model":"llama-2-7b","score":0.62,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-3-1b","score":0.43,"metric":"percent"},{"benchmark":"faix-text","model":"falcon3-10b","score":0.42,"metric":"percent"},{"benchmark":"faix-text","model":"granite-4.0-h-micro","score":0.4,"metric":"percent"},{"benchmark":"faix-text","model":"llama-1-33b","score":0.33,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-vl-4b-instruct","score":0.29,"metric":"percent"},{"benchmark":"faix-text","model":"falcon-h1-3b","score":0.21,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.2-3b","score":0.13,"metric":"percent"},{"benchmark":"faix-text","model":"claude-3-haiku","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"codellama-7b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-r1-distill-llama-8b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"deepseek-r1-distill-qwen-7b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"dream-7b-base","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"exaone-4.0-32b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"falcon-3-1b-base","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"falcon-h1-0.5b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"falcon-h1-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"falcon3-3b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"falcon3-7b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"gemma-3-270m-it","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-4.1-nano","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"gpt-5-nano-medium","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"granite-3.2-2b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"grok-3-mini","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"internvl-8b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"llada-8b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"llama-1b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.2-1.24b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.2-1b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"llama-3.2-90b-vision","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"llama-nemotron-super-v1","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"magistral-medium-1.2","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"magistral-small-1.2","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"ministral-8b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"mistral-large","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"mobilellm-p1","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"moonlight-base","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"ouro-1.4b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"ouro-2.6b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-0.5b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-7b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"qwen2.5-vl-7b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-0.6b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"qwen3-0.8b","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"smollm1-1.7b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"smollm2-1.7b-base","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"smollm2-135m-base","score":0,"metric":"percent"},{"benchmark":"faix-text","model":"smollm2-360m-base","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"gemini-3-pro","score":100,"metric":"percent"},{"benchmark":"faix-visual","model":"holo1.5-72b","score":88.8,"metric":"percent"},{"benchmark":"faix-visual","model":"gpt-4.1","score":74,"metric":"percent"},{"benchmark":"faix-visual","model":"grok-4-thinking","score":70,"metric":"percent"},{"benchmark":"faix-visual","model":"o3-low","score":66.67,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-opus-4.5","score":66,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen3-vl-235b-a22b-instruct","score":64.29,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-opus-4","score":52,"metric":"percent"},{"benchmark":"faix-visual","model":"ui-venus-72b","score":49.6,"metric":"percent"},{"benchmark":"faix-visual","model":"holo1.5-7b","score":48.8,"metric":"percent"},{"benchmark":"faix-visual","model":"gemini-2.0-flash","score":46.67,"metric":"percent"},{"benchmark":"faix-visual","model":"seed-1.5-vl","score":46.67,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen3-vl-32b-instruct","score":45.09,"metric":"percent"},{"benchmark":"faix-visual","model":"gemini-2.5-pro","score":44.77,"metric":"percent"},{"benchmark":"faix-visual","model":"molmo-72b","score":44.36,"metric":"percent"},{"benchmark":"faix-visual","model":"gpt-5","score":42.87,"metric":"percent"},{"benchmark":"faix-visual","model":"gpt-5.1","score":42.4,"metric":"percent"},{"benchmark":"faix-visual","model":"dots-vlm1","score":40.52,"metric":"percent"},{"benchmark":"faix-visual","model":"glm-4.5v","score":38.81,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen2-vl-72b","score":31.67,"metric":"percent"},{"benchmark":"faix-visual","model":"ui-tars-1.5-7b","score":28,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen2.5-vl-72b","score":27.68,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen3-vl-30b-a3b-instruct","score":26.67,"metric":"percent"},{"benchmark":"faix-visual","model":"molmo-7b-d","score":26.55,"metric":"percent"},{"benchmark":"faix-visual","model":"ui-venus-7b","score":24.4,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-4.5-haiku","score":24,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen3-vl-8b-instruct","score":23.35,"metric":"percent"},{"benchmark":"faix-visual","model":"llama-4-maverick","score":23.33,"metric":"percent"},{"benchmark":"faix-visual","model":"ernie-4.5-vl-28b-a3b-thinking","score":22.35,"metric":"percent"},{"benchmark":"faix-visual","model":"holo1.5-3b","score":22,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-sonnet-4.5","score":21.33,"metric":"percent"},{"benchmark":"faix-visual","model":"mimo-vl","score":20.53,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-3.5-sonnet","score":19.69,"metric":"percent"},{"benchmark":"faix-visual","model":"manzano-30b","score":18.67,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-sonnet-4","score":18.22,"metric":"percent"},{"benchmark":"faix-visual","model":"chatgpt-4o","score":18.06,"metric":"percent"},{"benchmark":"faix-visual","model":"step-3","score":17,"metric":"percent"},{"benchmark":"faix-visual","model":"gemini-2.5-flash","score":16.67,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen3-vl-4b-instruct","score":15.72,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-3.7-sonnet","score":15.05,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen2-vl-7b-instruct","score":14.91,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl2-llama-3-76b","score":14.8,"metric":"percent"},{"benchmark":"faix-visual","model":"glm-4.1v","score":14.5,"metric":"percent"},{"benchmark":"faix-visual","model":"fastvlm-7b","score":12.73,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl3.5-4b","score":12.67,"metric":"percent"},{"benchmark":"faix-visual","model":"gemini-1.5-pro","score":11.78,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-opus-4.1","score":11.56,"metric":"percent"},{"benchmark":"faix-visual","model":"llama-3.2-90b-vision","score":11.27,"metric":"percent"},{"benchmark":"faix-visual","model":"molmoe-1b","score":10.8,"metric":"percent"},{"benchmark":"faix-visual","model":"gemini-1.5-flash","score":10.33,"metric":"percent"},{"benchmark":"faix-visual","model":"phi-3-vision-4b","score":10.15,"metric":"percent"},{"benchmark":"faix-visual","model":"pixtral-12b","score":9.67,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-3-opus","score":9.09,"metric":"percent"},{"benchmark":"faix-visual","model":"llama-3.2v-11b-instruct","score":9.09,"metric":"percent"},{"benchmark":"faix-visual","model":"bagel-14b","score":9,"metric":"percent"},{"benchmark":"faix-visual","model":"claude-3-haiku","score":8.33,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen2.5-vl-7b","score":8.1,"metric":"percent"},{"benchmark":"faix-visual","model":"llama-4-maverick-17b-128e-instruct","score":8,"metric":"percent"},{"benchmark":"faix-visual","model":"holo1-7b","score":7.6,"metric":"percent"},{"benchmark":"faix-visual","model":"llava-onevision-72b","score":6.91,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen3-vl-2b-instruct","score":6.64,"metric":"percent"},{"benchmark":"faix-visual","model":"fastvlm-1.5b","score":6.18,"metric":"percent"},{"benchmark":"faix-visual","model":"mm1.5-30b","score":5.82,"metric":"percent"},{"benchmark":"faix-visual","model":"manzano-3b","score":5.67,"metric":"percent"},{"benchmark":"faix-visual","model":"gemma-3","score":5.64,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl-8b","score":5.1,"metric":"percent"},{"benchmark":"faix-visual","model":"gemini-2.5-flash-lite","score":4.62,"metric":"percent"},{"benchmark":"faix-visual","model":"llava-onevision-7b","score":4,"metric":"percent"},{"benchmark":"faix-visual","model":"gpt-5-nano-medium","score":3.88,"metric":"percent"},{"benchmark":"faix-visual","model":"kimi-vl-a3b-thinking","score":3.69,"metric":"percent"},{"benchmark":"faix-visual","model":"cambrian-34b","score":2.91,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl2.5-26b","score":2.91,"metric":"percent"},{"benchmark":"faix-visual","model":"gemma-3-27b-vl","score":2.5,"metric":"percent"},{"benchmark":"faix-visual","model":"cambrian-1-34b","score":2.4,"metric":"percent"},{"benchmark":"faix-visual","model":"holo1-3b","score":2.4,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen2.5-omni-7b","score":2.15,"metric":"percent"},{"benchmark":"faix-visual","model":"llama-4-scout-17b","score":1.6,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen2.5-vl-3b","score":0.94,"metric":"percent"},{"benchmark":"faix-visual","model":"mistral-small-3.1-24b-instruct","score":0.8,"metric":"percent"},{"benchmark":"faix-visual","model":"smolvlm2-2.2b","score":0.8,"metric":"percent"},{"benchmark":"faix-visual","model":"paligemma-mix-3b","score":0.4,"metric":"percent"},{"benchmark":"faix-visual","model":"xgen-mm-interleave-4b","score":0.4,"metric":"percent"},{"benchmark":"faix-visual","model":"mm1.5-3b","score":0.33,"metric":"percent"},{"benchmark":"faix-visual","model":"blip-3o-4b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"cambrian-1-8b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"emu3-8b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"fastvlm-0.5b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"gemini-2.0-pro","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"gpt-4v","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl2-8b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl2.5-2b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl2.5-4b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl3-2b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"internvl3.5-2b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"janus-pro-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"lfm2-vl-3b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"llava-1.5-13b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"llava-1.5-7b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"minicpm-v-2.0-3b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"mistral-medium-3","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"mistral-small-3.2-24b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"mm1-30b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"phi-3.5-vision-4b","score":0,"metric":"percent"},{"benchmark":"faix-visual","model":"qwen2.5-vl-3b","score":0,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-235b-a22b-instruct-2507","score":60,"metric":"percent"},{"benchmark":"faix-writing","model":"gpt-5","score":57.33,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-30b-a3b","score":54,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-next-80b-a3b-instruct","score":48,"metric":"percent"},{"benchmark":"faix-writing","model":"deepseek-v3","score":36,"metric":"percent"},{"benchmark":"faix-writing","model":"kimi-k2","score":33.33,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-omni-flash-instruct","score":30,"metric":"percent"},{"benchmark":"faix-writing","model":"gemini-2.5-pro","score":29.33,"metric":"percent"},{"benchmark":"faix-writing","model":"claude-opus-4.1","score":24,"metric":"percent"},{"benchmark":"faix-writing","model":"deepseek-v3.1","score":24,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-omni-30b-a3b","score":24,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-vl-30b-a3b-thinking","score":16,"metric":"percent"},{"benchmark":"faix-writing","model":"gemini-2.5-flash","score":14,"metric":"percent"},{"benchmark":"faix-writing","model":"claude-sonnet-4","score":12,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-4b","score":8,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-vl-30b-a3b-instruct","score":2,"metric":"percent"},{"benchmark":"faix-writing","model":"chatgpt-4o","score":0,"metric":"percent"},{"benchmark":"faix-writing","model":"claude-3.5-sonnet","score":0,"metric":"percent"},{"benchmark":"faix-writing","model":"deepseek-r1","score":0,"metric":"percent"},{"benchmark":"faix-writing","model":"glm-4.5","score":0,"metric":"percent"},{"benchmark":"faix-writing","model":"gpt-oss-120b","score":0,"metric":"percent"},{"benchmark":"faix-writing","model":"qwen3-32b","score":0,"metric":"percent"},{"benchmark":"proofbench-basic","model":"claude-sonnet-4","score":27.1,"metric":"percent"},{"benchmark":"proofbench-basic","model":"deepseek-r1","score":29,"metric":"percent"},{"benchmark":"proofbench-basic","model":"qwen3-235b-a22b","score":33.3,"metric":"percent"},{"benchmark":"proofbench-basic","model":"grok-4","score":46.7,"metric":"percent"},{"benchmark":"proofbench-basic","model":"gemini-2.5-pro","score":55.2,"metric":"percent"},{"benchmark":"proofbench-basic","model":"gpt-5","score":59,"metric":"percent"},{"benchmark":"proofbench-basic","model":"gemini-deep-think-imo-gold","score":89,"metric":"percent"},{"benchmark":"proofbench-basic","model":"deepseekmath-v2-heavy","score":99,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"claude-sonnet-4","score":4.8,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"deepseek-r1","score":3.8,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"qwen3-235b-a22b","score":5.2,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"grok-4","score":18.6,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gemini-2.5-pro","score":17.6,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gpt-5","score":20,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gemini-deep-think-imo-gold","score":65.7,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"deepseekmath-v2-heavy","score":61.9,"metric":"percent"},{"benchmark":"proofbench-basic","model":"gemini-2.5-deep-think","score":83.8,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gemini-2.5-deep-think","score":37.6,"metric":"percent"},{"benchmark":"math500","model":"intellect-3","score":98.1,"metric":"percent"},{"benchmark":"aime-2024","model":"intellect-3","score":90.8,"metric":"percent"},{"benchmark":"aime-2025","model":"intellect-3","score":88,"metric":"percent"},{"benchmark":"livecodebench","model":"intellect-3","score":69.3,"metric":"percent"},{"benchmark":"gpqa","model":"intellect-3","score":74.4,"metric":"percent"},{"benchmark":"hle","model":"intellect-3","score":14.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intellect-3","score":81.9,"metric":"percent"},{"benchmark":"math500","model":"glm-4.5-air","score":97.8,"metric":"percent"},{"benchmark":"aime-2024","model":"glm-4.5-air","score":84.6,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.5-air","score":82,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-air","score":61.5,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4.5-air","score":73.3,"metric":"percent"},{"benchmark":"hle","model":"glm-4.5-air","score":13.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-air","score":73.9,"metric":"percent"},{"benchmark":"math500","model":"glm-4.5","score":97,"metric":"percent"},{"benchmark":"aime-2024","model":"glm-4.5","score":85.8,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.5","score":83.3,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5","score":64.5,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4.5","score":77,"metric":"percent"},{"benchmark":"hle","model":"glm-4.5","score":14.8,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1-0528","score":87.3,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-0528","score":83.2,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0528","score":73.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-0528","score":62.5,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-r1-0528","score":77.5,"metric":"percent"},{"benchmark":"hle","model":"deepseek-r1-0528","score":15.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-0528","score":75.3,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v3.2","score":96.8,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v3.2","score":88.1,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v3.2","score":81.4,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.2","score":25.1,"metric":"avg@3"},{"benchmark":"math500","model":"gpt-oss-120b","score":96,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-120b","score":75.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":77.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":69.9,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-oss-120b","score":70,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-120b","score":10.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b","score":67.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3-pro","score":90.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-m2","score":82,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.2-thinking","score":85,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m2","score":77.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.2-thinking","score":82.4,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4.5","score":13.7,"metric":"percent"},{"benchmark":"hle","model":"gemini-3-pro","score":37.5,"metric":"avg@3"},{"benchmark":"hle","model":"kimi-k2-thinking","score":23.9,"metric":"avg@3"},{"benchmark":"hle","model":"minimax-m2","score":12.5,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.2-thinking","score":25.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-pro","score":90.7,"metric":"percent"},{"benchmark":"livecodebench","model":"minimax-m2","score":83,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-thinking","score":83.3,"metric":"percent"},{"benchmark":"codeforces","model":"claude-sonnet-4.5","score":1480,"metric":"ELO"},{"benchmark":"codeforces","model":"gpt-5-high","score":2537,"metric":"ELO"},{"benchmark":"codeforces","model":"gemini-3-pro","score":2708,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v3.2-thinking","score":2386,"metric":"ELO"},{"benchmark":"aime-2025","model":"minimax-m2","score":78.3,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.2-thinking","score":93.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"claude-sonnet-4.5","score":79.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-5-high","score":88.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-3-pro","score":97.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.2-thinking","score":92.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"claude-sonnet-4.5","score":81.7,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-5-high","score":89.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-3-pro","score":93.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"kimi-k2-thinking","score":89.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.2-thinking","score":90.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5-high","score":76,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3-pro","score":83.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v3.2-thinking","score":78.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5-high","score":35.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2-thinking","score":35.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v3.2-thinking","score":46.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.2-thinking","score":73.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5-high","score":55.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v3.2-thinking","score":70.2,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5-high","score":54.9,"metric":"percent"},{"benchmark":"browsecomp","model":"minimax-m2","score":44,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v3.2-thinking","score":51.4,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-5-high","score":63,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepseek-v3.2-thinking","score":65,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4.5","score":32,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.2-thinking","score":40.8,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-sonnet-4.5","score":46.5,"metric":"percent"},{"benchmark":"mcp-universe","model":"gpt-5-high","score":47.9,"metric":"percent"},{"benchmark":"mcp-universe","model":"gemini-3-pro","score":50.7,"metric":"percent"},{"benchmark":"mcp-universe","model":"kimi-k2-thinking","score":35.6,"metric":"percent"},{"benchmark":"mcp-universe","model":"minimax-m2","score":29.4,"metric":"percent"},{"benchmark":"mcp-universe","model":"deepseek-v3.2-thinking","score":45.9,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-sonnet-4.5","score":33.3,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-high","score":50.9,"metric":"percent"},{"benchmark":"mcpmark","model":"gemini-3-pro","score":43.1,"metric":"percent"},{"benchmark":"mcpmark","model":"kimi-k2-thinking","score":20.4,"metric":"percent"},{"benchmark":"mcpmark","model":"minimax-m2","score":24.4,"metric":"percent"},{"benchmark":"mcpmark","model":"deepseek-v3.2-thinking","score":38,"metric":"percent"},{"benchmark":"tool-decathlon","model":"claude-sonnet-4.5","score":38.6,"metric":"percent"},{"benchmark":"tool-decathlon","model":"gpt-5-high","score":29,"metric":"percent"},{"benchmark":"tool-decathlon","model":"gemini-3-pro","score":36.4,"metric":"percent"},{"benchmark":"tool-decathlon","model":"kimi-k2-thinking","score":17.6,"metric":"percent"},{"benchmark":"tool-decathlon","model":"minimax-m2","score":16,"metric":"percent"},{"benchmark":"tool-decathlon","model":"deepseek-v3.2-thinking","score":35.2,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3-nano-30b-a3b-base","score":78.56,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-30b-a3b-base","score":65.05,"metric":"percent"},{"benchmark":"agieval","model":"nemotron-3-nano-30b-a3b-base","score":68.32,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-nano-30b-a3b-base","score":78.05,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-nano-30b-a3b-base","score":75.49,"metric":"percent"},{"benchmark":"mmlu","model":"k2-v2","score":75.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"k2-v2","score":57,"metric":"percent"},{"benchmark":"bbh","model":"k2-v2","score":83.2,"metric":"percent"},{"benchmark":"hellaswag","model":"k2-v2","score":87.6,"metric":"percent"},{"benchmark":"winogrande","model":"k2-v2","score":83.9,"metric":"percent"},{"benchmark":"piqa","model":"k2-v2","score":84.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"k2-v2","score":60.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-v2","score":55.1,"metric":"percent"},{"benchmark":"gsm8k","model":"k2-v2","score":92.5,"metric":"percent"},{"benchmark":"math","model":"k2-v2","score":91.4,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-v2","score":46.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"k2-v2","score":66.3,"metric":"percent"},{"benchmark":"mbpp","model":"k2-v2","score":61.8,"metric":"percent"},{"benchmark":"humaneval","model":"k2-v2","score":54.3,"metric":"percent"},{"benchmark":"countdown","model":"k2-v2","score":75.6,"metric":"percent"},{"benchmark":"kk-4-people","model":"k2-v2","score":92.9,"metric":"percent"},{"benchmark":"kk-8-people","model":"k2-v2","score":82.8,"metric":"percent"},{"benchmark":"order-15-items","model":"k2-v2","score":87.6,"metric":"percent"},{"benchmark":"order-30-items","model":"k2-v2","score":40.3,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"k2-v2","score":65.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"k2-low-70b","score":40.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"k2-medium-70b","score":41.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"k2-high-70b","score":42.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"olmo-3-think-32b-sft","score":42.8,"metric":"percent"},{"benchmark":"longbench-v2","model":"olmo-3-think-32b-dpo","score":47.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"glm-4.5-air","score":49.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"minimax-m2","score":55.8,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen-3-235b-a22b-thinking","score":60.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen-2.5-72b","score":47.2,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-low-70b","score":27.3,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-medium-70b","score":62,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-high-70b","score":80.2,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-32b-sft","score":68.3,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-32b-dpo","score":73.3,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.5-air","score":81.3,"metric":"percent"},{"benchmark":"aime-2025","model":"minimax-m2","score":75.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen-3-235b-a22b-thinking","score":88.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen-2.5-72b","score":15.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"k2-low-70b","score":19,"metric":"percent"},{"benchmark":"hmmt-2025","model":"k2-medium-70b","score":45.6,"metric":"percent"},{"benchmark":"hmmt-2025","model":"k2-high-70b","score":71.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"olmo-3-think-32b-sft","score":43.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"olmo-3-think-32b-dpo","score":50.83,"metric":"percent"},{"benchmark":"hmmt-2025","model":"glm-4.5-air","score":73.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"minimax-m2","score":63.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen-3-235b-a22b-thinking","score":84.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen-2.5-72b","score":9.79,"metric":"percent"},{"benchmark":"gsm8k","model":"k2-low-70b","score":92.4,"metric":"percent"},{"benchmark":"gsm8k","model":"k2-medium-70b","score":92,"metric":"percent"},{"benchmark":"gsm8k","model":"k2-high-70b","score":94.8,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-think-32b-sft","score":96.1,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-think-32b-dpo","score":95.7,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4.5-air","score":96.1,"metric":"percent"},{"benchmark":"gsm8k","model":"minimax-m2","score":95.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-3-235b-a22b-thinking","score":93.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-2.5-72b","score":85.8,"metric":"percent"},{"benchmark":"minerva-math","model":"k2-low-70b","score":85,"metric":"percent"},{"benchmark":"minerva-math","model":"k2-medium-70b","score":90.6,"metric":"percent"},{"benchmark":"minerva-math","model":"k2-high-70b","score":94.5,"metric":"percent"},{"benchmark":"minerva-math","model":"olmo-3-think-32b-sft","score":96.9,"metric":"percent"},{"benchmark":"minerva-math","model":"olmo-3-think-32b-dpo","score":97.3,"metric":"percent"},{"benchmark":"minerva-math","model":"glm-4.5-air","score":94.9,"metric":"percent"},{"benchmark":"minerva-math","model":"minimax-m2","score":85.3,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen-3-235b-a22b-thinking","score":98,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen-2.5-72b","score":82.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-low-70b","score":48.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-medium-70b","score":60.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-high-70b","score":69.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-think-32b-sft","score":58,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-think-32b-dpo","score":59.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.5-air","score":75.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m2","score":76.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen-3-235b-a22b-thinking","score":80.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen-2.5-72b","score":50.5,"metric":"percent"},{"benchmark":"mbpp","model":"k2-low-70b","score":71,"metric":"percent"},{"benchmark":"mbpp","model":"k2-medium-70b","score":75.8,"metric":"percent"},{"benchmark":"mbpp","model":"k2-high-70b","score":84.8,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3-think-32b-sft","score":87.6,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3-think-32b-dpo","score":91.6,"metric":"percent"},{"benchmark":"mbpp","model":"glm-4.5-air","score":82.8,"metric":"percent"},{"benchmark":"mbpp","model":"minimax-m2","score":83.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-3-235b-a22b-thinking","score":96.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-2.5-72b","score":80,"metric":"percent"},{"benchmark":"humaneval","model":"k2-low-70b","score":82.3,"metric":"percent"},{"benchmark":"humaneval","model":"k2-medium-70b","score":91.5,"metric":"percent"},{"benchmark":"humaneval","model":"k2-high-70b","score":91.5,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3-think-32b-sft","score":96.3,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3-think-32b-dpo","score":96.3,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4.5-air","score":97.6,"metric":"percent"},{"benchmark":"humaneval","model":"minimax-m2","score":89.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-3-235b-a22b-thinking","score":94.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-2.5-72b","score":85.4,"metric":"percent"},{"benchmark":"livecodebench","model":"k2-low-70b","score":39.9,"metric":"percent"},{"benchmark":"livecodebench","model":"k2-medium-70b","score":51.3,"metric":"percent"},{"benchmark":"livecodebench","model":"k2-high-70b","score":67,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-32b-sft","score":67.9,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-32b-dpo","score":67.6,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-air","score":67.8,"metric":"percent"},{"benchmark":"livecodebench","model":"minimax-m2","score":79.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen-3-235b-a22b-thinking","score":72.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen-2.5-72b","score":36.7,"metric":"percent"},{"benchmark":"mmlu","model":"k2-v2","score":74.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-2.5-72b","score":86.1,"metric":"percent"},{"benchmark":"mmlu","model":"llama3.0-70b","score":79.5,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-70b","score":79.3,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-32b","score":75.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"k2-v2","score":43.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen-2.5-72b","score":58.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama3.0-70b","score":52.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-70b","score":53.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3-think-32b","score":49.6,"metric":"percent"},{"benchmark":"bbh","model":"k2-v2","score":68.4,"metric":"percent"},{"benchmark":"bbh","model":"qwen-2.5-72b","score":86.3,"metric":"percent"},{"benchmark":"bbh","model":"llama3.0-70b","score":82.2,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-70b","score":82.1,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-32b","score":77.6,"metric":"percent"},{"benchmark":"hellaswag","model":"k2-v2","score":87.8,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-2.5-72b","score":87.6,"metric":"percent"},{"benchmark":"hellaswag","model":"llama3.0-70b","score":88,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-70b","score":85,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-think-32b","score":84.8,"metric":"percent"},{"benchmark":"winogrande","model":"k2-v2","score":82.6,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-2.5-72b","score":83.9,"metric":"percent"},{"benchmark":"winogrande","model":"llama3.0-70b","score":85.3,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.1-70b","score":79.8,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-3-think-32b","score":90.3,"metric":"percent"},{"benchmark":"piqa","model":"k2-v2","score":84.2,"metric":"percent"},{"benchmark":"piqa","model":"qwen-2.5-72b","score":83.5,"metric":"percent"},{"benchmark":"piqa","model":"llama3.0-70b","score":84.6,"metric":"percent"},{"benchmark":"piqa","model":"llama-3.1-70b","score":84.3,"metric":"percent"},{"benchmark":"piqa","model":"olmo-3-think-32b","score":85.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"k2-v2","score":54,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen-2.5-72b","score":60.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama3.0-70b","score":45.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-70b","score":49.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"olmo-3-think-32b","score":54.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-v2","score":26.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen-2.5-72b","score":34.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama3.0-70b","score":21.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-70b","score":27.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-think-32b","score":30.3,"metric":"percent"},{"benchmark":"gsm8k","model":"k2-v2","score":68,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-2.5-72b","score":91.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama3.0-70b","score":83.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b","score":81.1,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-think-32b","score":80.5,"metric":"percent"},{"benchmark":"math","model":"k2-v2","score":27.8,"metric":"percent"},{"benchmark":"math","model":"qwen-2.5-72b","score":58.5,"metric":"percent"},{"benchmark":"math","model":"llama3.0-70b","score":41.9,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-70b","score":41.6,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-32b","score":43.4,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-v2","score":0,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen-2.5-72b","score":1.7,"metric":"percent"},{"benchmark":"aime-2025","model":"llama3.0-70b","score":0.1,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.1-70b","score":0.2,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-32b","score":14.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"k2-v2","score":64.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-2.5-72b","score":72.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama3.0-70b","score":69.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-70b","score":64.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-3-think-32b","score":65.4,"metric":"percent"},{"benchmark":"mbpp","model":"k2-v2","score":57.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-2.5-72b","score":75.4,"metric":"percent"},{"benchmark":"mbpp","model":"llama3.0-70b","score":69.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-70b","score":64.4,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3-think-32b","score":60.2,"metric":"percent"},{"benchmark":"humaneval","model":"k2-v2","score":50,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-2.5-72b","score":54.3,"metric":"percent"},{"benchmark":"humaneval","model":"llama3.0-70b","score":42.1,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-70b","score":50.6,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3-think-32b","score":36,"metric":"percent"},{"benchmark":"countdown","model":"k2-v2","score":1.3,"metric":"percent"},{"benchmark":"countdown","model":"qwen-2.5-72b","score":6,"metric":"percent"},{"benchmark":"countdown","model":"llama3.0-70b","score":1,"metric":"percent"},{"benchmark":"countdown","model":"llama-3.1-70b","score":0.5,"metric":"percent"},{"benchmark":"countdown","model":"olmo-3-think-32b","score":23.2,"metric":"percent"},{"benchmark":"kk-4-people","model":"k2-v2","score":4.8,"metric":"percent"},{"benchmark":"kk-4-people","model":"qwen-2.5-72b","score":26.1,"metric":"percent"},{"benchmark":"kk-4-people","model":"llama3.0-70b","score":4.2,"metric":"percent"},{"benchmark":"kk-4-people","model":"llama-3.1-70b","score":7.6,"metric":"percent"},{"benchmark":"kk-4-people","model":"olmo-3-think-32b","score":42.4,"metric":"percent"},{"benchmark":"kk-8-people","model":"k2-v2","score":0.5,"metric":"percent"},{"benchmark":"kk-8-people","model":"qwen-2.5-72b","score":5.7,"metric":"percent"},{"benchmark":"kk-8-people","model":"llama3.0-70b","score":1.1,"metric":"percent"},{"benchmark":"kk-8-people","model":"llama-3.1-70b","score":1.3,"metric":"percent"},{"benchmark":"kk-8-people","model":"olmo-3-think-32b","score":13,"metric":"percent"},{"benchmark":"order-15-items","model":"k2-v2","score":4.7,"metric":"percent"},{"benchmark":"order-15-items","model":"qwen-2.5-72b","score":37,"metric":"percent"},{"benchmark":"order-15-items","model":"llama3.0-70b","score":3.5,"metric":"percent"},{"benchmark":"order-15-items","model":"llama-3.1-70b","score":4.5,"metric":"percent"},{"benchmark":"order-15-items","model":"olmo-3-think-32b","score":25,"metric":"percent"},{"benchmark":"order-30-items","model":"k2-v2","score":0,"metric":"percent"},{"benchmark":"order-30-items","model":"qwen-2.5-72b","score":0.7,"metric":"percent"},{"benchmark":"order-30-items","model":"llama3.0-70b","score":0.2,"metric":"percent"},{"benchmark":"order-30-items","model":"llama-3.1-70b","score":0.1,"metric":"percent"},{"benchmark":"order-30-items","model":"olmo-3-think-32b","score":0.6,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"k2-v2","score":65.4,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"qwen-2.5-72b","score":74.1,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"llama3.0-70b","score":65,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"llama-3.1-70b","score":66.8,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"olmo-3-think-32b","score":47.8,"metric":"percent"},{"benchmark":"ifeval","model":"eurollm-22b","score":67.22,"metric":"percent"},{"benchmark":"hellaswag","model":"eurollm-22b","score":70.39,"metric":"percent"},{"benchmark":"mmlu","model":"eurollm-22b","score":69.81,"metric":"percent"},{"benchmark":"mmlu-pro","model":"eurollm-22b","score":50.85,"metric":"percent"},{"benchmark":"bbh","model":"eurollm-22b","score":55.33,"metric":"percent"},{"benchmark":"arc-challenge","model":"eurollm-22b","score":89.76,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"eurollm-22b","score":26.77,"metric":"percent"},{"benchmark":"gsm8k","model":"eurollm-22b","score":85.54,"metric":"percent"},{"benchmark":"math500","model":"eurollm-22b","score":54.47,"metric":"percent"},{"benchmark":"humaneval","model":"eurollm-22b","score":53.86,"metric":"percent"},{"benchmark":"ifeval","model":"apertus-70b","score":61.24,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-70b","score":70.24,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-70b","score":67.85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-70b","score":41.94,"metric":"percent"},{"benchmark":"bbh","model":"apertus-70b","score":56.12,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-70b","score":84.67,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apertus-70b","score":21.38,"metric":"percent"},{"benchmark":"gsm8k","model":"apertus-70b","score":80.04,"metric":"percent"},{"benchmark":"math500","model":"apertus-70b","score":42.27,"metric":"percent"},{"benchmark":"humaneval","model":"apertus-70b","score":44.51,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-2-32b-base","score":81.02,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-2-32b-base","score":54.81,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-2-32b-base","score":75.95,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-2-32b-base","score":51.25,"metric":"percent"},{"benchmark":"bbh","model":"olmo-2-32b-base","score":67.79,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-2-32b-base","score":92.06,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-2-32b-base","score":32.66,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-2-32b-base","score":92.47,"metric":"percent"},{"benchmark":"math500","model":"olmo-2-32b-base","score":50.47,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-2-32b-base","score":52.03,"metric":"percent"},{"benchmark":"ifeval","model":"mistral-3.2-24b","score":65.74,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-3.2-24b","score":86.51,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-3.2-24b","score":77.32,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-3.2-24b","score":67.45,"metric":"percent"},{"benchmark":"bbh","model":"mistral-3.2-24b","score":78.13,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-3.2-24b","score":93.43,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-3.2-24b","score":47.47,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-3.2-24b","score":95.53,"metric":"percent"},{"benchmark":"math500","model":"mistral-3.2-24b","score":81.47,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-3.2-24b","score":73.58,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.3-70b","score":82.81,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.3-70b","score":86.1,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.3-70b","score":84.62,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.3-70b","score":70.41,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.3-70b","score":82.32,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.3-70b","score":94.45,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.3-70b","score":46.63,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.3-70b","score":96.36,"metric":"percent"},{"benchmark":"math500","model":"llama-3.3-70b","score":74.6,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.3-70b","score":71.14,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-27b","score":80.71,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-27b","score":83.76,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b","score":80.45,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-27b","score":66.63,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-27b","score":82.16,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-27b","score":93.54,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-27b","score":47.64,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-27b","score":95.98,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-27b","score":88.47,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-27b","score":73.17,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-32b","score":81.89,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-32b","score":87.48,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-32b","score":83.97,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b","score":74.08,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-32b","score":83.68,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-32b","score":95.16,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-32b","score":54.71,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-32b","score":95.22,"metric":"percent"},{"benchmark":"math500","model":"qwen3-32b","score":85.73,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-32b","score":75,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b","score":83.67,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-30b-a3b","score":88.29,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b","score":84.95,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b","score":76.67,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-30b-a3b","score":86.13,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-30b-a3b","score":95.96,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b","score":58.59,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b","score":96.26,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b","score":89.73,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-30b-a3b","score":75,"metric":"percent"},{"benchmark":"videommmu","model":"seed-1.5-vl","score":81.4,"metric":"percent"},{"benchmark":"videommmu","model":"seed1.8","score":82.7,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-2.5-pro","score":76.1,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-3-pro","score":76.3,"metric":"percent"},{"benchmark":"mmvu","model":"seed-1.5-vl","score":70.1,"metric":"percent"},{"benchmark":"mmvu","model":"seed1.8","score":73.1,"metric":"percent"},{"benchmark":"vcrbench","model":"gemini-2.5-pro","score":53.4,"metric":"percent"},{"benchmark":"vcrbench","model":"gemini-3-pro","score":51.4,"metric":"percent"},{"benchmark":"vcrbench","model":"seed-1.5-vl","score":51.8,"metric":"percent"},{"benchmark":"vcrbench","model":"seed1.8","score":59.8,"metric":"percent"},{"benchmark":"videoreasonbench","model":"gemini-2.5-pro","score":59.7,"metric":"percent"},{"benchmark":"videoreasonbench","model":"gemini-3-pro","score":59.5,"metric":"percent"},{"benchmark":"videoreasonbench","model":"seed-1.5-vl","score":18.7,"metric":"percent"},{"benchmark":"videoreasonbench","model":"seed1.8","score":52.8,"metric":"percent"},{"benchmark":"videoholmes","model":"gemini-2.5-pro","score":62.4,"metric":"percent"},{"benchmark":"videoholmes","model":"gemini-3-pro","score":64.2,"metric":"percent"},{"benchmark":"videoholmes","model":"seed-1.5-vl","score":59.1,"metric":"percent"},{"benchmark":"videoholmes","model":"seed1.8","score":65.5,"metric":"percent"},{"benchmark":"minerva-math","model":"gemini-2.5-pro","score":67.6,"metric":"percent"},{"benchmark":"minerva-math","model":"gemini-3-pro","score":65,"metric":"percent"},{"benchmark":"minerva-math","model":"seed-1.5-vl","score":49.9,"metric":"percent"},{"benchmark":"minerva-math","model":"seed1.8","score":62.4,"metric":"percent"},{"benchmark":"videosimpleqa","model":"gemini-2.5-pro","score":69.6,"metric":"percent"},{"benchmark":"videosimpleqa","model":"gemini-3-pro","score":71.9,"metric":"percent"},{"benchmark":"videosimpleqa","model":"seed-1.5-vl","score":59.2,"metric":"percent"},{"benchmark":"videosimpleqa","model":"seed1.8","score":67.8,"metric":"percent"},{"benchmark":"tvbench","model":"gemini-2.5-pro","score":67.4,"metric":"percent"},{"benchmark":"tvbench","model":"gemini-3-pro","score":71.1,"metric":"percent"},{"benchmark":"tvbench","model":"seed-1.5-vl","score":66.6,"metric":"percent"},{"benchmark":"tvbench","model":"seed1.8","score":71.5,"metric":"percent"},{"benchmark":"tempcompass","model":"gemini-2.5-pro","score":83.9,"metric":"percent"},{"benchmark":"tempcompass","model":"gemini-3-pro","score":88,"metric":"percent"},{"benchmark":"tempcompass","model":"seed-1.5-vl","score":83.7,"metric":"percent"},{"benchmark":"tempcompass","model":"seed1.8","score":86.9,"metric":"percent"},{"benchmark":"tomato","model":"gemini-2.5-pro","score":50.3,"metric":"percent"},{"benchmark":"tomato","model":"gemini-3-pro","score":55.8,"metric":"percent"},{"benchmark":"tomato","model":"seed-1.5-vl","score":44.9,"metric":"percent"},{"benchmark":"tomato","model":"seed1.8","score":60.8,"metric":"percent"},{"benchmark":"egotempo","model":"gemini-2.5-pro","score":58.1,"metric":"percent"},{"benchmark":"egotempo","model":"gemini-3-pro","score":65.4,"metric":"percent"},{"benchmark":"egotempo","model":"seed-1.5-vl","score":51.7,"metric":"percent"},{"benchmark":"egotempo","model":"seed1.8","score":67,"metric":"percent"},{"benchmark":"motionbench","model":"gemini-2.5-pro","score":66.3,"metric":"percent"},{"benchmark":"motionbench","model":"gemini-3-pro","score":70.3,"metric":"percent"},{"benchmark":"motionbench","model":"seed-1.5-vl","score":68.8,"metric":"percent"},{"benchmark":"motionbench","model":"seed1.8","score":70.6,"metric":"percent"},{"benchmark":"countix","model":"gemini-2.5-pro","score":18.6,"metric":"percent"},{"benchmark":"countix","model":"gemini-3-pro","score":18.7,"metric":"percent"},{"benchmark":"countix","model":"seed-1.5-vl","score":26,"metric":"percent"},{"benchmark":"countix","model":"seed1.8","score":31,"metric":"percent"},{"benchmark":"videomme","model":"gemini-2.5-pro","score":86.9,"metric":"percent"},{"benchmark":"videomme","model":"gemini-3-pro","score":88.4,"metric":"percent"},{"benchmark":"videomme","model":"seed-1.5-vl","score":83,"metric":"percent"},{"benchmark":"videomme","model":"seed1.8","score":87.8,"metric":"percent"},{"benchmark":"cgbench","model":"gemini-2.5-pro","score":64.6,"metric":"percent"},{"benchmark":"cgbench","model":"gemini-3-pro","score":64.5,"metric":"percent"},{"benchmark":"cgbench","model":"seed-1.5-vl","score":57.4,"metric":"percent"},{"benchmark":"cgbench","model":"seed1.8","score":62.4,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-2.5-pro","score":77.6,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-3-pro","score":76.7,"metric":"percent"},{"benchmark":"longvideobench","model":"seed-1.5-vl","score":74,"metric":"percent"},{"benchmark":"longvideobench","model":"seed1.8","score":77.4,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-2.5-pro","score":73.5,"metric":"percent"},{"benchmark":"lvbench","model":"seed-1.5-vl","score":64.6,"metric":"percent"},{"benchmark":"lvbench","model":"seed1.8","score":73,"metric":"percent"},{"benchmark":"ovbench","model":"gemini-2.5-pro","score":61.2,"metric":"percent"},{"benchmark":"ovbench","model":"gemini-3-pro","score":62.7,"metric":"percent"},{"benchmark":"ovbench","model":"seed-1.5-vl","score":60,"metric":"percent"},{"benchmark":"ovbench","model":"seed1.8","score":65.1,"metric":"percent"},{"benchmark":"livesports-3k","model":"gemini-2.5-pro","score":75.8,"metric":"percent"},{"benchmark":"livesports-3k","model":"gemini-3-pro","score":74.5,"metric":"percent"},{"benchmark":"livesports-3k","model":"seed-1.5-vl","score":74.9,"metric":"percent"},{"benchmark":"livesports-3k","model":"seed1.8","score":77.5,"metric":"percent"},{"benchmark":"ovobench","model":"gemini-2.5-pro","score":70.9,"metric":"percent"},{"benchmark":"ovobench","model":"gemini-3-pro","score":70.1,"metric":"percent"},{"benchmark":"ovobench","model":"seed-1.5-vl","score":72.3,"metric":"percent"},{"benchmark":"ovobench","model":"seed1.8","score":72.6,"metric":"percent"},{"benchmark":"vispeak","model":"gemini-2.5-pro","score":84.5,"metric":"percent"},{"benchmark":"vispeak","model":"gemini-3-pro","score":89,"metric":"percent"},{"benchmark":"vispeak","model":"seed-1.5-vl","score":77,"metric":"percent"},{"benchmark":"vispeak","model":"seed1.8","score":79,"metric":"percent"},{"benchmark":"streamingbench","model":"seed-1.5-vl","score":68,"metric":"percent"},{"benchmark":"streamingbench","model":"seed1.8","score":84.4,"metric":"percent"},{"benchmark":"omnimmi","model":"seed-1.5-vl","score":49.5,"metric":"percent"},{"benchmark":"omnimmi","model":"seed1.8","score":53,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-sonnet-4.5","score":24.1,"metric":"percent"},{"benchmark":"browsecomp","model":"gemini-3-pro","score":37.8,"metric":"percent"},{"benchmark":"browsecomp","model":"seed1.8","score":67.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"claude-sonnet-4.5","score":42.4,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gemini-2.5-pro","score":34.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gemini-3-pro","score":51.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"seed1.8","score":81.3,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5-high","score":76.7,"metric":"percent"},{"benchmark":"gaia","model":"claude-sonnet-4.5","score":66,"metric":"percent"},{"benchmark":"gaia","model":"gemini-2.5-pro","score":57.3,"metric":"percent"},{"benchmark":"gaia","model":"gemini-3-pro","score":74.8,"metric":"percent"},{"benchmark":"gaia","model":"seed1.8","score":87.4,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5-high","score":62.2,"metric":"percent"},{"benchmark":"wide-search","model":"claude-sonnet-4.5","score":65.7,"metric":"percent"},{"benchmark":"wide-search","model":"gemini-2.5-pro","score":52.6,"metric":"percent"},{"benchmark":"wide-search","model":"gemini-3-pro","score":57,"metric":"percent"},{"benchmark":"wide-search","model":"seed1.8","score":63.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5-high","score":41.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-4.5","score":32,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-2.5-pro","score":19.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"seed1.8","score":40.9,"metric":"percent"},{"benchmark":"mm-browsecomp","model":"gemini-2.5-pro","score":7.2,"metric":"percent"},{"benchmark":"mm-browsecomp","model":"gemini-3-pro","score":25,"metric":"percent"},{"benchmark":"mm-browsecomp","model":"seed1.8","score":46.3,"metric":"percent"},{"benchmark":"hle-vl","model":"gemini-2.5-pro","score":19,"metric":"percent"},{"benchmark":"hle-vl","model":"gemini-3-pro","score":36,"metric":"percent"},{"benchmark":"hle-vl","model":"seed1.8","score":31.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4.5","score":77.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"seed1.8","score":72.9,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"gpt-5-high","score":41.7,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"claude-sonnet-4.5","score":44.3,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"gemini-2.5-pro","score":20.7,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"gemini-3-pro","score":42.7,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"seed1.8","score":42,"metric":"percent"},{"benchmark":"ainstein-swe-bench","model":"gpt-5-high","score":35.4,"metric":"percent"},{"benchmark":"ainstein-swe-bench","model":"claude-sonnet-4.5","score":33.7,"metric":"percent"},{"benchmark":"ainstein-swe-bench","model":"gemini-2.5-pro","score":19.3,"metric":"percent"},{"benchmark":"ainstein-swe-bench","model":"gemini-3-pro","score":42.8,"metric":"percent"},{"benchmark":"ainstein-swe-bench","model":"seed1.8","score":36.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-sonnet-4.5","score":42.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"seed1.8","score":45.2,"metric":"percent"},{"benchmark":"u-artifacts","model":"gpt-5-high","score":56.8,"metric":"percent"},{"benchmark":"u-artifacts","model":"claude-sonnet-4.5","score":37.3,"metric":"percent"},{"benchmark":"u-artifacts","model":"gemini-2.5-pro","score":33.4,"metric":"percent"},{"benchmark":"u-artifacts","model":"gemini-3-pro","score":57.8,"metric":"percent"},{"benchmark":"u-artifacts","model":"seed1.8","score":49.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5-high","score":61.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"claude-sonnet-4.5","score":68.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemini-2.5-pro","score":52.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemini-3-pro","score":62.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"seed1.8","score":57.2,"metric":"percent"},{"benchmark":"deepconsult","model":"gpt-5-high","score":57.2,"metric":"percent"},{"benchmark":"deepconsult","model":"claude-sonnet-4.5","score":38.3,"metric":"percent"},{"benchmark":"deepconsult","model":"gemini-2.5-pro","score":21.8,"metric":"percent"},{"benchmark":"deepconsult","model":"gemini-3-pro","score":48,"metric":"percent"},{"benchmark":"deepconsult","model":"seed1.8","score":41,"metric":"percent"},{"benchmark":"deepresearchbench","model":"gpt-5-high","score":48.7,"metric":"percent"},{"benchmark":"deepresearchbench","model":"claude-sonnet-4.5","score":39.9,"metric":"percent"},{"benchmark":"deepresearchbench","model":"gemini-2.5-pro","score":40,"metric":"percent"},{"benchmark":"deepresearchbench","model":"gemini-3-pro","score":49.6,"metric":"percent"},{"benchmark":"deepresearchbench","model":"seed1.8","score":43.5,"metric":"percent"},{"benchmark":"discox","model":"gpt-5-high","score":75.1,"metric":"percent"},{"benchmark":"discox","model":"claude-sonnet-4.5","score":71.6,"metric":"percent"},{"benchmark":"discox","model":"gemini-2.5-pro","score":73.5,"metric":"percent"},{"benchmark":"discox","model":"gemini-3-pro","score":75.8,"metric":"percent"},{"benchmark":"discox","model":"seed1.8","score":74.6,"metric":"percent"},{"benchmark":"finsearchcomp-t2t3","model":"gpt-5-high","score":64.5,"metric":"percent"},{"benchmark":"finsearchcomp-t2t3","model":"claude-sonnet-4.5","score":58.6,"metric":"percent"},{"benchmark":"finsearchcomp-t2t3","model":"gemini-2.5-pro","score":34,"metric":"percent"},{"benchmark":"finsearchcomp-t2t3","model":"gemini-3-pro","score":49.9,"metric":"percent"},{"benchmark":"finsearchcomp-t2t3","model":"seed1.8","score":62.8,"metric":"percent"},{"benchmark":"xpertbench-law","model":"gpt-5-high","score":54.7,"metric":"percent"},{"benchmark":"xpertbench-law","model":"claude-sonnet-4.5","score":58.7,"metric":"percent"},{"benchmark":"xpertbench-law","model":"gemini-2.5-pro","score":47.3,"metric":"percent"},{"benchmark":"xpertbench-law","model":"gemini-3-pro","score":52.3,"metric":"percent"},{"benchmark":"xpertbench-law","model":"seed1.8","score":55.2,"metric":"percent"},{"benchmark":"xpertbench-fin","model":"gpt-5-high","score":64.5,"metric":"percent"},{"benchmark":"xpertbench-fin","model":"claude-sonnet-4.5","score":44.5,"metric":"percent"},{"benchmark":"xpertbench-fin","model":"gemini-2.5-pro","score":30.3,"metric":"percent"},{"benchmark":"xpertbench-fin","model":"gemini-3-pro","score":56.1,"metric":"percent"},{"benchmark":"xpertbench-fin","model":"seed1.8","score":62,"metric":"percent"},{"benchmark":"xpertbench-edu","model":"gpt-5-high","score":56.9,"metric":"percent"},{"benchmark":"xpertbench-edu","model":"claude-sonnet-4.5","score":44.5,"metric":"percent"},{"benchmark":"xpertbench-edu","model":"gemini-2.5-pro","score":47.9,"metric":"percent"},{"benchmark":"xpertbench-edu","model":"gemini-3-pro","score":49.2,"metric":"percent"},{"benchmark":"xpertbench-edu","model":"seed1.8","score":47.9,"metric":"percent"},{"benchmark":"xpertbench-research","model":"gpt-5-high","score":48.2,"metric":"percent"},{"benchmark":"xpertbench-research","model":"claude-sonnet-4.5","score":27.5,"metric":"percent"},{"benchmark":"xpertbench-research","model":"gemini-2.5-pro","score":25.5,"metric":"percent"},{"benchmark":"xpertbench-research","model":"gemini-3-pro","score":34.9,"metric":"percent"},{"benchmark":"xpertbench-research","model":"seed1.8","score":31.4,"metric":"percent"},{"benchmark":"xpertbench-humanities","model":"gpt-5-high","score":68.5,"metric":"percent"},{"benchmark":"xpertbench-humanities","model":"claude-sonnet-4.5","score":54.9,"metric":"percent"},{"benchmark":"xpertbench-humanities","model":"gemini-2.5-pro","score":52.3,"metric":"percent"},{"benchmark":"xpertbench-humanities","model":"gemini-3-pro","score":68.2,"metric":"percent"},{"benchmark":"xpertbench-humanities","model":"seed1.8","score":60.2,"metric":"percent"},{"benchmark":"worldtravel2-multimodal","model":"gpt-5-high","score":45.9,"metric":"percent"},{"benchmark":"worldtravel2-multimodal","model":"claude-sonnet-4.5","score":41.3,"metric":"percent"},{"benchmark":"worldtravel2-multimodal","model":"gemini-2.5-pro","score":36,"metric":"percent"},{"benchmark":"worldtravel2-multimodal","model":"gemini-3-pro","score":47.2,"metric":"percent"},{"benchmark":"worldtravel2-multimodal","model":"seed1.8","score":47.2,"metric":"percent"},{"benchmark":"worldtravel2-text","model":"gpt-5-high","score":56.4,"metric":"percent"},{"benchmark":"worldtravel2-text","model":"claude-sonnet-4.5","score":53.3,"metric":"percent"},{"benchmark":"worldtravel2-text","model":"gemini-2.5-pro","score":44.5,"metric":"percent"},{"benchmark":"worldtravel2-text","model":"gemini-3-pro","score":53.3,"metric":"percent"},{"benchmark":"worldtravel2-text","model":"seed1.8","score":52.1,"metric":"percent"},{"benchmark":"osworld","model":"seed-1.5-vl","score":36.7,"metric":"percent"},{"benchmark":"osworld","model":"claude-sonnet-4.5","score":62.9,"metric":"percent"},{"benchmark":"osworld","model":"gemini-2.5-pro","score":13.3,"metric":"percent"},{"benchmark":"osworld","model":"gpt-03-cua","score":38.1,"metric":"percent"},{"benchmark":"osworld","model":"seed1.8","score":61.9,"metric":"percent"},{"benchmark":"realbench","model":"seed-1.5-vl","score":46,"metric":"percent"},{"benchmark":"realbench","model":"claude-sonnet-4.5","score":39.3,"metric":"percent"},{"benchmark":"realbench","model":"gemini-2.5-pro","score":38.4,"metric":"percent"},{"benchmark":"realbench","model":"gpt-03-cua","score":34.8,"metric":"percent"},{"benchmark":"realbench","model":"seed1.8","score":49.1,"metric":"percent"},{"benchmark":"online-mind2web","model":"seed-1.5-vl","score":76.4,"metric":"percent"},{"benchmark":"online-mind2web","model":"gemini-2.5-pro","score":69,"metric":"percent"},{"benchmark":"online-mind2web","model":"gpt-03-cua","score":61.3,"metric":"percent"},{"benchmark":"online-mind2web","model":"seed1.8","score":85.9,"metric":"percent"},{"benchmark":"androidworld","model":"seed-1.5-vl","score":62.1,"metric":"percent"},{"benchmark":"androidworld","model":"claude-sonnet-4.5","score":56,"metric":"percent"},{"benchmark":"androidworld","model":"gemini-2.5-pro","score":69.7,"metric":"percent"},{"benchmark":"androidworld","model":"seed1.8","score":70.7,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3-nano-30b-a3b-base","score":92.34,"metric":"percent"},{"benchmark":"math","model":"nemotron-3-nano-30b-a3b-base","score":82.88,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3-nano-30b-a3b-base","score":78.63,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3-nano-30b-a3b-base","score":91.89,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3-nano-30b-a3b-base","score":85.56,"metric":"percent"},{"benchmark":"openbookqa","model":"nemotron-3-nano-30b-a3b-base","score":46.2,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-3-nano-30b-a3b-base","score":84.33,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-3-nano-30b-a3b-base","score":79.64,"metric":"percent"},{"benchmark":"race","model":"nemotron-3-nano-30b-a3b-base","score":88.04,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"nemotron-3-nano-30b-a3b-base","score":74.47,"metric":"percent"},{"benchmark":"mgsm","model":"nemotron-3-nano-30b-a3b-base","score":83,"metric":"percent"},{"benchmark":"ruler-64k","model":"nemotron-3-nano-30b-a3b-base","score":87.5,"metric":"percent"},{"benchmark":"ruler-128k","model":"nemotron-3-nano-30b-a3b-base","score":82.92,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-3-nano-30b-a3b-base","score":75.44,"metric":"percent"},{"benchmark":"cute","model":"bolmo-7b","score":78.6,"metric":"percent"},{"benchmark":"cute","model":"evabyte-6.5b","score":50.8,"metric":"percent"},{"benchmark":"cute","model":"blt-7b","score":52.3,"metric":"percent"},{"benchmark":"cute","model":"tfree-hat-pretrained-7b-base","score":54.2,"metric":"percent"},{"benchmark":"cute","model":"olmo-3-7b","score":56.9,"metric":"percent"},{"benchmark":"execute","model":"bolmo-7b","score":71.6,"metric":"percent"},{"benchmark":"execute","model":"evabyte-6.5b","score":43.8,"metric":"percent"},{"benchmark":"execute","model":"blt-7b","score":46.3,"metric":"percent"},{"benchmark":"execute","model":"tfree-hat-pretrained-7b-base","score":41.6,"metric":"percent"},{"benchmark":"execute","model":"olmo-3-7b","score":55.1,"metric":"percent"},{"benchmark":"gsm8k","model":"bolmo-7b","score":68,"metric":"percent"},{"benchmark":"gsm8k","model":"evabyte-6.5b","score":36.7,"metric":"percent"},{"benchmark":"gsm8k","model":"blt-7b","score":24.2,"metric":"percent"},{"benchmark":"gsm8k","model":"tfree-hat-pretrained-7b-base","score":60.7,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-7b","score":73.1,"metric":"percent"},{"benchmark":"math","model":"bolmo-7b","score":29.8,"metric":"percent"},{"benchmark":"math","model":"evabyte-6.5b","score":17.3,"metric":"percent"},{"benchmark":"math","model":"blt-7b","score":7.3,"metric":"percent"},{"benchmark":"math","model":"tfree-hat-pretrained-7b-base","score":10.9,"metric":"percent"},{"benchmark":"math","model":"olmo-3-7b","score":37.5,"metric":"percent"},{"benchmark":"humaneval","model":"bolmo-7b","score":40.6,"metric":"percent"},{"benchmark":"humaneval","model":"evabyte-6.5b","score":34.7,"metric":"percent"},{"benchmark":"humaneval","model":"blt-7b","score":31.5,"metric":"percent"},{"benchmark":"humaneval","model":"tfree-hat-pretrained-7b-base","score":41.1,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3-7b","score":49,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.2-speciale","score":96,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.2-speciale","score":99.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.2-speciale","score":94.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v3.2-speciale","score":84.5,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-speciale","score":88.7,"metric":"percent"},{"benchmark":"codeforces","model":"deepseek-v3.2-speciale","score":2701,"metric":"ELO"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.2-speciale","score":85.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"trinity-mini","score":58.55,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b","score":70.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b-high","score":65.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"magistral-small-2509","score":56.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-think-32b","score":60.91,"metric":"percent"},{"benchmark":"bfcl-v3","model":"trinity-mini","score":59.67,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gpt-oss-20b-high","score":53.61,"metric":"percent"},{"benchmark":"bfcl-v3","model":"magistral-small-2509","score":44.25,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.2-speciale","score":30.6,"metric":"percent"},{"benchmark":"simpleqa","model":"trinity-mini","score":8.9,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-30b-a3b","score":9.1,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-oss-20b-high","score":5.5,"metric":"percent"},{"benchmark":"simpleqa","model":"magistral-small-2509","score":10.7,"metric":"percent"},{"benchmark":"musr","model":"trinity-mini","score":63.49,"metric":"percent"},{"benchmark":"musr","model":"qwen3-30b-a3b","score":64.4,"metric":"percent"},{"benchmark":"musr","model":"gpt-oss-20b-high","score":64.47,"metric":"percent"},{"benchmark":"musr","model":"magistral-small-2509","score":56.3,"metric":"percent"},{"benchmark":"mmlu","model":"trinity-mini","score":84.95,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b","score":87.26,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-20b-high","score":83.55,"metric":"percent"},{"benchmark":"mmlu","model":"magistral-small-2509","score":82.3,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-32b","score":85.6,"metric":"percent"},{"benchmark":"math500","model":"trinity-mini","score":92.1,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b","score":95.6,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-20b-high","score":92.8,"metric":"percent"},{"benchmark":"math500","model":"magistral-small-2509","score":87.4,"metric":"percent"},{"benchmark":"math500","model":"olmo-3-think-32b","score":95.8,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-flash-3b","score":60.34,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-flash-3b","score":29.54,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-flash-3b","score":52.03,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-flash-1b","score":44.63,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-flash-3b","score":61.19,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-flash-3b-tp","score":61.19,"metric":"percent"},{"benchmark":"mmmlu","model":"mistral-large-3-base","score":85.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-large-3-base","score":43.9,"metric":"percent"},{"benchmark":"simpleqa","model":"mistral-large-3-base","score":23.8,"metric":"percent"},{"benchmark":"amc-23","model":"mistral-large-3-base","score":52,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-large-3-base","score":34.4,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"ministral-3-14b-base","score":74.2,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gemma-3-12b-base","score":69,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen3-14b-base","score":75.4,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"ministral-3-8b-base","score":70.6,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen3-8b-base","score":70,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"ministral-3-3b-base","score":65.2,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen3-4b-base","score":67.7,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gemma-3-4b-base","score":51.6,"metric":"percent"},{"benchmark":"math","model":"ministral-3-14b-base","score":67.6,"metric":"percent"},{"benchmark":"math","model":"gemma-3-12b-base","score":48.7,"metric":"percent"},{"benchmark":"math","model":"qwen3-14b-base","score":62,"metric":"percent"},{"benchmark":"math","model":"ministral-3-8b-base","score":62.6,"metric":"percent"},{"benchmark":"math","model":"qwen3-8b-base","score":57.6,"metric":"percent"},{"benchmark":"math","model":"ministral-3-3b-base","score":60.1,"metric":"percent"},{"benchmark":"math","model":"qwen3-4b-base","score":40.5,"metric":"percent"},{"benchmark":"math","model":"gemma-3-4b-base","score":29.4,"metric":"percent"},{"benchmark":"refusalbench","model":"hermes-4.3-36b-pyche","score":72.29,"metric":"percent"},{"benchmark":"refusalbench","model":"hermes-4.3-36b","score":66.67,"metric":"percent"},{"benchmark":"refusalbench","model":"hermes-4.3-70b","score":59.2,"metric":"percent"},{"benchmark":"simpleqa","model":"hermes-4.3-36b-pyche","score":6,"metric":"percent"},{"benchmark":"simpleqa","model":"hermes-4.3-36b","score":5.6,"metric":"percent"},{"benchmark":"simpleqa","model":"hermes-4.3-70b","score":17.9,"metric":"percent"},{"benchmark":"openbookqa","model":"hermes-4.3-36b-pyche","score":96.6,"metric":"percent"},{"benchmark":"openbookqa","model":"hermes-4.3-36b","score":91.8,"metric":"percent"},{"benchmark":"openbookqa","model":"hermes-4.3-70b","score":94.8,"metric":"percent"},{"benchmark":"musr","model":"hermes-4.3-36b-pyche","score":69.7,"metric":"percent"},{"benchmark":"musr","model":"hermes-4.3-36b","score":64.7,"metric":"percent"},{"benchmark":"musr","model":"hermes-4.3-70b","score":70.4,"metric":"percent"},{"benchmark":"hle","model":"mirothinker-v0.2-32b","score":17.8,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"mirothinker-v0.2-32b","score":29.4,"metric":"percent"},{"benchmark":"browsecomp","model":"mirothinker-v0.2-32b","score":17.2,"metric":"percent"},{"benchmark":"gaia","model":"mirothinker-v0.2-32b","score":64.1,"metric":"percent"},{"benchmark":"aime-2025","model":"aquif-3.6-1b","score":75,"metric":"percent"},{"benchmark":"livecodebench","model":"aquif-3.6-1b","score":57.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"aquif-3.6-1b","score":52.8,"metric":"percent"},{"benchmark":"mmlu","model":"aquif-3.5-nano-1b","score":72.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"aquif-3.5-nano-1b","score":42,"metric":"percent"},{"benchmark":"aime-2025","model":"aquif-3.5-nano-1b","score":28.7,"metric":"percent"},{"benchmark":"livecodebench","model":"aquif-3.5-nano-1b","score":24.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"rnj-1","score":75.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"rnj-1","score":83.5,"metric":"percent"},{"benchmark":"bigcodebench","model":"rnj-1","score":57.1,"metric":"pass@1"},{"benchmark":"aime-2025","model":"rnj-1","score":43.3,"metric":"percent"},{"benchmark":"supergpqa","model":"rnj-1","score":30.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"rnj-1","score":20.8,"metric":"percent"},{"benchmark":"enamel","model":"rnj-1","score":49,"metric":"percent"},{"benchmark":"bfcl-v3","model":"rnj-1","score":62.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-8b","score":71.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-8b","score":81.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-8b","score":50.2,"metric":"pass@1"},{"benchmark":"aime-2025","model":"qwen3-8b","score":20.9,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-8b","score":36.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-8b","score":4.5,"metric":"percent"},{"benchmark":"enamel","model":"qwen3-8b","score":36.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-8b","score":60.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-7b-instruct","score":71.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-7b-instruct","score":84.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-7b-instruct","score":41,"metric":"pass@1"},{"benchmark":"aime-2025","model":"qwen2.5-coder-7b-instruct","score":0,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen2.5-coder-7b-instruct","score":21.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen2.5-coder-7b-instruct","score":0.5,"metric":"percent"},{"benchmark":"enamel","model":"qwen2.5-coder-7b-instruct","score":28.4,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen2.5-coder-7b-instruct","score":52.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codestral-12b-instruct","score":67.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codestral-12b-instruct","score":68.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"codestral-12b-instruct","score":50.5,"metric":"pass@1"},{"benchmark":"aime-2025","model":"codestral-12b-instruct","score":0,"metric":"percent"},{"benchmark":"supergpqa","model":"codestral-12b-instruct","score":19.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"codestral-12b-instruct","score":3.7,"metric":"percent"},{"benchmark":"enamel","model":"codestral-12b-instruct","score":29.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"codestral-12b-instruct","score":50.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-7b-sft","score":56.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-7b-sft","score":69.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"olmo-3-7b-sft","score":33.4,"metric":"pass@1"},{"benchmark":"aime-2025","model":"olmo-3-7b-sft","score":7.2,"metric":"percent"},{"benchmark":"supergpqa","model":"olmo-3-7b-sft","score":21,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"olmo-3-7b-sft","score":0,"metric":"percent"},{"benchmark":"enamel","model":"olmo-3-7b-sft","score":17.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"olmo-3-7b-sft","score":48.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.1-8b-instruct","score":72.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"llama-3.1-8b-instruct","score":38.3,"metric":"pass@1"},{"benchmark":"aime-2025","model":"llama-3.1-8b-instruct","score":2.7,"metric":"percent"},{"benchmark":"supergpqa","model":"llama-3.1-8b-instruct","score":20.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"llama-3.1-8b-instruct","score":1.8,"metric":"percent"},{"benchmark":"enamel","model":"llama-3.1-8b-instruct","score":9.2,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llama-3.1-8b-instruct","score":25.9,"metric":"percent"},{"benchmark":"supergpqa","model":"gemma-3-12b-it","score":29.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-oss-20b-moe","score":75.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-oss-20b-moe","score":81.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"gpt-oss-20b-moe","score":55.7,"metric":"pass@1"},{"benchmark":"aime-2025","model":"gpt-oss-20b-moe","score":46.7,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-oss-20b-moe","score":36.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-20b-moe","score":1.1,"metric":"percent"},{"benchmark":"enamel","model":"gpt-oss-20b-moe","score":38.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gpt-oss-20b-moe","score":45.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b","score":69.3,"metric":"percent"},{"benchmark":"aime-2025","model":"nvidia-nemotron-nano-9b-v2","score":72.1,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b","score":96.3,"metric":"percent"},{"benchmark":"math500","model":"nvidia-nemotron-nano-9b-v2","score":97.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-8b","score":59.6,"metric":"percent"},{"benchmark":"gpqa","model":"nvidia-nemotron-nano-9b-v2","score":64,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b","score":59.5,"metric":"percent"},{"benchmark":"livecodebench","model":"nvidia-nemotron-nano-9b-v2","score":71.1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-8b","score":66.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"nvidia-nemotron-nano-9b-v2","score":66.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-8b","score":89.4,"metric":"percent"},{"benchmark":"ifeval","model":"nvidia-nemotron-nano-9b-v2","score":90.3,"metric":"percent"},{"benchmark":"hle","model":"qwen3-8b","score":4.4,"metric":"avg@3"},{"benchmark":"hle","model":"nvidia-nemotron-nano-9b-v2","score":6.5,"metric":"avg@3"},{"benchmark":"ruler-128k","model":"qwen3-8b","score":74.1,"metric":"percent"},{"benchmark":"ruler-128k","model":"nvidia-nemotron-nano-9b-v2","score":78.9,"metric":"percent"},{"benchmark":"ai2d","model":"jina-vlm-2.4b-20251117","score":82,"metric":"percent"},{"benchmark":"chartqa","model":"jina-vlm-2.4b-20251117","score":81.9,"metric":"percent"},{"benchmark":"textvqa","model":"jina-vlm-2.4b-20251117","score":83.2,"metric":"percent"},{"benchmark":"docvqa","model":"jina-vlm-2.4b-20251117","score":90.6,"metric":"percent"},{"benchmark":"infovqa","model":"jina-vlm-2.4b-20251117","score":71.6,"metric":"percent"},{"benchmark":"ocrbench","model":"jina-vlm-2.4b-20251117","score":77.8,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"jina-vlm-2.4b-20251117","score":67.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"jina-vlm-2.4b-20251117","score":32.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"jina-vlm-2.4b-20251117","score":63.5,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2-vl-2b","score":74.7,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2-vl-2b","score":73.5,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2-vl-2b","score":79.7,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2-vl-2b","score":89.2,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2-vl-2b","score":64,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2-vl-2b","score":80.9,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"qwen2-vl-2b","score":62.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2-vl-2b","score":23.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2-vl-2b","score":55,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-2b-instruct","score":77.2,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-2b-instruct","score":79.5,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-2b-instruct","score":92.3,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-2b-instruct","score":71.9,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"qwen3-vl-2b-instruct","score":67.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-2b-instruct","score":28.8,"metric":"percent"},{"benchmark":"ai2d","model":"internvl3-2b","score":78.6,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3-2b","score":80.2,"metric":"percent"},{"benchmark":"textvqa","model":"internvl3-2b","score":77,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3-2b","score":87.4,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3-2b","score":67.1,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3-2b","score":83.5,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl3-2b","score":64.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3-2b","score":28.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3-2b","score":54.7,"metric":"percent"},{"benchmark":"ai2d","model":"internvl3.5-2b","score":78.8,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-2b","score":88.5,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-2b","score":69.3,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl3.5-2b","score":68,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3.5-2b","score":31.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3.5-2b","score":65,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4.6v","score":88.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4.6v-flash","score":86.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"glm-4.6v","score":88.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"glm-4.6v-flash","score":84.5,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4.6v","score":75.9,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4.6v-flash","score":74.7,"metric":"percent"},{"benchmark":"blink","model":"glm-4.6v","score":65.5,"metric":"percent"},{"benchmark":"blink","model":"glm-4.6v-flash","score":65.5,"metric":"percent"},{"benchmark":"muirbench","model":"glm-4.6v","score":77.1,"metric":"percent"},{"benchmark":"muirbench","model":"glm-4.6v-flash","score":75.7,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.6v","score":76,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.6v-flash","score":71.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"glm-4.6v","score":66,"metric":"percent"},{"benchmark":"mmmu-pro","model":"glm-4.6v-flash","score":60.6,"metric":"percent"},{"benchmark":"videommmu","model":"glm-4.6v","score":74.7,"metric":"percent"},{"benchmark":"videommmu","model":"glm-4.6v-flash","score":70.1,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.6v","score":85.2,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.6v-flash","score":82.7,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4.6v","score":88.8,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4.6v-flash","score":89.2,"metric":"percent"},{"benchmark":"dynamath","model":"glm-4.6v","score":54.5,"metric":"percent"},{"benchmark":"dynamath","model":"glm-4.6v-flash","score":43.7,"metric":"percent"},{"benchmark":"wemath","model":"glm-4.6v","score":69.8,"metric":"percent"},{"benchmark":"wemath","model":"glm-4.6v-flash","score":60,"metric":"percent"},{"benchmark":"zerobench-sub","model":"glm-4.6v","score":25.8,"metric":"percent"},{"benchmark":"zerobench-sub","model":"glm-4.6v-flash","score":22.5,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-4.6v","score":7.6,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-4.6v-flash","score":7.1,"metric":"percent"},{"benchmark":"design2code","model":"glm-4.6v","score":88.6,"metric":"percent"},{"benchmark":"design2code","model":"glm-4.6v-flash","score":69.8,"metric":"percent"},{"benchmark":"flame-react-eval","model":"glm-4.6v","score":86.3,"metric":"percent"},{"benchmark":"flame-react-eval","model":"glm-4.6v-flash","score":78.8,"metric":"percent"},{"benchmark":"osworld","model":"glm-4.6v","score":37.2,"metric":"percent"},{"benchmark":"osworld","model":"glm-4.6v-flash","score":21.1,"metric":"percent"},{"benchmark":"androidworld","model":"glm-4.6v","score":57,"metric":"percent"},{"benchmark":"androidworld","model":"glm-4.6v-flash","score":42.7,"metric":"percent"},{"benchmark":"webvoyager","model":"glm-4.6v","score":81,"metric":"percent"},{"benchmark":"webvoyager","model":"glm-4.6v-flash","score":71.8,"metric":"percent"},{"benchmark":"webquest-singleqa","model":"glm-4.6v","score":79.5,"metric":"percent"},{"benchmark":"webquest-singleqa","model":"glm-4.6v-flash","score":75.1,"metric":"percent"},{"benchmark":"webquest-multiqa","model":"glm-4.6v","score":59,"metric":"percent"},{"benchmark":"webquest-multiqa","model":"glm-4.6v-flash","score":53.4,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"glm-4.6v","score":54.9,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"glm-4.6v-flash","score":53,"metric":"percent"},{"benchmark":"mmlongbench-128k","model":"glm-4.6v","score":64.1,"metric":"percent"},{"benchmark":"mmlongbench-128k","model":"glm-4.6v-flash","score":63.4,"metric":"percent"},{"benchmark":"lvbench","model":"glm-4.6v","score":59.5,"metric":"percent"},{"benchmark":"lvbench","model":"glm-4.6v-flash","score":49.5,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4.6v","score":86.5,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4.6v-flash","score":84.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"glm-4.6v","score":65.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"glm-4.6v-flash","score":63.5,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"glm-4.6v","score":59.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"glm-4.6v-flash","score":59.5,"metric":"percent"},{"benchmark":"chartqa-pro","model":"glm-4.6v","score":65.5,"metric":"percent"},{"benchmark":"chartqa-pro","model":"glm-4.6v-flash","score":62.6,"metric":"percent"},{"benchmark":"chartmuseum","model":"glm-4.6v","score":58.4,"metric":"percent"},{"benchmark":"chartmuseum","model":"glm-4.6v-flash","score":49.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"glm-4.6v","score":63.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"glm-4.6v-flash","score":59.6,"metric":"percent"},{"benchmark":"omnispatial","model":"glm-4.6v","score":52,"metric":"percent"},{"benchmark":"omnispatial","model":"glm-4.6v-flash","score":50.6,"metric":"percent"},{"benchmark":"refcoco","model":"glm-4.6v","score":88.6,"metric":"percent"},{"benchmark":"refcoco","model":"glm-4.6v-flash","score":85.6,"metric":"percent"},{"benchmark":"treebench","model":"glm-4.6v","score":51.4,"metric":"percent"},{"benchmark":"treebench","model":"glm-4.6v-flash","score":45.7,"metric":"percent"},{"benchmark":"ref-l4-test","model":"glm-4.6v","score":88.9,"metric":"percent"},{"benchmark":"ref-l4-test","model":"glm-4.6v-flash","score":87.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2-thinking","score":92.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.2-thinking","score":55.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.1-thinking","score":50.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.5","score":52,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemini-3-pro","score":43.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.1-thinking","score":67,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.2-thinking","score":82.1,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.2-thinking","score":40.3,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.1-thinking","score":31,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gemini-3-pro","score":37.6,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.2-thinking","score":14.6,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.1-thinking","score":12.5,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gemini-3-pro","score":18.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.2-thinking","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.1-thinking","score":94,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.5","score":92.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-thinking","score":86.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.1-thinking","score":72.8,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.5","score":80,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-pro","score":75,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-thinking","score":52.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.1-thinking","score":17.6,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.2-thinking","score":70.9,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5","score":38.8,"metric":"percent"},{"benchmark":"gdpval","model":"claude-opus-4.5","score":59.6,"metric":"percent"},{"benchmark":"gdpval","model":"gemini-3-pro","score":53.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.5-medium","score":74.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.2-high","score":71.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.2-medium","score":69,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.1-medium","score":66,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-mini","score":59.8,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3.1-think-32b","score":78.1,"metric":"percent"},{"benchmark":"aime-2025","model":"apertus-70b-instruct","score":0.1,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3.1-think-32b","score":80.1,"metric":"percent"},{"benchmark":"zebralogic","model":"apertus-70b-instruct","score":9,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3.1-think-32b","score":93.8,"metric":"percent"},{"benchmark":"ifeval","model":"apertus-70b-instruct","score":70.4,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3.1-think-32b","score":68.1,"metric":"percent"},{"benchmark":"ifbench","model":"apertus-70b-instruct","score":26,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3.1-think-32b","score":86.4,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-70b-instruct","score":70.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3.1-think-32b","score":91.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"apertus-70b-instruct","score":42.9,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"dolphin-v2","score":0.054,"metric":"edit_distance"},{"benchmark":"aime-2024","model":"nanbeige4-3b-thinking-2511","score":90.4,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-4b-2507","score":83.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-8b","score":76,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-14b","score":79.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b-thinking-2507","score":89.2,"metric":"percent"},{"benchmark":"aime-2025","model":"nanbeige4-3b-thinking-2511","score":85.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-2507","score":81.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b","score":67.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-14b","score":70.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nanbeige4-3b-thinking-2511","score":82.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b-2507","score":67.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-8b","score":62,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-14b","score":64,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-32b","score":68.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-thinking-2507","score":73.4,"metric":"percent"},{"benchmark":"supergpqa","model":"nanbeige4-3b-thinking-2511","score":53.2,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-4b-2507","score":46.7,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-8b","score":39.1,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-14b","score":46.8,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-32b","score":54.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nanbeige4-3b-thinking-2511","score":53.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-4b-2507","score":44.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-8b","score":42.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-14b","score":45.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-32b","score":47.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-30b-a3b-thinking-2507","score":48.6,"metric":"percent"},{"benchmark":"fullstackbench","model":"nanbeige4-3b-thinking-2511","score":48,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3-4b-2507","score":47.1,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3-8b","score":51.5,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3-14b","score":55.7,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3-32b","score":58.2,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3-30b-a3b-thinking-2507","score":54.4,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"nanbeige4-3b-thinking-2511","score":60,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-4b-2507","score":40.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-8b","score":26.4,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-14b","score":39.9,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-32b","score":48.4,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-30b-a3b-thinking-2507","score":60,"metric":"percent"},{"benchmark":"multichallenge","model":"nanbeige4-3b-thinking-2511","score":41.2,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-4b-2507","score":41.8,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-8b","score":35.8,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-14b","score":36.4,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-32b","score":39.2,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-30b-a3b-thinking-2507","score":49.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.0-flash","score":73.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.0-flash-preview","score":49.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-flash-2.0","score":76.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-instruct-2507","score":74.2,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.0-flash","score":85,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.0-flash-preview","score":86,"metric":"percent"},{"benchmark":"hellaswag","model":"ling-flash-2.0","score":81.6,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-30b-a3b-instruct-2507","score":86.3,"metric":"percent"},{"benchmark":"humaneval","model":"llada2.0-flash","score":94.5,"metric":"percent"},{"benchmark":"humaneval","model":"llada2.0-flash-preview","score":80.5,"metric":"percent"},{"benchmark":"humaneval","model":"ling-flash-2.0","score":86,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-30b-a3b-instruct-2507","score":93.3,"metric":"percent"},{"benchmark":"aime-2025","model":"llada2.0-flash","score":60,"metric":"percent"},{"benchmark":"aime-2025","model":"llada2.0-flash-preview","score":23.3,"metric":"percent"},{"benchmark":"aime-2025","model":"ling-flash-2.0","score":55.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-instruct-2507","score":61.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b-instruct-2507","score":87.13,"metric":"percent"},{"benchmark":"mmlu","model":"ling-flash-2.0","score":87.98,"metric":"percent"},{"benchmark":"mmlu","model":"llada2.0-flash-preview","score":83.15,"metric":"percent"},{"benchmark":"mmlu","model":"llada2.0-flash","score":87.69,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-instruct-2507","score":74.23,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-flash-2.0","score":76.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.0-flash-preview","score":49.22,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.0-flash","score":73.36,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-30b-a3b-instruct-2507","score":57.34,"metric":"percent"},{"benchmark":"gpqa","model":"ling-flash-2.0","score":67.12,"metric":"percent"},{"benchmark":"gpqa","model":"llada2.0-flash-preview","score":46.59,"metric":"percent"},{"benchmark":"gpqa","model":"llada2.0-flash","score":61.98,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-30b-a3b-instruct-2507","score":95.81,"metric":"percent"},{"benchmark":"arc-challenge","model":"ling-flash-2.0","score":95.08,"metric":"percent"},{"benchmark":"arc-challenge","model":"llada2.0-flash-preview","score":93.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llada2.0-flash","score":95.93,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-30b-a3b-instruct-2507","score":86.36,"metric":"percent"},{"benchmark":"cmmlu","model":"ling-flash-2.0","score":86.59,"metric":"percent"},{"benchmark":"cmmlu","model":"llada2.0-flash-preview","score":67.53,"metric":"percent"},{"benchmark":"cmmlu","model":"llada2.0-flash","score":85.13,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-30b-a3b-instruct-2507","score":88.17,"metric":"percent"},{"benchmark":"c-eval","model":"ling-flash-2.0","score":88.03,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.0-flash-preview","score":66.54,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.0-flash","score":86.75,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen3-30b-a3b-instruct-2507","score":94.53,"metric":"percent"},{"benchmark":"gaokao-bench","model":"ling-flash-2.0","score":93.24,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llada2.0-flash-preview","score":86.12,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llada2.0-flash","score":93.9,"metric":"percent"},{"benchmark":"squad-v2.0","model":"qwen3-30b-a3b-instruct-2507","score":89.51,"metric":"percent"},{"benchmark":"squad-v2.0","model":"ling-flash-2.0","score":81.32,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llada2.0-flash-preview","score":85.61,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llada2.0-flash","score":90,"metric":"percent"},{"benchmark":"drop","model":"qwen3-30b-a3b-instruct-2507","score":87.57,"metric":"percent"},{"benchmark":"drop","model":"ling-flash-2.0","score":88.32,"metric":"percent"},{"benchmark":"drop","model":"llada2.0-flash-preview","score":79.49,"metric":"percent"},{"benchmark":"drop","model":"llada2.0-flash","score":87.9,"metric":"percent"},{"benchmark":"kor-bench","model":"qwen3-30b-a3b-instruct-2507","score":68,"metric":"percent"},{"benchmark":"kor-bench","model":"ling-flash-2.0","score":68.96,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.0-flash-preview","score":37.26,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.0-flash","score":64.24,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-30b-a3b-instruct-2507","score":86.31,"metric":"percent"},{"benchmark":"hellaswag","model":"ling-flash-2.0","score":81.59,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.0-flash-preview","score":86,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.0-flash","score":84.97,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-30b-a3b-instruct-2507","score":86.75,"metric":"percent"},{"benchmark":"cruxeval","model":"ling-flash-2.0","score":82.75,"metric":"percent"},{"benchmark":"cruxeval","model":"llada2.0-flash-preview","score":61.88,"metric":"percent"},{"benchmark":"cruxeval","model":"llada2.0-flash","score":85.12,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-30b-a3b-instruct-2507","score":86.65,"metric":"percent"},{"benchmark":"mbpp","model":"ling-flash-2.0","score":85.01,"metric":"percent"},{"benchmark":"mbpp","model":"llada2.0-flash-preview","score":77.75,"metric":"percent"},{"benchmark":"mbpp","model":"llada2.0-flash","score":88.29,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-30b-a3b-instruct-2507","score":70.67,"metric":"percent"},{"benchmark":"multipl-e","model":"ling-flash-2.0","score":65.76,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.0-flash-preview","score":62.43,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.0-flash","score":74.87,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-30b-a3b-instruct-2507","score":93.29,"metric":"percent"},{"benchmark":"humaneval","model":"ling-flash-2.0","score":85.98,"metric":"percent"},{"benchmark":"humaneval","model":"llada2.0-flash-preview","score":80.49,"metric":"percent"},{"benchmark":"humaneval","model":"llada2.0-flash","score":94.51,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-30b-a3b-instruct-2507","score":41.49,"metric":"percent"},{"benchmark":"bigcodebench","model":"ling-flash-2.0","score":40.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"llada2.0-flash-preview","score":30.44,"metric":"percent"},{"benchmark":"bigcodebench","model":"llada2.0-flash","score":41.58,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-instruct-2507","score":41.63,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-flash-2.0","score":44.11,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.0-flash-preview","score":28.58,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.0-flash","score":42.29,"metric":"percent"},{"benchmark":"spider","model":"qwen3-30b-a3b-instruct-2507","score":81.79,"metric":"percent"},{"benchmark":"spider","model":"ling-flash-2.0","score":80.58,"metric":"percent"},{"benchmark":"spider","model":"llada2.0-flash-preview","score":81.37,"metric":"percent"},{"benchmark":"spider","model":"llada2.0-flash","score":82.49,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b-instruct-2507","score":96.36,"metric":"percent"},{"benchmark":"gsm8k","model":"ling-flash-2.0","score":95.45,"metric":"percent"},{"benchmark":"gsm8k","model":"llada2.0-flash-preview","score":89.01,"metric":"percent"},{"benchmark":"gsm8k","model":"llada2.0-flash","score":96.06,"metric":"percent"},{"benchmark":"math","model":"qwen3-30b-a3b-instruct-2507","score":96.7,"metric":"percent"},{"benchmark":"math","model":"ling-flash-2.0","score":96.1,"metric":"percent"},{"benchmark":"math","model":"llada2.0-flash-preview","score":73.5,"metric":"percent"},{"benchmark":"math","model":"llada2.0-flash","score":95.44,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen3-30b-a3b-instruct-2507","score":77.59,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-flash-2.0","score":76.19,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.0-flash-preview","score":47.78,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.0-flash","score":74.07,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"qwen3-30b-a3b-instruct-2507","score":73.19,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"ling-flash-2.0","score":67.57,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"llada2.0-flash-preview","score":74.11,"metric":"percent"},{"benchmark":"bfcl-live-v2","model":"llada2.0-flash","score":75.43,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-instruct-2507","score":84.29,"metric":"percent"},{"benchmark":"ifeval","model":"ling-flash-2.0","score":81.52,"metric":"percent"},{"benchmark":"ifeval","model":"llada2.0-flash-preview","score":62.5,"metric":"percent"},{"benchmark":"ifeval","model":"llada2.0-flash","score":81.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"nemotron-3-nano-30b-a3b","score":67.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-30b-a3b-thinking-2507","score":57.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-oss-20b-a4b","score":48.5,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-nano-30b-a3b","score":99.2,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-thinking-2507","score":98.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b-a4b","score":91.7,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-nano-30b-a3b","score":71.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b-thinking-2507","score":51,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b-a4b","score":65,"metric":"percent"},{"benchmark":"swe-bench","model":"nemotron-3-nano-30b-a3b","score":38.8,"metric":"percent"},{"benchmark":"swe-bench","model":"qwen3-30b-a3b-thinking-2507","score":22,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-oss-20b-a4b","score":34,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-nano-30b-a3b","score":68.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b-a4b","score":61,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3-nano-30b-a3b","score":86.3,"metric":"percent"},{"benchmark":"ruler-1m","model":"qwen3-30b-a3b-thinking-2507","score":77.5,"metric":"percent"},{"benchmark":"isl-osl-8k-16k","model":"nemotron-3-nano-30b-a3b","score":3.3,"metric":"relative_throughput"},{"benchmark":"isl-osl-8k-16k","model":"qwen3-30b-a3b-thinking-2507","score":1,"metric":"relative_throughput"},{"benchmark":"isl-osl-8k-16k","model":"gpt-oss-20b-a4b","score":1.5,"metric":"relative_throughput"},{"benchmark":"swe-bench-verified","model":"mimo-v2-flash","score":73.4},{"benchmark":"swe-bench-multilingual","model":"mimo-v2-flash","score":71.7},{"benchmark":"aime-2025","model":"mimo-v2-flash","score":94.1},{"benchmark":"gpqa-diamond","model":"mimo-v2-flash","score":83.7},{"benchmark":"hle","model":"mimo-v2-flash","score":22.1},{"benchmark":"arena-hard-v2-creative-writing","model":"mimo-v2-flash","score":86.2},{"benchmark":"mmlu","model":"qwen3-8b","score":83,"metric":"percent"},{"benchmark":"mmlu","model":"nvidia-nemotron-nano-9b-v2","score":82.6,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-r1-0528","score":89.9,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-cascade-8b-thinking","score":84,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-cascade-8b","score":83.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b","score":75.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nvidia-nemotron-nano-9b-v2","score":73.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-cascade-8b-thinking","score":75.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-cascade-8b","score":75.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nvidia-nemotron-nano-9b-v2","score":64,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash-thinking","score":82.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-cascade-8b-thinking","score":66.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-cascade-8b","score":66.5,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen3-8b","score":85.8,"metric":"percent"},{"benchmark":"arena-hard","model":"nvidia-nemotron-nano-9b-v2","score":74.6,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-r1-0528","score":95.1,"metric":"percent"},{"benchmark":"arena-hard","model":"gemini-2.5-flash-thinking","score":95.7,"metric":"percent"},{"benchmark":"arena-hard","model":"nemotron-cascade-8b-thinking","score":85.8,"metric":"percent"},{"benchmark":"arena-hard","model":"nemotron-cascade-8b","score":87.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-8b","score":85,"metric":"percent"},{"benchmark":"ifeval","model":"nvidia-nemotron-nano-9b-v2","score":86.1,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-r1-0528","score":84.1,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-cascade-8b-thinking","score":83.7,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-cascade-8b","score":90.2,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-8b","score":34.4,"metric":"percent"},{"benchmark":"ifbench","model":"nvidia-nemotron-nano-9b-v2","score":37.4,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-r1-0528","score":38,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-2.5-flash-thinking","score":36.1,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-cascade-8b-thinking","score":41.4,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-cascade-8b","score":40.8,"metric":"percent"},{"benchmark":"aime-2024","model":"nvidia-nemotron-nano-9b-v2","score":81.9,"metric":"percent"},{"benchmark":"aime-2024","model":"gemini-2.5-flash-thinking","score":82.3,"metric":"percent"},{"benchmark":"aime-2024","model":"nemotron-cascade-8b-thinking","score":88.8,"metric":"percent"},{"benchmark":"aime-2024","model":"nemotron-cascade-8b","score":89.5,"metric":"percent"},{"benchmark":"aime-2025","model":"nvidia-nemotron-nano-9b-v2","score":72,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-cascade-8b-thinking","score":81.4,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-cascade-8b","score":80.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-8b","score":61.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nvidia-nemotron-nano-9b-v2","score":68.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepseek-r1-0528","score":74.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-2.5-flash-thinking","score":63.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nemotron-cascade-8b-thinking","score":74.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nemotron-cascade-8b","score":74.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b","score":58.3,"metric":"percent"},{"benchmark":"livecodebench","model":"nvidia-nemotron-nano-9b-v2","score":65.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-thinking","score":61.9,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-cascade-8b-thinking","score":71.4,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-cascade-8b","score":71.1,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-8b","score":46.1,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nvidia-nemotron-nano-9b-v2","score":59.3,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"deepseek-r1-0528","score":63.9,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gemini-2.5-flash-thinking","score":47.4,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nemotron-cascade-8b-thinking","score":64.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nemotron-cascade-8b","score":65.7,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-8b","score":2.2,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nvidia-nemotron-nano-9b-v2","score":4.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"deepseek-r1-0528","score":7,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gemini-2.5-flash-thinking","score":1.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nemotron-cascade-8b-thinking","score":6.1,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nemotron-cascade-8b","score":6.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-8b","score":20.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-2.5-flash-thinking","score":48.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-cascade-8b-thinking","score":38.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-cascade-8b","score":37.2,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-8b","score":68.1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"deepseek-r1-0528","score":67.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"nemotron-cascade-8b-thinking","score":67,"metric":"percent"},{"benchmark":"bfcl-v3","model":"nemotron-cascade-8b","score":64.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-14b","score":84.9,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-cascade-14b-thinking","score":85.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-14b","score":77.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-cascade-14b-thinking","score":77,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-cascade-14b-thinking","score":69.6,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen3-14b","score":91.7,"metric":"percent"},{"benchmark":"arena-hard","model":"nemotron-cascade-14b-thinking","score":89.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-14b","score":85.4,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-cascade-14b-thinking","score":81.9,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-14b","score":33.7,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-cascade-14b-thinking","score":41.7,"metric":"percent"},{"benchmark":"aime-2024","model":"nemotron-cascade-14b-thinking","score":89.7,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-cascade-14b-thinking","score":83.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-14b","score":65.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nemotron-cascade-14b-thinking","score":77.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-14b","score":63.5,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-cascade-14b-thinking","score":74.6,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-14b","score":53.6,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nemotron-cascade-14b-thinking","score":68.9,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-14b","score":2.6,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nemotron-cascade-14b-thinking","score":10.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-14b","score":27.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-cascade-14b-thinking","score":43.1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-14b","score":70.4,"metric":"percent"},{"benchmark":"bfcl-v3","model":"nemotron-cascade-14b-thinking","score":67.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":78.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b","score":75,"metric":"percent"},{"benchmark":"aime-2025","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":89.1,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b","score":91.7,"metric":"percent"},{"benchmark":"aime-2025","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":99.2,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b","score":98.7,"metric":"percent"},{"benchmark":"gpqa","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":73,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-oss-20b","score":71.5,"metric":"percent"},{"benchmark":"gpqa","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":75,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-oss-20b","score":74.2,"metric":"percent"},{"benchmark":"livecodebench","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":68.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b","score":61,"metric":"percent"},{"benchmark":"scicode","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":33.3,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-30b-a3b-thinking-2507","score":33,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-20b","score":34,"metric":"percent"},{"benchmark":"hle","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":10.6,"metric":"percent"},{"benchmark":"hle","model":"qwen3-30b-a3b-thinking-2507","score":9.8,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-20b","score":10.9,"metric":"percent"},{"benchmark":"hle","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":15.5,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-20b","score":17.3,"metric":"percent"},{"benchmark":"minif2f-pass1","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":50,"metric":"percent"},{"benchmark":"minif2f-pass1","model":"qwen3-30b-a3b-thinking-2507","score":5.7,"metric":"percent"},{"benchmark":"minif2f-pass1","model":"gpt-oss-20b","score":12.1,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":79.9,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"qwen3-30b-a3b-thinking-2507","score":16.8,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"gpt-oss-20b","score":43,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":8.5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"qwen3-30b-a3b-thinking-2507","score":5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-oss-20b","score":6,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":38.8,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"qwen3-30b-a3b-thinking-2507","score":22,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"gpt-oss-20b","score":34,"metric":"percent"},{"benchmark":"tau2-airline","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":48,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-oss-20b","score":38,"metric":"percent"},{"benchmark":"tau2-retail","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":56.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-oss-20b","score":38,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":42.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":53.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-30b-a3b-thinking-2507","score":46.4,"metric":"percent"},{"benchmark":"ifbench","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":71.5,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b","score":65,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":38.5,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"qwen3-30b-a3b-thinking-2507","score":44.8,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"gpt-oss-20b","score":33.8,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":72.1,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"qwen3-30b-a3b-thinking-2507","score":49.6,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"gpt-oss-20b","score":71.2,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":63.2,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"qwen3-30b-a3b-thinking-2507","score":66,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"gpt-oss-20b","score":25.9,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":67.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-oss-20b","score":48.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":35.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-30b-a3b-thinking-2507","score":59,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-20b","score":34,"metric":"percent"},{"benchmark":"ruler-100-256k","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":92.9,"metric":"percent"},{"benchmark":"ruler-100-256k","model":"qwen3-30b-a3b-thinking-2507","score":89.4,"metric":"percent"},{"benchmark":"ruler-100-512k","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":91.3,"metric":"percent"},{"benchmark":"ruler-100-512k","model":"qwen3-30b-a3b-thinking-2507","score":84,"metric":"percent"},{"benchmark":"ruler-100-1m","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":86.3,"metric":"percent"},{"benchmark":"ruler-100-1m","model":"qwen3-30b-a3b-thinking-2507","score":77.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":59.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-30b-a3b-thinking-2507","score":77.6,"metric":"percent"},{"benchmark":"mmlu-prox","model":"gpt-oss-20b","score":69.1,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":86.2,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-30b-a3b-thinking-2507","score":85.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gpt-oss-20b","score":83.2,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5","score":97.1,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5","score":89.6,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5","score":88.9,"metric":"percent"},{"benchmark":"infoqa","model":"gpt-5","score":83,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-5","score":78.7,"metric":"percent"},{"benchmark":"vqav2","model":"gpt-5","score":79.7,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5","score":80.8,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5","score":81.8,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5","score":82.7,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5","score":90.8,"metric":"percent"},{"benchmark":"pixmocount","model":"gpt-5","score":67.2,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-5","score":78.6,"metric":"percent"},{"benchmark":"mmiu","model":"gpt-5","score":71,"metric":"percent"},{"benchmark":"blink","model":"gpt-5","score":66.5,"metric":"percent"},{"benchmark":"img-qa-avg","model":"gpt-5","score":83.7,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"gpt-5","score":72.1,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-mini","score":95.8,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5-mini","score":88.2,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5-mini","score":86.7,"metric":"percent"},{"benchmark":"infoqa","model":"gpt-5-mini","score":82.2,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-5-mini","score":79.1,"metric":"percent"},{"benchmark":"vqav2","model":"gpt-5-mini","score":72.1,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5-mini","score":77,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-mini","score":78.7,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5-mini","score":79.2,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5-mini","score":87.1,"metric":"percent"},{"benchmark":"pixmocount","model":"gpt-5-mini","score":74.4,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-5-mini","score":71.4,"metric":"percent"},{"benchmark":"mmiu","model":"gpt-5-mini","score":64.5,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-mini","score":68.7,"metric":"percent"},{"benchmark":"img-qa-avg","model":"gpt-5-mini","score":81.9,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"gpt-5-mini","score":68.2,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-3-pro","score":98.7,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-3-pro","score":93.7,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-3-pro","score":87.1,"metric":"percent"},{"benchmark":"infoqa","model":"gemini-3-pro","score":86.9,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-3-pro","score":74.1,"metric":"percent"},{"benchmark":"vqav2","model":"gemini-3-pro","score":74.1,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-3-pro","score":73.6,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-3-pro","score":85.2,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-3-pro","score":89.1,"metric":"percent"},{"benchmark":"countbench","model":"gemini-3-pro","score":96.1,"metric":"percent"},{"benchmark":"pixmocount","model":"gemini-3-pro","score":90,"metric":"percent"},{"benchmark":"muirbench","model":"gemini-3-pro","score":86.1,"metric":"percent"},{"benchmark":"mmiu","model":"gemini-3-pro","score":72.1,"metric":"percent"},{"benchmark":"blink","model":"gemini-3-pro","score":87.4,"metric":"percent"},{"benchmark":"img-qa-avg","model":"gemini-3-pro","score":86.2,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"gemini-3-pro","score":81.9,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-pro","score":94.3,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-pro","score":82.7,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-pro","score":91.5,"metric":"percent"},{"benchmark":"infoqa","model":"gemini-2.5-pro","score":82,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-2.5-pro","score":70.3,"metric":"percent"},{"benchmark":"vqav2","model":"gemini-2.5-pro","score":67.1,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-2.5-pro","score":77.4,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-pro","score":79.6,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-pro","score":84.6,"metric":"percent"},{"benchmark":"countbench","model":"gemini-2.5-pro","score":90.8,"metric":"percent"},{"benchmark":"pixmocount","model":"gemini-2.5-pro","score":73.8,"metric":"percent"},{"benchmark":"muirbench","model":"gemini-2.5-pro","score":74.5,"metric":"percent"},{"benchmark":"mmiu","model":"gemini-2.5-pro","score":68.9,"metric":"percent"},{"benchmark":"blink","model":"gemini-2.5-pro","score":73.7,"metric":"percent"},{"benchmark":"img-qa-avg","model":"gemini-2.5-pro","score":81.3,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"gemini-2.5-pro","score":72.4,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-flash","score":95.9,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-flash","score":76.8,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-flash","score":91.1,"metric":"percent"},{"benchmark":"infoqa","model":"gemini-2.5-flash","score":80.9,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-2.5-flash","score":73,"metric":"percent"},{"benchmark":"vqav2","model":"gemini-2.5-flash","score":69.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-2.5-flash","score":74.5,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-flash","score":79,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-flash","score":81.2,"metric":"percent"},{"benchmark":"countbench","model":"gemini-2.5-flash","score":86.7,"metric":"percent"},{"benchmark":"pixmocount","model":"gemini-2.5-flash","score":63.9,"metric":"percent"},{"benchmark":"muirbench","model":"gemini-2.5-flash","score":73.5,"metric":"percent"},{"benchmark":"mmiu","model":"gemini-2.5-flash","score":61.2,"metric":"percent"},{"benchmark":"blink","model":"gemini-2.5-flash","score":70.2,"metric":"percent"},{"benchmark":"img-qa-avg","model":"gemini-2.5-flash","score":79.3,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"gemini-2.5-flash","score":68.3,"metric":"percent"},{"benchmark":"img-qa-avg","model":"claude-sonnet-4.5","score":76.3,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"claude-sonnet-4.5","score":59.5,"metric":"percent"},{"benchmark":"infoqa","model":"internvl3.5-4b","score":78,"metric":"percent"},{"benchmark":"vqav2","model":"internvl3.5-4b","score":78.1,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3.5-4b","score":77.1,"metric":"percent"},{"benchmark":"countbench","model":"internvl3.5-4b","score":82.2,"metric":"percent"},{"benchmark":"pixmocount","model":"internvl3.5-4b","score":62.4,"metric":"percent"},{"benchmark":"muirbench","model":"internvl3.5-4b","score":53.1,"metric":"percent"},{"benchmark":"mmiu","model":"internvl3.5-4b","score":49.2,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-4b","score":58.1,"metric":"percent"},{"benchmark":"img-qa-avg","model":"internvl3.5-4b","score":77.2,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"internvl3.5-4b","score":53.5,"metric":"percent"},{"benchmark":"ai2d","model":"internvl3.5-8b","score":84,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-8b","score":86.7,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-8b","score":92.3,"metric":"percent"},{"benchmark":"infoqa","model":"internvl3.5-8b","score":79.1,"metric":"percent"},{"benchmark":"textvqa","model":"internvl3.5-8b","score":78.2,"metric":"percent"},{"benchmark":"vqav2","model":"internvl3.5-8b","score":79.5,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-8b","score":67.5,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-8b","score":73.4,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3.5-8b","score":78.4,"metric":"percent"},{"benchmark":"countbench","model":"internvl3.5-8b","score":79.6,"metric":"percent"},{"benchmark":"pixmocount","model":"internvl3.5-8b","score":61.9,"metric":"percent"},{"benchmark":"muirbench","model":"internvl3.5-8b","score":55.8,"metric":"percent"},{"benchmark":"mmiu","model":"internvl3.5-8b","score":49.4,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-8b","score":59.5,"metric":"percent"},{"benchmark":"img-qa-avg","model":"internvl3.5-8b","score":78.2,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"internvl3.5-8b","score":54.9,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-4b-instruct","score":84.6,"metric":"percent"},{"benchmark":"infoqa","model":"qwen3-vl-4b-instruct","score":80.3,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-4b-instruct","score":81,"metric":"percent"},{"benchmark":"vqav2","model":"qwen3-vl-4b-instruct","score":81.7,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-4b-instruct","score":73.7,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-4b-instruct","score":85.5,"metric":"percent"},{"benchmark":"pixmocount","model":"qwen3-vl-4b-instruct","score":58,"metric":"percent"},{"benchmark":"mmiu","model":"qwen3-vl-4b-instruct","score":43.2,"metric":"percent"},{"benchmark":"img-qa-avg","model":"qwen3-vl-4b-instruct","score":78.4,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"qwen3-vl-4b-instruct","score":57.6,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-8b-instruct","score":89.6,"metric":"percent"},{"benchmark":"infoqa","model":"qwen3-vl-8b-instruct","score":83.1,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-8b-instruct","score":82.8,"metric":"percent"},{"benchmark":"vqav2","model":"qwen3-vl-8b-instruct","score":82.3,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-8b-instruct","score":77.2,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-8b-instruct","score":90.4,"metric":"percent"},{"benchmark":"pixmocount","model":"qwen3-vl-8b-instruct","score":65,"metric":"percent"},{"benchmark":"mmiu","model":"qwen3-vl-8b-instruct","score":35.3,"metric":"percent"},{"benchmark":"img-qa-avg","model":"qwen3-vl-8b-instruct","score":81.2,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"qwen3-vl-8b-instruct","score":56.3,"metric":"percent"},{"benchmark":"ai2d","model":"keye-vl-1.5-8b","score":89.5,"metric":"percent"},{"benchmark":"chartqa","model":"keye-vl-1.5-8b","score":94.1,"metric":"percent"},{"benchmark":"docvqa","model":"keye-vl-1.5-8b","score":93.4,"metric":"percent"},{"benchmark":"infoqa","model":"keye-vl-1.5-8b","score":74.9,"metric":"percent"},{"benchmark":"textvqa","model":"keye-vl-1.5-8b","score":81.5,"metric":"percent"},{"benchmark":"vqav2","model":"keye-vl-1.5-8b","score":79.3,"metric":"percent"},{"benchmark":"realworldqa","model":"keye-vl-1.5-8b","score":73.5,"metric":"percent"},{"benchmark":"mmmu","model":"keye-vl-1.5-8b","score":71.4,"metric":"percent"},{"benchmark":"mathvista","model":"keye-vl-1.5-8b","score":81.2,"metric":"percent"},{"benchmark":"countbench","model":"keye-vl-1.5-8b","score":81.6,"metric":"percent"},{"benchmark":"pixmocount","model":"keye-vl-1.5-8b","score":57.4,"metric":"percent"},{"benchmark":"muirbench","model":"keye-vl-1.5-8b","score":51.2,"metric":"percent"},{"benchmark":"mmiu","model":"keye-vl-1.5-8b","score":50.3,"metric":"percent"},{"benchmark":"blink","model":"keye-vl-1.5-8b","score":54.9,"metric":"percent"},{"benchmark":"img-qa-avg","model":"keye-vl-1.5-8b","score":79.8,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"keye-vl-1.5-8b","score":52.1,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4.1v-9b","score":87.9,"metric":"percent"},{"benchmark":"chartqa","model":"glm-4.1v-9b","score":70,"metric":"percent"},{"benchmark":"docvqa","model":"glm-4.1v-9b","score":93.3,"metric":"percent"},{"benchmark":"infoqa","model":"glm-4.1v-9b","score":80.3,"metric":"percent"},{"benchmark":"textvqa","model":"glm-4.1v-9b","score":79.6,"metric":"percent"},{"benchmark":"vqav2","model":"glm-4.1v-9b","score":68.3,"metric":"percent"},{"benchmark":"realworldqa","model":"glm-4.1v-9b","score":70.7,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.1v-9b","score":68,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.1v-9b","score":80.7,"metric":"percent"},{"benchmark":"countbench","model":"glm-4.1v-9b","score":88,"metric":"percent"},{"benchmark":"pixmocount","model":"glm-4.1v-9b","score":60.7,"metric":"percent"},{"benchmark":"muirbench","model":"glm-4.1v-9b","score":74.7,"metric":"percent"},{"benchmark":"mmiu","model":"glm-4.1v-9b","score":62.4,"metric":"percent"},{"benchmark":"blink","model":"glm-4.1v-9b","score":65.1,"metric":"percent"},{"benchmark":"img-qa-avg","model":"glm-4.1v-9b","score":77,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"glm-4.1v-9b","score":67.4,"metric":"percent"},{"benchmark":"ai2d","model":"minicpm-v-4.5-8b","score":86.5,"metric":"percent"},{"benchmark":"chartqa","model":"minicpm-v-4.5-8b","score":87.4,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-v-4.5-8b","score":94.7,"metric":"percent"},{"benchmark":"infoqa","model":"minicpm-v-4.5-8b","score":73.4,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-v-4.5-8b","score":82.2,"metric":"percent"},{"benchmark":"vqav2","model":"minicpm-v-4.5-8b","score":64.1,"metric":"percent"},{"benchmark":"realworldqa","model":"minicpm-v-4.5-8b","score":72.1,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v-4.5-8b","score":67.7,"metric":"percent"},{"benchmark":"mathvista","model":"minicpm-v-4.5-8b","score":79.9,"metric":"percent"},{"benchmark":"countbench","model":"minicpm-v-4.5-8b","score":83.9,"metric":"percent"},{"benchmark":"pixmocount","model":"minicpm-v-4.5-8b","score":62.8,"metric":"percent"},{"benchmark":"muirbench","model":"minicpm-v-4.5-8b","score":53.3,"metric":"percent"},{"benchmark":"mmiu","model":"minicpm-v-4.5-8b","score":46.5,"metric":"percent"},{"benchmark":"blink","model":"minicpm-v-4.5-8b","score":42,"metric":"percent"},{"benchmark":"img-qa-avg","model":"minicpm-v-4.5-8b","score":77.7,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"minicpm-v-4.5-8b","score":47.3,"metric":"percent"},{"benchmark":"ai2d","model":"eagle2.5-8b","score":84.5,"metric":"percent"},{"benchmark":"chartqa","model":"eagle2.5-8b","score":87.5,"metric":"percent"},{"benchmark":"docvqa","model":"eagle2.5-8b","score":94.1,"metric":"percent"},{"benchmark":"infoqa","model":"eagle2.5-8b","score":80.4,"metric":"percent"},{"benchmark":"textvqa","model":"eagle2.5-8b","score":83.7,"metric":"percent"},{"benchmark":"vqav2","model":"eagle2.5-8b","score":82.4,"metric":"percent"},{"benchmark":"realworldqa","model":"eagle2.5-8b","score":76.7,"metric":"percent"},{"benchmark":"mmmu","model":"eagle2.5-8b","score":55.8,"metric":"percent"},{"benchmark":"mathvista","model":"eagle2.5-8b","score":67.8,"metric":"percent"},{"benchmark":"countbench","model":"eagle2.5-8b","score":90.2,"metric":"percent"},{"benchmark":"pixmocount","model":"eagle2.5-8b","score":90.2,"metric":"percent"},{"benchmark":"muirbench","model":"eagle2.5-8b","score":61.8,"metric":"percent"},{"benchmark":"mmiu","model":"eagle2.5-8b","score":48.4,"metric":"percent"},{"benchmark":"blink","model":"eagle2.5-8b","score":45.8,"metric":"percent"},{"benchmark":"img-qa-avg","model":"eagle2.5-8b","score":81.2,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"eagle2.5-8b","score":52,"metric":"percent"},{"benchmark":"ai2d","model":"plm-3b","score":90.9,"metric":"percent"},{"benchmark":"chartqa","model":"plm-3b","score":84.3,"metric":"percent"},{"benchmark":"docvqa","model":"plm-3b","score":93.8,"metric":"percent"},{"benchmark":"infoqa","model":"plm-3b","score":74.6,"metric":"percent"},{"benchmark":"textvqa","model":"plm-3b","score":84.3,"metric":"percent"},{"benchmark":"vqav2","model":"plm-3b","score":84.4,"metric":"percent"},{"benchmark":"realworldqa","model":"plm-3b","score":72.4,"metric":"percent"},{"benchmark":"mmmu","model":"plm-3b","score":41.2,"metric":"percent"},{"benchmark":"mathvista","model":"plm-3b","score":59.1,"metric":"percent"},{"benchmark":"countbench","model":"plm-3b","score":87.1,"metric":"percent"},{"benchmark":"pixmocount","model":"plm-3b","score":63,"metric":"percent"},{"benchmark":"muirbench","model":"plm-3b","score":25.7,"metric":"percent"},{"benchmark":"mmiu","model":"plm-3b","score":40.6,"metric":"percent"},{"benchmark":"blink","model":"plm-3b","score":55.4,"metric":"percent"},{"benchmark":"img-qa-avg","model":"plm-3b","score":75.9,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"plm-3b","score":40.6,"metric":"percent"},{"benchmark":"ai2d","model":"plm-8b","score":92.7,"metric":"percent"},{"benchmark":"chartqa","model":"plm-8b","score":85.5,"metric":"percent"},{"benchmark":"docvqa","model":"plm-8b","score":94.6,"metric":"percent"},{"benchmark":"infoqa","model":"plm-8b","score":80,"metric":"percent"},{"benchmark":"textvqa","model":"plm-8b","score":86.5,"metric":"percent"},{"benchmark":"vqav2","model":"plm-8b","score":85.6,"metric":"percent"},{"benchmark":"realworldqa","model":"plm-8b","score":75,"metric":"percent"},{"benchmark":"mmmu","model":"plm-8b","score":46.1,"metric":"percent"},{"benchmark":"mathvista","model":"plm-8b","score":59.9,"metric":"percent"},{"benchmark":"countbench","model":"plm-8b","score":91.8,"metric":"percent"},{"benchmark":"pixmocount","model":"plm-8b","score":68,"metric":"percent"},{"benchmark":"muirbench","model":"plm-8b","score":23.5,"metric":"percent"},{"benchmark":"mmiu","model":"plm-8b","score":27.4,"metric":"percent"},{"benchmark":"blink","model":"plm-8b","score":56,"metric":"percent"},{"benchmark":"img-qa-avg","model":"plm-8b","score":78.7,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"plm-8b","score":35.7,"metric":"percent"},{"benchmark":"ai2d","model":"molmoe-1b","score":34.9,"metric":"percent"},{"benchmark":"chartqa","model":"molmoe-1b","score":34,"metric":"percent"},{"benchmark":"docvqa","model":"molmoe-1b","score":87.2,"metric":"percent"},{"benchmark":"infoqa","model":"molmoe-1b","score":79.6,"metric":"percent"},{"benchmark":"mmmu","model":"molmoe-1b","score":68.6,"metric":"percent"},{"benchmark":"mathvista","model":"molmo-7b-o","score":44.5,"metric":"percent"},{"benchmark":"countbench","model":"molmo-7b-o","score":89,"metric":"percent"},{"benchmark":"img-qa-avg","model":"molmo-7b-o","score":74.6,"metric":"percent"},{"benchmark":"mathvista","model":"molmo-7b-d","score":51.6,"metric":"percent"},{"benchmark":"countbench","model":"molmo-7b-d","score":88.5,"metric":"percent"},{"benchmark":"img-qa-avg","model":"molmo-7b-d","score":77.3,"metric":"percent"},{"benchmark":"mathvista","model":"molmo-72b","score":58.6,"metric":"percent"},{"benchmark":"countbench","model":"molmo-72b","score":91.2,"metric":"percent"},{"benchmark":"img-qa-avg","model":"molmo-72b","score":81.2,"metric":"percent"},{"benchmark":"ai2d","model":"molmo2-4b","score":95.6,"metric":"percent"},{"benchmark":"chartqa","model":"molmo2-4b","score":86.1,"metric":"percent"},{"benchmark":"docvqa","model":"molmo2-4b","score":87.8,"metric":"percent"},{"benchmark":"infoqa","model":"molmo2-4b","score":78.6,"metric":"percent"},{"benchmark":"textvqa","model":"molmo2-4b","score":85,"metric":"percent"},{"benchmark":"vqav2","model":"molmo2-4b","score":86.6,"metric":"percent"},{"benchmark":"realworldqa","model":"molmo2-4b","score":75.4,"metric":"percent"},{"benchmark":"mmmu","model":"molmo2-4b","score":50.9,"metric":"percent"},{"benchmark":"mathvista","model":"molmo2-4b","score":56.7,"metric":"percent"},{"benchmark":"countbench","model":"molmo2-4b","score":93.9,"metric":"percent"},{"benchmark":"pixmocount","model":"molmo2-4b","score":88.1,"metric":"percent"},{"benchmark":"muirbench","model":"molmo2-4b","score":60.5,"metric":"percent"},{"benchmark":"mmiu","model":"molmo2-4b","score":55.5,"metric":"percent"},{"benchmark":"blink","model":"molmo2-4b","score":57.5,"metric":"percent"},{"benchmark":"img-qa-avg","model":"molmo2-4b","score":80.4,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"molmo2-4b","score":57.8,"metric":"percent"},{"benchmark":"ai2d","model":"molmo2-8b","score":95.8,"metric":"percent"},{"benchmark":"chartqa","model":"molmo2-8b","score":86,"metric":"percent"},{"benchmark":"docvqa","model":"molmo2-8b","score":93.2,"metric":"percent"},{"benchmark":"infoqa","model":"molmo2-8b","score":80.1,"metric":"percent"},{"benchmark":"textvqa","model":"molmo2-8b","score":85.7,"metric":"percent"},{"benchmark":"vqav2","model":"molmo2-8b","score":87,"metric":"percent"},{"benchmark":"realworldqa","model":"molmo2-8b","score":77.6,"metric":"percent"},{"benchmark":"mmmu","model":"molmo2-8b","score":53,"metric":"percent"},{"benchmark":"mathvista","model":"molmo2-8b","score":58.9,"metric":"percent"},{"benchmark":"countbench","model":"molmo2-8b","score":93.7,"metric":"percent"},{"benchmark":"pixmocount","model":"molmo2-8b","score":88.5,"metric":"percent"},{"benchmark":"muirbench","model":"molmo2-8b","score":63.7,"metric":"percent"},{"benchmark":"mmiu","model":"molmo2-8b","score":54.2,"metric":"percent"},{"benchmark":"blink","model":"molmo2-8b","score":51.3,"metric":"percent"},{"benchmark":"img-qa-avg","model":"molmo2-8b","score":81.7,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"molmo2-8b","score":56.4,"metric":"percent"},{"benchmark":"ai2d","model":"molmo2-o-7b","score":93.7,"metric":"percent"},{"benchmark":"chartqa","model":"molmo2-o-7b","score":84.9,"metric":"percent"},{"benchmark":"docvqa","model":"molmo2-o-7b","score":90.4,"metric":"percent"},{"benchmark":"infoqa","model":"molmo2-o-7b","score":77.9,"metric":"percent"},{"benchmark":"textvqa","model":"molmo2-o-7b","score":84.7,"metric":"percent"},{"benchmark":"vqav2","model":"molmo2-o-7b","score":86.6,"metric":"percent"},{"benchmark":"realworldqa","model":"molmo2-o-7b","score":73.6,"metric":"percent"},{"benchmark":"mmmu","model":"molmo2-o-7b","score":45.8,"metric":"percent"},{"benchmark":"mathvista","model":"molmo2-o-7b","score":54.2,"metric":"percent"},{"benchmark":"countbench","model":"molmo2-o-7b","score":95.1,"metric":"percent"},{"benchmark":"pixmocount","model":"molmo2-o-7b","score":88.9,"metric":"percent"},{"benchmark":"muirbench","model":"molmo2-o-7b","score":58.4,"metric":"percent"},{"benchmark":"mmiu","model":"molmo2-o-7b","score":51.7,"metric":"percent"},{"benchmark":"blink","model":"molmo2-o-7b","score":50.5,"metric":"percent"},{"benchmark":"img-qa-avg","model":"molmo2-o-7b","score":79.7,"metric":"percent"},{"benchmark":"multiimg-qa-avg","model":"molmo2-o-7b","score":53.5,"metric":"percent"},{"benchmark":"frontierscience","model":"gpt-4o","score":0.4,"metric":"percent"},{"benchmark":"frontierscience","model":"o1","score":3.2,"metric":"percent"},{"benchmark":"frontierscience","model":"o4-mini","score":8.3,"metric":"percent"},{"benchmark":"frontierscience","model":"gemini-3-pro","score":12.4,"metric":"percent"},{"benchmark":"frontierscience","model":"o3","score":14.1,"metric":"percent"},{"benchmark":"frontierscience","model":"grok-4","score":15.9,"metric":"percent"},{"benchmark":"frontierscience","model":"claude-opus-4.5","score":17.5,"metric":"percent"},{"benchmark":"frontierscience","model":"gpt-5.2","score":25.2,"metric":"percent"},{"benchmark":"hle","model":"gemini-3-flash","score":33.7,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-2.5-flash","score":11,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-2.5-pro","score":21.6,"metric":"avg@3"},{"benchmark":"hle","model":"claude-4.5-sonnet-thinking","score":13.7,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.2-extra-high","score":34.5,"metric":"avg@3"},{"benchmark":"hle","model":"grok-4.1-fast","score":17.6,"metric":"avg@3"},{"benchmark":"arc-agi-2","model":"gemini-3-flash","score":33.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash","score":2.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking","score":13.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-extra-high","score":52.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3-flash","score":90.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2-extra-high","score":92.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"grok-4.1-fast","score":84.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3-flash","score":95.2,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-4.5-sonnet-thinking","score":87,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.2-extra-high","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4.1-fast","score":91.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3-flash","score":81.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-flash","score":66.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-4.5-sonnet-thinking","score":68,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.2-extra-high","score":79.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"grok-4.1-fast","score":63,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gemini-3-flash","score":69.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gemini-2.5-flash","score":3.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-4.5-sonnet-thinking","score":36.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5.2-extra-high","score":86.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3-flash","score":80.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-flash","score":63.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-4.5-sonnet-thinking","score":68.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.2-extra-high","score":82.1,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gemini-3-flash","score":0.121,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemini-2.5-flash","score":0.154,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"claude-4.5-sonnet-thinking","score":0.145,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.2-extra-high","score":0.143,"metric":"edit_distance"},{"benchmark":"videommmu","model":"gemini-3-flash","score":86.9,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-2.5-flash","score":79.2,"metric":"percent"},{"benchmark":"videommmu","model":"claude-4.5-sonnet-thinking","score":77.8,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5.2-extra-high","score":85.9,"metric":"percent"},{"benchmark":"livecodebench-pro","model":"gemini-3-flash","score":2316,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gemini-2.5-flash","score":1143,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"claude-4.5-sonnet-thinking","score":1418,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-5.2-extra-high","score":2393,"metric":"elo"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-flash","score":47.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-2.5-flash","score":16.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-4.5-sonnet-thinking","score":42.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3-flash","score":78,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-2.5-flash","score":60.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-2.5-pro","score":69.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.2-extra-high","score":80,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"grok-4.1-fast","score":50.6,"metric":"percent"},{"benchmark":"toolathlon","model":"gemini-3-flash","score":49.4,"metric":"percent"},{"benchmark":"toolathlon","model":"gemini-3-pro","score":36.4,"metric":"percent"},{"benchmark":"toolathlon","model":"gemini-2.5-flash","score":3.7,"metric":"percent"},{"benchmark":"toolathlon","model":"gemini-2.5-pro","score":10.5,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-4.5-sonnet-thinking","score":38.9,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.2-extra-high","score":46.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3-flash","score":57.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3-pro","score":54.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-2.5-flash","score":3.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-2.5-pro","score":8.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-4.5-sonnet-thinking","score":43.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.2-extra-high","score":60.6,"metric":"percent"},{"benchmark":"vending-bench-2","model":"gemini-3-flash","score":3635,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"gemini-3-pro","score":5478,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"gemini-2.5-flash","score":549,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"gemini-2.5-pro","score":574,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"claude-4.5-sonnet-thinking","score":3839,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"gpt-5.2-extra-high","score":3952,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"grok-4.1-fast","score":1107,"metric":"net_worth_mean"},{"benchmark":"facts-benchmark-suite","model":"gemini-3-flash","score":61.9,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"gemini-2.5-flash","score":50.4,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"claude-4.5-sonnet-thinking","score":48.9,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"gpt-5.2-extra-high","score":61.4,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"grok-4.1-fast","score":42.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-3-flash","score":68.7,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-3-pro","score":72.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-2.5-flash","score":28.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-2.5-pro","score":54.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-4.5-sonnet-thinking","score":29.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.2-extra-high","score":38,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"grok-4.1-fast","score":19.5,"metric":"percent"},{"benchmark":"mmmlu","model":"gemini-3-flash","score":91.8,"metric":"percent"},{"benchmark":"mmmlu","model":"gemini-2.5-flash","score":86.6,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-4.5-sonnet-thinking","score":89.1,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5.2-extra-high","score":89.6,"metric":"percent"},{"benchmark":"mmmlu","model":"grok-4.1-fast","score":86.8,"metric":"percent"},{"benchmark":"global-piqa","model":"gemini-3-flash","score":92.8,"metric":"percent"},{"benchmark":"global-piqa","model":"gemini-2.5-flash","score":90.2,"metric":"percent"},{"benchmark":"global-piqa","model":"claude-4.5-sonnet-thinking","score":90.1,"metric":"percent"},{"benchmark":"global-piqa","model":"gpt-5.2-extra-high","score":91.2,"metric":"percent"},{"benchmark":"global-piqa","model":"grok-4.1-fast","score":85.6,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gemini-3-flash","score":67.2,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gemini-2.5-flash","score":54.3,"metric":"percent"},{"benchmark":"mrcr-128k","model":"claude-4.5-sonnet-thinking","score":47.1,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gpt-5.2-extra-high","score":81.9,"metric":"percent"},{"benchmark":"mrcr-128k","model":"grok-4.1-fast","score":54.6,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-3-flash","score":22.1,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-2.5-flash","score":21,"metric":"percent"},{"benchmark":"mrcr-1m","model":"claude-4.5-sonnet-thinking","score":9.6,"metric":"percent"},{"benchmark":"mrcr-1m","model":"grok-4.1-fast","score":6.1,"metric":"percent"},{"benchmark":"mmlu","model":"motif-2-12.7b-reasoning","score":84.07,"metric":"percent"},{"benchmark":"mmlu-redux","model":"motif-2-12.7b-reasoning","score":88.89,"metric":"percent"},{"benchmark":"bbh","model":"motif-2-12.7b-reasoning","score":78.34,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"motif-2-12.7b-reasoning","score":70,"metric":"percent"},{"benchmark":"gsm8k","model":"motif-2-12.7b-reasoning","score":95.53,"metric":"percent"},{"benchmark":"math","model":"motif-2-12.7b-reasoning","score":95.07,"metric":"percent"},{"benchmark":"mbpp","model":"motif-2-12.7b-reasoning","score":88.9,"metric":"percent"},{"benchmark":"livebench","model":"motif-2-12.7b-reasoning","score":49.9,"metric":"percent"},{"benchmark":"ifeval","model":"motif-2-12.7b-reasoning","score":79.11,"metric":"percent"},{"benchmark":"ifeval","model":"motif-2-12.7b-reasoning","score":81.89,"metric":"percent"},{"benchmark":"math500","model":"motif-2-12.7b-reasoning","score":99.3,"metric":"percent"},{"benchmark":"aime-2024","model":"motif-2-12.7b-reasoning","score":88.3,"metric":"percent"},{"benchmark":"aime-2025","model":"motif-2-12.7b-reasoning","score":80,"metric":"percent"},{"benchmark":"zebralogic","model":"motif-2-12.7b-reasoning","score":77,"metric":"percent"},{"benchmark":"bfcl-v3","model":"motif-2-12.7b-reasoning","score":60.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"motif-2-12.7b-reasoning","score":65,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"motif-2-12.7b-reasoning","score":60.1,"metric":"percent"},{"benchmark":"humaneval","model":"motif-2-12.7b-reasoning","score":93.2,"metric":"percent"},{"benchmark":"hellaswag","model":"eurollm-22b","score":61.74,"metric":"percent"},{"benchmark":"mmlu","model":"eurollm-22b","score":64.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"eurollm-22b","score":45.33,"metric":"percent"},{"benchmark":"arc-challenge","model":"eurollm-22b","score":82.66,"metric":"percent"},{"benchmark":"mgsm","model":"eurollm-22b","score":76.07,"metric":"percent"},{"benchmark":"flores","model":"eurollm-22b","score":88.88,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"eurollm-22b","score":83.62,"metric":"percent"},{"benchmark":"borda-count-multilingual","model":"eurollm-22b","score":4.9,"metric":"borda_count"},{"benchmark":"hellaswag","model":"apertus-70b","score":61.22,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-70b","score":60.33,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-70b","score":36.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-70b","score":78.59,"metric":"percent"},{"benchmark":"mgsm","model":"apertus-70b","score":72.73,"metric":"percent"},{"benchmark":"flores","model":"apertus-70b","score":88.17,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"apertus-70b","score":81.96,"metric":"percent"},{"benchmark":"borda-count-multilingual","model":"apertus-70b","score":6.6,"metric":"borda_count"},{"benchmark":"hellaswag","model":"olmo-2-32b-base","score":44.29,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-2-32b-base","score":62.79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-2-32b-base","score":39.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-2-32b-base","score":81.09,"metric":"percent"},{"benchmark":"mgsm","model":"olmo-2-32b-base","score":79.18,"metric":"percent"},{"benchmark":"flores","model":"olmo-2-32b-base","score":82.39,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"olmo-2-32b-base","score":76.38,"metric":"percent"},{"benchmark":"borda-count-multilingual","model":"olmo-2-32b-base","score":7.1,"metric":"borda_count"},{"benchmark":"hellaswag","model":"mistral-3.2-24b","score":82.59,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-3.2-24b","score":74.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-3.2-24b","score":64.09,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-3.2-24b","score":89.22,"metric":"percent"},{"benchmark":"mgsm","model":"mistral-3.2-24b","score":89.58,"metric":"percent"},{"benchmark":"flores","model":"mistral-3.2-24b","score":82.73,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"mistral-3.2-24b","score":72.81,"metric":"percent"},{"benchmark":"borda-count-multilingual","model":"mistral-3.2-24b","score":4.7,"metric":"borda_count"},{"benchmark":"hellaswag","model":"llama-3.3-70b","score":73.54,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.3-70b","score":78.43,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.3-70b","score":65.68,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.3-70b","score":90.13,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.3-70b","score":91.64,"metric":"percent"},{"benchmark":"flores","model":"llama-3.3-70b","score":88.15,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"llama-3.3-70b","score":82.28,"metric":"percent"},{"benchmark":"borda-count-multilingual","model":"llama-3.3-70b","score":3.3,"metric":"borda_count"},{"benchmark":"hellaswag","model":"gemma-3-27b","score":74.6,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b","score":74.58,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-27b","score":60.21,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-27b","score":90.09,"metric":"percent"},{"benchmark":"mgsm","model":"gemma-3-27b","score":88.44,"metric":"percent"},{"benchmark":"flores","model":"gemma-3-27b","score":88.81,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gemma-3-27b","score":83.65,"metric":"percent"},{"benchmark":"borda-count-multilingual","model":"gemma-3-27b","score":3.7,"metric":"borda_count"},{"benchmark":"hellaswag","model":"qwen3-32b","score":79.51,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-32b","score":78.97,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b","score":70.14,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-32b","score":92.55,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-32b","score":91.69,"metric":"percent"},{"benchmark":"flores","model":"qwen3-32b","score":86.36,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-32b","score":81.69,"metric":"percent"},{"benchmark":"borda-count-multilingual","model":"qwen3-32b","score":2.9,"metric":"borda_count"},{"benchmark":"hellaswag","model":"qwen3-30b-a3b","score":78.96,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b","score":79.54,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b","score":71.98,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-30b-a3b","score":92.33,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-30b-a3b","score":90.53,"metric":"percent"},{"benchmark":"flores","model":"qwen3-30b-a3b","score":86.57,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-30b-a3b","score":81.9,"metric":"percent"},{"benchmark":"borda-count-multilingual","model":"qwen3-30b-a3b","score":2.9,"metric":"borda_count"},{"benchmark":"aime-2025","model":"claude-sonnet-4.5","score":87,"metric":"percent"},{"benchmark":"aime-2025","model":"seed1.8","score":94.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"claude-sonnet-4.5","score":66.7,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-2.5-pro","score":86.7,"metric":"percent"},{"benchmark":"hmmt-2025","model":"seed1.8","score":89.7,"metric":"percent"},{"benchmark":"beyondaime","model":"gpt-5-high","score":74,"metric":"percent"},{"benchmark":"beyondaime","model":"claude-sonnet-4.5","score":62,"metric":"percent"},{"benchmark":"beyondaime","model":"gemini-2.5-pro","score":62,"metric":"percent"},{"benchmark":"beyondaime","model":"gemini-3-pro","score":83,"metric":"percent"},{"benchmark":"beyondaime","model":"seed1.8","score":77,"metric":"percent"},{"benchmark":"amobench","model":"gpt-5-high","score":50,"metric":"percent"},{"benchmark":"amobench","model":"claude-sonnet-4.5","score":32,"metric":"percent"},{"benchmark":"amobench","model":"gemini-2.5-pro","score":38.7,"metric":"percent"},{"benchmark":"amobench","model":"gemini-3-pro","score":64,"metric":"percent"},{"benchmark":"amobench","model":"seed1.8","score":60,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-sonnet-4.5","score":65.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-2.5-pro","score":57.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"seed1.8","score":76.3,"metric":"percent"},{"benchmark":"aethercode","model":"gpt-5-high","score":43.3,"metric":"percent"},{"benchmark":"aethercode","model":"claude-sonnet-4.5","score":18.2,"metric":"percent"},{"benchmark":"aethercode","model":"gemini-2.5-pro","score":32.4,"metric":"percent"},{"benchmark":"aethercode","model":"gemini-3-pro","score":56.7,"metric":"percent"},{"benchmark":"aethercode","model":"seed1.8","score":38.2,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4.5","score":64,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":73.6,"metric":"percent"},{"benchmark":"livecodebench","model":"seed1.8","score":79.5,"metric":"percent"},{"benchmark":"livecodebench-pro","model":"gpt-5-high","score":2114,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"claude-sonnet-4.5","score":1364,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gemini-2.5-pro","score":1765,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"seed1.8","score":1930,"metric":"elo"},{"benchmark":"gpqa-diamond","model":"claude-sonnet-4.5","score":83.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed1.8","score":83.8,"metric":"percent"},{"benchmark":"phybench","model":"gpt-5-high","score":40,"metric":"percent"},{"benchmark":"phybench","model":"claude-sonnet-4.5","score":31,"metric":"percent"},{"benchmark":"phybench","model":"gemini-2.5-pro","score":48,"metric":"percent"},{"benchmark":"phybench","model":"gemini-3-pro","score":59,"metric":"percent"},{"benchmark":"phybench","model":"seed1.8","score":41,"metric":"percent"},{"benchmark":"biobench","model":"gpt-5-high","score":48,"metric":"percent"},{"benchmark":"biobench","model":"claude-sonnet-4.5","score":44.6,"metric":"percent"},{"benchmark":"biobench","model":"gemini-2.5-pro","score":41.5,"metric":"percent"},{"benchmark":"biobench","model":"gemini-3-pro","score":51.9,"metric":"percent"},{"benchmark":"biobench","model":"seed1.8","score":42.3,"metric":"percent"},{"benchmark":"kor-bench","model":"gpt-5-high","score":77.4,"metric":"percent"},{"benchmark":"kor-bench","model":"claude-sonnet-4.5","score":74.5,"metric":"percent"},{"benchmark":"kor-bench","model":"gemini-2.5-pro","score":74.2,"metric":"percent"},{"benchmark":"kor-bench","model":"gemini-3-pro","score":75,"metric":"percent"},{"benchmark":"kor-bench","model":"seed1.8","score":76.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4.5","score":63.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro","score":37,"metric":"percent"},{"benchmark":"arc-agi-1","model":"seed1.8","score":67.9,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"gpt-5-high","score":78.9,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"claude-sonnet-4.5","score":70.2,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"gemini-2.5-pro","score":75.3,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"gemini-3-pro","score":80.6,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"seed1.8","score":80.3,"metric":"percent"},{"benchmark":"mars-bench","model":"gpt-5-high","score":77.2,"metric":"percent"},{"benchmark":"mars-bench","model":"claude-sonnet-4.5","score":72.5,"metric":"percent"},{"benchmark":"mars-bench","model":"gemini-2.5-pro","score":73.6,"metric":"percent"},{"benchmark":"mars-bench","model":"gemini-3-pro","score":80.8,"metric":"percent"},{"benchmark":"mars-bench","model":"seed1.8","score":70.1,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5-high","score":69.6,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-sonnet-4.5","score":57.2,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-2.5-pro","score":55.4,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-3-pro","score":67.4,"metric":"percent"},{"benchmark":"multichallenge","model":"seed1.8","score":66.7,"metric":"percent"},{"benchmark":"collie-hard","model":"gpt-5-high","score":99,"metric":"percent"},{"benchmark":"collie-hard","model":"claude-sonnet-4.5","score":77.6,"metric":"percent"},{"benchmark":"collie-hard","model":"gemini-2.5-pro","score":69.5,"metric":"percent"},{"benchmark":"collie-hard","model":"gemini-3-pro","score":95.5,"metric":"percent"},{"benchmark":"collie-hard","model":"seed1.8","score":72.6,"metric":"percent"},{"benchmark":"eifbench","model":"gpt-5-high","score":66.7,"metric":"percent"},{"benchmark":"eifbench","model":"claude-sonnet-4.5","score":47,"metric":"percent"},{"benchmark":"eifbench","model":"gemini-2.5-pro","score":44.7,"metric":"percent"},{"benchmark":"eifbench","model":"gemini-3-pro","score":50.1,"metric":"percent"},{"benchmark":"eifbench","model":"seed1.8","score":48.6,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-5-high","score":93.8,"metric":"percent"},{"benchmark":"mmlu","model":"claude-sonnet-4.5","score":93.1,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-2.5-pro","score":92.9,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-3-pro","score":93.8,"metric":"percent"},{"benchmark":"mmlu","model":"seed1.8","score":92.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-sonnet-4.5","score":88.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-pro","score":86.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed1.8","score":84.9,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5-high","score":66.8,"metric":"percent"},{"benchmark":"supergpqa","model":"claude-sonnet-4.5","score":66.1,"metric":"percent"},{"benchmark":"supergpqa","model":"gemini-2.5-pro","score":64.9,"metric":"percent"},{"benchmark":"supergpqa","model":"gemini-3-pro","score":75.3,"metric":"percent"},{"benchmark":"supergpqa","model":"seed1.8","score":64.8,"metric":"percent"},{"benchmark":"lpfqa","model":"gpt-5-high","score":54.4,"metric":"percent"},{"benchmark":"lpfqa","model":"claude-sonnet-4.5","score":49.5,"metric":"percent"},{"benchmark":"lpfqa","model":"gemini-2.5-pro","score":47.7,"metric":"percent"},{"benchmark":"lpfqa","model":"gemini-3-pro","score":51.1,"metric":"percent"},{"benchmark":"lpfqa","model":"seed1.8","score":49.1,"metric":"percent"},{"benchmark":"education-bench","model":"gpt-5-high","score":55,"metric":"percent"},{"benchmark":"education-bench","model":"claude-sonnet-4.5","score":53,"metric":"percent"},{"benchmark":"education-bench","model":"gemini-2.5-pro","score":52.4,"metric":"percent"},{"benchmark":"education-bench","model":"gemini-3-pro","score":57,"metric":"percent"},{"benchmark":"education-bench","model":"seed1.8","score":60.8,"metric":"percent"},{"benchmark":"customer-support-qa","model":"gpt-5-high","score":63.4,"metric":"percent"},{"benchmark":"customer-support-qa","model":"claude-sonnet-4.5","score":59.4,"metric":"percent"},{"benchmark":"customer-support-qa","model":"gemini-2.5-pro","score":64.6,"metric":"percent"},{"benchmark":"customer-support-qa","model":"gemini-3-pro","score":65.5,"metric":"percent"},{"benchmark":"customer-support-qa","model":"seed1.8","score":69,"metric":"percent"},{"benchmark":"information-processing","model":"gpt-5-high","score":54.3,"metric":"percent"},{"benchmark":"information-processing","model":"claude-sonnet-4.5","score":55,"metric":"percent"},{"benchmark":"information-processing","model":"gemini-2.5-pro","score":52.4,"metric":"percent"},{"benchmark":"information-processing","model":"gemini-3-pro","score":56.5,"metric":"percent"},{"benchmark":"information-processing","model":"seed1.8","score":53.9,"metric":"percent"},{"benchmark":"intention-recognition","model":"gpt-5-high","score":63.8,"metric":"percent"},{"benchmark":"intention-recognition","model":"claude-sonnet-4.5","score":62.7,"metric":"percent"},{"benchmark":"intention-recognition","model":"gemini-2.5-pro","score":58.3,"metric":"percent"},{"benchmark":"intention-recognition","model":"gemini-3-pro","score":65.3,"metric":"percent"},{"benchmark":"intention-recognition","model":"seed1.8","score":63.2,"metric":"percent"},{"benchmark":"information-extraction","model":"gpt-5-high","score":46.1,"metric":"percent"},{"benchmark":"information-extraction","model":"claude-sonnet-4.5","score":46.9,"metric":"percent"},{"benchmark":"information-extraction","model":"gemini-2.5-pro","score":44.6,"metric":"percent"},{"benchmark":"information-extraction","model":"gemini-3-pro","score":46,"metric":"percent"},{"benchmark":"information-extraction","model":"seed1.8","score":43.7,"metric":"percent"},{"benchmark":"complex-workflow","model":"gpt-5-high","score":53,"metric":"percent"},{"benchmark":"complex-workflow","model":"claude-sonnet-4.5","score":55.4,"metric":"percent"},{"benchmark":"complex-workflow","model":"gemini-2.5-pro","score":54.4,"metric":"percent"},{"benchmark":"complex-workflow","model":"gemini-3-pro","score":58.2,"metric":"percent"},{"benchmark":"complex-workflow","model":"seed1.8","score":54.6,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-high","score":79.8,"metric":"percent"},{"benchmark":"mmmu","model":"claude-sonnet-4.5","score":83.3,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-3-pro","score":87,"metric":"percent"},{"benchmark":"mmmu","model":"seed1.5-vl-thinking","score":77.9,"metric":"percent"},{"benchmark":"mmmu","model":"seed1.8","score":83.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-high","score":68,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-sonnet-4.5","score":76,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed1.5-vl-thinking","score":67.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed1.8","score":73.2,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5-high","score":80.4,"metric":"percent"},{"benchmark":"mathvista","model":"claude-sonnet-4.5","score":80.6,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-3-pro","score":89.8,"metric":"percent"},{"benchmark":"mathvista","model":"seed1.5-vl-thinking","score":85.6,"metric":"percent"},{"benchmark":"mathvista","model":"seed1.8","score":87.7,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-high","score":73.6,"metric":"percent"},{"benchmark":"mathvision","model":"claude-sonnet-4.5","score":77.2,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3-pro","score":86.1,"metric":"percent"},{"benchmark":"mathvision","model":"seed1.5-vl-thinking","score":68.7,"metric":"percent"},{"benchmark":"mathvision","model":"seed1.8","score":81.3,"metric":"percent"},{"benchmark":"dynamath","model":"gpt-5-high","score":52.7,"metric":"percent"},{"benchmark":"dynamath","model":"claude-sonnet-4.5","score":61.5,"metric":"percent"},{"benchmark":"dynamath","model":"gemini-2.5-pro","score":56.3,"metric":"percent"},{"benchmark":"dynamath","model":"gemini-3-pro","score":63.3,"metric":"percent"},{"benchmark":"dynamath","model":"seed1.5-vl-thinking","score":57.1,"metric":"percent"},{"benchmark":"dynamath","model":"seed1.8","score":61.5,"metric":"percent"},{"benchmark":"logicvista","model":"gpt-5-high","score":71.8,"metric":"percent"},{"benchmark":"logicvista","model":"claude-sonnet-4.5","score":70,"metric":"percent"},{"benchmark":"logicvista","model":"gemini-2.5-pro","score":73.8,"metric":"percent"},{"benchmark":"logicvista","model":"gemini-3-pro","score":80.8,"metric":"percent"},{"benchmark":"logicvista","model":"seed1.5-vl-thinking","score":73.4,"metric":"percent"},{"benchmark":"logicvista","model":"seed1.8","score":73.4,"metric":"percent"},{"benchmark":"emma","model":"gpt-5-high","score":53.5,"metric":"percent"},{"benchmark":"emma","model":"claude-sonnet-4.5","score":61.7,"metric":"percent"},{"benchmark":"emma","model":"gemini-2.5-pro","score":59.4,"metric":"percent"},{"benchmark":"emma","model":"gemini-3-pro","score":66.5,"metric":"percent"},{"benchmark":"emma","model":"seed1.5-vl-thinking","score":49.5,"metric":"percent"},{"benchmark":"emma","model":"seed1.8","score":59.5,"metric":"percent"},{"benchmark":"sfe","model":"gpt-5-high","score":50.5,"metric":"percent"},{"benchmark":"sfe","model":"claude-sonnet-4.5","score":46,"metric":"percent"},{"benchmark":"sfe","model":"gemini-2.5-pro","score":47.7,"metric":"percent"},{"benchmark":"sfe","model":"gemini-3-pro","score":61.9,"metric":"percent"},{"benchmark":"sfe","model":"seed1.5-vl-thinking","score":44.4,"metric":"percent"},{"benchmark":"sfe","model":"seed1.8","score":51.2,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5-high","score":4,"metric":"percent"},{"benchmark":"zerobench","model":"claude-sonnet-4.5","score":6,"metric":"percent"},{"benchmark":"zerobench","model":"gemini-3-pro","score":10,"metric":"percent"},{"benchmark":"zerobench","model":"seed1.8","score":11,"metric":"percent"},{"benchmark":"vpct","model":"gpt-5-high","score":41,"metric":"percent"},{"benchmark":"vpct","model":"claude-sonnet-4.5","score":56,"metric":"percent"},{"benchmark":"vpct","model":"gemini-2.5-pro","score":52,"metric":"percent"},{"benchmark":"vpct","model":"gemini-3-pro","score":90,"metric":"percent"},{"benchmark":"vpct","model":"seed1.5-vl-thinking","score":35,"metric":"percent"},{"benchmark":"vpct","model":"seed1.8","score":61,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gpt-5-high","score":30.2,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"claude-sonnet-4.5","score":21.7,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gemini-2.5-pro","score":24.3,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gemini-3-pro","score":50.6,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"seed1.5-vl-thinking","score":26.5,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"seed1.8","score":62,"metric":"percent"},{"benchmark":"vlmsareblind","model":"gpt-5-high","score":80.9,"metric":"percent"},{"benchmark":"vlmsareblind","model":"claude-sonnet-4.5","score":84.2,"metric":"percent"},{"benchmark":"vlmsareblind","model":"gemini-2.5-pro","score":84.3,"metric":"percent"},{"benchmark":"vlmsareblind","model":"gemini-3-pro","score":97.5,"metric":"percent"},{"benchmark":"vlmsareblind","model":"seed1.5-vl-thinking","score":92.1,"metric":"percent"},{"benchmark":"vlmsareblind","model":"seed1.8","score":93,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5-high","score":48.1,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-sonnet-4.5","score":56.1,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-2.5-pro","score":62,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3-pro","score":69.7,"metric":"percent"},{"benchmark":"simplevqa","model":"seed1.8","score":65.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5-high","score":59.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-sonnet-4.5","score":64.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-3-pro","score":69.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"seed1.5-vl-thinking","score":60.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"seed1.8","score":63.9,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-high","score":74.1,"metric":"percent"},{"benchmark":"mmstar","model":"claude-sonnet-4.5","score":77.8,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-3-pro","score":83.1,"metric":"percent"},{"benchmark":"mmstar","model":"seed1.5-vl-thinking","score":77.8,"metric":"percent"},{"benchmark":"mmstar","model":"seed1.8","score":77.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-5-high","score":87.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-sonnet-4.5","score":85.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.5-pro","score":90.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-3-pro","score":93.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"seed1.5-vl-thinking","score":89.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"seed1.8","score":90.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-5-high","score":86.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"claude-sonnet-4.5","score":84.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.5-pro","score":89.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-3-pro","score":91.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"seed1.5-vl-thinking","score":89.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"seed1.8","score":90.6,"metric":"percent"},{"benchmark":"mme-cc","model":"gpt-5-high","score":27.5,"metric":"percent"},{"benchmark":"mme-cc","model":"gemini-2.5-pro","score":42.7,"metric":"percent"},{"benchmark":"mme-cc","model":"gemini-3-pro","score":56.9,"metric":"percent"},{"benchmark":"mme-cc","model":"seed1.5-vl-thinking","score":33.7,"metric":"percent"},{"benchmark":"mme-cc","model":"seed1.8","score":43.4,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-5-high","score":71.8,"metric":"percent"},{"benchmark":"muirbench","model":"claude-sonnet-4.5","score":78.2,"metric":"percent"},{"benchmark":"muirbench","model":"gemini-3-pro","score":78.2,"metric":"percent"},{"benchmark":"muirbench","model":"seed1.5-vl-thinking","score":72.3,"metric":"percent"},{"benchmark":"muirbench","model":"seed1.8","score":78.7,"metric":"percent"},{"benchmark":"mmvp","model":"gpt-5-high","score":74.7,"metric":"percent"},{"benchmark":"mmvp","model":"claude-sonnet-4.5","score":84.3,"metric":"percent"},{"benchmark":"mmvp","model":"gemini-2.5-pro","score":70.7,"metric":"percent"},{"benchmark":"mmvp","model":"gemini-3-pro","score":90,"metric":"percent"},{"benchmark":"mmvp","model":"seed1.5-vl-thinking","score":69.3,"metric":"percent"},{"benchmark":"mmvp","model":"seed1.8","score":91.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5-high","score":36.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-sonnet-4.5","score":3.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"seed1.8","score":73.1,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5-high","score":91,"metric":"percent"},{"benchmark":"countbench","model":"claude-sonnet-4.5","score":91,"metric":"percent"},{"benchmark":"countbench","model":"gemini-3-pro","score":97.3,"metric":"percent"},{"benchmark":"countbench","model":"seed1.5-vl-thinking","score":91.8,"metric":"percent"},{"benchmark":"countbench","model":"seed1.8","score":96.3,"metric":"percent"},{"benchmark":"fsc-147","model":"gpt-5-high","score":22,"metric":"percent"},{"benchmark":"fsc-147","model":"claude-sonnet-4.5","score":28,"metric":"percent"},{"benchmark":"fsc-147","model":"gemini-2.5-pro","score":24.5,"metric":"percent"},{"benchmark":"fsc-147","model":"gemini-3-pro","score":12.1,"metric":"percent"},{"benchmark":"fsc-147","model":"seed1.5-vl-thinking","score":17.9,"metric":"percent"},{"benchmark":"fsc-147","model":"seed1.8","score":33.8,"metric":"percent"},{"benchmark":"point-bench","model":"gpt-5-high","score":41.8,"metric":"percent"},{"benchmark":"point-bench","model":"claude-sonnet-4.5","score":62.7,"metric":"percent"},{"benchmark":"point-bench","model":"gemini-2.5-pro","score":85.5,"metric":"percent"},{"benchmark":"point-bench","model":"gemini-3-pro","score":74.9,"metric":"percent"},{"benchmark":"point-bench","model":"seed1.5-vl-thinking","score":13.6,"metric":"percent"},{"benchmark":"point-bench","model":"seed1.8","score":76.5,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-high","score":63.4,"metric":"percent"},{"benchmark":"blink","model":"claude-sonnet-4.5","score":69.6,"metric":"percent"},{"benchmark":"blink","model":"gemini-3-pro","score":77.1,"metric":"percent"},{"benchmark":"blink","model":"seed1.8","score":74.3,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"gpt-5-high","score":17.2,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"claude-sonnet-4.5","score":22.3,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"gemini-2.5-pro","score":17.6,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"gemini-3-pro","score":25.4,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"seed1.5-vl-thinking","score":11.7,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5-high","score":21.7,"metric":"percent"},{"benchmark":"refspatialbench","model":"claude-sonnet-4.5","score":28.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-2.5-pro","score":33.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-3-pro","score":65.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"seed1.5-vl-thinking","score":58.8,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5-high","score":49.8,"metric":"percent"},{"benchmark":"erqa","model":"claude-sonnet-4.5","score":60,"metric":"percent"},{"benchmark":"erqa","model":"gemini-2.5-pro","score":56,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3-pro","score":70.5,"metric":"percent"},{"benchmark":"erqa","model":"seed1.5-vl-thinking","score":47,"metric":"percent"},{"benchmark":"erqa","model":"seed1.8","score":58.8,"metric":"percent"},{"benchmark":"da-2k","model":"gpt-5-high","score":68.2,"metric":"percent"},{"benchmark":"da-2k","model":"claude-sonnet-4.5","score":78.6,"metric":"percent"},{"benchmark":"da-2k","model":"gemini-2.5-pro","score":76.5,"metric":"percent"},{"benchmark":"da-2k","model":"gemini-3-pro","score":82.1,"metric":"percent"},{"benchmark":"da-2k","model":"seed1.5-vl-thinking","score":85.3,"metric":"percent"},{"benchmark":"da-2k","model":"seed1.8","score":25.8,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-5-high","score":79.3,"metric":"percent"},{"benchmark":"cv-bench","model":"claude-sonnet-4.5","score":84.6,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-2.5-pro","score":85.9,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-3-pro","score":92,"metric":"percent"},{"benchmark":"cv-bench","model":"seed1.5-vl-thinking","score":84.9,"metric":"percent"},{"benchmark":"cv-bench","model":"seed1.8","score":88,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-high","score":86.2,"metric":"percent"},{"benchmark":"ai2d","model":"claude-sonnet-4.5","score":89,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-pro","score":88.4,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-3-pro","score":93.5,"metric":"percent"},{"benchmark":"ai2d","model":"seed1.5-vl-thinking","score":87.3,"metric":"percent"},{"benchmark":"ai2d","model":"seed1.8","score":89.1,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5-high","score":0.145,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"claude-sonnet-4.5","score":0.147,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"seed1.5-vl-thinking","score":0.152,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"seed1.8","score":0.106,"metric":"edit_distance"},{"benchmark":"charxiv-rq","model":"gpt-5-high","score":68.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-sonnet-4.5","score":69.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed1.5-vl-thinking","score":60.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed1.8","score":71.4,"metric":"percent"},{"benchmark":"dude","model":"gpt-5-high","score":54,"metric":"percent"},{"benchmark":"dude","model":"claude-sonnet-4.5","score":67.1,"metric":"percent"},{"benchmark":"dude","model":"gemini-2.5-pro","score":65.3,"metric":"percent"},{"benchmark":"dude","model":"gemini-3-pro","score":70.1,"metric":"percent"},{"benchmark":"dude","model":"seed1.5-vl-thinking","score":67.3,"metric":"percent"},{"benchmark":"dude","model":"seed1.8","score":69.4,"metric":"percent"},{"benchmark":"mmlb-niah-128k","model":"gemini-2.5-pro","score":69.9,"metric":"percent"},{"benchmark":"mmlb-niah-128k","model":"gemini-3-pro","score":70.5,"metric":"percent"},{"benchmark":"mmlb-niah-128k","model":"seed1.5-vl-thinking","score":62.4,"metric":"percent"},{"benchmark":"mmlb-niah-128k","model":"seed1.8","score":72.2,"metric":"percent"},{"benchmark":"mmlb-vrag-128k","model":"gemini-2.5-pro","score":79.6,"metric":"percent"},{"benchmark":"mmlb-vrag-128k","model":"gemini-3-pro","score":88.9,"metric":"percent"},{"benchmark":"mmlb-vrag-128k","model":"seed1.5-vl-thinking","score":75.4,"metric":"percent"},{"benchmark":"mmlb-vrag-128k","model":"seed1.8","score":83.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"gemma-2-9b-it","score":43.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-8b","score":34.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-8b-dpo","score":33.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-8b-sft","score":12.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"magpie-8b","score":49,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"ministral-8b-instruct","score":31.4,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-8b","score":66,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-8b-dpo","score":65.8,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-8b-sft","score":67.9,"metric":"percent"},{"benchmark":"bbh","model":"ministral-8b-instruct","score":56.2,"metric":"percent"},{"benchmark":"drop","model":"gemma-2-9b-it","score":58.8,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-tulu-3-8b","score":62.6,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-tulu-3-8b-dpo","score":62.5,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-tulu-3-8b-sft","score":61.3,"metric":"percent"},{"benchmark":"drop","model":"magpie-8b","score":49.4,"metric":"percent"},{"benchmark":"drop","model":"ministral-8b-instruct","score":56.2,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-9b-it","score":79.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-8b","score":87.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-8b-dpo","score":84.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-8b-sft","score":76.2,"metric":"percent"},{"benchmark":"gsm8k","model":"magpie-8b","score":61.2,"metric":"percent"},{"benchmark":"gsm8k","model":"ministral-8b-instruct","score":80,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2-9b-it","score":71.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-8b","score":83.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-8b-dpo","score":83.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-8b-sft","score":86.2,"metric":"percent"},{"benchmark":"humaneval","model":"magpie-8b","score":75.4,"metric":"percent"},{"benchmark":"humaneval","model":"ministral-8b-instruct","score":91,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-7b-instruct","score":93.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-2-9b-it","score":67,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-8b","score":79.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-8b-dpo","score":78.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-8b-sft","score":81.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"magpie-8b","score":69.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ministral-8b-instruct","score":88.5,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-2-9b-it","score":69.9,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-8b","score":82.4,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-8b-dpo","score":81.1,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-8b-sft","score":72.8,"metric":"percent"},{"benchmark":"ifeval","model":"magpie-8b","score":38.8,"metric":"percent"},{"benchmark":"ifeval","model":"ministral-8b-instruct","score":56.4,"metric":"percent"},{"benchmark":"math","model":"gemma-2-9b-it","score":29.8,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-8b-instruct","score":42.5,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-8b","score":43.7,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-8b-dpo","score":42,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-8b-sft","score":31.5,"metric":"percent"},{"benchmark":"math","model":"magpie-8b","score":5.1,"metric":"percent"},{"benchmark":"math","model":"ministral-8b-instruct","score":40,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-7b-instruct","score":14.8,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-9b-it","score":74.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-8b","score":68.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-8b-dpo","score":68.7,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-8b-sft","score":65.9,"metric":"percent"},{"benchmark":"mmlu","model":"magpie-8b","score":62,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-8b-instruct","score":68.5,"metric":"percent"},{"benchmark":"popqa","model":"gemma-2-9b-it","score":28.3,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-8b","score":29.1,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-8b-dpo","score":29.3,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-8b-sft","score":29.3,"metric":"percent"},{"benchmark":"popqa","model":"magpie-8b","score":22.5,"metric":"percent"},{"benchmark":"popqa","model":"ministral-8b-instruct","score":20.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-2-9b-it","score":61.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-tulu-3-8b","score":55,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-tulu-3-8b-dpo","score":56.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-tulu-3-8b-sft","score":46.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"magpie-8b","score":57,"metric":"percent"},{"benchmark":"truthfulqa","model":"ministral-8b-instruct","score":55.5,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-70b-sft","score":78.9,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-70b-dpo","score":83.3,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-70b","score":83.1,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-70b-instruct","score":85.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-72b-instruct","score":85.5,"metric":"percent"},{"benchmark":"mmlu","model":"hermes-3-llama-3.1-70b","score":80.4,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-nemotron-70b","score":83.8,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-70b-sft","score":48.6,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-70b-dpo","score":46.3,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-70b","score":46.5,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-70b-instruct","score":46.4,"metric":"percent"},{"benchmark":"popqa","model":"qwen2.5-72b-instruct","score":30.6,"metric":"percent"},{"benchmark":"popqa","model":"hermes-3-llama-3.1-70b","score":48.1,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-nemotron-70b","score":36.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-tulu-3-70b-sft","score":55.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-tulu-3-70b-dpo","score":67.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-tulu-3-70b","score":67.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-70b-instruct","score":66.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-72b-instruct","score":69.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"hermes-3-llama-3.1-70b","score":66.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-nemotron-70b","score":62.6,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-70b-sft","score":82.7,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-70b-dpo","score":81.8,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-70b","score":82,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-70b-instruct","score":73.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-72b-instruct","score":67.2,"metric":"percent"},{"benchmark":"bbh","model":"hermes-3-llama-3.1-70b","score":82.1,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-tulu-3-70b-sft","score":77.2,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-tulu-3-70b-dpo","score":74.1,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-tulu-3-70b","score":74.3,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-70b-instruct","score":77,"metric":"percent"},{"benchmark":"drop","model":"qwen2.5-72b-instruct","score":34.2,"metric":"percent"},{"benchmark":"drop","model":"hermes-3-llama-3.1-70b","score":73.2,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-nemotron-70b","score":68.8,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-70b-sft","score":53.7,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-70b-dpo","score":62.3,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-70b","score":63,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-70b-instruct","score":56.4,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-72b-instruct","score":74.3,"metric":"percent"},{"benchmark":"math","model":"hermes-3-llama-3.1-70b","score":41.9,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-nemotron-70b","score":55,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-70b-sft","score":91.1,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-70b-dpo","score":93.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-70b","score":93.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b-instruct","score":93.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-72b-instruct","score":89.5,"metric":"percent"},{"benchmark":"gsm8k","model":"hermes-3-llama-3.1-70b","score":90,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-nemotron-70b","score":84.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-70b-sft","score":92.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-70b-dpo","score":92.4,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-70b","score":92.4,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-70b-instruct","score":93.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-72b-instruct","score":94,"metric":"percent"},{"benchmark":"humaneval","model":"hermes-3-llama-3.1-70b","score":89.6,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-nemotron-70b","score":94.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-70b-sft","score":87.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-70b-dpo","score":88.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-70b","score":88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-70b-instruct","score":89.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-72b-instruct","score":90.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"hermes-3-llama-3.1-70b","score":85.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-nemotron-70b","score":85.5,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-70b-sft","score":82.1,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-70b-dpo","score":82.6,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-70b","score":83.2,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-70b-instruct","score":88,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-72b-instruct","score":87.6,"metric":"percent"},{"benchmark":"ifeval","model":"hermes-3-llama-3.1-70b","score":76,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-nemotron-70b","score":79.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-70b-sft","score":26.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-70b-dpo","score":49.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-70b","score":49.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-70b-instruct","score":33.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen2.5-72b-instruct","score":47.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"hermes-3-llama-3.1-70b","score":28.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-nemotron-70b","score":66.1,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-405b-sft","score":84.4,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-405b-dpo","score":86.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-tulu-3-405b","score":87,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-405b-instruct","score":88,"metric":"percent"},{"benchmark":"mmlu","model":"hermes-3-llama-3.1-405b","score":84.9,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3","score":82.1,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4o-2024-11-24","score":87.9,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-405b-sft","score":55.7,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-405b-dpo","score":55.4,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-tulu-3-405b","score":55.5,"metric":"percent"},{"benchmark":"popqa","model":"llama-3.1-405b-instruct","score":52.9,"metric":"percent"},{"benchmark":"popqa","model":"hermes-3-llama-3.1-405b","score":54.2,"metric":"percent"},{"benchmark":"popqa","model":"deepseek-v3","score":44.9,"metric":"percent"},{"benchmark":"popqa","model":"gpt-4o-2024-11-24","score":53.6,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-405b-sft","score":88,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-405b-dpo","score":88.8,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-tulu-3-405b","score":88.6,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-405b-instruct","score":87.1,"metric":"percent"},{"benchmark":"bbh","model":"hermes-3-llama-3.1-405b","score":87.7,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3","score":89.5,"metric":"percent"},{"benchmark":"bbh","model":"gpt-4o-2024-11-24","score":83.3,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-405b-sft","score":63.4,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-405b-dpo","score":59.9,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-tulu-3-405b","score":67.3,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-405b-instruct","score":66.6,"metric":"percent"},{"benchmark":"math","model":"hermes-3-llama-3.1-405b","score":58.4,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3","score":72.5,"metric":"percent"},{"benchmark":"math","model":"gpt-4o-2024-11-24","score":68.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-405b-sft","score":93.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-405b-dpo","score":94.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-tulu-3-405b","score":95.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-405b-instruct","score":95.4,"metric":"percent"},{"benchmark":"gsm8k","model":"hermes-3-llama-3.1-405b","score":92.7,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3","score":94.1,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4o-2024-11-24","score":91.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-405b-sft","score":95.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-405b-dpo","score":97.2,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-tulu-3-405b","score":95.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-405b-instruct","score":95.9,"metric":"percent"},{"benchmark":"humaneval","model":"hermes-3-llama-3.1-405b","score":92.3,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v3","score":94.6,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-2024-11-24","score":97,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-405b-sft","score":93.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-405b-dpo","score":93.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-tulu-3-405b","score":92.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-405b-instruct","score":90.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"hermes-3-llama-3.1-405b","score":86.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3","score":91.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4o-2024-11-24","score":92.7,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-405b-sft","score":82.4,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-405b-dpo","score":85,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-tulu-3-405b","score":86,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-405b-instruct","score":88.4,"metric":"percent"},{"benchmark":"ifeval","model":"hermes-3-llama-3.1-405b","score":81.9,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v3","score":88,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4o-2024-11-24","score":84.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-405b-sft","score":30.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-405b-dpo","score":49.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-tulu-3-405b","score":51.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-405b-instruct","score":38.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"hermes-3-llama-3.1-405b","score":30.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-v3","score":53.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"gpt-4o-2024-11-24","score":65,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"llama-4-behemoth","score":49.4,"metric":"percent"},{"benchmark":"math500","model":"llama-4-behemoth","score":95,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-behemoth","score":82.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-4-behemoth","score":73.7,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"llama-4-behemoth","score":85.8,"metric":"percent"},{"benchmark":"mmmu","model":"llama-4-behemoth","score":76.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-2.0-pro","score":36,"metric":"percent"},{"benchmark":"math500","model":"gemini-2.0-pro","score":91.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-4.5","score":71.4,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gpt-4.5","score":85.1,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4.5","score":74.4,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-opus-4.5","score":31,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"grok-4","score":38,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5-codex-high","score":36,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-sonnet-4.5","score":33,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-opus-4.1","score":32,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-v3.2-exp","score":29,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-4.5-haiku","score":26,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gemini-2.5-pro","score":25,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"minimax-m2","score":24,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"kimi-k2-0905","score":23,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-oss-120b-high","score":22,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5-minimal","score":18,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"grok-4-fast","score":18,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gemini-2.5-flash","score":16,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-r1-0528","score":15,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"magistral-medium-1.2","score":13,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"qwen3-235b-a22b-2507","score":13,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-oss-20b-high","score":10,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"apriel-1.5-15b-thinker","score":10,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"llama-4-maverick","score":6,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"exaone-4.0-32b","score":4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-codex-high","score":87,"metric":"percent"},{"benchmark":"tau2-telecom","model":"minimax-m2","score":87,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-high","score":85,"metric":"percent"},{"benchmark":"tau2-telecom","model":"grok-4","score":75,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2-0905","score":73,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.1","score":71,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-4.6","score":71,"metric":"percent"},{"benchmark":"tau2-telecom","model":"apriel-1.5-15b-thinker","score":68,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-120b","score":66,"metric":"percent"},{"benchmark":"tau2-telecom","model":"grok-4-fast","score":66,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-20b-high","score":60,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-4.5-haiku","score":55,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-pro","score":54,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-235b-a22b-2507","score":53,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash","score":46,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-r1-0528","score":37,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v3.2-exp","score":34,"metric":"percent"},{"benchmark":"tau2-telecom","model":"llama-nemotron-super-49b-v1.5","score":28,"metric":"percent"},{"benchmark":"tau2-telecom","model":"llama-4-maverick","score":18,"metric":"percent"},{"benchmark":"tau2-telecom","model":"exaone-4.0-32b","score":17,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5-high","score":76,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-4.5-haiku","score":70,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5-codex-high","score":69,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v3.2-exp","score":69,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-235b-a22b-2507","score":67,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-opus-4.1","score":66,"metric":"percent"},{"benchmark":"aa-lcr","model":"grok-4-fast","score":65,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-2.5-flash","score":64,"metric":"percent"},{"benchmark":"aa-lcr","model":"minimax-m2","score":61,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-r1-0528","score":55,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-4.6","score":54,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2-0905","score":52,"metric":"percent"},{"benchmark":"aa-lcr","model":"magistral-medium-1.2","score":51,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-120b-high","score":51,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-20b-high","score":34,"metric":"percent"},{"benchmark":"metr","model":"claude-opus-4.5","score":4.82,"metric":"hours"},{"benchmark":"metr","model":"gpt-5.1-codex-max","score":2.88,"metric":"hours"},{"benchmark":"metr","model":"gpt-5","score":2.3,"metric":"hours"},{"benchmark":"metr","model":"claude-sonnet-4.5","score":2.03,"metric":"hours"},{"benchmark":"metr","model":"claude-opus-4.1","score":1.9,"metric":"hours"},{"benchmark":"metr","model":"grok-4","score":1.82,"metric":"hours"},{"benchmark":"metr","model":"o3","score":1.57,"metric":"hours"},{"benchmark":"metr","model":"claude-opus-4","score":1.43,"metric":"hours"},{"benchmark":"metr","model":"o4-mini","score":1.32,"metric":"hours"},{"benchmark":"metr","model":"claude-sonnet-4","score":1.25,"metric":"hours"},{"benchmark":"metr","model":"claude-3.7-sonnet","score":0.93,"metric":"hours"},{"benchmark":"metr","model":"kimi-k2-thinking","score":0.97,"metric":"hours"},{"benchmark":"metr","model":"gpt-oss-120b","score":0.75,"metric":"hours"},{"benchmark":"metr","model":"gemini-2.5-pro-preview","score":0.67,"metric":"hours"},{"benchmark":"metr","model":"deepseek-r1-0528","score":0.53,"metric":"hours"},{"benchmark":"metr","model":"o1","score":0.68,"metric":"hours"},{"benchmark":"metr","model":"gpt-2","score":0,"metric":"hours"},{"benchmark":"metr","model":"gpt-3","score":0,"metric":"hours"},{"benchmark":"metr","model":"gpt-3.5","score":0.02,"metric":"hours"},{"benchmark":"metr","model":"gpt-4","score":0.08,"metric":"hours"},{"benchmark":"metr","model":"gpt-4-1106-preview","score":0.15,"metric":"hours"},{"benchmark":"metr","model":"deepseek-v3-0324","score":0.38,"metric":"hours"},{"benchmark":"metr","model":"deepseek-r1","score":0.45,"metric":"hours"},{"benchmark":"metr","model":"deepseek-v3","score":0.3,"metric":"hours"},{"benchmark":"metr","model":"claude-3.5-sonnet-20241022","score":0.5,"metric":"hours"},{"benchmark":"metr","model":"o1-preview","score":0.37,"metric":"hours"},{"benchmark":"metr","model":"qwen-2.5-72b","score":0.08,"metric":"hours"},{"benchmark":"metr","model":"qwen2-72b","score":0.03,"metric":"hours"},{"benchmark":"metr","model":"claude-3.5-sonnet-20240620","score":0.32,"metric":"hours"},{"benchmark":"metr","model":"gpt-4o","score":0.15,"metric":"hours"},{"benchmark":"metr","model":"gpt-4-turbo","score":0.12,"metric":"hours"},{"benchmark":"metr","model":"claude-3-opus","score":0.1,"metric":"hours"},{"benchmark":"metr","model":"gpt-4-0125-preview","score":0.08,"metric":"hours"},{"benchmark":"hle","model":"gpt-4-turbo","score":3.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4-turbo","score":69,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-4-turbo","score":48,"metric":"percent"},{"benchmark":"scicode","model":"gpt-4-turbo","score":32,"metric":"percent"},{"benchmark":"hle","model":"gemini-3-pro-preview","score":37.2,"metric":"percent"},{"benchmark":"hle","model":"gemini-3-flash","score":34.7,"metric":"percent"},{"benchmark":"hle","model":"kat-coder-pro-v1","score":33.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.2-high","score":31.4,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.5","score":28.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5-codex-high","score":23.4,"metric":"percent"},{"benchmark":"hle","model":"mimo-v2-flash","score":21.1,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-120b-high","score":18.5,"metric":"percent"},{"benchmark":"hle","model":"grok-4.1-fast","score":17.6,"metric":"percent"},{"benchmark":"hle","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":10.2,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-20b-high","score":9.8,"metric":"percent"},{"benchmark":"hle","model":"k2-high-70b","score":9.8,"metric":"percent"},{"benchmark":"hle","model":"apriel-1.5-15b-thinker","score":9.8,"metric":"percent"},{"benchmark":"hle","model":"nova-pro","score":8.9,"metric":"percent"},{"benchmark":"hle","model":"nova-lite","score":8.6,"metric":"percent"},{"benchmark":"hle","model":"olmo-3-think-32b","score":5.9,"metric":"percent"},{"benchmark":"hle","model":"mistral-large-3","score":4.1,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3-flash","score":71,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-3-flash","score":78.3,"metric":"percent"},{"benchmark":"spatialviz","model":"gemini-3-flash","score":65.3,"metric":"percent"},{"benchmark":"intphys-2","model":"gemini-3-flash","score":63.4,"metric":"percent"},{"benchmark":"enigmaval","model":"gemini-3-flash","score":15.9,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3-pro","score":70.2,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-3-pro","score":77.3,"metric":"percent"},{"benchmark":"spatialviz","model":"gemini-3-pro","score":63.2,"metric":"percent"},{"benchmark":"intphys-2","model":"gemini-3-pro","score":56.9,"metric":"percent"},{"benchmark":"enigmaval","model":"gemini-3-pro","score":17.8,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.2","score":60.7,"metric":"percent"},{"benchmark":"mindcube","model":"gpt-5.2","score":61.7,"metric":"percent"},{"benchmark":"spatialviz","model":"gpt-5.2","score":65.8,"metric":"percent"},{"benchmark":"intphys-2","model":"gpt-5.2","score":58.3,"metric":"percent"},{"benchmark":"enigmaval","model":"gpt-5.2","score":14.5,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5-mini","score":56.5,"metric":"percent"},{"benchmark":"mindcube","model":"gpt-5-mini","score":61.1,"metric":"percent"},{"benchmark":"spatialviz","model":"gpt-5-mini","score":52.5,"metric":"percent"},{"benchmark":"intphys-2","model":"gpt-5-mini","score":59.2,"metric":"percent"},{"benchmark":"enigmaval","model":"gpt-5-mini","score":8.2,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.1","score":59.8,"metric":"percent"},{"benchmark":"mindcube","model":"gpt-5.1","score":62,"metric":"percent"},{"benchmark":"spatialviz","model":"gpt-5.1","score":51.3,"metric":"percent"},{"benchmark":"intphys-2","model":"gpt-5.1","score":52,"metric":"percent"},{"benchmark":"enigmaval","model":"gpt-5.1","score":11.7,"metric":"percent"},{"benchmark":"erqa","model":"gemini-2.5-pro","score":60.8,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-2.5-pro","score":59.6,"metric":"percent"},{"benchmark":"spatialviz","model":"gemini-2.5-pro","score":46.6,"metric":"percent"},{"benchmark":"intphys-2","model":"gemini-2.5-pro","score":56,"metric":"percent"},{"benchmark":"enigmaval","model":"gemini-2.5-pro","score":5.6,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-4.5","score":54,"metric":"percent"},{"benchmark":"mindcube","model":"claude-opus-4.5","score":61.2,"metric":"percent"},{"benchmark":"spatialviz","model":"claude-opus-4.5","score":43,"metric":"percent"},{"benchmark":"intphys-2","model":"claude-opus-4.5","score":56.3,"metric":"percent"},{"benchmark":"enigmaval","model":"claude-opus-4.5","score":12.4,"metric":"percent"},{"benchmark":"erqa","model":"claude-sonnet-4.5","score":50.3,"metric":"percent"},{"benchmark":"mindcube","model":"claude-sonnet-4.5","score":58.3,"metric":"percent"},{"benchmark":"spatialviz","model":"claude-sonnet-4.5","score":41.6,"metric":"percent"},{"benchmark":"intphys-2","model":"claude-sonnet-4.5","score":56.3,"metric":"percent"},{"benchmark":"enigmaval","model":"claude-sonnet-4.5","score":6,"metric":"percent"},{"benchmark":"erqa","model":"grok-4","score":50.1,"metric":"percent"},{"benchmark":"mindcube","model":"grok-4","score":64.7,"metric":"percent"},{"benchmark":"spatialviz","model":"grok-4","score":34.8,"metric":"percent"},{"benchmark":"intphys-2","model":"grok-4","score":54.9,"metric":"percent"},{"benchmark":"enigmaval","model":"grok-4","score":7.8,"metric":"percent"},{"benchmark":"erqa","model":"gemini-2.5-flash","score":53.7,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-2.5-flash","score":53,"metric":"percent"},{"benchmark":"spatialviz","model":"gemini-2.5-flash","score":38.2,"metric":"percent"},{"benchmark":"intphys-2","model":"gemini-2.5-flash","score":58,"metric":"percent"},{"benchmark":"enigmaval","model":"gemini-2.5-flash","score":2.7,"metric":"percent"},{"benchmark":"erqa","model":"grok-4.1-fast","score":46.3,"metric":"percent"},{"benchmark":"mindcube","model":"grok-4.1-fast","score":52.7,"metric":"percent"},{"benchmark":"spatialviz","model":"grok-4.1-fast","score":38.5,"metric":"percent"},{"benchmark":"intphys-2","model":"grok-4.1-fast","score":55,"metric":"percent"},{"benchmark":"enigmaval","model":"grok-4.1-fast","score":5.2,"metric":"percent"},{"benchmark":"erqa","model":"gemini-2.5-flash-lite","score":51,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-2.5-flash-lite","score":49.2,"metric":"percent"},{"benchmark":"spatialviz","model":"gemini-2.5-flash-lite","score":35.2,"metric":"percent"},{"benchmark":"intphys-2","model":"gemini-2.5-flash-lite","score":54.1,"metric":"percent"},{"benchmark":"enigmaval","model":"gemini-2.5-flash-lite","score":0.8,"metric":"percent"},{"benchmark":"erqa","model":"claude-4.5-haiku","score":44.6,"metric":"percent"},{"benchmark":"mindcube","model":"claude-4.5-haiku","score":50.4,"metric":"percent"},{"benchmark":"spatialviz","model":"claude-4.5-haiku","score":38.4,"metric":"percent"},{"benchmark":"intphys-2","model":"claude-4.5-haiku","score":51.9,"metric":"percent"},{"benchmark":"enigmaval","model":"claude-4.5-haiku","score":2.3,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5-nano","score":41.8,"metric":"percent"},{"benchmark":"mindcube","model":"gpt-5-nano","score":40.3,"metric":"percent"},{"benchmark":"spatialviz","model":"gpt-5-nano","score":35.7,"metric":"percent"},{"benchmark":"intphys-2","model":"gpt-5-nano","score":51,"metric":"percent"},{"benchmark":"enigmaval","model":"gpt-5-nano","score":2.9,"metric":"percent"},{"benchmark":"erqa","model":"gpt-4o","score":47,"metric":"percent"},{"benchmark":"mindcube","model":"gpt-4o","score":38,"metric":"percent"},{"benchmark":"spatialviz","model":"gpt-4o","score":31.1,"metric":"percent"},{"benchmark":"intphys-2","model":"gpt-4o","score":53,"metric":"percent"},{"benchmark":"enigmaval","model":"gpt-4o","score":0.8,"metric":"percent"},{"benchmark":"swe-bench","model":"gemini-3-pro","score":74.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-3-pro","score":53.4,"metric":"percent"},{"benchmark":"textquests","model":"gemini-3-pro","score":41,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.2","score":29.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2","score":43.3,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-5.2","score":71.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5.2","score":47.7,"metric":"percent"},{"benchmark":"textquests","model":"gpt-5.2","score":37,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.5","score":25.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.5","score":30.6,"metric":"percent"},{"benchmark":"swe-bench","model":"claude-opus-4.5","score":74.4,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4.5","score":52.3,"metric":"percent"},{"benchmark":"textquests","model":"claude-opus-4.5","score":38.7,"metric":"percent"},{"benchmark":"hle","model":"gemini-3-flash","score":36.6,"metric":"percent"},{"benchmark":"swe-bench","model":"gemini-3-flash","score":58.7,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-3-flash","score":40.1,"metric":"percent"},{"benchmark":"textquests","model":"gemini-3-flash","score":36.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.1","score":27.2,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-5.1","score":66.6,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5.1","score":42.1,"metric":"percent"},{"benchmark":"textquests","model":"gpt-5.1","score":34.2,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4.5","score":13.7,"metric":"avg@3"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4.5","score":13.6,"metric":"percent"},{"benchmark":"swe-bench","model":"claude-sonnet-4.5","score":70,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-sonnet-4.5","score":42.5,"metric":"percent"},{"benchmark":"textquests","model":"claude-sonnet-4.5","score":31,"metric":"percent"},{"benchmark":"hle","model":"grok-4","score":24.5,"metric":"percent"},{"benchmark":"swe-bench","model":"grok-4","score":48.4,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-4","score":33,"metric":"percent"},{"benchmark":"textquests","model":"grok-4","score":27.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v3.2","score":5,"metric":"percent"},{"benchmark":"swe-bench","model":"deepseek-v3.2","score":60,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.2","score":29.5,"metric":"percent"},{"benchmark":"textquests","model":"deepseek-v3.2","score":21.2,"metric":"percent"},{"benchmark":"hle","model":"kimi-k2","score":21.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k2","score":5,"metric":"percent"},{"benchmark":"swe-bench","model":"kimi-k2","score":59,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2","score":31.8,"metric":"percent"},{"benchmark":"textquests","model":"kimi-k2","score":18.3,"metric":"percent"},{"benchmark":"hle","model":"gpt-5-mini","score":19.4,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-5-mini","score":60.6,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5-mini","score":22.2,"metric":"percent"},{"benchmark":"textquests","model":"gpt-5-mini","score":17.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro","score":4,"metric":"percent"},{"benchmark":"swe-bench","model":"gemini-2.5-pro","score":47,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-pro","score":26.1,"metric":"percent"},{"benchmark":"textquests","model":"gemini-2.5-pro","score":23.2,"metric":"percent"},{"benchmark":"hle","model":"claude-4.5-haiku","score":9.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-haiku","score":4,"metric":"percent"},{"benchmark":"swe-bench","model":"claude-4.5-haiku","score":61.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-4.5-haiku","score":29.8,"metric":"percent"},{"benchmark":"textquests","model":"claude-4.5-haiku","score":15.1,"metric":"percent"},{"benchmark":"hle","model":"grok-4.1-fast","score":18.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.1-fast","score":6.7,"metric":"percent"},{"benchmark":"swe-bench","model":"grok-4.1-fast","score":42,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-4.1-fast","score":33,"metric":"percent"},{"benchmark":"textquests","model":"grok-4.1-fast","score":16.4,"metric":"percent"},{"benchmark":"hle","model":"qwen3-max","score":4.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"qwen3-max","score":4.2,"metric":"percent"},{"benchmark":"swe-bench","model":"qwen3-max","score":34.6,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-max","score":23.1,"metric":"percent"},{"benchmark":"textquests","model":"qwen3-max","score":12.4,"metric":"percent"},{"benchmark":"hle","model":"gemini-2.5-flash","score":12.1,"metric":"percent"},{"benchmark":"swe-bench","model":"gemini-2.5-flash","score":32,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-flash","score":17.1,"metric":"percent"},{"benchmark":"textquests","model":"gemini-2.5-flash","score":14.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5-nano","score":8.2,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-nano","score":2.6,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-5-nano","score":25.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5-nano","score":9.1,"metric":"percent"},{"benchmark":"textquests","model":"gpt-5-nano","score":1.2,"metric":"percent"},{"benchmark":"hle","model":"gpt-4o","score":2.7,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-4o","score":21.6,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-4o","score":7.8,"metric":"percent"},{"benchmark":"textquests","model":"gpt-4o","score":13.1,"metric":"percent"},{"benchmark":"hle","model":"gemini-2.5-flash-lite","score":6.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-lite","score":0,"metric":"percent"},{"benchmark":"swe-bench","model":"gemini-2.5-flash-lite","score":22,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-flash-lite","score":3.5,"metric":"percent"},{"benchmark":"textquests","model":"gemini-2.5-flash-lite","score":11.7,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-2.5-flash-lite","score":93.6,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gemini-2.5-flash-lite","score":83.4,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.5-flash-lite","score":46,"metric":"percent"},{"benchmark":"machiavelli","model":"gemini-2.5-flash-lite","score":71.8,"metric":"percent"},{"benchmark":"textquests-harm","model":"gemini-2.5-flash-lite","score":22.8,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-2.5-flash","score":91.7,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gemini-2.5-flash","score":80,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.5-flash","score":49.1,"metric":"percent"},{"benchmark":"machiavelli","model":"gemini-2.5-flash","score":57.7,"metric":"percent"},{"benchmark":"textquests-harm","model":"gemini-2.5-flash","score":11.7,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-2.5-pro","score":90.6,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gemini-2.5-pro","score":72,"metric":"percent"},{"benchmark":"mask","model":"gemini-2.5-pro","score":55.7,"metric":"percent"},{"benchmark":"machiavelli","model":"gemini-2.5-pro","score":62.8,"metric":"percent"},{"benchmark":"textquests-harm","model":"gemini-2.5-pro","score":15.9,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"deepseek-v3.2","score":89,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"deepseek-v3.2","score":58.8,"metric":"percent"},{"benchmark":"mask","model":"deepseek-v3.2","score":53,"metric":"percent"},{"benchmark":"machiavelli","model":"deepseek-v3.2","score":57.1,"metric":"percent"},{"benchmark":"textquests-harm","model":"deepseek-v3.2","score":21.6,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"grok-4.1-fast","score":77.5,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"grok-4.1-fast","score":72.1,"metric":"percent"},{"benchmark":"mask","model":"grok-4.1-fast","score":29,"metric":"percent"},{"benchmark":"machiavelli","model":"grok-4.1-fast","score":52.6,"metric":"percent"},{"benchmark":"textquests-harm","model":"grok-4.1-fast","score":9.1,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gpt-5-nano","score":76.1,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gpt-5-nano","score":80,"metric":"percent"},{"benchmark":"mask","model":"gpt-5-nano","score":87.7,"metric":"percent"},{"benchmark":"machiavelli","model":"gpt-5-nano","score":54.2,"metric":"percent"},{"benchmark":"textquests-harm","model":"gpt-5-nano","score":18.2,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-3-flash","score":70.9,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gemini-3-flash","score":55.1,"metric":"percent"},{"benchmark":"mask","model":"gemini-3-flash","score":38.3,"metric":"percent"},{"benchmark":"machiavelli","model":"gemini-3-flash","score":62.4,"metric":"percent"},{"benchmark":"textquests-harm","model":"gemini-3-flash","score":17.8,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"grok-4","score":56.4,"metric":"percent"},{"benchmark":"mask","model":"grok-4","score":58.3,"metric":"percent"},{"benchmark":"machiavelli","model":"grok-4","score":58.6,"metric":"percent"},{"benchmark":"textquests-harm","model":"grok-4","score":24.3,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gemini-3-pro","score":60.7,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gemini-3-pro","score":57.2,"metric":"percent"},{"benchmark":"mask","model":"gemini-3-pro","score":42,"metric":"percent"},{"benchmark":"machiavelli","model":"gemini-3-pro","score":62.8,"metric":"percent"},{"benchmark":"textquests-harm","model":"gemini-3-pro","score":21.4,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gpt-5.1","score":57.8,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gpt-5.1","score":47.8,"metric":"percent"},{"benchmark":"mask","model":"gpt-5.1","score":88,"metric":"percent"},{"benchmark":"machiavelli","model":"gpt-5.1","score":57.9,"metric":"percent"},{"benchmark":"textquests-harm","model":"gpt-5.1","score":16.7,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gpt-5-mini","score":54.9,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gpt-5-mini","score":65,"metric":"percent"},{"benchmark":"mask","model":"gpt-5-mini","score":82.6,"metric":"percent"},{"benchmark":"machiavelli","model":"gpt-5-mini","score":56.1,"metric":"percent"},{"benchmark":"textquests-harm","model":"gpt-5-mini","score":17.5,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-4.5-haiku","score":51.6,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"claude-4.5-haiku","score":60.5,"metric":"percent"},{"benchmark":"mask","model":"claude-4.5-haiku","score":94.5,"metric":"percent"},{"benchmark":"machiavelli","model":"claude-4.5-haiku","score":52.2,"metric":"percent"},{"benchmark":"textquests-harm","model":"claude-4.5-haiku","score":16.6,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"gpt-5.2","score":44.9,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"gpt-5.2","score":43.7,"metric":"percent"},{"benchmark":"mask","model":"gpt-5.2","score":87.1,"metric":"percent"},{"benchmark":"machiavelli","model":"gpt-5.2","score":55.4,"metric":"percent"},{"benchmark":"textquests-harm","model":"gpt-5.2","score":20.5,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-sonnet-4.5","score":40,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"claude-sonnet-4.5","score":64.1,"metric":"percent"},{"benchmark":"mask","model":"claude-sonnet-4.5","score":96.1,"metric":"percent"},{"benchmark":"machiavelli","model":"claude-sonnet-4.5","score":53.7,"metric":"percent"},{"benchmark":"textquests-harm","model":"claude-sonnet-4.5","score":17.1,"metric":"percent"},{"benchmark":"art-agent-red-teaming","model":"claude-opus-4.5","score":33.6,"metric":"percent"},{"benchmark":"hle-overconfidence","model":"claude-opus-4.5","score":56.9,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4.5","score":94.1,"metric":"percent"},{"benchmark":"machiavelli","model":"claude-opus-4.5","score":53.3,"metric":"percent"},{"benchmark":"textquests-harm","model":"claude-opus-4.5","score":20.3,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.7","score":95.7,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.7","score":84.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.7","score":85.7,"metric":"percent"},{"benchmark":"hle","model":"glm-4.7","score":24.8,"metric":"avg@3"},{"benchmark":"swe-bench-verified","model":"glm-4.7","score":73.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-4.7","score":41,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-4.7","score":52,"metric":"percent"},{"benchmark":"hle-with-tools","model":"glm-4.7","score":42.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"glm-4.6","score":30.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v3.2","score":40.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-sonnet-4.5","score":32,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.1-high","score":42.7,"metric":"avg@3"},{"benchmark":"browsecomp-with-content-manager","model":"glm-4.7","score":67.5,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"glm-4.6","score":57.5,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"deepseek-v3.2","score":67.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.7","score":84.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.6","score":83.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.1-high","score":87,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.1-high","score":88.1,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.1-high","score":25.7,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"kimi-k2-thinking","score":44.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemini-3-pro","score":45.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5-high","score":35.2,"metric":"avg@3"},{"benchmark":"aime-2025","model":"gpt-5.1-high","score":94,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"glm-4.7","score":97.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"glm-4.6","score":89.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"kimi-k2-thinking","score":89.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"deepseek-v3.2","score":92.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemini-3-pro","score":97.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"claude-sonnet-4.5","score":79.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5-high","score":88.3,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5.1-high","score":96.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-4.7","score":93.5,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-4.6","score":87.7,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"kimi-k2-thinking","score":89.2,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"deepseek-v3.2","score":90.2,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gemini-3-pro","score":93.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"claude-sonnet-4.5","score":81.7,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5-high","score":89.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"glm-4.7","score":82,"metric":"percent"},{"benchmark":"imo-answerbench","model":"glm-4.6","score":73.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.1-high","score":87,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.1-high","score":76.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-4.7","score":66.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-sonnet-4.5","score":68,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"glm-4.7","score":33.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"kimi-k2-thinking","score":30.6,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-v3.2","score":35.4,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gemini-3-pro","score":39,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-sonnet-4.5","score":33.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5.1-high","score":43,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v3.2","score":46.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1-high","score":47.6,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.1-high","score":50.8,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"kimi-k2-thinking","score":60.2,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"gemini-3-pro","score":59.2,"metric":"percent"},{"benchmark":"kmmlu","model":"ax-k1","score":73,"metric":"percent"},{"benchmark":"kmmlu","model":"deepseek-v3.1","score":78.7,"metric":"percent"},{"benchmark":"kmmlu","model":"glm-4.6","score":77.7,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"ax-k1","score":68.3,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"deepseek-v3.1","score":75.9,"metric":"percent"},{"benchmark":"kmmlu-redux","model":"glm-4.6","score":73.4,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"ax-k1","score":60.3,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"deepseek-v3.1","score":67.9,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"glm-4.6","score":68.2,"metric":"percent"},{"benchmark":"click","model":"ax-k1","score":77.2,"metric":"percent"},{"benchmark":"click","model":"deepseek-v3.1","score":80.9,"metric":"percent"},{"benchmark":"click","model":"glm-4.6","score":77.9,"metric":"percent"},{"benchmark":"ifbench","model":"ax-k1","score":44.3,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v3.1","score":37.8,"metric":"percent"},{"benchmark":"ifbench","model":"glm-4.6","score":36.7,"metric":"percent"},{"benchmark":"ifeval","model":"ax-k1","score":78.6,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v3.1","score":82.7,"metric":"percent"},{"benchmark":"ifeval","model":"glm-4.6","score":87.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ax-k1","score":79.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3.1","score":87.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"glm-4.6","score":89,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ax-k1","score":75.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3.1","score":86.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"glm-4.6","score":92.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ax-k1","score":85.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3.1","score":92.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"glm-4.6","score":94.2,"metric":"percent"},{"benchmark":"mmlu","model":"solar-pro-preview","score":79.14,"metric":"percent"},{"benchmark":"mmlu","model":"phi-3-medium-4k-instruct","score":78.02,"metric":"percent"},{"benchmark":"mmlu","model":"phi-3.5-moe-instruct","score":78.66,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-27b-it","score":76.13,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-8b-instruct","score":68.25,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-70b-instruct","score":82.09,"metric":"percent"},{"benchmark":"mmlu-pro","model":"solar-pro-preview","score":52.11,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3-medium-4k-instruct","score":47.51,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3.5-moe-instruct","score":46.99,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-27b-it","score":45.68,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b-instruct","score":37.88,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-70b-instruct","score":53.01,"metric":"percent"},{"benchmark":"ifeval","model":"solar-pro-preview","score":84.37,"metric":"percent"},{"benchmark":"ifeval","model":"phi-3-medium-4k-instruct","score":64.37,"metric":"percent"},{"benchmark":"ifeval","model":"phi-3.5-moe-instruct","score":69.15,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-2-27b-it","score":75.36,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-8b-instruct","score":77.4,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-70b-instruct","score":84.13,"metric":"percent"},{"benchmark":"arc-challenge","model":"solar-pro-preview","score":68.86,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-3-medium-4k-instruct","score":66.55,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-3.5-moe-instruct","score":68.34,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2-27b-it","score":74.06,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-8b-instruct","score":60.24,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-70b-instruct","score":70.39,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"solar-pro-preview","score":36.38,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"phi-3-medium-4k-instruct","score":35.78,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"phi-3.5-moe-instruct","score":34.38,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-2-27b-it","score":36.38,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-8b-instruct","score":35.26,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-70b-instruct","score":41.06,"metric":"percent"},{"benchmark":"hellaswag","model":"solar-pro-preview","score":86.36,"metric":"percent"},{"benchmark":"hellaswag","model":"phi-3-medium-4k-instruct","score":85.68,"metric":"percent"},{"benchmark":"hellaswag","model":"phi-3.5-moe-instruct","score":85.97,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2-27b-it","score":86.02,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-8b-instruct","score":80.08,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-70b-instruct","score":86.42,"metric":"percent"},{"benchmark":"eqbench","model":"solar-pro-preview","score":77.91,"metric":"percent"},{"benchmark":"eqbench","model":"phi-3-medium-4k-instruct","score":76.78,"metric":"percent"},{"benchmark":"eqbench","model":"phi-3.5-moe-instruct","score":77.22,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-2-27b-it","score":80.32,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.1-8b-instruct","score":65.8,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.1-70b-instruct","score":82.52,"metric":"percent"},{"benchmark":"bbh","model":"solar-pro-preview","score":67.31,"metric":"percent"},{"benchmark":"bbh","model":"phi-3-medium-4k-instruct","score":63.09,"metric":"percent"},{"benchmark":"bbh","model":"phi-3.5-moe-instruct","score":62.58,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-27b-it","score":64.88,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-8b-instruct","score":51.06,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-70b-instruct","score":69.54,"metric":"percent"},{"benchmark":"musr","model":"solar-pro-preview","score":45.85,"metric":"percent"},{"benchmark":"musr","model":"phi-3-medium-4k-instruct","score":42.28,"metric":"percent"},{"benchmark":"musr","model":"phi-3.5-moe-instruct","score":46.79,"metric":"percent"},{"benchmark":"musr","model":"gemma-2-27b-it","score":45.67,"metric":"percent"},{"benchmark":"musr","model":"llama-3.1-8b-instruct","score":29.68,"metric":"percent"},{"benchmark":"musr","model":"llama-3.1-70b-instruct","score":47.22,"metric":"percent"},{"benchmark":"gsm8k","model":"solar-pro-preview","score":89.69,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3-medium-4k-instruct","score":84.76,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3.5-moe-instruct","score":82.26,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-27b-it","score":62.85,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b-instruct","score":75.97,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b-instruct","score":92.12,"metric":"percent"},{"benchmark":"mbpp","model":"solar-pro-preview","score":61.59,"metric":"percent"},{"benchmark":"mbpp","model":"phi-3-medium-4k-instruct","score":60.27,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-27b-it","score":63.08,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-8b-instruct","score":52.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-70b-instruct","score":65.51,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"glm-4.7","score":66.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m2.1","score":74,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"minimax-m2.1","score":49.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"minimax-m2.1","score":72.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"minimax-m2.1","score":47.9,"metric":"percent"},{"benchmark":"vibe-average","model":"minimax-m2.1","score":88.6,"metric":"percent"},{"benchmark":"vibe-web","model":"minimax-m2.1","score":91.5,"metric":"percent"},{"benchmark":"vibe-simulation","model":"minimax-m2.1","score":87.1,"metric":"percent"},{"benchmark":"vibe-android","model":"minimax-m2.1","score":89.7,"metric":"percent"},{"benchmark":"vibe-ios","model":"minimax-m2.1","score":88,"metric":"percent"},{"benchmark":"vibe-backend","model":"minimax-m2.1","score":86.7,"metric":"percent"},{"benchmark":"vibe-average","model":"minimax-m2","score":67.5,"metric":"percent"},{"benchmark":"vibe-average","model":"claude-sonnet-4.5","score":85.2,"metric":"percent"},{"benchmark":"vibe-average","model":"gemini-3-pro","score":82.4,"metric":"percent"},{"benchmark":"vibe-web","model":"minimax-m2","score":80.4,"metric":"percent"},{"benchmark":"vibe-web","model":"claude-sonnet-4.5","score":87.3,"metric":"percent"},{"benchmark":"vibe-web","model":"gemini-3-pro","score":89.5,"metric":"percent"},{"benchmark":"vibe-simulation","model":"minimax-m2","score":77,"metric":"percent"},{"benchmark":"vibe-simulation","model":"claude-sonnet-4.5","score":79.1,"metric":"percent"},{"benchmark":"vibe-simulation","model":"gemini-3-pro","score":89.2,"metric":"percent"},{"benchmark":"vibe-android","model":"minimax-m2","score":69.2,"metric":"percent"},{"benchmark":"vibe-android","model":"claude-sonnet-4.5","score":87.5,"metric":"percent"},{"benchmark":"vibe-android","model":"gemini-3-pro","score":78.7,"metric":"percent"},{"benchmark":"vibe-ios","model":"minimax-m2","score":39.5,"metric":"percent"},{"benchmark":"vibe-ios","model":"claude-sonnet-4.5","score":81.2,"metric":"percent"},{"benchmark":"vibe-ios","model":"gemini-3-pro","score":75.8,"metric":"percent"},{"benchmark":"vibe-backend","model":"minimax-m2","score":67.3,"metric":"percent"},{"benchmark":"vibe-backend","model":"claude-sonnet-4.5","score":90.8,"metric":"percent"},{"benchmark":"vibe-backend","model":"gemini-3-pro","score":78.7,"metric":"percent"},{"benchmark":"zeroscrolls-spacedigest","model":"flan-ul2","score":36,"metric":"es"},{"benchmark":"zeroscrolls-spacedigest","model":"claude-v1.3","score":61.6,"metric":"es"},{"benchmark":"zeroscrolls-spacedigest","model":"gpt-4","score":62.8,"metric":"es"},{"benchmark":"zeroscrolls-spacedigest","model":"t0pp","score":15.2,"metric":"es"},{"benchmark":"zeroscrolls-spacedigest","model":"flan-t5","score":48.7,"metric":"es"},{"benchmark":"zeroscrolls-spacedigest","model":"davinci-003","score":31.3,"metric":"es"},{"benchmark":"zeroscrolls-squality","model":"t0pp","score":3.9,"metric":"rouge_gm"},{"benchmark":"zeroscrolls-squality","model":"flan-t5","score":8,"metric":"rouge_gm"},{"benchmark":"zeroscrolls-squality","model":"flan-ul2","score":5.7,"metric":"rouge_gm"},{"benchmark":"zeroscrolls-squality","model":"davinci-003","score":22,"metric":"rouge_gm"},{"benchmark":"zeroscrolls-squality","model":"gpt-3.5-turbo-0301","score":20.4,"metric":"rouge_gm"},{"benchmark":"zeroscrolls-squality","model":"claude-v1.3","score":21,"metric":"rouge_gm"},{"benchmark":"zeroscrolls-squality","model":"gpt-4","score":22.6,"metric":"rouge_gm"},{"benchmark":"zeroscrolls-govreport","model":"t0pp","score":7.1,"metric":"rgeo"},{"benchmark":"zeroscrolls-summscreenfd","model":"t0pp","score":9.6,"metric":"rgeo"},{"benchmark":"zeroscrolls-qmsum","model":"t0pp","score":7.2,"metric":"rgeo"},{"benchmark":"zeroscrolls-qasper","model":"t0pp","score":25,"metric":"f1"},{"benchmark":"zeroscrolls-narrativeqa","model":"t0pp","score":18.7,"metric":"f1"},{"benchmark":"zeroscrolls-quality","model":"t0pp","score":21.4,"metric":"ac"},{"benchmark":"zeroscrolls-musique","model":"t0pp","score":35.3,"metric":"f1"},{"benchmark":"zeroscrolls-booksumsort","model":"t0pp","score":0,"metric":"cidx"},{"benchmark":"zeroscrolls-govreport","model":"flan-t5","score":17.6,"metric":"rgeo"},{"benchmark":"zeroscrolls-summscreenfd","model":"flan-t5","score":7.8,"metric":"rgeo"},{"benchmark":"zeroscrolls-qmsum","model":"flan-t5","score":11,"metric":"rgeo"},{"benchmark":"zeroscrolls-qasper","model":"flan-t5","score":48.3,"metric":"f1"},{"benchmark":"zeroscrolls-narrativeqa","model":"flan-t5","score":19.3,"metric":"f1"},{"benchmark":"zeroscrolls-quality","model":"flan-t5","score":75.2,"metric":"ac"},{"benchmark":"zeroscrolls-musique","model":"flan-t5","score":46.8,"metric":"f1"},{"benchmark":"zeroscrolls-booksumsort","model":"flan-t5","score":16.4,"metric":"cidx"},{"benchmark":"zeroscrolls-govreport","model":"flan-ul2","score":16.1,"metric":"rgeo"},{"benchmark":"zeroscrolls-summscreenfd","model":"flan-ul2","score":11.5,"metric":"rgeo"},{"benchmark":"zeroscrolls-qmsum","model":"flan-ul2","score":13.6,"metric":"rgeo"},{"benchmark":"zeroscrolls-qasper","model":"flan-ul2","score":56.9,"metric":"f1"},{"benchmark":"zeroscrolls-narrativeqa","model":"flan-ul2","score":25.5,"metric":"f1"},{"benchmark":"zeroscrolls-quality","model":"flan-ul2","score":75.6,"metric":"ac"},{"benchmark":"zeroscrolls-musique","model":"flan-ul2","score":51.3,"metric":"f1"},{"benchmark":"zeroscrolls-booksumsort","model":"flan-ul2","score":14,"metric":"cidx"},{"benchmark":"zeroscrolls-govreport","model":"davinci-003","score":21.7,"metric":"rgeo"},{"benchmark":"zeroscrolls-summscreenfd","model":"davinci-003","score":16.1,"metric":"rgeo"},{"benchmark":"zeroscrolls-qmsum","model":"davinci-003","score":16.9,"metric":"rgeo"},{"benchmark":"zeroscrolls-qasper","model":"davinci-003","score":52.7,"metric":"f1"},{"benchmark":"zeroscrolls-narrativeqa","model":"davinci-003","score":24.6,"metric":"f1"},{"benchmark":"zeroscrolls-quality","model":"davinci-003","score":69,"metric":"ac"},{"benchmark":"zeroscrolls-musique","model":"davinci-003","score":33.5,"metric":"f1"},{"benchmark":"zeroscrolls-booksumsort","model":"davinci-003","score":49.5,"metric":"cidx"},{"benchmark":"zeroscrolls-govreport","model":"gpt-3.5-turbo-0301","score":21.3,"metric":"rgeo"},{"benchmark":"zeroscrolls-summscreenfd","model":"gpt-3.5-turbo-0301","score":16.1,"metric":"rgeo"},{"benchmark":"zeroscrolls-qmsum","model":"gpt-3.5-turbo-0301","score":15.6,"metric":"rgeo"},{"benchmark":"zeroscrolls-qasper","model":"gpt-3.5-turbo-0301","score":49.3,"metric":"f1"},{"benchmark":"zeroscrolls-narrativeqa","model":"gpt-3.5-turbo-0301","score":25.1,"metric":"f1"},{"benchmark":"zeroscrolls-quality","model":"gpt-3.5-turbo-0301","score":66.6,"metric":"ac"},{"benchmark":"zeroscrolls-musique","model":"gpt-3.5-turbo-0301","score":27.1,"metric":"f1"},{"benchmark":"zeroscrolls-spacedigest","model":"gpt-3.5-turbo-0301","score":49.1,"metric":"es"},{"benchmark":"zeroscrolls-booksumsort","model":"gpt-3.5-turbo-0301","score":49.8,"metric":"cidx"},{"benchmark":"zeroscrolls-govreport","model":"claude-v1.3","score":24.2,"metric":"rgeo"},{"benchmark":"zeroscrolls-summscreenfd","model":"claude-v1.3","score":16.1,"metric":"rgeo"},{"benchmark":"zeroscrolls-qmsum","model":"claude-v1.3","score":14.6,"metric":"rgeo"},{"benchmark":"zeroscrolls-qasper","model":"claude-v1.3","score":52.3,"metric":"f1"},{"benchmark":"zeroscrolls-narrativeqa","model":"claude-v1.3","score":32.6,"metric":"f1"},{"benchmark":"zeroscrolls-quality","model":"claude-v1.3","score":84.8,"metric":"ac"},{"benchmark":"zeroscrolls-musique","model":"claude-v1.3","score":36.1,"metric":"f1"},{"benchmark":"zeroscrolls-booksumsort","model":"claude-v1.3","score":47.4,"metric":"cidx"},{"benchmark":"zeroscrolls-govreport","model":"gpt-4","score":26.3,"metric":"rgeo"},{"benchmark":"zeroscrolls-summscreenfd","model":"gpt-4","score":17.3,"metric":"rgeo"},{"benchmark":"zeroscrolls-qmsum","model":"gpt-4","score":18.5,"metric":"rgeo"},{"benchmark":"zeroscrolls-qasper","model":"gpt-4","score":50.7,"metric":"f1"},{"benchmark":"zeroscrolls-narrativeqa","model":"gpt-4","score":27.6,"metric":"f1"},{"benchmark":"zeroscrolls-quality","model":"gpt-4","score":89.2,"metric":"ac"},{"benchmark":"zeroscrolls-musique","model":"gpt-4","score":41.1,"metric":"f1"},{"benchmark":"zeroscrolls-booksumsort","model":"gpt-4","score":60.5,"metric":"cidx"},{"benchmark":"zeroscrolls-govreport","model":"colt5","score":41,"metric":"rgeo"},{"benchmark":"zeroscrolls-summscreenfd","model":"colt5","score":20,"metric":"rgeo"},{"benchmark":"zeroscrolls-qmsum","model":"colt5","score":22.5,"metric":"rgeo"},{"benchmark":"zeroscrolls-qasper","model":"colt5","score":53.1,"metric":"f1"},{"benchmark":"zeroscrolls-narrativeqa","model":"colt5","score":31,"metric":"f1"},{"benchmark":"zeroscrolls-quality","model":"colt5","score":47,"metric":"ac"},{"benchmark":"boolq","model":"gpt-3","score":60.5,"metric":"percent"},{"benchmark":"piqa","model":"gpt-3","score":81,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-3","score":78.9,"metric":"percent"},{"benchmark":"winogrande","model":"gpt-3","score":70.2,"metric":"percent"},{"benchmark":"arc-easy","model":"gpt-3","score":68.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"gpt-3","score":51.4,"metric":"percent"},{"benchmark":"openbookqa","model":"gpt-3","score":57.6,"metric":"percent"},{"benchmark":"boolq","model":"gopher-280b","score":79.3,"metric":"percent"},{"benchmark":"piqa","model":"gopher-280b","score":81.8,"metric":"percent"},{"benchmark":"siqa","model":"gopher-280b","score":50.6,"metric":"percent"},{"benchmark":"hellaswag","model":"gopher-280b","score":79.2,"metric":"percent"},{"benchmark":"winogrande","model":"gopher-280b","score":70.1,"metric":"percent"},{"benchmark":"boolq","model":"chinchilla-70b","score":83.7,"metric":"percent"},{"benchmark":"piqa","model":"chinchilla-70b","score":81.8,"metric":"percent"},{"benchmark":"siqa","model":"chinchilla-70b","score":51.3,"metric":"percent"},{"benchmark":"hellaswag","model":"chinchilla-70b","score":80.8,"metric":"percent"},{"benchmark":"winogrande","model":"chinchilla-70b","score":74.9,"metric":"percent"},{"benchmark":"boolq","model":"palm-62b","score":84.8,"metric":"percent"},{"benchmark":"piqa","model":"palm-62b","score":80.5,"metric":"percent"},{"benchmark":"hellaswag","model":"palm-62b","score":79.7,"metric":"percent"},{"benchmark":"winogrande","model":"palm-62b","score":77,"metric":"percent"},{"benchmark":"arc-easy","model":"palm-62b","score":75.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"palm-62b","score":52.5,"metric":"percent"},{"benchmark":"openbookqa","model":"palm-62b","score":50.4,"metric":"percent"},{"benchmark":"boolq","model":"palm-cont-62b","score":83.9,"metric":"percent"},{"benchmark":"piqa","model":"palm-cont-62b","score":81.4,"metric":"percent"},{"benchmark":"hellaswag","model":"palm-cont-62b","score":80.6,"metric":"percent"},{"benchmark":"winogrande","model":"palm-cont-62b","score":77,"metric":"percent"},{"benchmark":"boolq","model":"palm-540b","score":88,"metric":"percent"},{"benchmark":"piqa","model":"palm-540b","score":82.3,"metric":"percent"},{"benchmark":"hellaswag","model":"palm-540b","score":83.4,"metric":"percent"},{"benchmark":"winogrande","model":"palm-540b","score":81.1,"metric":"percent"},{"benchmark":"arc-easy","model":"palm-540b","score":76.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"palm-540b","score":53,"metric":"percent"},{"benchmark":"openbookqa","model":"palm-540b","score":53.4,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-7b","score":76.5,"metric":"percent"},{"benchmark":"piqa","model":"llama-1-7b","score":79.8,"metric":"percent"},{"benchmark":"siqa","model":"llama-1-7b","score":48.9,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-1-7b","score":76.1,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1-7b","score":70.1,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-1-7b","score":72.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-1-7b","score":47.6,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-1-7b","score":57.2,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-13b","score":78.1,"metric":"percent"},{"benchmark":"piqa","model":"llama-1-13b","score":80.1,"metric":"percent"},{"benchmark":"siqa","model":"llama-1-13b","score":50.4,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-1-13b","score":79.2,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1-13b","score":73,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-1-13b","score":74.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-1-13b","score":52.7,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-1-13b","score":56.4,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-33b","score":83.1,"metric":"percent"},{"benchmark":"siqa","model":"llama-1-33b","score":50.4,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-1-33b","score":58.6,"metric":"percent"},{"benchmark":"piqa","model":"llama-1-65b","score":82.8,"metric":"percent"},{"benchmark":"siqa","model":"llama-1-65b","score":52.3,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-1-65b","score":84.2,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1-65b","score":77,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-1-65b","score":78.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-1-65b","score":56,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-1-65b","score":60.2,"metric":"percent"},{"benchmark":"lambada","model":"gpt-2","score":63.24,"metric":"percent"},{"benchmark":"winogrande","model":"gpt-2","score":70.7,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-2.6b-exp","score":44.4,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-2.6b","score":24.73,"metric":"percent"},{"benchmark":"ifbench","model":"llama-3.2-3b-instruct","score":23.67,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.0-micro","score":24,"metric":"percent"},{"benchmark":"ifbench","model":"smollm3-3b","score":19.93,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-3n-e2b-it","score":23.73,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2-2.6b-exp","score":73.05,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2-2.6b","score":60.46,"metric":"percent"},{"benchmark":"multi-if","model":"llama-3.2-3b-instruct","score":50.93,"metric":"percent"},{"benchmark":"multi-if","model":"granite-4.0-micro","score":57.96,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-3n-e2b-it","score":60.29,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-2.6b-exp","score":88.13,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-2.6b","score":81.25,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.2-3b-instruct","score":73.49,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-micro","score":82.36,"metric":"percent"},{"benchmark":"ifeval","model":"smollm3-3b","score":74.55,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3n-e2b-it","score":74.57,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2-2.6b-exp","score":53.87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2-2.6b","score":47.59,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-3b-instruct","score":35.98,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-micro","score":41.65,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm3-3b","score":53.62,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3n-e2b-it","score":39.76,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2-2.6b-exp","score":41.31,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2-2.6b","score":33.84,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.2-3b-instruct","score":21.72,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.0-micro","score":28.28,"metric":"percent"},{"benchmark":"gpqa","model":"smollm3-3b","score":28.99,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3n-e2b-it","score":31.11,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2-2.6b-exp","score":22.67,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2-2.6b","score":9.83,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.2-3b-instruct","score":0.67,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-4.0-micro","score":1,"metric":"percent"},{"benchmark":"aime-2025","model":"smollm3-3b","score":10,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3n-e2b-it","score":8.67,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2-350m-math","score":27.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-6b","score":27.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mobilellm-r1-950m","score":28,"metric":"percent"},{"benchmark":"math500","model":"lfm2-350m-math","score":79.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3-6b","score":74.5,"metric":"percent"},{"benchmark":"math500","model":"mobilellm-r1-950m","score":60.7,"metric":"percent"},{"benchmark":"aime-2024","model":"lfm2-350m-math","score":21.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-6b","score":11.5,"metric":"percent"},{"benchmark":"aime-2024","model":"mobilellm-r1-950m","score":13.1,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2-350m-math","score":27.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-6b","score":17.8,"metric":"percent"},{"benchmark":"aime-2025","model":"mobilellm-r1-950m","score":8.4,"metric":"percent"},{"benchmark":"amc-23","model":"lfm2-350m-math","score":67.2,"metric":"percent"},{"benchmark":"amc-23","model":"qwen3-6b","score":51.9,"metric":"percent"},{"benchmark":"amc-23","model":"mobilellm-r1-950m","score":40.2,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4","score":79,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-4","score":65,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-4","score":24,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4","score":35.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4","score":63.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4","score":15,"metric":"percent"},{"benchmark":"vibe-web","model":"claude-opus-4.5","score":89.1,"metric":"percent"},{"benchmark":"vibe-simulation","model":"claude-opus-4.5","score":84,"metric":"percent"},{"benchmark":"vibe-android","model":"claude-opus-4.5","score":92.2,"metric":"percent"},{"benchmark":"vibe-ios","model":"claude-opus-4.5","score":90,"metric":"percent"},{"benchmark":"vibe-backend","model":"claude-opus-4.5","score":98,"metric":"percent"},{"benchmark":"swe-review","model":"minimax-m2.1","score":8.9,"metric":"percent"},{"benchmark":"swe-review","model":"minimax-m2","score":3.4,"metric":"percent"},{"benchmark":"swe-review","model":"claude-sonnet-4.5","score":10.5,"metric":"percent"},{"benchmark":"swe-review","model":"claude-opus-4.5","score":16.2,"metric":"percent"},{"benchmark":"swe-review","model":"deepseek-v3.2","score":6.4,"metric":"percent"},{"benchmark":"swe-perf","model":"minimax-m2.1","score":3.1,"metric":"percent"},{"benchmark":"swe-perf","model":"minimax-m2","score":1.4,"metric":"percent"},{"benchmark":"swe-perf","model":"claude-sonnet-4.5","score":3,"metric":"percent"},{"benchmark":"swe-perf","model":"claude-opus-4.5","score":4.7,"metric":"percent"},{"benchmark":"swe-perf","model":"gemini-3-pro","score":6.5,"metric":"percent"},{"benchmark":"swe-perf","model":"gpt-5.2-thinking","score":3.6,"metric":"percent"},{"benchmark":"swe-perf","model":"deepseek-v3.2","score":0.9,"metric":"percent"},{"benchmark":"octocodingbench","model":"minimax-m2.1","score":26.1,"metric":"percent"},{"benchmark":"octocodingbench","model":"minimax-m2","score":13.3,"metric":"percent"},{"benchmark":"octocodingbench","model":"claude-sonnet-4.5","score":22.8,"metric":"percent"},{"benchmark":"octocodingbench","model":"claude-opus-4.5","score":36.2,"metric":"percent"},{"benchmark":"octocodingbench","model":"gemini-3-pro","score":22.9,"metric":"percent"},{"benchmark":"octocodingbench","model":"deepseek-v3.2","score":26,"metric":"percent"},{"benchmark":"swt-bench","model":"minimax-m2.1","score":69.3,"metric":"percent"},{"benchmark":"swt-bench","model":"minimax-m2","score":32.8,"metric":"percent"},{"benchmark":"swt-bench","model":"claude-sonnet-4.5","score":69.5,"metric":"percent"},{"benchmark":"swt-bench","model":"claude-opus-4.5","score":80.2,"metric":"percent"},{"benchmark":"swt-bench","model":"gemini-3-pro","score":79.7,"metric":"percent"},{"benchmark":"swt-bench","model":"gpt-5.2-thinking","score":80.7,"metric":"percent"},{"benchmark":"swt-bench","model":"deepseek-v3.2","score":62,"metric":"percent"},{"benchmark":"toolathlon","model":"minimax-m2.1","score":43.5,"metric":"percent"},{"benchmark":"toolathlon","model":"minimax-m2","score":16.7,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-sonnet-4.5","score":38.9,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-opus-4.5","score":43.5,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.2-thinking","score":41.7,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v3.2","score":35.2,"metric":"percent"},{"benchmark":"browsecomp","model":"minimax-m2.1","score":47.4,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-sonnet-4.5","score":19.6,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-opus-4.5","score":37,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.2-thinking","score":65.8,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"minimax-m2.1","score":62,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"minimax-m2","score":56.9,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"claude-sonnet-4.5","score":26.1,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"claude-opus-4.5","score":57.8,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"gpt-5.2-thinking","score":70,"metric":"percent"},{"benchmark":"aime-2025","model":"minimax-m2.1","score":83,"metric":"percent"},{"benchmark":"aime-2025","model":"minimax-m2","score":78,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4.5","score":88,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.5","score":91,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3-pro","score":96,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.2-thinking","score":98,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.2","score":92,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-m2.1","score":88,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-sonnet-4.5","score":88,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.5","score":90,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3-pro","score":90,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.2-thinking","score":87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.2","score":86,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m2.1","score":83,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m2","score":78,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-sonnet-4.5","score":83,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3-pro","score":91,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2-thinking","score":90,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.2","score":84,"metric":"percent"},{"benchmark":"hle","model":"minimax-m2.1","score":22.2,"metric":"avg@3"},{"benchmark":"hle","model":"minimax-m2","score":12.5,"metric":"avg@3"},{"benchmark":"hle","model":"claude-sonnet-4.5","score":17.3,"metric":"avg@3"},{"benchmark":"hle","model":"claude-opus-4.5","score":28.4,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-3-pro","score":37.2,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.2-thinking","score":31.4,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v3.2","score":22.2,"metric":"avg@3"},{"benchmark":"livecodebench","model":"minimax-m2.1","score":81,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4.5","score":71,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.5","score":87,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-pro","score":92,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.2-thinking","score":89,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2","score":86,"metric":"percent"},{"benchmark":"scicode","model":"minimax-m2.1","score":41,"metric":"percent"},{"benchmark":"scicode","model":"minimax-m2","score":36,"metric":"percent"},{"benchmark":"scicode","model":"claude-sonnet-4.5","score":45,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.5","score":50,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3-pro","score":56,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.2-thinking","score":52,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v3.2","score":39,"metric":"percent"},{"benchmark":"ifbench","model":"minimax-m2.1","score":70,"metric":"percent"},{"benchmark":"ifbench","model":"minimax-m2","score":72,"metric":"percent"},{"benchmark":"ifbench","model":"claude-sonnet-4.5","score":57,"metric":"percent"},{"benchmark":"ifbench","model":"claude-opus-4.5","score":58,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-3-pro","score":70,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.2-thinking","score":75,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v3.2","score":61,"metric":"percent"},{"benchmark":"aa-lcr","model":"minimax-m2.1","score":62,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-sonnet-4.5","score":66,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-opus-4.5","score":74,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-3-pro","score":71,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.2-thinking","score":73,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v3.2","score":65,"metric":"percent"},{"benchmark":"tau2-telecom","model":"minimax-m2.1","score":87,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-sonnet-4.5","score":78,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.5","score":90,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-3-pro","score":87,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.2-thinking","score":85,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v3.2","score":91,"metric":"percent"},{"benchmark":"docmath","model":"gemini-2.5-pro","score":62.38,"metric":"percent"},{"benchmark":"lbv2","model":"gemini-2.5-pro","score":65.72,"metric":"percent"},{"benchmark":"frames","model":"gemini-2.5-pro","score":74.51,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gemini-2.5-pro","score":79.92,"metric":"percent"},{"benchmark":"corpusqa","model":"gemini-2.5-pro","score":80.62,"metric":"percent"},{"benchmark":"lbv1-qa","model":"gemini-2.5-pro","score":71.28,"metric":"percent"},{"benchmark":"docmath","model":"gpt-5","score":67.62,"metric":"percent"},{"benchmark":"lbv2","model":"gpt-5","score":62.82,"metric":"percent"},{"benchmark":"frames","model":"gpt-5","score":84.59,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gpt-5","score":77.29,"metric":"percent"},{"benchmark":"corpusqa","model":"gpt-5","score":81.56,"metric":"percent"},{"benchmark":"lbv1-qa","model":"gpt-5","score":73.7,"metric":"percent"},{"benchmark":"docmath","model":"deepseek-r1-0528","score":63.44,"metric":"percent"},{"benchmark":"lbv2","model":"deepseek-r1-0528","score":59.48,"metric":"percent"},{"benchmark":"frames","model":"deepseek-r1-0528","score":76.86,"metric":"percent"},{"benchmark":"mrcr-128k","model":"deepseek-r1-0528","score":64.88,"metric":"percent"},{"benchmark":"corpusqa","model":"deepseek-r1-0528","score":77.5,"metric":"percent"},{"benchmark":"lbv1-qa","model":"deepseek-r1-0528","score":69.9,"metric":"percent"},{"benchmark":"docmath","model":"qwen3-235b-a22b-thinking-2507","score":65.75,"metric":"percent"},{"benchmark":"lbv2","model":"qwen3-235b-a22b-thinking-2507","score":57.46,"metric":"percent"},{"benchmark":"frames","model":"qwen3-235b-a22b-thinking-2507","score":75.12,"metric":"percent"},{"benchmark":"mrcr-128k","model":"qwen3-235b-a22b-thinking-2507","score":66.17,"metric":"percent"},{"benchmark":"corpusqa","model":"qwen3-235b-a22b-thinking-2507","score":75.31,"metric":"percent"},{"benchmark":"lbv1-qa","model":"qwen3-235b-a22b-thinking-2507","score":70.9,"metric":"percent"},{"benchmark":"docmath","model":"qwen3-max-thinking-preview","score":64.12,"metric":"percent"},{"benchmark":"lbv2","model":"qwen3-max-thinking-preview","score":57.89,"metric":"percent"},{"benchmark":"frames","model":"qwen3-max-thinking-preview","score":77.93,"metric":"percent"},{"benchmark":"mrcr-128k","model":"qwen3-max-thinking-preview","score":71.24,"metric":"percent"},{"benchmark":"corpusqa","model":"qwen3-max-thinking-preview","score":74.69,"metric":"percent"},{"benchmark":"lbv1-qa","model":"qwen3-max-thinking-preview","score":70.71,"metric":"percent"},{"benchmark":"docmath","model":"gemini-2.5-flash-thinking","score":64.75,"metric":"percent"},{"benchmark":"lbv2","model":"gemini-2.5-flash-thinking","score":56.77,"metric":"percent"},{"benchmark":"frames","model":"gemini-2.5-flash-thinking","score":65.78,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gemini-2.5-flash-thinking","score":78.84,"metric":"percent"},{"benchmark":"corpusqa","model":"gemini-2.5-flash-thinking","score":79.38,"metric":"percent"},{"benchmark":"lbv1-qa","model":"gemini-2.5-flash-thinking","score":66.86,"metric":"percent"},{"benchmark":"docmath","model":"gpt-5-nano","score":63.88,"metric":"percent"},{"benchmark":"lbv2","model":"gpt-5-nano","score":43.74,"metric":"percent"},{"benchmark":"frames","model":"gpt-5-nano","score":73.54,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gpt-5-nano","score":43.88,"metric":"percent"},{"benchmark":"corpusqa","model":"gpt-5-nano","score":50.31,"metric":"percent"},{"benchmark":"lbv1-qa","model":"gpt-5-nano","score":67.1,"metric":"percent"},{"benchmark":"docmath","model":"gpt-oss-120b","score":61.25,"metric":"percent"},{"benchmark":"lbv2","model":"gpt-oss-120b","score":47.01,"metric":"percent"},{"benchmark":"frames","model":"gpt-oss-120b","score":72.69,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gpt-oss-120b","score":39.68,"metric":"percent"},{"benchmark":"corpusqa","model":"gpt-oss-120b","score":64.38,"metric":"percent"},{"benchmark":"lbv1-qa","model":"gpt-oss-120b","score":66.3,"metric":"percent"},{"benchmark":"docmath","model":"qwenlong-l1","score":64.75,"metric":"percent"},{"benchmark":"lbv2","model":"qwenlong-l1","score":40.76,"metric":"percent"},{"benchmark":"frames","model":"qwenlong-l1","score":72.39,"metric":"percent"},{"benchmark":"mrcr-128k","model":"qwenlong-l1","score":47.86,"metric":"percent"},{"benchmark":"corpusqa","model":"qwenlong-l1","score":42.5,"metric":"percent"},{"benchmark":"lbv1-qa","model":"qwenlong-l1","score":68.4,"metric":"percent"},{"benchmark":"docmath","model":"qwen3-30b-a3b-thinking-2507","score":62.26,"metric":"percent"},{"benchmark":"lbv2","model":"qwen3-30b-a3b-thinking-2507","score":49.11,"metric":"percent"},{"benchmark":"frames","model":"qwen3-30b-a3b-thinking-2507","score":70.27,"metric":"percent"},{"benchmark":"mrcr-128k","model":"qwen3-30b-a3b-thinking-2507","score":51.27,"metric":"percent"},{"benchmark":"corpusqa","model":"qwen3-30b-a3b-thinking-2507","score":71.56,"metric":"percent"},{"benchmark":"lbv1-qa","model":"qwen3-30b-a3b-thinking-2507","score":67.1,"metric":"percent"},{"benchmark":"docmath","model":"qwenlong-l1.5-30b-a3b","score":66.26,"metric":"percent"},{"benchmark":"lbv2","model":"qwenlong-l1.5-30b-a3b","score":55.27,"metric":"percent"},{"benchmark":"frames","model":"qwenlong-l1.5-30b-a3b","score":74.76,"metric":"percent"},{"benchmark":"mrcr-128k","model":"qwenlong-l1.5-30b-a3b","score":82.99,"metric":"percent"},{"benchmark":"corpusqa","model":"qwenlong-l1.5-30b-a3b","score":81.25,"metric":"percent"},{"benchmark":"lbv1-qa","model":"qwenlong-l1.5-30b-a3b","score":70.4,"metric":"percent"},{"benchmark":"docmath","model":"gpt-4o","score":62.4,"metric":"percent"},{"benchmark":"docmath","model":"gpt-4-turbo","score":61.9,"metric":"percent"},{"benchmark":"docmath","model":"claude-3-opus","score":61.8,"metric":"percent"},{"benchmark":"docmath","model":"claude-3.5-sonnet","score":59.2,"metric":"percent"},{"benchmark":"docmath","model":"claude-3-sonnet","score":58.5,"metric":"percent"},{"benchmark":"docmath","model":"gemini-1.5-flash","score":54.5,"metric":"percent"},{"benchmark":"docmath","model":"gemini-1.5-pro","score":52.8,"metric":"percent"},{"benchmark":"docmath","model":"claude-3-haiku","score":52.5,"metric":"percent"},{"benchmark":"docmath","model":"gpt-4o-mini","score":52.2,"metric":"percent"},{"benchmark":"docmath","model":"gpt-3.5-turbo","score":34,"metric":"percent"},{"benchmark":"docmath","model":"mistral-large","score":59.7,"metric":"percent"},{"benchmark":"docmath","model":"deepseek-coder-v2","score":57.3,"metric":"percent"},{"benchmark":"docmath","model":"llama-3.1-70b","score":54.1,"metric":"percent"},{"benchmark":"docmath","model":"qwen2-72b","score":52.4,"metric":"percent"},{"benchmark":"docmath","model":"llama-3-70b","score":50.1,"metric":"percent"},{"benchmark":"docmath","model":"mixtral-8x22b","score":47.6,"metric":"percent"},{"benchmark":"docmath","model":"gemma-2-9b","score":41.8,"metric":"percent"},{"benchmark":"docmath","model":"command-r-plus","score":39.9,"metric":"percent"},{"benchmark":"docmath","model":"yi-1.5-9b","score":38.1,"metric":"percent"},{"benchmark":"docmath","model":"yi-1.5-34b","score":36.9,"metric":"percent"},{"benchmark":"docmath","model":"llama-3.1-8b","score":35.1,"metric":"percent"},{"benchmark":"docmath","model":"codestral-22b","score":31,"metric":"percent"},{"benchmark":"docmath","model":"llama-3-8b","score":30.1,"metric":"percent"},{"benchmark":"docmath","model":"qwen2-7b","score":29.9,"metric":"percent"},{"benchmark":"docmath","model":"mixtral-8x7b","score":21.9,"metric":"percent"},{"benchmark":"docmath","model":"deepseek-math-7b","score":21.8,"metric":"percent"},{"benchmark":"docmath","model":"llama-2-70b","score":20.8,"metric":"percent"},{"benchmark":"docmath","model":"starcoder2-15b","score":11.5,"metric":"percent"},{"benchmark":"docmath","model":"gemma-2-7b","score":9,"metric":"percent"},{"benchmark":"docmath","model":"llama-2-7b","score":8.4,"metric":"percent"},{"benchmark":"docmath","model":"deepseek-coder-33b","score":7.6,"metric":"percent"},{"benchmark":"docmath","model":"gemma-2-2b","score":4.1,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"hyperclovax-seed-think","score":11,"metric":"percent"},{"benchmark":"tau2-telecom","model":"hyperclovax-seed-think","score":87,"metric":"percent"},{"benchmark":"aa-lcr","model":"hyperclovax-seed-think","score":12,"metric":"percent"},{"benchmark":"hle","model":"hyperclovax-seed-think","score":5.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"hyperclovax-seed-think","score":79,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hyperclovax-seed-think","score":62,"metric":"percent"},{"benchmark":"livecodebench","model":"hyperclovax-seed-think","score":63,"metric":"percent"},{"benchmark":"scicode","model":"hyperclovax-seed-think","score":28,"metric":"percent"},{"benchmark":"ifbench","model":"hyperclovax-seed-think","score":38,"metric":"percent"},{"benchmark":"aime-2025","model":"hyperclovax-seed-think","score":59,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-8b-instruct","score":91.47,"metric":"percent"},{"benchmark":"arc-challenge","model":"wedlm-8b-instruct","score":92.92,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-8b-instruct","score":89.91,"metric":"percent"},{"benchmark":"gsm8k","model":"wedlm-8b-instruct","score":92.27,"metric":"percent"},{"benchmark":"math","model":"qwen3-8b-instruct","score":69.6,"metric":"percent"},{"benchmark":"math","model":"wedlm-8b-instruct","score":64.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-8b-instruct","score":71.95,"metric":"percent"},{"benchmark":"humaneval","model":"wedlm-8b-instruct","score":80.49,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b-instruct","score":71.52,"metric":"percent"},{"benchmark":"mmlu","model":"wedlm-8b-instruct","score":75.14,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-8b-instruct","score":41.41,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"wedlm-8b-instruct","score":44.95,"metric":"percent"},{"benchmark":"mmlu","model":"monad","score":30,"metric":"percent"},{"benchmark":"mmlu","model":"seed1.6","score":88.83,"metric":"percent"},{"benchmark":"mmlu","model":"llama-4-maverick-base","score":85.16,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3-base","score":87.19,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-235b-a22b-base","score":87.81,"metric":"percent"},{"benchmark":"mmlu","model":"seed1.5","score":88.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed1.6","score":69.98,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-maverick-base","score":63.91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3-base","score":59.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-a22b-base","score":68.18,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed1.5","score":66.47,"metric":"percent"},{"benchmark":"supergpqa","model":"seed1.6","score":45.08,"metric":"percent"},{"benchmark":"supergpqa","model":"llama-4-maverick-base","score":40.85,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3-base","score":41.53,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-235b-a22b-base","score":44.06,"metric":"percent"},{"benchmark":"supergpqa","model":"seed1.5","score":36.81,"metric":"percent"},{"benchmark":"bbh","model":"seed1.6","score":92.08,"metric":"percent"},{"benchmark":"bbh","model":"llama-4-maverick-base","score":83.62,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3-base","score":86.22,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-235b-a22b-base","score":88.87,"metric":"percent"},{"benchmark":"bbh","model":"seed1.5","score":88.36,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed1.6","score":43.43,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-4-maverick-base","score":43.94,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3-base","score":41.92,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-235b-a22b-base","score":47.47,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed1.5","score":45.25,"metric":"percent"},{"benchmark":"gsm8k","model":"seed1.6","score":93.1,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-4-maverick-base","score":87.72,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3-base","score":87.57,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-235b-a22b-base","score":94.39,"metric":"percent"},{"benchmark":"gsm8k","model":"seed1.5","score":89.99,"metric":"percent"},{"benchmark":"math","model":"seed1.6","score":72.86,"metric":"percent"},{"benchmark":"math","model":"llama-4-maverick-base","score":63.32,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3-base","score":62.62,"metric":"percent"},{"benchmark":"math","model":"qwen3-235b-a22b-base","score":71.84,"metric":"percent"},{"benchmark":"math","model":"seed1.5","score":66.18,"metric":"percent"},{"benchmark":"mbpp","model":"seed1.6","score":83.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-4-maverick-base","score":75.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v3-base","score":74.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-235b-a22b-base","score":81.4,"metric":"percent"},{"benchmark":"mbpp","model":"seed1.5","score":81.4,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.1-codex-max","score":34.94,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-4.5","score":20.1,"metric":"percent"},{"benchmark":"posttrainbench","model":"gemini-3-pro","score":18.04,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.2","score":17.48,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-sonnet-4.5","score":14.67,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-v2-lite-instruct","score":81.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-v2-lite-instruct","score":75.6,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-v2-lite-instruct","score":85.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-v2-lite-instruct","score":70.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-v2-lite-instruct","score":37.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-lite-instruct","score":18.9,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"deepseek-coder-v2-lite-instruct","score":49.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-7b-instruct","score":87.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-7b-instruct","score":81.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-7b-instruct","score":84.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-7b-instruct","score":72.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-7b-instruct","score":37.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-7b-instruct","score":13.5,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"qwen2.5-coder-7b-instruct","score":42.2,"metric":"percent"},{"benchmark":"humaneval","model":"seed-coder-8b-instruct","score":81.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"seed-coder-8b-instruct","score":75.6,"metric":"percent"},{"benchmark":"mbpp","model":"seed-coder-8b-instruct","score":86.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"seed-coder-8b-instruct","score":73.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"seed-coder-8b-instruct","score":44.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"seed-coder-8b-instruct","score":23.6,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"seed-coder-8b-instruct","score":55.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-14b-instruct","score":62.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-14b-instruct","score":59.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-14b-instruct","score":88.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-14b-instruct","score":77.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-14b-instruct","score":47,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-14b-instruct","score":6.1,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"qwen2.5-coder-14b-instruct","score":53.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-coder-30b-a3b-instruct","score":93.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-coder-30b-a3b-instruct","score":87.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-coder-30b-a3b-instruct","score":90.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-coder-30b-a3b-instruct","score":77.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-coder-30b-a3b-instruct","score":46.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen3-coder-30b-a3b-instruct","score":27.7,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"qwen3-coder-30b-a3b-instruct","score":60.9,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v3.2","score":93.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3.2","score":88.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v3.2","score":93.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3.2","score":77.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-v3.2","score":48.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-v3.2","score":27,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"deepseek-v3.2","score":64.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-32b-instruct","score":93.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-32b-instruct","score":86.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-32b-instruct","score":90.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-32b-instruct","score":77.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-32b-instruct","score":48,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-32b-instruct","score":24.3,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"qwen2.5-coder-32b-instruct","score":57.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-235b-a22b-instruct-2507","score":96.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-235b-a22b-instruct-2507","score":91.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-235b-a22b-instruct-2507","score":92.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-235b-a22b-instruct-2507","score":77.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-235b-a22b-instruct-2507","score":47.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen3-235b-a22b-instruct-2507","score":25.7,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"qwen3-235b-a22b-instruct-2507","score":62.7,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-235b-a22b-thinking-2507","score":98.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-235b-a22b-thinking-2507","score":93.3,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-235b-a22b-thinking-2507","score":95.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-235b-a22b-thinking-2507","score":81.5,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-235b-a22b-thinking-2507","score":44.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen3-235b-a22b-thinking-2507","score":23,"metric":"pass@1"},{"benchmark":"humaneval","model":"qwen3-coder-480b-a35b-instruct","score":97.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-coder-480b-a35b-instruct","score":92.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-coder-480b-a35b-instruct","score":94.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-coder-480b-a35b-instruct","score":80.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-coder-480b-a35b-instruct","score":49.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen3-coder-480b-a35b-instruct","score":27.7,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"qwen3-coder-480b-a35b-instruct","score":66.4,"metric":"percent"},{"benchmark":"humaneval","model":"kimi-dev-72b","score":93.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kimi-dev-72b","score":86,"metric":"percent"},{"benchmark":"mbpp","model":"kimi-dev-72b","score":79.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kimi-dev-72b","score":68.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"kimi-dev-72b","score":45.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"kimi-dev-72b","score":31.8,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"kimi-dev-72b","score":38.6,"metric":"percent"},{"benchmark":"humaneval","model":"kimi-k2-instruct-0905","score":94.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kimi-k2-instruct-0905","score":89.6,"metric":"percent"},{"benchmark":"mbpp","model":"kimi-k2-instruct-0905","score":91.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kimi-k2-instruct-0905","score":74.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"kimi-k2-instruct-0905","score":49.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"kimi-k2-instruct-0905","score":30.4,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"kimi-k2-instruct-0905","score":63.5,"metric":"percent"},{"benchmark":"humaneval","model":"kimi-k2-thinking","score":98.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kimi-k2-thinking","score":92.7,"metric":"percent"},{"benchmark":"mbpp","model":"kimi-k2-thinking","score":97.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kimi-k2-thinking","score":82.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"kimi-k2-thinking","score":46.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"kimi-k2-thinking","score":28.4,"metric":"pass@1"},{"benchmark":"humaneval","model":"kat-dev-32b","score":90.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kat-dev-32b","score":86.6,"metric":"percent"},{"benchmark":"mbpp","model":"kat-dev-32b","score":89.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kat-dev-32b","score":76.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"kat-dev-32b","score":46.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"kat-dev-32b","score":25.7,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"kat-dev-32b","score":58.8,"metric":"percent"},{"benchmark":"humaneval","model":"kat-dev-72b-exp","score":88.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kat-dev-72b-exp","score":81.7,"metric":"percent"},{"benchmark":"mbpp","model":"kat-dev-72b-exp","score":85.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kat-dev-72b-exp","score":69.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"kat-dev-72b-exp","score":48.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"kat-dev-72b-exp","score":26.4,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"kat-dev-72b-exp","score":52.9,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4.7","score":87.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"glm-4.7","score":79.9,"metric":"percent"},{"benchmark":"mbpp","model":"glm-4.7","score":90.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"glm-4.7","score":75.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"glm-4.7","score":45.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"glm-4.7","score":26.4,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"glm-4.7","score":70.2,"metric":"percent"},{"benchmark":"humaneval","model":"iquest-coder-v1-40b-instruct","score":96.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"iquest-coder-v1-40b-instruct","score":90.2,"metric":"percent"},{"benchmark":"mbpp","model":"iquest-coder-v1-40b-instruct","score":91.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"iquest-coder-v1-40b-instruct","score":77.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"iquest-coder-v1-40b-instruct","score":54.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"iquest-coder-v1-40b-instruct","score":33.1,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"iquest-coder-v1-40b-instruct","score":71.4,"metric":"percent"},{"benchmark":"humaneval","model":"iquest-coder-v1-40b-loop-instruct","score":97.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"iquest-coder-v1-40b-loop-instruct","score":91.5,"metric":"percent"},{"benchmark":"mbpp","model":"iquest-coder-v1-40b-loop-instruct","score":92.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"iquest-coder-v1-40b-loop-instruct","score":77.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"iquest-coder-v1-40b-loop-instruct","score":49.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"iquest-coder-v1-40b-loop-instruct","score":27.7,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"iquest-coder-v1-40b-loop-instruct","score":68.3,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-3-flash-preview","score":88.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-3-flash-preview","score":84.8,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-3-flash-preview","score":92.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-3-flash-preview","score":79.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"gemini-3-flash-preview","score":44.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-3-flash-preview","score":25.6,"metric":"pass@1"},{"benchmark":"humaneval","model":"gemini-3-pro-preview","score":100,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-3-pro-preview","score":94.5,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-3-pro-preview","score":71.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-3-pro-preview","score":64.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"gemini-3-pro-preview","score":47.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-3-pro-preview","score":25,"metric":"pass@1"},{"benchmark":"humaneval","model":"claude-opus-4.5","score":98.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-opus-4.5","score":93.3,"metric":"percent"},{"benchmark":"mbpp","model":"claude-opus-4.5","score":96.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-opus-4.5","score":83.9,"metric":"percent"},{"benchmark":"bigcodebench","model":"claude-opus-4.5","score":53.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-opus-4.5","score":35.1,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"claude-opus-4.5","score":72.3,"metric":"percent"},{"benchmark":"humaneval","model":"claude-sonnet-4.5","score":98.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-sonnet-4.5","score":93.3,"metric":"percent"},{"benchmark":"mbpp","model":"claude-sonnet-4.5","score":95.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-sonnet-4.5","score":82.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"claude-sonnet-4.5","score":51.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-sonnet-4.5","score":29.1,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"claude-sonnet-4.5","score":69.7,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-v2-lite-instruct","score":57.1,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-v2-lite-instruct","score":56.2,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-7b-instruct","score":66.9,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-7b-instruct","score":66,"metric":"percent"},{"benchmark":"crux-i","model":"seed-coder-8b-instruct","score":62,"metric":"percent"},{"benchmark":"crux-o","model":"seed-coder-8b-instruct","score":66.6,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-14b-instruct","score":75.6,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-14b-instruct","score":79.2,"metric":"percent"},{"benchmark":"crux-i","model":"qwen3-coder-30b-a3b-instruct","score":76.9,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-coder-30b-a3b-instruct","score":80.5,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v3.2","score":82.1,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v3.2","score":94.2,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-32b-instruct","score":78.8,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-32b-instruct","score":84,"metric":"percent"},{"benchmark":"crux-i","model":"qwen3-235b-a22b-instruct-2507","score":62,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-235b-a22b-instruct-2507","score":89.5,"metric":"percent"},{"benchmark":"crux-i","model":"qwen3-235b-a22b-thinking-2507","score":15.2,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-235b-a22b-thinking-2507","score":46.9,"metric":"percent"},{"benchmark":"crux-i","model":"qwen3-coder-480b-a35b-instruct","score":87.1,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-coder-480b-a35b-instruct","score":90.4,"metric":"percent"},{"benchmark":"crux-i","model":"kimi-dev-72b","score":33,"metric":"percent"},{"benchmark":"crux-o","model":"kimi-dev-72b","score":64.2,"metric":"percent"},{"benchmark":"crux-i","model":"kimi-k2-instruct-0905","score":86.8,"metric":"percent"},{"benchmark":"crux-o","model":"kimi-k2-instruct-0905","score":89.5,"metric":"percent"},{"benchmark":"crux-i","model":"kimi-k2-thinking","score":92.2,"metric":"percent"},{"benchmark":"crux-o","model":"kimi-k2-thinking","score":86.2,"metric":"percent"},{"benchmark":"crux-i","model":"kat-dev-32b","score":42.5,"metric":"percent"},{"benchmark":"crux-o","model":"kat-dev-32b","score":65.1,"metric":"percent"},{"benchmark":"crux-i","model":"kat-dev-72b-exp","score":71.4,"metric":"percent"},{"benchmark":"crux-o","model":"kat-dev-72b-exp","score":81.1,"metric":"percent"},{"benchmark":"crux-i","model":"glm-4.7","score":65.6,"metric":"percent"},{"benchmark":"crux-o","model":"glm-4.7","score":81.2,"metric":"percent"},{"benchmark":"crux-i","model":"iquest-coder-v1-40b-instruct","score":93.5,"metric":"percent"},{"benchmark":"crux-o","model":"iquest-coder-v1-40b-instruct","score":87,"metric":"percent"},{"benchmark":"crux-i","model":"iquest-coder-v1-40b-thinking","score":97.9,"metric":"percent"},{"benchmark":"crux-o","model":"iquest-coder-v1-40b-thinking","score":98.9,"metric":"percent"},{"benchmark":"crux-i","model":"iquest-coder-v1-40b-loop-instruct","score":91.1,"metric":"percent"},{"benchmark":"crux-o","model":"iquest-coder-v1-40b-loop-instruct","score":85.5,"metric":"percent"},{"benchmark":"crux-i","model":"iquest-coder-v1-40b-loop-thinking","score":98.5,"metric":"percent"},{"benchmark":"crux-o","model":"iquest-coder-v1-40b-loop-thinking","score":99.4,"metric":"percent"},{"benchmark":"crux-i","model":"gemini-3-flash-preview","score":96.5,"metric":"percent"},{"benchmark":"crux-o","model":"gemini-3-flash-preview","score":97.6,"metric":"percent"},{"benchmark":"crux-i","model":"gemini-3-pro-preview","score":98.8,"metric":"percent"},{"benchmark":"crux-o","model":"gemini-3-pro-preview","score":99.1,"metric":"percent"},{"benchmark":"crux-i","model":"claude-opus-4.5","score":98.4,"metric":"percent"},{"benchmark":"crux-o","model":"claude-opus-4.5","score":98,"metric":"percent"},{"benchmark":"crux-i","model":"claude-sonnet-4.5","score":96.2,"metric":"percent"},{"benchmark":"crux-o","model":"claude-sonnet-4.5","score":96.2,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-5.1","score":70.8,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-5.1","score":71.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepseek-coder-v2-lite-instruct","score":13.2,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-coder-v2-lite-instruct","score":19.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen2.5-coder-7b-instruct","score":14.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-coder-7b-instruct","score":18.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"seed-coder-8b-instruct","score":19.2,"metric":"percent"},{"benchmark":"livecodebench","model":"seed-coder-8b-instruct","score":22.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen2.5-coder-14b-instruct","score":22.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-coder-14b-instruct","score":24.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-coder-30b-a3b-instruct","score":43.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-coder-30b-a3b-instruct","score":36,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen2.5-coder-32b-instruct","score":30.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-coder-32b-instruct","score":27.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-235b-a22b-instruct-2507","score":53.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b-instruct-2507","score":51.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-235b-a22b-thinking-2507","score":80.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-coder-480b-a35b-instruct","score":48.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-coder-480b-a35b-instruct","score":53.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"kimi-dev-72b","score":46.1,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-dev-72b","score":40,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"kimi-k2-instruct-0905","score":52.1,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-instruct-0905","score":53.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"kat-dev-32b","score":32.9,"metric":"percent"},{"benchmark":"livecodebench","model":"kat-dev-32b","score":32.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"kat-dev-72b-exp","score":13.8,"metric":"percent"},{"benchmark":"livecodebench","model":"kat-dev-72b-exp","score":16,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-40b-instruct","score":55.7,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-40b-instruct","score":46.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-40b-thinking","score":83.8,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-40b-thinking","score":80.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-40b-loop-instruct","score":48.6,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-40b-loop-instruct","score":48.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-40b-loop-thinking","score":86.2,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-40b-loop-thinking","score":81.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-flash-preview","score":90.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-pro-preview","score":91.7,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.5","score":87.1,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4.5","score":73,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.1","score":87,"metric":"percent"},{"benchmark":"aider-polyglot-diff","model":"deepseek-coder-v2-lite-instruct","score":1.3,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"deepseek-coder-v2-lite-instruct","score":2.2,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen2.5-coder-7b-instruct","score":1.8,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"qwen2.5-coder-7b-instruct","score":4.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"seed-coder-8b-instruct","score":6.2,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"seed-coder-8b-instruct","score":5.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen2.5-coder-14b-instruct","score":8,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"qwen2.5-coder-14b-instruct","score":8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen3-coder-30b-a3b-instruct","score":28.4,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"qwen3-coder-30b-a3b-instruct","score":29.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen2.5-coder-32b-instruct","score":8.4,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"qwen2.5-coder-32b-instruct","score":14.7,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen3-235b-a22b-instruct-2507","score":53.3,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"qwen3-235b-a22b-instruct-2507","score":57.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen3-235b-a22b-thinking-2507","score":25.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen3-coder-480b-a35b-instruct","score":57.8,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"qwen3-coder-480b-a35b-instruct","score":61.8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"kimi-dev-72b","score":12,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"kimi-dev-72b","score":20,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"kimi-k2-instruct-0905","score":60,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"kimi-k2-instruct-0905","score":50.7,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"kat-dev-32b","score":8.9,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"kat-dev-32b","score":34.2,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"kat-dev-72b-exp","score":16.4,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"kat-dev-72b-exp","score":15.6,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"iquest-coder-v1-40b-instruct","score":82.7,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"iquest-coder-v1-40b-instruct","score":80.8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"iquest-coder-v1-40b-loop-instruct","score":68.9,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"iquest-coder-v1-40b-loop-instruct","score":62.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gemini-3-pro-preview","score":91.9,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"gemini-3-pro-preview","score":92.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-opus-4.5","score":89.4,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"claude-opus-4.5","score":87.1,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-sonnet-4.5","score":78.8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-5.1","score":63.1,"metric":"pass@2"},{"benchmark":"aider-polyglot","model":"gpt-5.1","score":65.3,"metric":"pass@2"},{"benchmark":"agentic-coding","model":"deepseek-coder-v2-lite-instruct","score":5,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-coder-v2-lite-instruct","score":0,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-coder-v2-lite-instruct","score":26.7,"metric":"percent"},{"benchmark":"agentic-coding","model":"qwen2.5-coder-7b-instruct","score":6.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen2.5-coder-7b-instruct","score":0,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen2.5-coder-7b-instruct","score":38.4,"metric":"percent"},{"benchmark":"general-tool-use","model":"qwen2.5-coder-7b-instruct","score":54.2,"metric":"percent"},{"benchmark":"agentic-coding","model":"seed-coder-8b-instruct","score":7.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"seed-coder-8b-instruct","score":2.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"seed-coder-8b-instruct","score":38.2,"metric":"percent"},{"benchmark":"agentic-coding","model":"qwen2.5-coder-14b-instruct","score":8.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen2.5-coder-14b-instruct","score":0,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen2.5-coder-14b-instruct","score":42.7,"metric":"percent"},{"benchmark":"general-tool-use","model":"qwen2.5-coder-14b-instruct","score":59.9,"metric":"percent"},{"benchmark":"agentic-coding","model":"qwen3-coder-30b-a3b-instruct","score":23.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-coder-30b-a3b-instruct","score":23.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-coder-30b-a3b-instruct","score":51.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-30b-a3b-instruct","score":36.1,"metric":"percent"},{"benchmark":"general-tool-use","model":"qwen3-coder-30b-a3b-instruct","score":63.4,"metric":"percent"},{"benchmark":"agentic-coding","model":"deepseek-v3.2","score":23.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.2","score":46.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v3.2","score":73.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.2","score":47.2,"metric":"percent"},{"benchmark":"general-tool-use","model":"deepseek-v3.2","score":68.8,"metric":"percent"},{"benchmark":"agentic-coding","model":"qwen2.5-coder-32b-instruct","score":5,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen2.5-coder-32b-instruct","score":4.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen2.5-coder-32b-instruct","score":32.5,"metric":"percent"},{"benchmark":"general-tool-use","model":"qwen2.5-coder-32b-instruct","score":62.3,"metric":"percent"},{"benchmark":"agentic-coding","model":"qwen3-235b-a22b-instruct-2507","score":15,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-235b-a22b-instruct-2507","score":13.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-235b-a22b-instruct-2507","score":45.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-235b-a22b-instruct-2507","score":49,"metric":"percent"},{"benchmark":"general-tool-use","model":"qwen3-235b-a22b-instruct-2507","score":71.2,"metric":"percent"},{"benchmark":"agentic-coding","model":"qwen3-235b-a22b-thinking-2507","score":8.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-235b-a22b-thinking-2507","score":3.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-235b-a22b-thinking-2507","score":44.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-235b-a22b-thinking-2507","score":43.2,"metric":"percent"},{"benchmark":"general-tool-use","model":"qwen3-235b-a22b-thinking-2507","score":71.9,"metric":"percent"},{"benchmark":"agentic-coding","model":"qwen3-coder-480b-a35b-instruct","score":37.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-coder-480b-a35b-instruct","score":23.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-coder-480b-a35b-instruct","score":67,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-480b-a35b-instruct","score":54,"metric":"percent"},{"benchmark":"general-tool-use","model":"qwen3-coder-480b-a35b-instruct","score":68.7,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-dev-72b","score":2.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-dev-72b","score":60.4,"metric":"percent"},{"benchmark":"general-tool-use","model":"kimi-dev-72b","score":55.5,"metric":"percent"},{"benchmark":"agentic-coding","model":"kimi-k2-instruct-0905","score":44.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-instruct-0905","score":27.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2-instruct-0905","score":69.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-instruct-0905","score":53.4,"metric":"percent"},{"benchmark":"general-tool-use","model":"kimi-k2-instruct-0905","score":70.3,"metric":"percent"},{"benchmark":"agentic-coding","model":"kimi-k2-thinking","score":47.1,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2-thinking","score":33.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2-thinking","score":71.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-thinking","score":55.7,"metric":"percent"},{"benchmark":"agentic-coding","model":"kat-dev-32b","score":17.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"kat-dev-32b","score":10.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kat-dev-32b","score":62.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kat-dev-32b","score":33.7,"metric":"percent"},{"benchmark":"general-tool-use","model":"kat-dev-32b","score":64.7,"metric":"percent"},{"benchmark":"agentic-coding","model":"kat-dev-72b-exp","score":21.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"kat-dev-72b-exp","score":7.9,"metric":"percent"},{"benchmark":"agentic-coding","model":"glm-4.7","score":36.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"glm-4.7","score":41,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-4.7","score":73.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.7","score":53.7,"metric":"percent"},{"benchmark":"general-tool-use","model":"glm-4.7","score":64.8,"metric":"percent"},{"benchmark":"agentic-coding","model":"iquest-coder-v1-40b-instruct","score":52.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"iquest-coder-v1-40b-instruct","score":33,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"iquest-coder-v1-40b-instruct","score":75.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"iquest-coder-v1-40b-instruct","score":64.3,"metric":"percent"},{"benchmark":"general-tool-use","model":"iquest-coder-v1-40b-instruct","score":51.7,"metric":"percent"},{"benchmark":"agentic-coding","model":"iquest-coder-v1-40b-loop-instruct","score":51.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"iquest-coder-v1-40b-loop-instruct","score":33,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"iquest-coder-v1-40b-loop-instruct","score":81.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"iquest-coder-v1-40b-loop-instruct","score":62.5,"metric":"percent"},{"benchmark":"general-tool-use","model":"iquest-coder-v1-40b-loop-instruct","score":73.9,"metric":"percent"},{"benchmark":"agentic-coding","model":"gemini-3-flash-preview","score":53.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-3-flash-preview","score":47.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-flash-preview","score":78,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3-flash-preview","score":60.6,"metric":"percent"},{"benchmark":"agentic-coding","model":"gemini-3-pro-preview","score":46.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-3-pro-preview","score":54.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-pro-preview","score":76.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3-pro-preview","score":60.3,"metric":"percent"},{"benchmark":"general-tool-use","model":"gemini-3-pro-preview","score":78.2,"metric":"percent"},{"benchmark":"agentic-coding","model":"claude-opus-4.5","score":47.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4.5","score":59.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.5","score":80.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.5","score":57.9,"metric":"percent"},{"benchmark":"general-tool-use","model":"claude-opus-4.5","score":78.9,"metric":"percent"},{"benchmark":"agentic-coding","model":"claude-sonnet-4.5","score":51,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-sonnet-4.5","score":50,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-sonnet-4.5","score":77.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4.5","score":58.6,"metric":"percent"},{"benchmark":"general-tool-use","model":"claude-sonnet-4.5","score":77.7,"metric":"percent"},{"benchmark":"agentic-coding","model":"gpt-5.1","score":35,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1","score":76.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.1","score":55.1,"metric":"percent"},{"benchmark":"general-tool-use","model":"gpt-5.1","score":64.4,"metric":"percent"},{"benchmark":"beavertails","model":"qwen2.5-coder-32b-instruct","score":68,"metric":"percent"},{"benchmark":"harmbench","model":"qwen2.5-coder-32b-instruct","score":47.5,"metric":"percent"},{"benchmark":"do-anything-now","model":"qwen2.5-coder-32b-instruct","score":69.7,"metric":"percent"},{"benchmark":"do-not-answer","model":"qwen2.5-coder-32b-instruct","score":53.7,"metric":"percent"},{"benchmark":"trustllm","model":"qwen2.5-coder-32b-instruct","score":70.2,"metric":"percent"},{"benchmark":"wildguardtest","model":"qwen2.5-coder-32b-instruct","score":73.9,"metric":"percent"},{"benchmark":"xstest","model":"qwen2.5-coder-32b-instruct","score":90.6,"metric":"percent"},{"benchmark":"beavertails","model":"qwen3-coder-480b-a35b-instruct","score":70.5,"metric":"percent"},{"benchmark":"harmbench","model":"qwen3-coder-480b-a35b-instruct","score":94.2,"metric":"percent"},{"benchmark":"do-anything-now","model":"qwen3-coder-480b-a35b-instruct","score":95.7,"metric":"percent"},{"benchmark":"do-not-answer","model":"qwen3-coder-480b-a35b-instruct","score":69.9,"metric":"percent"},{"benchmark":"trustllm","model":"qwen3-coder-480b-a35b-instruct","score":88.4,"metric":"percent"},{"benchmark":"wildguardtest","model":"qwen3-coder-480b-a35b-instruct","score":85,"metric":"percent"},{"benchmark":"xstest","model":"qwen3-coder-480b-a35b-instruct","score":90.1,"metric":"percent"},{"benchmark":"beavertails","model":"iquest-coder-v1-40b-instruct","score":67.5,"metric":"percent"},{"benchmark":"harmbench","model":"iquest-coder-v1-40b-instruct","score":57.3,"metric":"percent"},{"benchmark":"do-anything-now","model":"iquest-coder-v1-40b-instruct","score":63.3,"metric":"percent"},{"benchmark":"do-not-answer","model":"iquest-coder-v1-40b-instruct","score":53.9,"metric":"percent"},{"benchmark":"trustllm","model":"iquest-coder-v1-40b-instruct","score":65,"metric":"percent"},{"benchmark":"wildguardtest","model":"iquest-coder-v1-40b-instruct","score":78.1,"metric":"percent"},{"benchmark":"xstest","model":"iquest-coder-v1-40b-instruct","score":89.3,"metric":"percent"},{"benchmark":"beavertails","model":"iquest-coder-v1-40b-thinking","score":76.7,"metric":"percent"},{"benchmark":"harmbench","model":"iquest-coder-v1-40b-thinking","score":94.8,"metric":"percent"},{"benchmark":"do-anything-now","model":"iquest-coder-v1-40b-thinking","score":97.7,"metric":"percent"},{"benchmark":"do-not-answer","model":"iquest-coder-v1-40b-thinking","score":58.6,"metric":"percent"},{"benchmark":"trustllm","model":"iquest-coder-v1-40b-thinking","score":86.4,"metric":"percent"},{"benchmark":"wildguardtest","model":"iquest-coder-v1-40b-thinking","score":86.8,"metric":"percent"},{"benchmark":"xstest","model":"iquest-coder-v1-40b-thinking","score":94.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v3.0","score":61.43,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v3.0","score":81.38,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v3.0","score":47.65,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v3.0","score":67.55,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v3.0","score":78.53,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v3.0","score":74.15,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-14b","score":56.57,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-14b","score":81.08,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-14b","score":52.06,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-14b","score":69.36,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-14b","score":73.48,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-14b","score":67.63,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v2","score":60.58,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v2","score":79.84,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v2","score":46.13,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v2","score":63.06,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v2","score":77.82,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v2","score":67.78,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-14b","score":58.28,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-14b","score":83.99,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen-14b","score":49.43,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b","score":67.7,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-14b","score":76.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b","score":58.98,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-8b","score":60.24,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3-8b","score":82.23,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3-8b","score":42.93,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-8b","score":66.7,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3-8b","score":78.45,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b","score":45.19,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-4.5b-v3","score":51.19,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-4.5b-v3","score":73.01,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-4.5b-v3","score":45.63,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-4.5b-v3","score":61.32,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-4.5b-v3","score":71.35,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-4.5b-v3","score":63.61,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-v0.1","score":59.98,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-v0.1","score":83.31,"metric":"percent"},{"benchmark":"truthfulqa","model":"mistral-7b-v0.1","score":42.15,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-v0.1","score":64.16,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b-v0.1","score":78.37,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.1","score":37.83,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-v0.2","score":60.84,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-v0.2","score":83.08,"metric":"percent"},{"benchmark":"truthfulqa","model":"mistral-7b-v0.2","score":41.76,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-v0.2","score":63.62,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b-v0.2","score":78.22,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.2","score":34.72,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-7b-v0.1","score":45.22,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-7b-v0.1","score":67.92,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-7b-v0.1","score":47.16,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-7b-v0.1","score":43.2,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-7b-v0.1","score":66.85,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-7b-v0.1","score":29.49,"metric":"percent"},{"benchmark":"arc-challenge","model":"solar-10.7b-instruct-v1.0","score":71.08,"metric":"percent"},{"benchmark":"hellaswag","model":"solar-10.7b-instruct-v1.0","score":88.16,"metric":"percent"},{"benchmark":"truthfulqa","model":"solar-10.7b-instruct-v1.0","score":71.43,"metric":"percent"},{"benchmark":"mmlu","model":"solar-10.7b-instruct-v1.0","score":66.21,"metric":"percent"},{"benchmark":"winogrande","model":"solar-10.7b-instruct-v1.0","score":83.58,"metric":"percent"},{"benchmark":"gsm8k","model":"solar-10.7b-instruct-v1.0","score":64.75,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-3-medium-4k-instruct","score":67.32,"metric":"percent"},{"benchmark":"hellaswag","model":"phi-3-medium-4k-instruct","score":85.76,"metric":"percent"},{"benchmark":"truthfulqa","model":"phi-3-medium-4k-instruct","score":57.71,"metric":"percent"},{"benchmark":"mmlu","model":"phi-3-medium-4k-instruct","score":77.83,"metric":"percent"},{"benchmark":"winogrande","model":"phi-3-medium-4k-instruct","score":72.69,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3-medium-4k-instruct","score":79.38,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v3.0-instruct","score":64.59,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v3.0-instruct","score":81.96,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v3.0-instruct","score":54.25,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v3.0-instruct","score":71.11,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v3.0-instruct","score":77.19,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v3.0-instruct","score":85.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v2.5-instruct","score":61.95,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v2.5-instruct","score":80.71,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v2.5-instruct","score":53.17,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v2.5-instruct","score":67.44,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v2.5-instruct","score":79.72,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v2.5-instruct","score":85.52,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v2.6-instruct","score":62.54,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v2.6-instruct","score":80.56,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v2.6-instruct","score":53.43,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v2.6-instruct","score":67.53,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v2.6-instruct","score":78.77,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v2.6-instruct","score":83.78,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v2.2-instruct","score":59.9,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v2.2-instruct","score":80.16,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v2.2-instruct","score":58.34,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v2.2-instruct","score":64.34,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v2.2-instruct","score":75.3,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v2.2-instruct","score":81.12,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v2.3-instruct","score":59.3,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v2.3-instruct","score":80.11,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v2.3-instruct","score":57.42,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v2.3-instruct","score":64.57,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v2.3-instruct","score":76.24,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v2.3-instruct","score":81.27,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v2.1-instruct","score":59.56,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v2.1-instruct","score":80.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v2.1-instruct","score":59.35,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v2.1-instruct","score":64.18,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v2.1-instruct","score":75.06,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v2.1-instruct","score":80.59,"metric":"percent"},{"benchmark":"arc-challenge","model":"openchat-3.5-0106-gemma","score":64.68,"metric":"percent"},{"benchmark":"hellaswag","model":"openchat-3.5-0106-gemma","score":81.08,"metric":"percent"},{"benchmark":"truthfulqa","model":"openchat-3.5-0106-gemma","score":54.93,"metric":"percent"},{"benchmark":"mmlu","model":"openchat-3.5-0106-gemma","score":64.69,"metric":"percent"},{"benchmark":"winogrande","model":"openchat-3.5-0106-gemma","score":78.3,"metric":"percent"},{"benchmark":"gsm8k","model":"openchat-3.5-0106-gemma","score":72.86,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-11b-v2.0-instruct","score":58.62,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-11b-v2.0-instruct","score":78.65,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-11b-v2.0-instruct","score":54.65,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-11b-v2.0-instruct","score":63.71,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-11b-v2.0-instruct","score":76.32,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-11b-v2.0-instruct","score":76.27,"metric":"percent"},{"benchmark":"arc-challenge","model":"meta-llama-3-8b-instruct","score":60.75,"metric":"percent"},{"benchmark":"hellaswag","model":"meta-llama-3-8b-instruct","score":78.55,"metric":"percent"},{"benchmark":"truthfulqa","model":"meta-llama-3-8b-instruct","score":51.65,"metric":"percent"},{"benchmark":"mmlu","model":"meta-llama-3-8b-instruct","score":67.07,"metric":"percent"},{"benchmark":"winogrande","model":"meta-llama-3-8b-instruct","score":74.51,"metric":"percent"},{"benchmark":"gsm8k","model":"meta-llama-3-8b-instruct","score":68.69,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-instruct-v0.2","score":63.14,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-instruct-v0.2","score":84.88,"metric":"percent"},{"benchmark":"truthfulqa","model":"mistral-7b-instruct-v0.2","score":68.26,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-instruct-v0.2","score":60.78,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b-instruct-v0.2","score":77.19,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-instruct-v0.2","score":40.03,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-4.5b-v3-instruct","score":56.06,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-4.5b-v3-instruct","score":73.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-4.5b-v3-instruct","score":50.79,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-4.5b-v3-instruct","score":63.66,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-4.5b-v3-instruct","score":71.19,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-4.5b-v3-instruct","score":73.69,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-7b","score":61.09,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-7b","score":82.47,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-7b","score":44.91,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-7b","score":66.03,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-7b","score":78.45,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-7b","score":52.77,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-32b-chat","score":66.04,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-32b-chat","score":85.49,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-32b-chat","score":66.95,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-32b-chat","score":74.99,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-32b-chat","score":77.19,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-14b-chat","score":58.7,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-14b-chat","score":82.27,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-14b-chat","score":60.36,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-14b-chat","score":68.57,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-14b-chat","score":73.09,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-14b-chat","score":30.63,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-7b-chat","score":55.89,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-7b-chat","score":78.56,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-7b-chat","score":53.54,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-7b-chat","score":61.65,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-7b-chat","score":67.72,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-7b-chat","score":13.57,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-instruct-v0.1","score":54.52,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-instruct-v0.1","score":75.63,"metric":"percent"},{"benchmark":"truthfulqa","model":"mistral-7b-instruct-v0.1","score":56.28,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-instruct-v0.1","score":55.38,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b-instruct-v0.1","score":73.72,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-instruct-v0.1","score":14.25,"metric":"percent"},{"benchmark":"arc-challenge","model":"bielik-7b-instruct-v0.1","score":47.53,"metric":"percent"},{"benchmark":"hellaswag","model":"bielik-7b-instruct-v0.1","score":68.91,"metric":"percent"},{"benchmark":"truthfulqa","model":"bielik-7b-instruct-v0.1","score":46.18,"metric":"percent"},{"benchmark":"mmlu","model":"bielik-7b-instruct-v0.1","score":49.47,"metric":"percent"},{"benchmark":"winogrande","model":"bielik-7b-instruct-v0.1","score":65.51,"metric":"percent"},{"benchmark":"gsm8k","model":"bielik-7b-instruct-v0.1","score":29.95,"metric":"percent"},{"benchmark":"browsecomp","model":"mirothinker-v1.5-30b","score":56.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"mirothinker-v1.5-30b","score":66.8,"metric":"percent"},{"benchmark":"hle","model":"mirothinker-v1.5-30b","score":31,"metric":"avg@3"},{"benchmark":"gaia","model":"mirothinker-v1.5-30b","score":72,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"mirothinker-v1.5-30b","score":73.1,"metric":"avg@3"},{"benchmark":"frames","model":"mirothinker-v1.5-30b","score":87.3,"metric":"percent"},{"benchmark":"seal-0","model":"mirothinker-v1.5-30b","score":46.2,"metric":"percent"},{"benchmark":"browsecomp","model":"mirothinker-v1.5-235b","score":69.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"mirothinker-v1.5-235b","score":71.5,"metric":"percent"},{"benchmark":"hle","model":"mirothinker-v1.5-235b","score":39.2,"metric":"avg@3"},{"benchmark":"gaia","model":"mirothinker-v1.5-235b","score":80.8,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"mirothinker-v1.5-235b","score":77.1,"metric":"avg@3"},{"benchmark":"frames","model":"mirothinker-v1.5-235b","score":88.3,"metric":"percent"},{"benchmark":"seal-0","model":"mirothinker-v1.5-235b","score":52.7,"metric":"percent"},{"benchmark":"bfcl-v3","model":"lfm2.5-1.2b-instruct","score":49.12,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-1.7b","score":46.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.0-1b","score":52.43,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemma-3-1b-it","score":16.64,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2.5-1.2b-instruct","score":14,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-1.7b","score":9.33,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-4.0-1b","score":3.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-1b-it","score":1,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-1.2b-instruct","score":60.98,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-1.7b","score":56.48,"metric":"percent"},{"benchmark":"multi-if","model":"granite-4.0-1b","score":43.65,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-3-1b-it","score":44.31,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-1.2b-instruct","score":47.33,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-1.7b","score":21.33,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.0-1b","score":21,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-3-1b-it","score":20.47,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-1.2b-instruct","score":86.23,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-1.7b","score":73.68,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-1b","score":79.61,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-1b-it","score":63.25,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-1.2b-instruct","score":44.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":42.91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-1b","score":33.53,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-1b-it","score":14.04,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2.5-1.2b-instruct","score":38.89,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-1.7b","score":34.85,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.0-1b","score":24.24,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.2-1b-instruct","score":16.57,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-3-1b-it","score":24.24,"metric":"percent"},{"benchmark":"livecodebench","model":"nouscoder-14b","score":67.87,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5-high-code-web","score":12.6,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5-high-code","score":10.6,"metric":"percent"},{"benchmark":"critpt","model":"gemini-3-pro","score":9.1,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5-high","score":5.7,"metric":"percent"},{"benchmark":"critpt","model":"gemini-2.5-pro","score":2,"metric":"percent"},{"benchmark":"critpt","model":"o3-high","score":1.4,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-r1","score":1.1,"metric":"percent"},{"benchmark":"critpt","model":"gemini-2.5-flash","score":1.1,"metric":"percent"},{"benchmark":"critpt","model":"o4-mini-high","score":0.6,"metric":"percent"},{"benchmark":"critpt","model":"claude-opus-4","score":0.3,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5-minimal","score":0,"metric":"percent"},{"benchmark":"critpt","model":"llama-4-maverick","score":0,"metric":"percent"},{"benchmark":"critpt","model":"gpt-4o","score":0,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5.2-high","score":11.6,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon-h1r-7b","score":88.1,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-8b","score":77.9,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-0528-qwen3-8b","score":83.3,"metric":"percent"},{"benchmark":"aime-2024","model":"phi-4-reasoning-plus","score":77.2,"metric":"percent"},{"benchmark":"aime-2024","model":"apriel-1.5-15b-thinker","score":86.2,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-20b","score":83.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-32b","score":79.4,"metric":"percent"},{"benchmark":"aime-2024","model":"nemotron-h-47b-reasoning","score":64.6,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon-h1r-7b","score":83.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b","score":65.8,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0528-qwen3-8b","score":75.8,"metric":"percent"},{"benchmark":"aime-2025","model":"phi-4-reasoning-plus","score":71.2,"metric":"percent"},{"benchmark":"aime-2025","model":"apriel-1.5-15b-thinker","score":80,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b","score":84.4,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b","score":71,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-h-47b-reasoning","score":51.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"falcon-h1r-7b","score":64.9,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-8b","score":41,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-r1-0528-qwen3-8b","score":54.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"phi-4-reasoning-plus","score":47.7,"metric":"percent"},{"benchmark":"hmmt-2025","model":"apriel-1.5-15b-thinker","score":61,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-oss-20b","score":64.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-32b","score":49.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"nemotron-h-47b-reasoning","score":34.2,"metric":"percent"},{"benchmark":"amobench","model":"falcon-h1r-7b","score":36.3,"metric":"percent"},{"benchmark":"amobench","model":"qwen3-8b","score":14.1,"metric":"percent"},{"benchmark":"amobench","model":"deepseek-r1-0528-qwen3-8b","score":23.3,"metric":"percent"},{"benchmark":"amobench","model":"phi-4-reasoning-plus","score":15,"metric":"percent"},{"benchmark":"amobench","model":"apriel-1.5-15b-thinker","score":22.2,"metric":"percent"},{"benchmark":"amobench","model":"gpt-oss-20b","score":26,"metric":"percent"},{"benchmark":"amobench","model":"qwen3-32b","score":21.3,"metric":"percent"},{"benchmark":"amobench","model":"nemotron-h-47b-reasoning","score":7,"metric":"percent"},{"benchmark":"math500","model":"falcon-h1r-7b","score":97.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b","score":97.4,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1-0528-qwen3-8b","score":96.8,"metric":"percent"},{"benchmark":"math500","model":"phi-4-reasoning-plus","score":95.4,"metric":"percent"},{"benchmark":"math500","model":"apriel-1.5-15b-thinker","score":97.2,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-20b","score":94.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-32b","score":96.8,"metric":"percent"},{"benchmark":"math500","model":"nemotron-h-47b-reasoning","score":91.4,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon-h1r-7b","score":68.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b","score":53,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-0528-qwen3-8b","score":57.2,"metric":"percent"},{"benchmark":"livecodebench","model":"phi-4-reasoning-plus","score":53.1,"metric":"percent"},{"benchmark":"livecodebench","model":"apriel-1.5-15b-thinker","score":53,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b","score":72,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b","score":61,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-h-47b-reasoning","score":47.4,"metric":"percent"},{"benchmark":"scicode","model":"falcon-h1r-7b","score":28.3,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-8b","score":28.3,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-r1-0528-qwen3-8b","score":22.2,"metric":"percent"},{"benchmark":"scicode","model":"phi-4-reasoning-plus","score":29.8,"metric":"percent"},{"benchmark":"scicode","model":"apriel-1.5-15b-thinker","score":31.9,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-20b","score":34.9,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-32b","score":36.4,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-h-47b-reasoning","score":26.1,"metric":"percent"},{"benchmark":"scicode-main","model":"falcon-h1r-7b","score":3.9,"metric":"percent"},{"benchmark":"scicode-main","model":"qwen3-8b","score":6.7,"metric":"percent"},{"benchmark":"scicode-main","model":"deepseek-r1-0528-qwen3-8b","score":2.6,"metric":"percent"},{"benchmark":"scicode-main","model":"phi-4-reasoning-plus","score":7.2,"metric":"percent"},{"benchmark":"scicode-main","model":"apriel-1.5-15b-thinker","score":8.2,"metric":"percent"},{"benchmark":"scicode-main","model":"gpt-oss-20b","score":6.2,"metric":"percent"},{"benchmark":"scicode-main","model":"qwen3-32b","score":9.2,"metric":"percent"},{"benchmark":"scicode-main","model":"nemotron-h-47b-reasoning","score":4.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"falcon-h1r-7b","score":61.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-8b","score":61.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-0528-qwen3-8b","score":61.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"phi-4-reasoning-plus","score":67.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apriel-1.5-15b-thinker","score":68.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b","score":61.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-32b","score":67.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-h-47b-reasoning","score":56.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-h1r-7b","score":72.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b","score":63.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-0528-qwen3-8b","score":69.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-4-reasoning-plus","score":79.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apriel-1.5-15b-thinker","score":76.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b","score":75.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b","score":73.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-h-47b-reasoning","score":78.6,"metric":"percent"},{"benchmark":"hle","model":"falcon-h1r-7b","score":11.1,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3-8b","score":4.2,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-r1-0528-qwen3-8b","score":5.6,"metric":"avg@3"},{"benchmark":"hle","model":"phi-4-reasoning-plus","score":5.9,"metric":"avg@3"},{"benchmark":"hle","model":"apriel-1.5-15b-thinker","score":12,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-oss-20b","score":9.8,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3-32b","score":8.3,"metric":"avg@3"},{"benchmark":"hle","model":"nemotron-h-47b-reasoning","score":4.4,"metric":"avg@3"},{"benchmark":"ifbench","model":"falcon-h1r-7b","score":53.4,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-8b","score":35.3,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-r1-0528-qwen3-8b","score":29.2,"metric":"percent"},{"benchmark":"ifbench","model":"phi-4-reasoning-plus","score":51.7,"metric":"percent"},{"benchmark":"ifbench","model":"apriel-1.5-15b-thinker","score":55.8,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b","score":69.4,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-32b","score":35.4,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-h-47b-reasoning","score":34.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"falcon-h1r-7b","score":25.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-8b","score":27.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-20b","score":60.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-32b","score":29.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-h-47b-reasoning","score":11.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5-high","score":41.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"gpt-5-high","score":77.9,"metric":"avg@3"},{"benchmark":"frames","model":"gpt-5-high","score":86,"metric":"percent"},{"benchmark":"seal-0","model":"gpt-5-high","score":51.4,"metric":"percent"},{"benchmark":"browsecomp","model":"chatgpt-agent","score":68.9,"metric":"percent"},{"benchmark":"hle","model":"chatgpt-agent","score":41.6,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-3-pro","score":45.8,"metric":"avg@3"},{"benchmark":"hle","model":"claude-sonnet-4.5","score":32,"metric":"avg@3"},{"benchmark":"hle","model":"seed1.8","score":40.9,"metric":"avg@3"},{"benchmark":"hle","model":"kimi-k2-thinking","score":44.9,"metric":"avg@3"},{"benchmark":"browsecomp","model":"glm-4.7","score":67.5,"metric":"percent"},{"benchmark":"hle","model":"glm-4.7","score":42.8,"metric":"avg@3"},{"benchmark":"browsecomp","model":"minimax-m2.1","score":62,"metric":"percent"},{"benchmark":"browsecomp","model":"mimo-v2-flash","score":58.3,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v3.2","score":67.6,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.2","score":40.8,"metric":"avg@3"},{"benchmark":"critpt","model":"gpt-5.2-extra-high","score":11.6,"metric":"percent"},{"benchmark":"critpt","model":"gemini-3-pro-preview","score":8.6,"metric":"percent"},{"benchmark":"critpt","model":"gemini-3-flash","score":4.9,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5.1-high","score":4.6,"metric":"percent"},{"benchmark":"critpt","model":"claude-opus-4.5","score":4.3,"metric":"percent"},{"benchmark":"critpt","model":"mimo-v2-flash","score":4.3,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v3.2","score":2.9,"metric":"percent"},{"benchmark":"critpt","model":"grok-4.1-fast","score":2.9,"metric":"percent"},{"benchmark":"critpt","model":"kimi-k2-thinking","score":2.6,"metric":"percent"},{"benchmark":"critpt","model":"grok-4","score":2,"metric":"percent"},{"benchmark":"critpt","model":"glm-4.7","score":1.7,"metric":"percent"},{"benchmark":"critpt","model":"gpt-oss-120b-high","score":1.4,"metric":"percent"},{"benchmark":"critpt","model":"gpt-oss-120b","score":1.1,"metric":"percent"},{"benchmark":"critpt","model":"claude-sonnet-4.5","score":1.1,"metric":"percent"},{"benchmark":"critpt","model":"nemotron-3-nano-30b-a3b","score":1.1,"metric":"percent"},{"benchmark":"critpt","model":"minimax-m2.1","score":0.9,"metric":"percent"},{"benchmark":"critpt","model":"apriel-1.5-15b-thinker","score":0.3,"metric":"percent"},{"benchmark":"critpt","model":"mistral-large-3","score":0,"metric":"percent"},{"benchmark":"critpt","model":"nova-pro","score":0,"metric":"percent"},{"benchmark":"critpt","model":"nova-lite","score":0,"metric":"percent"},{"benchmark":"critpt","model":"kat-coder-pro-v1","score":0,"metric":"percent"},{"benchmark":"critpt","model":"k2-v2","score":0,"metric":"percent"},{"benchmark":"critpt","model":"qwen3-235b-a22b-2507","score":0,"metric":"percent"},{"benchmark":"critpt","model":"midm-k-2.5-pro","score":0,"metric":"percent"},{"benchmark":"tau2-telecom","model":"midm-k-2.5-pro","score":87,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"midm-k-2.5-pro","score":83,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"midm-k-2.5-pro","score":2,"metric":"percent"},{"benchmark":"aa-lcr","model":"midm-k-2.5-pro","score":9,"metric":"percent"},{"benchmark":"hle","model":"midm-k-2.5-pro","score":7.7,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"midm-k-2.5-pro","score":70,"metric":"percent"},{"benchmark":"scicode","model":"midm-k-2.5-pro","score":33,"metric":"percent"},{"benchmark":"ifbench","model":"midm-k-2.5-pro","score":49,"metric":"percent"},{"benchmark":"mmlu","model":"solar-open-100b","score":88.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"solar-open-100b","score":80.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"solar-open-100b","score":68.1,"metric":"percent"},{"benchmark":"hle","model":"solar-open-100b","score":10.5,"metric":"avg@3"},{"benchmark":"aime-2024","model":"solar-open-100b","score":91.7,"metric":"percent"},{"benchmark":"aime-2025","model":"solar-open-100b","score":84.3,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"solar-open-100b","score":73.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"solar-open-100b","score":80,"metric":"percent"},{"benchmark":"livecodebench","model":"solar-open-100b","score":74.2,"metric":"percent"},{"benchmark":"ifbench","model":"solar-open-100b","score":53.7,"metric":"percent"},{"benchmark":"ifeval","model":"solar-open-100b","score":88,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"solar-open-100b","score":74.8,"metric":"percent"},{"benchmark":"writingbench","model":"solar-open-100b","score":7.51,"metric":"score"},{"benchmark":"tau2-airline","model":"solar-open-100b","score":52.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"solar-open-100b","score":55.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"solar-open-100b","score":59.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"solar-open-100b","score":35,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-120b-high","score":88.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b-high","score":80.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b-high","score":78,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-120b-high","score":18.4,"metric":"avg@3"},{"benchmark":"aime-2024","model":"gpt-oss-120b-high","score":94.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b-high","score":91.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-oss-120b-high","score":80,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-oss-120b-high","score":73.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b-high","score":89.9,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-120b-high","score":70.8,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-120b-high","score":91.4,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-oss-120b-high","score":79.6,"metric":"percent"},{"benchmark":"writingbench","model":"gpt-oss-120b-high","score":6.61,"metric":"score"},{"benchmark":"tau2-airline","model":"gpt-oss-120b-high","score":56,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-120b-high","score":57.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-oss-120b-high","score":76.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-120b-high","score":48.3,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-120b-medium","score":87.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b-medium","score":78.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b-medium","score":69.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-120b-medium","score":7.23,"metric":"avg@3"},{"benchmark":"aime-2024","model":"gpt-oss-120b-medium","score":77.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b-medium","score":75,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-oss-120b-medium","score":63.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-oss-120b-medium","score":66.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b-medium","score":82.8,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-120b-medium","score":61.2,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-120b-medium","score":86.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-oss-120b-medium","score":72.7,"metric":"percent"},{"benchmark":"writingbench","model":"gpt-oss-120b-medium","score":6.55,"metric":"score"},{"benchmark":"tau2-airline","model":"gpt-oss-120b-medium","score":52.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-120b-medium","score":47.4,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-oss-120b-medium","score":68.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-120b-medium","score":45,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.5-air","score":83.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-air","score":81.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.5-air","score":75.8,"metric":"percent"},{"benchmark":"hle","model":"glm-4.5-air","score":10.8,"metric":"avg@3"},{"benchmark":"aime-2024","model":"glm-4.5-air","score":88.7,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.5-air","score":82.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"glm-4.5-air","score":66.7,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-4.5-air","score":70,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-air","score":71.9,"metric":"percent"},{"benchmark":"ifbench","model":"glm-4.5-air","score":37.8,"metric":"percent"},{"benchmark":"ifeval","model":"glm-4.5-air","score":86.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"glm-4.5-air","score":62.5,"metric":"percent"},{"benchmark":"writingbench","model":"glm-4.5-air","score":7.4,"metric":"score"},{"benchmark":"tau2-airline","model":"glm-4.5-air","score":60.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-4.5-air","score":28.1,"metric":"percent"},{"benchmark":"tau2-retail","model":"glm-4.5-air","score":71.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-4.5-air","score":37.3,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2.5-vl-1.6b","score":50.67,"metric":"percent"},{"benchmark":"mm-ifeval","model":"lfm2.5-vl-1.6b","score":52.29,"metric":"percent"},{"benchmark":"blink","model":"lfm2.5-vl-1.6b","score":48.82,"metric":"percent"},{"benchmark":"infovqa","model":"lfm2.5-vl-1.6b","score":62.71,"metric":"percent"},{"benchmark":"ocrbench","model":"lfm2.5-vl-1.6b","score":41.44,"metric":"percent"},{"benchmark":"realworldqa","model":"lfm2.5-vl-1.6b","score":64.84,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2.5-vl-1.6b","score":40.56,"metric":"percent"},{"benchmark":"mmmb","model":"lfm2.5-vl-1.6b","score":76.96,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"lfm2.5-vl-1.6b","score":65.9,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2-vl-1.6b","score":49.87,"metric":"percent"},{"benchmark":"mm-ifeval","model":"lfm2-vl-1.6b","score":46.35,"metric":"percent"},{"benchmark":"blink","model":"lfm2-vl-1.6b","score":44.5,"metric":"percent"},{"benchmark":"infovqa","model":"lfm2-vl-1.6b","score":58.35,"metric":"percent"},{"benchmark":"ocrbench","model":"lfm2-vl-1.6b","score":35.11,"metric":"percent"},{"benchmark":"realworldqa","model":"lfm2-vl-1.6b","score":65.75,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2-vl-1.6b","score":39.67,"metric":"percent"},{"benchmark":"mmmb","model":"lfm2-vl-1.6b","score":72.13,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"lfm2-vl-1.6b","score":60.57,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-1b","score":50.27,"metric":"percent"},{"benchmark":"mm-ifeval","model":"internvl3.5-1b","score":36.17,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-1b","score":44.19,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-1b","score":60.99,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3.5-1b","score":33.53,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-1b","score":57.12,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-1b","score":41.89,"metric":"percent"},{"benchmark":"mmmb","model":"internvl3.5-1b","score":68.93,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"internvl3.5-1b","score":58.32,"metric":"percent"},{"benchmark":"mmstar","model":"fastvlm-1.5b","score":53.13,"metric":"percent"},{"benchmark":"mm-ifeval","model":"fastvlm-1.5b","score":24.99,"metric":"percent"},{"benchmark":"blink","model":"fastvlm-1.5b","score":43.29,"metric":"percent"},{"benchmark":"infovqa","model":"fastvlm-1.5b","score":23.92,"metric":"percent"},{"benchmark":"ocrbench","model":"fastvlm-1.5b","score":26.61,"metric":"percent"},{"benchmark":"realworldqa","model":"fastvlm-1.5b","score":61.56,"metric":"percent"},{"benchmark":"mmmu","model":"fastvlm-1.5b","score":38.78,"metric":"percent"},{"benchmark":"mmmb","model":"fastvlm-1.5b","score":64.84,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"fastvlm-1.5b","score":50.89,"metric":"percent"},{"benchmark":"alpacaeval","model":"lfm2.5-audio-1.5b","score":3.76,"metric":"score"},{"benchmark":"voicebench-commoneval","model":"lfm2.5-audio-1.5b","score":3.53,"metric":"score"},{"benchmark":"voicebench-wildvoice","model":"lfm2.5-audio-1.5b","score":3.15,"metric":"score"},{"benchmark":"voicebench-sd-qa","model":"lfm2.5-audio-1.5b","score":30.92,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"lfm2.5-audio-1.5b","score":33.04,"metric":"percent"},{"benchmark":"obqa","model":"lfm2.5-audio-1.5b","score":44.4,"metric":"percent"},{"benchmark":"bbh","model":"lfm2.5-audio-1.5b","score":49.54,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-audio-1.5b","score":28.48,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"lfm2.5-audio-1.5b","score":99.04,"metric":"percent"},{"benchmark":"alpacaeval","model":"lfm2-audio-1.5b","score":3.71,"metric":"score"},{"benchmark":"voicebench-commoneval","model":"lfm2-audio-1.5b","score":3.49,"metric":"score"},{"benchmark":"voicebench-wildvoice","model":"lfm2-audio-1.5b","score":3.17,"metric":"score"},{"benchmark":"voicebench-sd-qa","model":"lfm2-audio-1.5b","score":30.56,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"lfm2-audio-1.5b","score":31.95,"metric":"percent"},{"benchmark":"obqa","model":"lfm2-audio-1.5b","score":44.4,"metric":"percent"},{"benchmark":"bbh","model":"lfm2-audio-1.5b","score":30.54,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-audio-1.5b","score":31.23,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"lfm2-audio-1.5b","score":97.31,"metric":"percent"},{"benchmark":"alpacaeval","model":"moshi","score":2.01,"metric":"score"},{"benchmark":"voicebench-commoneval","model":"moshi","score":1.6,"metric":"score"},{"benchmark":"voicebench-wildvoice","model":"moshi","score":1.3,"metric":"score"},{"benchmark":"voicebench-sd-qa","model":"moshi","score":15.64,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"moshi","score":24.04,"metric":"percent"},{"benchmark":"obqa","model":"moshi","score":25.93,"metric":"percent"},{"benchmark":"bbh","model":"moshi","score":47.4,"metric":"percent"},{"benchmark":"ifeval","model":"moshi","score":10.12,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"moshi","score":44.23,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen2.5-omni-3b","score":3.72,"metric":"score"},{"benchmark":"voicebench-commoneval","model":"qwen2.5-omni-3b","score":3.51,"metric":"score"},{"benchmark":"voicebench-wildvoice","model":"qwen2.5-omni-3b","score":3.42,"metric":"score"},{"benchmark":"voicebench-sd-qa","model":"qwen2.5-omni-3b","score":44.94,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"qwen2.5-omni-3b","score":55.29,"metric":"percent"},{"benchmark":"obqa","model":"qwen2.5-omni-3b","score":76.26,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-omni-3b","score":61.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-omni-3b","score":32.9,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"qwen2.5-omni-3b","score":88.46,"metric":"percent"},{"benchmark":"alpacaeval","model":"mini-omni2","score":2.32,"metric":"score"},{"benchmark":"voicebench-commoneval","model":"mini-omni2","score":2.18,"metric":"score"},{"benchmark":"voicebench-wildvoice","model":"mini-omni2","score":1.79,"metric":"score"},{"benchmark":"voicebench-sd-qa","model":"mini-omni2","score":9.31,"metric":"percent"},{"benchmark":"voicebench-mmsu","model":"mini-omni2","score":24.27,"metric":"percent"},{"benchmark":"obqa","model":"mini-omni2","score":26.59,"metric":"percent"},{"benchmark":"bbh","model":"mini-omni2","score":46.4,"metric":"percent"},{"benchmark":"ifeval","model":"mini-omni2","score":11.56,"metric":"percent"},{"benchmark":"voicebench-advbench","model":"mini-omni2","score":57.5,"metric":"percent"},{"benchmark":"asr-ami","model":"lfm2.5-audio-1.5b","score":15.63,"metric":"wer"},{"benchmark":"asr-earnings22","model":"lfm2.5-audio-1.5b","score":14.56,"metric":"wer"},{"benchmark":"asr-gigaspeech","model":"lfm2.5-audio-1.5b","score":10.47,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"lfm2.5-audio-1.5b","score":1.95,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"lfm2.5-audio-1.5b","score":4.3,"metric":"wer"},{"benchmark":"asr-spgispeech","model":"lfm2.5-audio-1.5b","score":2.76,"metric":"wer"},{"benchmark":"asr-ted-lium","model":"lfm2.5-audio-1.5b","score":3.47,"metric":"wer"},{"benchmark":"asr-voxpopuli","model":"lfm2.5-audio-1.5b","score":7.13,"metric":"wer"},{"benchmark":"asr-ami","model":"lfm2-audio-1.5b","score":15.36,"metric":"wer"},{"benchmark":"asr-earnings22","model":"lfm2-audio-1.5b","score":19.75,"metric":"wer"},{"benchmark":"asr-gigaspeech","model":"lfm2-audio-1.5b","score":10.63,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"lfm2-audio-1.5b","score":2.03,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"lfm2-audio-1.5b","score":4.39,"metric":"wer"},{"benchmark":"asr-spgispeech","model":"lfm2-audio-1.5b","score":4.17,"metric":"wer"},{"benchmark":"asr-ted-lium","model":"lfm2-audio-1.5b","score":3.56,"metric":"wer"},{"benchmark":"asr-voxpopuli","model":"lfm2-audio-1.5b","score":9.93,"metric":"wer"},{"benchmark":"asr-ami","model":"qwen2.5-omni-3b","score":15.05,"metric":"wer"},{"benchmark":"asr-earnings22","model":"qwen2.5-omni-3b","score":14.81,"metric":"wer"},{"benchmark":"asr-gigaspeech","model":"qwen2.5-omni-3b","score":11.76,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"qwen2.5-omni-3b","score":2.14,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"qwen2.5-omni-3b","score":4.52,"metric":"wer"},{"benchmark":"asr-spgispeech","model":"qwen2.5-omni-3b","score":3.24,"metric":"wer"},{"benchmark":"asr-ted-lium","model":"qwen2.5-omni-3b","score":5.08,"metric":"wer"},{"benchmark":"asr-voxpopuli","model":"qwen2.5-omni-3b","score":5.6,"metric":"wer"},{"benchmark":"asr-ami","model":"whisper-large-v3","score":15.95,"metric":"wer"},{"benchmark":"asr-earnings22","model":"whisper-large-v3","score":11.29,"metric":"wer"},{"benchmark":"asr-gigaspeech","model":"whisper-large-v3","score":10.02,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"whisper-large-v3","score":2.01,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"whisper-large-v3","score":3.91,"metric":"wer"},{"benchmark":"asr-spgispeech","model":"whisper-large-v3","score":2.94,"metric":"wer"},{"benchmark":"asr-ted-lium","model":"whisper-large-v3","score":3.86,"metric":"wer"},{"benchmark":"asr-voxpopuli","model":"whisper-large-v3","score":9.54,"metric":"wer"},{"benchmark":"mmlu-redux","model":"deepseek-r1-distill-qwen-1.5b","score":53,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-1.7b","score":74.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"smollm3-3b","score":75.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-4b","score":83.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-r1-distill-llama-8b","score":78.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"youtu-llm-2b","score":75.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-distill-qwen-1.5b","score":36.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":54.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm3-3b","score":53,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b","score":69.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-distill-llama-8b","score":57.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"youtu-llm-2b","score":61.6,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-r1-distill-qwen-1.5b","score":29.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-1.7b","score":70.4,"metric":"percent"},{"benchmark":"ifeval","model":"smollm3-3b","score":60.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b","score":83.6,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-r1-distill-llama-8b","score":34.6,"metric":"percent"},{"benchmark":"ifeval","model":"youtu-llm-2b","score":81.2,"metric":"percent"},{"benchmark":"drop","model":"deepseek-r1-distill-qwen-1.5b","score":41.3,"metric":"percent"},{"benchmark":"drop","model":"qwen3-1.7b","score":72.5,"metric":"percent"},{"benchmark":"drop","model":"smollm3-3b","score":72,"metric":"percent"},{"benchmark":"drop","model":"qwen3-4b","score":82.9,"metric":"percent"},{"benchmark":"drop","model":"deepseek-r1-distill-llama-8b","score":73.1,"metric":"percent"},{"benchmark":"drop","model":"youtu-llm-2b","score":86.7,"metric":"percent"},{"benchmark":"musr","model":"deepseek-r1-distill-qwen-1.5b","score":43.8,"metric":"percent"},{"benchmark":"musr","model":"qwen3-1.7b","score":56.6,"metric":"percent"},{"benchmark":"musr","model":"smollm3-3b","score":54.1,"metric":"percent"},{"benchmark":"musr","model":"qwen3-4b","score":60.5,"metric":"percent"},{"benchmark":"musr","model":"deepseek-r1-distill-llama-8b","score":59.7,"metric":"percent"},{"benchmark":"musr","model":"youtu-llm-2b","score":57.4,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1-distill-qwen-1.5b","score":84.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-1.7b","score":89.8,"metric":"percent"},{"benchmark":"math500","model":"smollm3-3b","score":91.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-4b","score":95,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1-distill-llama-8b","score":90.8,"metric":"percent"},{"benchmark":"math500","model":"youtu-llm-2b","score":93.7,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-distill-qwen-1.5b","score":30.2,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-1.7b","score":44.2,"metric":"percent"},{"benchmark":"aime-2024","model":"smollm3-3b","score":46.7,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-4b","score":73.3,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-distill-llama-8b","score":52.5,"metric":"percent"},{"benchmark":"aime-2024","model":"youtu-llm-2b","score":65.4,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-distill-qwen-1.5b","score":23.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-1.7b","score":37.1,"metric":"percent"},{"benchmark":"aime-2025","model":"smollm3-3b","score":34.2,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b","score":64.2,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-distill-llama-8b","score":34.4,"metric":"percent"},{"benchmark":"aime-2025","model":"youtu-llm-2b","score":49.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-distill-qwen-1.5b","score":33.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-1.7b","score":36.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"smollm3-3b","score":43.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b","score":55.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-distill-llama-8b","score":45.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"youtu-llm-2b","score":48,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-r1-distill-qwen-1.5b","score":31,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-1.7b","score":69.1,"metric":"percent"},{"benchmark":"bbh","model":"smollm3-3b","score":76.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-4b","score":87.8,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-r1-distill-llama-8b","score":77.8,"metric":"percent"},{"benchmark":"bbh","model":"youtu-llm-2b","score":77.5,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-r1-distill-qwen-1.5b","score":64,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-1.7b","score":84.8,"metric":"percent"},{"benchmark":"humaneval","model":"smollm3-3b","score":79.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-4b","score":95.4,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-r1-distill-llama-8b","score":88.1,"metric":"percent"},{"benchmark":"humaneval","model":"youtu-llm-2b","score":95.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-r1-distill-qwen-1.5b","score":59.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-1.7b","score":76.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"smollm3-3b","score":74.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-4b","score":87.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-r1-distill-llama-8b","score":82.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"youtu-llm-2b","score":89,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-r1-distill-qwen-1.5b","score":51.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-1.7b","score":80.5,"metric":"percent"},{"benchmark":"mbpp","model":"smollm3-3b","score":66.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-4b","score":92.3,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-r1-distill-llama-8b","score":73.9,"metric":"percent"},{"benchmark":"mbpp","model":"youtu-llm-2b","score":85,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-r1-distill-qwen-1.5b","score":44.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-1.7b","score":67.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"smollm3-3b","score":56.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-4b","score":77.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-r1-distill-llama-8b","score":61,"metric":"percent"},{"benchmark":"mbpp-plus","model":"youtu-llm-2b","score":71.7,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-distill-qwen-1.5b","score":19.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-1.7b","score":30.7,"metric":"percent"},{"benchmark":"livecodebench","model":"smollm3-3b","score":30.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b","score":48.5,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-distill-llama-8b","score":36.8,"metric":"percent"},{"benchmark":"livecodebench","model":"youtu-llm-2b","score":43.7,"metric":"percent"},{"benchmark":"gaia","model":"qwen3-1.7b","score":11.4,"metric":"percent"},{"benchmark":"gaia","model":"smollm3-3b","score":11.7,"metric":"percent"},{"benchmark":"gaia","model":"qwen3-4b","score":25.5,"metric":"percent"},{"benchmark":"gaia","model":"youtu-llm-2b","score":33.9,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"qwen3-1.7b","score":11.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"smollm3-3b","score":13.9,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"qwen3-4b","score":18.4,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"youtu-llm-2b","score":19.5,"metric":"avg@3"},{"benchmark":"swe-bench-verified","model":"qwen3-1.7b","score":0.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"smollm3-3b","score":7.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-4b","score":5.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"youtu-llm-2b","score":17.7,"metric":"percent"},{"benchmark":"enconda-bench","model":"qwen3-1.7b","score":10.8,"metric":"percent"},{"benchmark":"enconda-bench","model":"smollm3-3b","score":3.5,"metric":"percent"},{"benchmark":"enconda-bench","model":"qwen3-4b","score":16.1,"metric":"percent"},{"benchmark":"enconda-bench","model":"youtu-llm-2b","score":21.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-1.7b","score":55.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"smollm3-3b","score":31.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-4b","score":61.7,"metric":"percent"},{"benchmark":"bfcl-v3","model":"youtu-llm-2b","score":58,"metric":"percent"},{"benchmark":"mmlu-pro","model":"k-exaone","score":83.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-4.0-32b-thinking","score":81.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b-high","score":80.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k-exaone","score":79.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"exaone-4.0-32b-thinking","score":75.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b-high","score":80.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-235b-a22b-thinking-2507","score":81.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"k-exaone","score":13.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"exaone-4.0-32b-thinking","score":10.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-oss-120b-high","score":14.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-235b-a22b-thinking-2507","score":18.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v3.2-thinking","score":25.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"k-exaone","score":76.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"exaone-4.0-32b-thinking","score":66.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-oss-120b-high","score":75.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-235b-a22b-thinking-2507","score":74.8,"metric":"percent"},{"benchmark":"aime-2025","model":"k-exaone","score":92.8,"metric":"percent"},{"benchmark":"aime-2025","model":"exaone-4.0-32b-thinking","score":85.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b-high","score":92.5,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"k-exaone","score":86.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"exaone-4.0-32b-thinking","score":78.1,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-oss-120b-high","score":84.9,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-235b-a22b-thinking-2507","score":88.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"deepseek-v3.2-thinking","score":90.2,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"k-exaone","score":25.9,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"exaone-4.0-32b-thinking","score":4.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gpt-oss-120b-high","score":35.4,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-235b-a22b-thinking-2507","score":16,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"deepseek-v3.2-thinking","score":27.9,"metric":"percent"},{"benchmark":"livecodebench","model":"k-exaone","score":80.7,"metric":"percent"},{"benchmark":"livecodebench","model":"exaone-4.0-32b-thinking","score":66.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b-high","score":81.9,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-thinking","score":79.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"k-exaone","score":29,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-oss-120b-high","score":18.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-235b-a22b-thinking-2507","score":13.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"k-exaone","score":49.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-120b-high","score":62.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-235b-a22b-thinking-2507","score":25,"metric":"percent"},{"benchmark":"tau2-retail","model":"k-exaone","score":78.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"exaone-4.0-32b-thinking","score":67.5,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-oss-120b-high","score":69.1,"metric":"percent"},{"benchmark":"tau2-retail","model":"deepseek-v3.2-thinking","score":77.9,"metric":"percent"},{"benchmark":"tau2-airline","model":"k-exaone","score":60.4,"metric":"percent"},{"benchmark":"tau2-airline","model":"exaone-4.0-32b-thinking","score":52,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-oss-120b-high","score":60.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"deepseek-v3.2-thinking","score":66,"metric":"percent"},{"benchmark":"tau2-telecom","model":"k-exaone","score":73.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"exaone-4.0-32b-thinking","score":23.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-120b-high","score":60.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v3.2-thinking","score":85.8,"metric":"percent"},{"benchmark":"browsecomp","model":"k-exaone","score":31.4,"metric":"percent"},{"benchmark":"ifbench","model":"k-exaone","score":67.3,"metric":"percent"},{"benchmark":"ifbench","model":"exaone-4.0-32b-thinking","score":36,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-120b-high","score":69.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-235b-a22b-thinking-2507","score":52.6,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v3.2-thinking","score":62.5,"metric":"percent"},{"benchmark":"ifeval","model":"k-exaone","score":89.7,"metric":"percent"},{"benchmark":"ifeval","model":"exaone-4.0-32b-thinking","score":84.7,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-120b-high","score":89.5,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v3.2-thinking","score":92.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"k-exaone","score":53.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"exaone-4.0-32b-thinking","score":14,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-120b-high","score":50.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-235b-a22b-thinking-2507","score":67,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v3.2-thinking","score":65,"metric":"percent"},{"benchmark":"mrcr-128k","model":"k-exaone","score":52.3,"metric":"percent"},{"benchmark":"mrcr-128k","model":"exaone-4.0-32b-thinking","score":20.1,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gpt-oss-120b-high","score":29.9,"metric":"percent"},{"benchmark":"mrcr-128k","model":"qwen3-235b-a22b-thinking-2507","score":58.6,"metric":"percent"},{"benchmark":"mrcr-128k","model":"deepseek-v3.2-thinking","score":57.7,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"k-exaone","score":67.3,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"exaone-4.0-32b-thinking","score":67.7,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"gpt-oss-120b-high","score":62.4,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-235b-a22b-thinking-2507","score":71.6,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"deepseek-v3.2-thinking","score":72.1,"metric":"percent"},{"benchmark":"kobolt","model":"k-exaone","score":61.8,"metric":"percent"},{"benchmark":"kobolt","model":"exaone-4.0-32b-thinking","score":25.4,"metric":"percent"},{"benchmark":"kobolt","model":"gpt-oss-120b-high","score":54.3,"metric":"percent"},{"benchmark":"kobolt","model":"qwen3-235b-a22b-thinking-2507","score":56.1,"metric":"percent"},{"benchmark":"kobolt","model":"deepseek-v3.2-thinking","score":62.7,"metric":"percent"},{"benchmark":"click","model":"k-exaone","score":83.9,"metric":"percent"},{"benchmark":"click","model":"exaone-4.0-32b-thinking","score":78.8,"metric":"percent"},{"benchmark":"click","model":"gpt-oss-120b-high","score":74.6,"metric":"percent"},{"benchmark":"click","model":"qwen3-235b-a22b-thinking-2507","score":81.3,"metric":"percent"},{"benchmark":"click","model":"deepseek-v3.2-thinking","score":86.3,"metric":"percent"},{"benchmark":"hrm8k","model":"k-exaone","score":90.9,"metric":"percent"},{"benchmark":"hrm8k","model":"exaone-4.0-32b-thinking","score":89.4,"metric":"percent"},{"benchmark":"hrm8k","model":"gpt-oss-120b-high","score":91.6,"metric":"percent"},{"benchmark":"hrm8k","model":"qwen3-235b-a22b-thinking-2507","score":92,"metric":"percent"},{"benchmark":"hrm8k","model":"deepseek-v3.2-thinking","score":90.6,"metric":"percent"},{"benchmark":"ko-longbench","model":"k-exaone","score":86.8,"metric":"percent"},{"benchmark":"ko-longbench","model":"exaone-4.0-32b-thinking","score":68,"metric":"percent"},{"benchmark":"ko-longbench","model":"gpt-oss-120b-high","score":82.2,"metric":"percent"},{"benchmark":"ko-longbench","model":"qwen3-235b-a22b-thinking-2507","score":83.2,"metric":"percent"},{"benchmark":"ko-longbench","model":"deepseek-v3.2-thinking","score":87.9,"metric":"percent"},{"benchmark":"mmmlu","model":"k-exaone","score":85.7,"metric":"percent"},{"benchmark":"mmmlu","model":"exaone-4.0-32b-thinking","score":83.2,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-oss-120b-high","score":83.8,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-235b-a22b-thinking-2507","score":87.3,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v3.2-thinking","score":88,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"k-exaone","score":90.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"exaone-4.0-32b-thinking","score":80.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gpt-oss-120b-high","score":93.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-235b-a22b-thinking-2507","score":94.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"deepseek-v3.2-thinking","score":90,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"k-exaone","score":89.9,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"exaone-4.0-32b-thinking","score":62.8,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"gpt-oss-120b-high","score":98.2,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"qwen3-235b-a22b-thinking-2507","score":85.5,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"deepseek-v3.2-thinking","score":79.1,"metric":"percent"},{"benchmark":"kgc-safety","model":"k-exaone","score":96.1,"metric":"percent"},{"benchmark":"kgc-safety","model":"exaone-4.0-32b-thinking","score":58,"metric":"percent"},{"benchmark":"kgc-safety","model":"gpt-oss-120b-high","score":92.5,"metric":"percent"},{"benchmark":"kgc-safety","model":"qwen3-235b-a22b-thinking-2507","score":66.2,"metric":"percent"},{"benchmark":"kgc-safety","model":"deepseek-v3.2-thinking","score":73,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b","score":79.7,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-4b","score":79,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b","score":39.8,"metric":"percent"},{"benchmark":"musr","model":"qwen3-4b","score":58.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-4b","score":90.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-4b","score":62.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-4b","score":73.3,"metric":"percent"},{"benchmark":"ifeval","model":"exaone-3.5-2.4b-instruct","score":81.1,"metric":"percent"},{"benchmark":"bbh","model":"exaone-3.5-2.4b-instruct","score":46.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"exaone-3.5-2.4b-instruct","score":28.1,"metric":"percent"},{"benchmark":"musr","model":"exaone-3.5-2.4b-instruct","score":49.7,"metric":"percent"},{"benchmark":"gsm8k","model":"exaone-3.5-2.4b-instruct","score":82.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"exaone-3.5-2.4b-instruct","score":59.8,"metric":"percent"},{"benchmark":"mmlu","model":"exaone-3.5-2.4b-instruct","score":59.5,"metric":"percent"},{"benchmark":"ifeval","model":"midm-2.0-mini-instruct","score":73.6,"metric":"percent"},{"benchmark":"bbh","model":"midm-2.0-mini-instruct","score":44.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"midm-2.0-mini-instruct","score":26.6,"metric":"percent"},{"benchmark":"musr","model":"midm-2.0-mini-instruct","score":51.7,"metric":"percent"},{"benchmark":"gsm8k","model":"midm-2.0-mini-instruct","score":83.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"midm-2.0-mini-instruct","score":60.9,"metric":"percent"},{"benchmark":"mmlu","model":"midm-2.0-mini-instruct","score":56.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-14b","score":83.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-14b","score":83.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-14b","score":49.8,"metric":"percent"},{"benchmark":"musr","model":"qwen3-14b","score":57.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-14b","score":88,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-14b","score":73.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-14b","score":70.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-14b","score":82.7,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-8b-instruct","score":79.9,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-8b-instruct","score":60.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-8b-instruct","score":21.6,"metric":"percent"},{"benchmark":"musr","model":"llama-3.1-8b-instruct","score":50.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b-instruct","score":81.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.1-8b-instruct","score":81.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b-instruct","score":47.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-8b-instruct","score":70.7,"metric":"percent"},{"benchmark":"ifeval","model":"exaone-3.5-7.8b-instruct","score":83.6,"metric":"percent"},{"benchmark":"bbh","model":"exaone-3.5-7.8b-instruct","score":50.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"exaone-3.5-7.8b-instruct","score":33.1,"metric":"percent"},{"benchmark":"musr","model":"exaone-3.5-7.8b-instruct","score":51.2,"metric":"percent"},{"benchmark":"gsm8k","model":"exaone-3.5-7.8b-instruct","score":81.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"exaone-3.5-7.8b-instruct","score":79.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-3.5-7.8b-instruct","score":40.7,"metric":"percent"},{"benchmark":"mmlu","model":"exaone-3.5-7.8b-instruct","score":69,"metric":"percent"},{"benchmark":"ifeval","model":"midm-2.0-base-instruct","score":84,"metric":"percent"},{"benchmark":"bbh","model":"midm-2.0-base-instruct","score":77.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"midm-2.0-base-instruct","score":33.5,"metric":"percent"},{"benchmark":"musr","model":"midm-2.0-base-instruct","score":51.9,"metric":"percent"},{"benchmark":"gsm8k","model":"midm-2.0-base-instruct","score":91.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"midm-2.0-base-instruct","score":77.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"midm-2.0-base-instruct","score":53.3,"metric":"percent"},{"benchmark":"mmlu","model":"midm-2.0-base-instruct","score":73.7,"metric":"percent"},{"benchmark":"bbh","model":"mimo-v2-flash-base","score":88.5,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3.1","score":88.2,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3.2-exp","score":88.7,"metric":"percent"},{"benchmark":"mmlu","model":"mimo-v2-flash-base","score":86.7,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3.1","score":87.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3.2-exp","score":87.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mimo-v2-flash-base","score":90.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-k2-base","score":90.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3.1","score":90,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3.2-exp","score":90.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-v2-flash-base","score":73.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2-base","score":69.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.1","score":58.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.2-exp","score":62.1,"metric":"percent"},{"benchmark":"drop","model":"mimo-v2-flash-base","score":84.7,"metric":"percent"},{"benchmark":"drop","model":"kimi-k2-base","score":83.6,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v3.1","score":86.3,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v3.2-exp","score":86.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"mimo-v2-flash-base","score":95.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"kimi-k2-base","score":96.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v3.1","score":95.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v3.2-exp","score":95.5,"metric":"percent"},{"benchmark":"hellaswag","model":"mimo-v2-flash-base","score":88.5,"metric":"percent"},{"benchmark":"hellaswag","model":"kimi-k2-base","score":94.6,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v3.1","score":89.2,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v3.2-exp","score":89.4,"metric":"percent"},{"benchmark":"winogrande","model":"mimo-v2-flash-base","score":83.8,"metric":"percent"},{"benchmark":"winogrande","model":"kimi-k2-base","score":85.3,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v3.1","score":85.9,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v3.2-exp","score":85.6,"metric":"percent"},{"benchmark":"triviaqa","model":"mimo-v2-flash-base","score":80.3,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v3.1","score":83.5,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v3.2-exp","score":83.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-v2-flash-base","score":55.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2-base","score":48.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.1","score":51,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.2-exp","score":52,"metric":"percent"},{"benchmark":"supergpqa","model":"mimo-v2-flash-base","score":41.1,"metric":"percent"},{"benchmark":"supergpqa","model":"kimi-k2-base","score":44.7,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3.1","score":42.3,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3.2-exp","score":43.6,"metric":"percent"},{"benchmark":"simpleqa","model":"mimo-v2-flash-base","score":20.6,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3.1","score":26.3,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3.2-exp","score":27,"metric":"percent"},{"benchmark":"gsm8k","model":"mimo-v2-flash-base","score":92.3,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3.1","score":91.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3.2-exp","score":91.1,"metric":"percent"},{"benchmark":"math","model":"mimo-v2-flash-base","score":71,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3.1","score":62.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3.2-exp","score":62.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mimo-v2-flash-base","score":70.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kimi-k2-base","score":84.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3.1","score":64.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3.2-exp","score":67.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mimo-v2-flash-base","score":71.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kimi-k2-base","score":73.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3.1","score":72.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3.2-exp","score":69.8,"metric":"percent"},{"benchmark":"crux-i","model":"mimo-v2-flash-base","score":67.5,"metric":"percent"},{"benchmark":"crux-i","model":"kimi-k2-base","score":74,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v3.1","score":62.1,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v3.2-exp","score":63.9,"metric":"percent"},{"benchmark":"crux-o","model":"mimo-v2-flash-base","score":79.1,"metric":"percent"},{"benchmark":"crux-o","model":"kimi-k2-base","score":83.5,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v3.1","score":76.4,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v3.2-exp","score":74.9,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"mimo-v2-flash-base","score":59.5,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"kimi-k2-base","score":60.5,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"deepseek-v3.1","score":45.9,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"deepseek-v3.2-exp","score":45.7,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"mimo-v2-flash-base","score":56.7,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"kimi-k2-base","score":58.8,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"deepseek-v3.1","score":52.5,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"deepseek-v3.2-exp","score":50.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"mimo-v2-flash-base","score":70.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"kimi-k2-base","score":61.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v3.1","score":63,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v3.2-exp","score":62.9,"metric":"pass@1"},{"benchmark":"livecodebench","model":"mimo-v2-flash-base","score":30.8,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-base","score":26.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.1","score":24.8,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-exp","score":24.9,"metric":"percent"},{"benchmark":"swe-bench","model":"mimo-v2-flash-base","score":30.8,"metric":"percent"},{"benchmark":"swe-bench","model":"kimi-k2-base","score":28.2,"metric":"percent"},{"benchmark":"swe-bench","model":"deepseek-v3.1","score":24.8,"metric":"percent"},{"benchmark":"swe-bench","model":"deepseek-v3.2-exp","score":9.4,"metric":"percent"},{"benchmark":"c-eval","model":"mimo-v2-flash-base","score":87.9,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3.1","score":90,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3.2-exp","score":91,"metric":"percent"},{"benchmark":"cmmlu","model":"mimo-v2-flash-base","score":87.4,"metric":"percent"},{"benchmark":"cmmlu","model":"kimi-k2-base","score":90.9,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v3.1","score":88.8,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v3.2-exp","score":88.9,"metric":"percent"},{"benchmark":"csimpleqa","model":"mimo-v2-flash-base","score":61.5,"metric":"percent"},{"benchmark":"csimpleqa","model":"kimi-k2-base","score":77.6,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v3.1","score":70.9,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v3.2-exp","score":68,"metric":"percent"},{"benchmark":"global-mmlu","model":"mimo-v2-flash-base","score":76.6,"metric":"percent"},{"benchmark":"global-mmlu","model":"kimi-k2-base","score":80.7,"metric":"percent"},{"benchmark":"global-mmlu","model":"deepseek-v3.1","score":81.9,"metric":"percent"},{"benchmark":"global-mmlu","model":"deepseek-v3.2-exp","score":82,"metric":"percent"},{"benchmark":"include","model":"mimo-v2-flash-base","score":71.4,"metric":"percent"},{"benchmark":"include","model":"kimi-k2-base","score":75.3,"metric":"percent"},{"benchmark":"include","model":"deepseek-v3.1","score":77.2,"metric":"percent"},{"benchmark":"include","model":"deepseek-v3.2-exp","score":77.2,"metric":"percent"},{"benchmark":"mimo-niah-multi-32k","model":"mimo-v2-flash-base","score":99.3,"metric":"percent"},{"benchmark":"mimo-niah-multi-32k","model":"kimi-k2-base","score":99.8,"metric":"percent"},{"benchmark":"mimo-niah-multi-32k","model":"deepseek-v3.1","score":99.7,"metric":"percent"},{"benchmark":"mimo-niah-multi-32k","model":"deepseek-v3.2-exp","score":85.6,"metric":"percent"},{"benchmark":"mimo-niah-multi-64k","model":"mimo-v2-flash-base","score":99.9,"metric":"percent"},{"benchmark":"mimo-niah-multi-64k","model":"kimi-k2-base","score":100,"metric":"percent"},{"benchmark":"mimo-niah-multi-64k","model":"deepseek-v3.1","score":98.6,"metric":"percent"},{"benchmark":"mimo-niah-multi-64k","model":"deepseek-v3.2-exp","score":85.9,"metric":"percent"},{"benchmark":"mimo-niah-multi-128k","model":"mimo-v2-flash-base","score":98.6,"metric":"percent"},{"benchmark":"mimo-niah-multi-128k","model":"kimi-k2-base","score":99.5,"metric":"percent"},{"benchmark":"mimo-niah-multi-128k","model":"deepseek-v3.1","score":97.2,"metric":"percent"},{"benchmark":"mimo-niah-multi-128k","model":"deepseek-v3.2-exp","score":94.3,"metric":"percent"},{"benchmark":"mimo-niah-multi-256k","model":"mimo-v2-flash-base","score":96.7,"metric":"percent"},{"benchmark":"gsm-infinite-hard-16k","model":"mimo-v2-flash-base","score":37.7,"metric":"percent"},{"benchmark":"gsm-infinite-hard-16k","model":"kimi-k2-base","score":34.6,"metric":"percent"},{"benchmark":"gsm-infinite-hard-16k","model":"deepseek-v3.1","score":41.5,"metric":"percent"},{"benchmark":"gsm-infinite-hard-16k","model":"deepseek-v3.2-exp","score":50.4,"metric":"percent"},{"benchmark":"gsm-infinite-hard-32k","model":"mimo-v2-flash-base","score":33.7,"metric":"percent"},{"benchmark":"gsm-infinite-hard-32k","model":"kimi-k2-base","score":26.1,"metric":"percent"},{"benchmark":"gsm-infinite-hard-32k","model":"deepseek-v3.1","score":38.8,"metric":"percent"},{"benchmark":"gsm-infinite-hard-32k","model":"deepseek-v3.2-exp","score":45.2,"metric":"percent"},{"benchmark":"gsm-infinite-hard-64k","model":"mimo-v2-flash-base","score":31.5,"metric":"percent"},{"benchmark":"gsm-infinite-hard-64k","model":"kimi-k2-base","score":16,"metric":"percent"},{"benchmark":"gsm-infinite-hard-64k","model":"deepseek-v3.1","score":34.7,"metric":"percent"},{"benchmark":"gsm-infinite-hard-64k","model":"deepseek-v3.2-exp","score":32.6,"metric":"percent"},{"benchmark":"gsm-infinite-hard-128k","model":"mimo-v2-flash-base","score":29,"metric":"percent"},{"benchmark":"gsm-infinite-hard-128k","model":"kimi-k2-base","score":8.8,"metric":"percent"},{"benchmark":"gsm-infinite-hard-128k","model":"deepseek-v3.1","score":28.7,"metric":"percent"},{"benchmark":"gsm-infinite-hard-128k","model":"deepseek-v3.2-exp","score":25.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-v2-flash","score":84.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-v2-flash","score":83.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"mimo-v2-flash","score":22.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2-thinking","score":23.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5-high","score":26.3,"metric":"percent"},{"benchmark":"aime-2025","model":"mimo-v2-flash","score":94.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"mimo-v2-flash","score":84.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"deepseek-v3.2-thinking","score":92.5,"metric":"percent"},{"benchmark":"livecodebench","model":"mimo-v2-flash","score":80.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-high","score":84.5,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"mimo-v2-flash","score":54.1,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"kimi-k2-thinking","score":71.9,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"deepseek-v3.2-thinking","score":53.4,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"gemini-3-pro","score":72.6,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"claude-sonnet-4.5","score":63.3,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"gpt-5-high","score":71.9,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"mimo-v2-flash","score":86.2,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"kimi-k2-thinking","score":80.1,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"deepseek-v3.2-thinking","score":88.8,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"gemini-3-pro","score":93.6,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"claude-sonnet-4.5","score":76.7,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"gpt-5-high","score":92.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"mimo-v2-flash","score":60.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"kimi-k2-thinking","score":45.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v3.2-thinking","score":58.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-3-pro","score":65.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-sonnet-4.5","score":61.8,"metric":"percent"},{"benchmark":"mrcr-128k","model":"mimo-v2-flash","score":45.7,"metric":"percent"},{"benchmark":"mrcr-128k","model":"kimi-k2-thinking","score":44.2,"metric":"percent"},{"benchmark":"mrcr-128k","model":"deepseek-v3.2-thinking","score":55.5,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gemini-3-pro","score":89.7,"metric":"percent"},{"benchmark":"mrcr-128k","model":"claude-sonnet-4.5","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mimo-v2-flash","score":73.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"mimo-v2-flash","score":71.7,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"mimo-v2-flash","score":30.5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-v3.2-thinking","score":35.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"mimo-v2-flash","score":38.5,"metric":"percent"},{"benchmark":"browsecomp","model":"mimo-v2-flash","score":45.4,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"mimo-v2-flash","score":58.3,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"deepseek-v3.2-thinking","score":67.6,"metric":"percent"},{"benchmark":"aa-omniscience","model":"gemini-3-pro-preview","score":13,"metric":"index"},{"benchmark":"aa-omniscience","model":"claude-opus-4.5","score":10,"metric":"index"},{"benchmark":"aa-omniscience","model":"gemini-3-flash","score":10,"metric":"index"},{"benchmark":"aa-omniscience","model":"gpt-5.1-high","score":2,"metric":"index"},{"benchmark":"aa-omniscience","model":"grok-4","score":1,"metric":"index"},{"benchmark":"aa-omniscience","model":"claude-sonnet-4.5","score":-2,"metric":"index"},{"benchmark":"aa-omniscience","model":"gpt-5.2-high","score":-4,"metric":"index"},{"benchmark":"aa-omniscience","model":"deepseek-v3.2","score":-23,"metric":"index"},{"benchmark":"aa-omniscience","model":"kimi-k2-thinking","score":-23,"metric":"index"},{"benchmark":"aa-omniscience","model":"minimax-m2.1","score":-30,"metric":"index"},{"benchmark":"aa-omniscience","model":"grok-4.1-fast","score":-31,"metric":"index"},{"benchmark":"aa-omniscience","model":"kat-coder-pro-v1","score":-36,"metric":"index"},{"benchmark":"aa-omniscience","model":"glm-4.7","score":-36,"metric":"index"},{"benchmark":"aa-omniscience","model":"mistral-large-3","score":-41,"metric":"index"},{"benchmark":"aa-omniscience","model":"mimo-v2-flash","score":-42,"metric":"index"},{"benchmark":"aa-omniscience","model":"llama-4-maverick","score":-43,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3-235b-2507","score":-48,"metric":"index"},{"benchmark":"aa-omniscience","model":"nova-pro","score":-50,"metric":"index"},{"benchmark":"aa-omniscience","model":"gpt-oss-120b-high","score":-52,"metric":"index"},{"benchmark":"aa-omniscience","model":"nemotron-3-nano-30b-a3b","score":-52,"metric":"index"},{"benchmark":"aa-omniscience","model":"midm-k-2.5-pro","score":-55,"metric":"index"},{"benchmark":"aa-omniscience","model":"k2-v2","score":-57,"metric":"index"},{"benchmark":"aa-omniscience","model":"nova-lite","score":-58,"metric":"index"},{"benchmark":"aa-omniscience","model":"apriel-1.6-15b-thinker","score":-60,"metric":"index"},{"benchmark":"aa-omniscience","model":"gpt-oss-20b-high","score":-65,"metric":"index"},{"benchmark":"aime-2025","model":"deepseek-v3.2-thinking","score":93.5,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2-thinking","score":99.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-235b-a22b-thinking-2507","score":92.6,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.7-thinking","score":95.3,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.5-thinking","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3-pro","score":99.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.2-thinking-xhigh","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"longcat-flash-thinking-2601","score":99.6,"metric":"percent"},{"benchmark":"aime-2025","model":"longcat-flash-thinking-2601","score":100,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.2-thinking","score":93.5,"metric":"percent"},{"benchmark":"hmmt-2025","model":"kimi-k2-thinking","score":95.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"glm-4.7-thinking","score":98.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"claude-opus-4.5-thinking","score":98.6,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-3-pro","score":99.8,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-5.2-thinking-xhigh","score":99.6,"metric":"percent"},{"benchmark":"hmmt-2025","model":"longcat-flash-thinking-2601","score":93.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"longcat-flash-thinking-2601","score":97.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v3.2-thinking","score":77.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2-thinking","score":78.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-235b-a22b-thinking-2507","score":73,"metric":"percent"},{"benchmark":"imo-answerbench","model":"glm-4.7-thinking","score":84,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.5-thinking","score":82.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3-pro","score":86.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"longcat-flash-thinking-2601","score":78.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"longcat-flash-thinking-2601","score":86.8,"metric":"percent"},{"benchmark":"amobench","model":"deepseek-v3.2-thinking","score":51.9,"metric":"percent"},{"benchmark":"amobench","model":"kimi-k2-thinking","score":56,"metric":"percent"},{"benchmark":"amobench","model":"qwen3-235b-a22b-thinking-2507","score":47.8,"metric":"percent"},{"benchmark":"amobench","model":"glm-4.7-thinking","score":62.4,"metric":"percent"},{"benchmark":"amobench","model":"claude-opus-4.5-thinking","score":66,"metric":"percent"},{"benchmark":"amobench","model":"gemini-3-pro","score":72.5,"metric":"percent"},{"benchmark":"amobench","model":"longcat-flash-thinking-2601","score":61.6,"metric":"percent"},{"benchmark":"amobench","model":"longcat-flash-thinking-2601","score":66,"metric":"percent"},{"benchmark":"amobench-zh","model":"deepseek-v3.2-thinking","score":52,"metric":"percent"},{"benchmark":"amobench-zh","model":"kimi-k2-thinking","score":51.8,"metric":"percent"},{"benchmark":"amobench-zh","model":"qwen3-235b-a22b-thinking-2507","score":28.8,"metric":"percent"},{"benchmark":"amobench-zh","model":"glm-4.7-thinking","score":35.1,"metric":"percent"},{"benchmark":"amobench-zh","model":"claude-opus-4.5-thinking","score":67.7,"metric":"percent"},{"benchmark":"amobench-zh","model":"gemini-3-pro","score":74.9,"metric":"percent"},{"benchmark":"amobench-zh","model":"longcat-flash-thinking-2601","score":56.8,"metric":"percent"},{"benchmark":"amobench-zh","model":"longcat-flash-thinking-2601","score":67.5,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-4.7-thinking","score":52,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"glm-4.7-thinking","score":67.5,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.2-thinking-xhigh","score":65.8,"metric":"percent"},{"benchmark":"browsecomp","model":"longcat-flash-thinking-2601","score":56.6,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"longcat-flash-thinking-2601","score":73.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"glm-4.7-thinking","score":66.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"longcat-flash-thinking-2601","score":69,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"longcat-flash-thinking-2601","score":77.7,"metric":"percent"},{"benchmark":"rw-search","model":"deepseek-v3.2-thinking","score":74,"metric":"percent"},{"benchmark":"rw-search","model":"kimi-k2-thinking","score":63,"metric":"percent"},{"benchmark":"rw-search","model":"qwen3-235b-a22b-thinking-2507","score":20.5,"metric":"percent"},{"benchmark":"rw-search","model":"glm-4.7-thinking","score":69,"metric":"percent"},{"benchmark":"rw-search","model":"claude-opus-4.5-thinking","score":75.5,"metric":"percent"},{"benchmark":"rw-search","model":"gemini-3-pro","score":74.5,"metric":"percent"},{"benchmark":"rw-search","model":"gpt-5.2-thinking-xhigh","score":82,"metric":"percent"},{"benchmark":"rw-search","model":"longcat-flash-thinking-2601","score":79.5,"metric":"percent"},{"benchmark":"tau2-retail","model":"deepseek-v3.2-thinking","score":81.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4.5-thinking","score":88.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-5.2-thinking-xhigh","score":82,"metric":"percent"},{"benchmark":"tau2-retail","model":"longcat-flash-thinking-2601","score":88.6,"metric":"percent"},{"benchmark":"tau2-airline","model":"deepseek-v3.2-thinking","score":63.8,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-235b-a22b-thinking-2507","score":58.6,"metric":"percent"},{"benchmark":"tau2-airline","model":"longcat-flash-thinking-2601","score":76.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v3.2-thinking","score":96.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-235b-a22b-thinking-2507","score":47.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.5-thinking","score":98.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.2-thinking-xhigh","score":98.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"longcat-flash-thinking-2601","score":99.3,"metric":"percent"},{"benchmark":"vitabench","model":"deepseek-v3.2-thinking","score":24,"metric":"percent"},{"benchmark":"vitabench","model":"kimi-k2-thinking","score":12.8,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3-235b-a22b-thinking-2507","score":14.5,"metric":"percent"},{"benchmark":"vitabench","model":"glm-4.7-thinking","score":18.3,"metric":"percent"},{"benchmark":"vitabench","model":"claude-opus-4.5-thinking","score":28.5,"metric":"percent"},{"benchmark":"vitabench","model":"gemini-3-pro","score":31.5,"metric":"percent"},{"benchmark":"vitabench","model":"gpt-5.2-thinking-xhigh","score":24.3,"metric":"percent"},{"benchmark":"vitabench","model":"longcat-flash-thinking-2601","score":29.3,"metric":"percent"},{"benchmark":"random-complex-tasks","model":"deepseek-v3.2-thinking","score":32.5,"metric":"percent"},{"benchmark":"random-complex-tasks","model":"kimi-k2-thinking","score":29.7,"metric":"percent"},{"benchmark":"random-complex-tasks","model":"qwen3-235b-a22b-thinking-2507","score":32.7,"metric":"percent"},{"benchmark":"random-complex-tasks","model":"glm-4.7-thinking","score":25.3,"metric":"percent"},{"benchmark":"random-complex-tasks","model":"claude-opus-4.5-thinking","score":32.6,"metric":"percent"},{"benchmark":"random-complex-tasks","model":"gemini-3-pro","score":32.5,"metric":"percent"},{"benchmark":"random-complex-tasks","model":"gpt-5.2-thinking-xhigh","score":17.2,"metric":"percent"},{"benchmark":"random-complex-tasks","model":"longcat-flash-thinking-2601","score":35.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v3.2-thinking","score":24.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2-thinking","score":24.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-235b-a22b-thinking-2507","score":17.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-4.7-thinking","score":26.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4.5-thinking","score":32,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3-pro","score":40.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.2-thinking-xhigh","score":34.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"longcat-flash-thinking-2601","score":25.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.2-thinking","score":86.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2-thinking","score":85.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-235b-a22b-thinking-2507","score":80.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.7-thinking","score":84.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.5-thinking","score":86.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2-thinking-xhigh","score":92.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"longcat-flash-thinking-2601","score":80.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"longcat-flash-thinking-2601","score":85.2,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-thinking","score":82.4,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-thinking","score":75.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b-thinking-2507","score":76.2,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.7-thinking","score":84.8,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.5-thinking","score":82.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-pro","score":88.1,"metric":"percent"},{"benchmark":"livecodebench","model":"longcat-flash-thinking-2601","score":82.8,"metric":"percent"},{"benchmark":"ojbench","model":"deepseek-v3.2-thinking","score":41.8,"metric":"percent"},{"benchmark":"ojbench","model":"kimi-k2-thinking","score":42.3,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-235b-a22b-thinking-2507","score":35.6,"metric":"percent"},{"benchmark":"ojbench","model":"glm-4.7-thinking","score":44.6,"metric":"percent"},{"benchmark":"ojbench","model":"claude-opus-4.5-thinking","score":46.7,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-3-pro","score":61.2,"metric":"percent"},{"benchmark":"ojbench","model":"longcat-flash-thinking-2601","score":42.2,"metric":"percent"},{"benchmark":"oibench-en","model":"deepseek-v3.2-thinking","score":43.3,"metric":"percent"},{"benchmark":"oibench-en","model":"kimi-k2-thinking","score":39,"metric":"percent"},{"benchmark":"oibench-en","model":"qwen3-235b-a22b-thinking-2507","score":36.8,"metric":"percent"},{"benchmark":"oibench-en","model":"glm-4.7-thinking","score":30.8,"metric":"percent"},{"benchmark":"oibench-en","model":"claude-opus-4.5-thinking","score":50,"metric":"percent"},{"benchmark":"oibench-en","model":"gemini-3-pro","score":58.2,"metric":"percent"},{"benchmark":"oibench-en","model":"longcat-flash-thinking-2601","score":47.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.7-thinking","score":73.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.5-thinking","score":80.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.2-thinking-xhigh","score":80,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"longcat-flash-thinking-2601","score":70,"metric":"percent"},{"benchmark":"cvtg-2k-word-accuracy","model":"seedream-4.5","score":0.899,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"seedream-4.5","score":0.9483,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"seedream-4.5","score":0.8069,"metric":"score"},{"benchmark":"longtext-bench-en","model":"seedream-4.5","score":0.989,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"seedream-4.5","score":0.987,"metric":"score"},{"benchmark":"cvtg-2k-word-accuracy","model":"seedream-4.0","score":0.8451,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"seedream-4.0","score":0.9224,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"seedream-4.0","score":0.7975,"metric":"score"},{"benchmark":"longtext-bench-en","model":"seedream-4.0","score":0.921,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"seedream-4.0","score":0.926,"metric":"score"},{"benchmark":"cvtg-2k-word-accuracy","model":"nano-banana-2.0","score":0.7788,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"nano-banana-2.0","score":0.8754,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"nano-banana-2.0","score":0.7372,"metric":"score"},{"benchmark":"longtext-bench-en","model":"nano-banana-2.0","score":0.981,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"nano-banana-2.0","score":0.949,"metric":"score"},{"benchmark":"cvtg-2k-word-accuracy","model":"gpt-image-1-high","score":0.8569,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"gpt-image-1-high","score":0.9478,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"gpt-image-1-high","score":0.7982,"metric":"score"},{"benchmark":"longtext-bench-en","model":"gpt-image-1-high","score":0.956,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"gpt-image-1-high","score":0.619,"metric":"score"},{"benchmark":"cvtg-2k-word-accuracy","model":"qwen-image","score":0.8288,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"qwen-image","score":0.9116,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"qwen-image","score":0.8017,"metric":"score"},{"benchmark":"longtext-bench-en","model":"qwen-image","score":0.943,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"qwen-image","score":0.946,"metric":"score"},{"benchmark":"cvtg-2k-word-accuracy","model":"qwen-image-2512","score":0.8604,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"qwen-image-2512","score":0.929,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"qwen-image-2512","score":0.7819,"metric":"score"},{"benchmark":"longtext-bench-en","model":"qwen-image-2512","score":0.956,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"qwen-image-2512","score":0.965,"metric":"score"},{"benchmark":"cvtg-2k-word-accuracy","model":"z-image","score":0.8671,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"z-image","score":0.9367,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"z-image","score":0.7969,"metric":"score"},{"benchmark":"longtext-bench-en","model":"z-image","score":0.935,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"z-image","score":0.936,"metric":"score"},{"benchmark":"cvtg-2k-word-accuracy","model":"z-image-turbo","score":0.8585,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"z-image-turbo","score":0.9281,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"z-image-turbo","score":0.8048,"metric":"score"},{"benchmark":"longtext-bench-en","model":"z-image-turbo","score":0.917,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"z-image-turbo","score":0.926,"metric":"score"},{"benchmark":"cvtg-2k-word-accuracy","model":"glm-image","score":0.9116,"metric":"score"},{"benchmark":"cvtg-2k-ned","model":"glm-image","score":0.9557,"metric":"score"},{"benchmark":"cvtg-2k-clipscore","model":"glm-image","score":0.7877,"metric":"score"},{"benchmark":"longtext-bench-en","model":"glm-image","score":0.952,"metric":"score"},{"benchmark":"longtext-bench-zh","model":"glm-image","score":0.979,"metric":"score"},{"benchmark":"oneig-bench-en","model":"seedream-4.5","score":0.576,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"seedream-4.5","score":0.551,"metric":"score"},{"benchmark":"tiif-bench-short","model":"seedream-4.5","score":90.49,"metric":"score"},{"benchmark":"tiif-bench-long","model":"seedream-4.5","score":88.52,"metric":"score"},{"benchmark":"dpg-bench","model":"seedream-4.5","score":88.63,"metric":"score"},{"benchmark":"oneig-bench-en","model":"seedream-4.0","score":0.576,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"seedream-4.0","score":0.553,"metric":"score"},{"benchmark":"tiif-bench-short","model":"seedream-4.0","score":90.45,"metric":"score"},{"benchmark":"tiif-bench-long","model":"seedream-4.0","score":88.08,"metric":"score"},{"benchmark":"dpg-bench","model":"seedream-4.0","score":88.54,"metric":"score"},{"benchmark":"oneig-bench-en","model":"nano-banana-2.0","score":0.578,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"nano-banana-2.0","score":0.567,"metric":"score"},{"benchmark":"tiif-bench-short","model":"nano-banana-2.0","score":91,"metric":"score"},{"benchmark":"tiif-bench-long","model":"nano-banana-2.0","score":88.26,"metric":"score"},{"benchmark":"dpg-bench","model":"nano-banana-2.0","score":87.16,"metric":"score"},{"benchmark":"oneig-bench-en","model":"gpt-image-1-high","score":0.533,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"gpt-image-1-high","score":0.474,"metric":"score"},{"benchmark":"tiif-bench-short","model":"gpt-image-1-high","score":89.15,"metric":"score"},{"benchmark":"tiif-bench-long","model":"gpt-image-1-high","score":88.29,"metric":"score"},{"benchmark":"dpg-bench","model":"gpt-image-1-high","score":85.15,"metric":"score"},{"benchmark":"tiif-bench-short","model":"dall-e-3","score":74.96,"metric":"score"},{"benchmark":"tiif-bench-long","model":"dall-e-3","score":70.81,"metric":"score"},{"benchmark":"dpg-bench","model":"dall-e-3","score":83.5,"metric":"score"},{"benchmark":"oneig-bench-en","model":"qwen-image","score":0.539,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"qwen-image","score":0.548,"metric":"score"},{"benchmark":"tiif-bench-short","model":"qwen-image","score":86.14,"metric":"score"},{"benchmark":"tiif-bench-long","model":"qwen-image","score":86.83,"metric":"score"},{"benchmark":"dpg-bench","model":"qwen-image","score":88.32,"metric":"score"},{"benchmark":"oneig-bench-en","model":"qwen-image-2512","score":0.53,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"qwen-image-2512","score":0.515,"metric":"score"},{"benchmark":"tiif-bench-short","model":"qwen-image-2512","score":83.24,"metric":"score"},{"benchmark":"tiif-bench-long","model":"qwen-image-2512","score":84.93,"metric":"score"},{"benchmark":"dpg-bench","model":"qwen-image-2512","score":87.2,"metric":"score"},{"benchmark":"oneig-bench-en","model":"z-image","score":0.546,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"z-image","score":0.535,"metric":"score"},{"benchmark":"tiif-bench-short","model":"z-image","score":80.2,"metric":"score"},{"benchmark":"tiif-bench-long","model":"z-image","score":83.01,"metric":"score"},{"benchmark":"dpg-bench","model":"z-image","score":88.14,"metric":"score"},{"benchmark":"oneig-bench-en","model":"z-image-turbo","score":0.528,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"z-image-turbo","score":0.507,"metric":"score"},{"benchmark":"tiif-bench-short","model":"z-image-turbo","score":77.73,"metric":"score"},{"benchmark":"tiif-bench-long","model":"z-image-turbo","score":80.05,"metric":"score"},{"benchmark":"dpg-bench","model":"z-image-turbo","score":84.86,"metric":"score"},{"benchmark":"oneig-bench-en","model":"flux-1-dev","score":0.434,"metric":"score"},{"benchmark":"tiif-bench-short","model":"flux-1-dev","score":71.09,"metric":"score"},{"benchmark":"tiif-bench-long","model":"flux-1-dev","score":71.78,"metric":"score"},{"benchmark":"dpg-bench","model":"flux-1-dev","score":83.52,"metric":"score"},{"benchmark":"tiif-bench-short","model":"sd3-medium","score":67.46,"metric":"score"},{"benchmark":"tiif-bench-long","model":"sd3-medium","score":66.09,"metric":"score"},{"benchmark":"dpg-bench","model":"sd3-medium","score":84.08,"metric":"score"},{"benchmark":"oneig-bench-en","model":"sd-xl","score":0.316,"metric":"score"},{"benchmark":"tiif-bench-short","model":"sd-xl","score":54.96,"metric":"score"},{"benchmark":"tiif-bench-long","model":"sd-xl","score":42.13,"metric":"score"},{"benchmark":"dpg-bench","model":"sd-xl","score":74.65,"metric":"score"},{"benchmark":"oneig-bench-en","model":"bagel","score":0.361,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"bagel","score":0.37,"metric":"score"},{"benchmark":"tiif-bench-short","model":"bagel","score":71.5,"metric":"score"},{"benchmark":"tiif-bench-long","model":"bagel","score":71.7,"metric":"score"},{"benchmark":"oneig-bench-en","model":"janus-pro","score":0.267,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"janus-pro","score":0.24,"metric":"score"},{"benchmark":"tiif-bench-short","model":"janus-pro","score":66.5,"metric":"score"},{"benchmark":"tiif-bench-long","model":"janus-pro","score":65.01,"metric":"score"},{"benchmark":"dpg-bench","model":"janus-pro","score":84.19,"metric":"score"},{"benchmark":"oneig-bench-en","model":"show-o2","score":0.308,"metric":"score"},{"benchmark":"tiif-bench-short","model":"show-o2","score":59.72,"metric":"score"},{"benchmark":"tiif-bench-long","model":"show-o2","score":58.86,"metric":"score"},{"benchmark":"oneig-bench-en","model":"glm-image","score":0.528,"metric":"score"},{"benchmark":"oneig-bench-zh","model":"glm-image","score":0.511,"metric":"score"},{"benchmark":"tiif-bench-short","model":"glm-image","score":81.01,"metric":"score"},{"benchmark":"tiif-bench-long","model":"glm-image","score":81.02,"metric":"score"},{"benchmark":"dpg-bench","model":"glm-image","score":84.78,"metric":"score"},{"benchmark":"swe-bench-verified","model":"frogboss-32b-2510","score":54.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"cwm-32b","score":53.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"swe-mirror-lm-32b","score":52.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"frogmini-14b-2510","score":45.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepswe-32b-preview","score":42.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"skywork-swe-32b","score":38,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"r2e-gym-32b","score":34.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"swe-gym-32b","score":20.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.5-358b","score":64.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-480b","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.5-358b","score":54.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-r1-0528","score":45.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"swe-rl-70b","score":41,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"swe-fixer-72b","score":32.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4","score":70.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4","score":66.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4","score":66.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5","score":65.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-4o","score":29.3,"metric":"percent"},{"benchmark":"livebench","model":"openpangu-r-72b-2512-fast-thinking","score":67.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openpangu-r-72b-2512-fast-thinking","score":84.2,"metric":"percent"},{"benchmark":"mmlu-prox","model":"openpangu-r-72b-2512-fast-thinking","score":76.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"openpangu-r-72b-2512-fast-thinking","score":45.3,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-r-72b-2512-fast-thinking","score":86.3,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"openpangu-r-72b-2512-fast-thinking","score":3.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-r-72b-2512-fast-thinking","score":76.8,"metric":"percent"},{"benchmark":"supergpqa","model":"openpangu-r-72b-2512-fast-thinking","score":58.9,"metric":"percent"},{"benchmark":"aime-2024","model":"openpangu-r-72b-2512-fast-thinking","score":75.6,"metric":"percent"},{"benchmark":"aime-2025","model":"openpangu-r-72b-2512-fast-thinking","score":60.6,"metric":"percent"},{"benchmark":"cnmo-2024","model":"openpangu-r-72b-2512-fast-thinking","score":77.8,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"openpangu-r-72b-2512-fast-thinking","score":45.4,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-r-72b-2512-fast-thinking","score":41.9,"metric":"percent"},{"benchmark":"codeforces","model":"openpangu-r-72b-2512-fast-thinking","score":1044.5,"metric":"ELO"},{"benchmark":"bfcl-v3","model":"openpangu-r-72b-2512-fast-thinking","score":74.6,"metric":"percent"},{"benchmark":"tau1-airline","model":"openpangu-r-72b-2512-fast-thinking","score":45.3,"metric":"percent"},{"benchmark":"tau1-retail","model":"openpangu-r-72b-2512-fast-thinking","score":70.1,"metric":"percent"},{"benchmark":"tau2-airline","model":"openpangu-r-72b-2512-fast-thinking","score":58,"metric":"percent"},{"benchmark":"tau2-retail","model":"openpangu-r-72b-2512-fast-thinking","score":71.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"openpangu-r-72b-2512-fast-thinking","score":48.8,"metric":"percent"},{"benchmark":"acebench","model":"openpangu-r-72b-2512-fast-thinking","score":74.3,"metric":"percent"},{"benchmark":"livebench","model":"openpangu-r-72b-2512-slow-thinking","score":75.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openpangu-r-72b-2512-slow-thinking","score":84.8,"metric":"percent"},{"benchmark":"mmlu-prox","model":"openpangu-r-72b-2512-slow-thinking","score":80.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"openpangu-r-72b-2512-slow-thinking","score":55.3,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-r-72b-2512-slow-thinking","score":79.1,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"openpangu-r-72b-2512-slow-thinking","score":2.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-r-72b-2512-slow-thinking","score":83.2,"metric":"percent"},{"benchmark":"supergpqa","model":"openpangu-r-72b-2512-slow-thinking","score":64.2,"metric":"percent"},{"benchmark":"aime-2024","model":"openpangu-r-72b-2512-slow-thinking","score":89,"metric":"percent"},{"benchmark":"aime-2025","model":"openpangu-r-72b-2512-slow-thinking","score":81.3,"metric":"percent"},{"benchmark":"cnmo-2024","model":"openpangu-r-72b-2512-slow-thinking","score":82.8,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"openpangu-r-72b-2512-slow-thinking","score":74.8,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-r-72b-2512-slow-thinking","score":69.5,"metric":"percent"},{"benchmark":"codeforces","model":"openpangu-r-72b-2512-slow-thinking","score":1701.4,"metric":"ELO"},{"benchmark":"bfcl-v3","model":"openpangu-r-72b-2512-slow-thinking","score":76.5,"metric":"percent"},{"benchmark":"tau1-airline","model":"openpangu-r-72b-2512-slow-thinking","score":56,"metric":"percent"},{"benchmark":"tau1-retail","model":"openpangu-r-72b-2512-slow-thinking","score":73,"metric":"percent"},{"benchmark":"tau2-airline","model":"openpangu-r-72b-2512-slow-thinking","score":65.3,"metric":"percent"},{"benchmark":"tau2-retail","model":"openpangu-r-72b-2512-slow-thinking","score":78.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"openpangu-r-72b-2512-slow-thinking","score":49.4,"metric":"percent"},{"benchmark":"acebench","model":"openpangu-r-72b-2512-slow-thinking","score":79.6,"metric":"percent"},{"benchmark":"mmmu","model":"step3-vl-10b-sere","score":78.11,"metric":"percent"},{"benchmark":"mmmu","model":"step3-vl-10b-pacore","score":80.11,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.6v","score":75.2,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-235b-a22b","score":78.7,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-pro","score":83.89,"metric":"percent"},{"benchmark":"mmmu","model":"seed-1.5-vl","score":79.11,"metric":"percent"},{"benchmark":"mathvista","model":"step3-vl-10b-sere","score":83.97,"metric":"percent"},{"benchmark":"mathvista","model":"step3-vl-10b-pacore","score":85.5,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.6v","score":83.51,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-235b-a22b","score":85.1,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-pro","score":83.88,"metric":"percent"},{"benchmark":"mathvista","model":"seed-1.5-vl","score":85.6,"metric":"percent"},{"benchmark":"mathvision","model":"step3-vl-10b-sere","score":70.81,"metric":"percent"},{"benchmark":"mathvision","model":"step3-vl-10b-pacore","score":75.95,"metric":"percent"},{"benchmark":"mathvision","model":"glm-4.6v","score":63.5,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-235b-a22b","score":72.1,"metric":"percent"},{"benchmark":"mathvision","model":"seed-1.5-vl","score":68.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"step3-vl-10b-sere","score":92.05,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"step3-vl-10b-pacore","score":92.38,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4.6v","score":92.75,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-vl-235b-a22b","score":92.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.5-pro","score":93.19,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"seed-1.5-vl","score":92.11,"metric":"percent"},{"benchmark":"mmstar","model":"step3-vl-10b-sere","score":77.48,"metric":"percent"},{"benchmark":"mmstar","model":"step3-vl-10b-pacore","score":77.64,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4.6v","score":75.3,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-235b-a22b","score":76.8,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-pro","score":79.18,"metric":"percent"},{"benchmark":"mmstar","model":"seed-1.5-vl","score":77.91,"metric":"percent"},{"benchmark":"ocrbench","model":"step3-vl-10b-sere","score":86.75,"metric":"percent"},{"benchmark":"ocrbench","model":"step3-vl-10b-pacore","score":89,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4.6v","score":86.2,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-235b-a22b","score":87.3,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-pro","score":85.9,"metric":"percent"},{"benchmark":"ocrbench","model":"seed-1.5-vl","score":85.2,"metric":"percent"},{"benchmark":"aime-2025","model":"step3-vl-10b-sere","score":87.66,"metric":"percent"},{"benchmark":"aime-2025","model":"step3-vl-10b-pacore","score":94.43,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.6v","score":71.88,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-235b-a22b","score":83.59,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-pro","score":83.96,"metric":"percent"},{"benchmark":"aime-2025","model":"seed-1.5-vl","score":64.06,"metric":"percent"},{"benchmark":"hmmt-2025","model":"step3-vl-10b-sere","score":78.18,"metric":"percent"},{"benchmark":"hmmt-2025","model":"step3-vl-10b-pacore","score":92.14,"metric":"percent"},{"benchmark":"hmmt-2025","model":"glm-4.6v","score":57.29,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-vl-235b-a22b","score":67.71,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-2.5-pro","score":65.68,"metric":"percent"},{"benchmark":"hmmt-2025","model":"seed-1.5-vl","score":51.3,"metric":"percent"},{"benchmark":"livecodebench","model":"step3-vl-10b-sere","score":75.77,"metric":"percent"},{"benchmark":"livecodebench","model":"step3-vl-10b-pacore","score":76.43,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.6v","score":48.71,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-235b-a22b","score":69.45,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":72.01,"metric":"percent"},{"benchmark":"livecodebench","model":"seed-1.5-vl","score":57.1,"metric":"percent"},{"benchmark":"mmmu","model":"step3-vl-10b","score":78.11,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.6v-flash","score":71.17,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-8b-thinking","score":73.53,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-8b","score":71.69,"metric":"percent"},{"benchmark":"mmmu","model":"mimo-vl-7b-rl-2508","score":71.14,"metric":"percent"},{"benchmark":"mathvision","model":"step3-vl-10b","score":70.81,"metric":"percent"},{"benchmark":"mathvision","model":"glm-4.6v-flash","score":54.05,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-8b-thinking","score":59.6,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3.5-8b","score":52.05,"metric":"percent"},{"benchmark":"mathvision","model":"mimo-vl-7b-rl-2508","score":59.65,"metric":"percent"},{"benchmark":"mathvista","model":"step3-vl-10b","score":83.97,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.6v-flash","score":82.85,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-8b-thinking","score":78.5,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3.5-8b","score":76.78,"metric":"percent"},{"benchmark":"mathvista","model":"mimo-vl-7b-rl-2508","score":79.86,"metric":"percent"},{"benchmark":"phyx","model":"step3-vl-10b","score":59.45,"metric":"percent"},{"benchmark":"phyx","model":"glm-4.6v-flash","score":52.28,"metric":"percent"},{"benchmark":"phyx","model":"qwen3-vl-8b-thinking","score":57.67,"metric":"percent"},{"benchmark":"phyx","model":"internvl3.5-8b","score":50.51,"metric":"percent"},{"benchmark":"phyx","model":"mimo-vl-7b-rl-2508","score":56,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"step3-vl-10b","score":92.05,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4.6v-flash","score":91.04,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-vl-8b-thinking","score":90.55,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3.5-8b","score":88.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mimo-vl-7b-rl-2508","score":89.91,"metric":"percent"},{"benchmark":"mmstar","model":"step3-vl-10b","score":77.48,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4.6v-flash","score":74.26,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-8b-thinking","score":73.58,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-8b","score":69.83,"metric":"percent"},{"benchmark":"mmstar","model":"mimo-vl-7b-rl-2508","score":72.93,"metric":"percent"},{"benchmark":"remi","model":"step3-vl-10b","score":67.29,"metric":"percent"},{"benchmark":"remi","model":"glm-4.6v-flash","score":60.75,"metric":"percent"},{"benchmark":"remi","model":"qwen3-vl-8b-thinking","score":57.17,"metric":"percent"},{"benchmark":"remi","model":"internvl3.5-8b","score":52.65,"metric":"percent"},{"benchmark":"remi","model":"mimo-vl-7b-rl-2508","score":63.13,"metric":"percent"},{"benchmark":"ocrbench","model":"step3-vl-10b","score":86.75,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4.6v-flash","score":85.97,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-8b-thinking","score":82.85,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3.5-8b","score":83.7,"metric":"percent"},{"benchmark":"ocrbench","model":"mimo-vl-7b-rl-2508","score":85.4,"metric":"percent"},{"benchmark":"ai2d","model":"step3-vl-10b","score":89.35,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4.6v-flash","score":88.93,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-8b-thinking","score":83.32,"metric":"percent"},{"benchmark":"ai2d","model":"internvl3.5-8b","score":82.34,"metric":"percent"},{"benchmark":"ai2d","model":"mimo-vl-7b-rl-2508","score":84.96,"metric":"percent"},{"benchmark":"screenspot-v2","model":"step3-vl-10b","score":92.61,"metric":"percent"},{"benchmark":"screenspot-v2","model":"glm-4.6v-flash","score":92.14,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-8b-thinking","score":93.6,"metric":"percent"},{"benchmark":"screenspot-v2","model":"internvl3.5-8b","score":84.02,"metric":"percent"},{"benchmark":"screenspot-v2","model":"mimo-vl-7b-rl-2508","score":90.82,"metric":"percent"},{"benchmark":"screenspot-pro","model":"step3-vl-10b","score":51.55,"metric":"percent"},{"benchmark":"screenspot-pro","model":"glm-4.6v-flash","score":45.68,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-8b-thinking","score":46.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"internvl3.5-8b","score":15.39,"metric":"percent"},{"benchmark":"screenspot-pro","model":"mimo-vl-7b-rl-2508","score":34.84,"metric":"percent"},{"benchmark":"osworld-g","model":"step3-vl-10b","score":59.02,"metric":"percent"},{"benchmark":"osworld-g","model":"glm-4.6v-flash","score":54.71,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-8b-thinking","score":56.7,"metric":"percent"},{"benchmark":"osworld-g","model":"internvl3.5-8b","score":31.91,"metric":"percent"},{"benchmark":"osworld-g","model":"mimo-vl-7b-rl-2508","score":50.54,"metric":"percent"},{"benchmark":"blink","model":"step3-vl-10b","score":66.79,"metric":"percent"},{"benchmark":"blink","model":"glm-4.6v-flash","score":64.9,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-8b-thinking","score":62.78,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-8b","score":55.4,"metric":"percent"},{"benchmark":"blink","model":"mimo-vl-7b-rl-2508","score":62.57,"metric":"percent"},{"benchmark":"all-angles-bench","model":"step3-vl-10b","score":57.21,"metric":"percent"},{"benchmark":"all-angles-bench","model":"glm-4.6v-flash","score":53.24,"metric":"percent"},{"benchmark":"all-angles-bench","model":"qwen3-vl-8b-thinking","score":45.88,"metric":"percent"},{"benchmark":"all-angles-bench","model":"internvl3.5-8b","score":45.29,"metric":"percent"},{"benchmark":"all-angles-bench","model":"mimo-vl-7b-rl-2508","score":51.62,"metric":"percent"},{"benchmark":"humaneval-v","model":"step3-vl-10b","score":66.05,"metric":"percent"},{"benchmark":"humaneval-v","model":"glm-4.6v-flash","score":29.26,"metric":"percent"},{"benchmark":"humaneval-v","model":"qwen3-vl-8b-thinking","score":26.94,"metric":"percent"},{"benchmark":"humaneval-v","model":"internvl3.5-8b","score":24.31,"metric":"percent"},{"benchmark":"humaneval-v","model":"mimo-vl-7b-rl-2508","score":31.96,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.7-flash","score":91.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.7-flash","score":75.2,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.7-flash","score":64,"metric":"percent"},{"benchmark":"hle","model":"glm-4.7-flash","score":14.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.7-flash","score":59.2,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-4.7-flash","score":42.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-30b-a3b-thinking-2507","score":22,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3-30b-a3b-thinking-2507","score":2.29,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b","score":71.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-20b","score":34,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-oss-20b","score":28.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b","score":75.37,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b","score":79.19,"metric":"percent"},{"benchmark":"mmlu-pro","model":"telechat3-105b-a4.7b-thinking","score":78.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"telechat3-36b-thinking","score":80.89,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b","score":65.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-thinking-2507","score":67.68,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b","score":80.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"telechat3-105b-a4.7b-thinking","score":66,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"telechat3-36b-thinking","score":70.56,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-30b-a3b","score":79.1,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"qwen3-32b","score":81,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gpt-oss-120b","score":80.77,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"telechat3-105b-a4.7b-thinking","score":82.1,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"telechat3-36b-thinking","score":84.33,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b","score":86.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-32b","score":90,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-120b","score":82.4,"metric":"percent"},{"benchmark":"ifeval","model":"telechat3-105b-a4.7b-thinking","score":83.7,"metric":"percent"},{"benchmark":"ifeval","model":"telechat3-36b-thinking","score":82.96,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b","score":98,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b-thinking-2507","score":94.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3-32b","score":97.2,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-120b","score":90,"metric":"percent"},{"benchmark":"math500","model":"telechat3-105b-a4.7b-thinking","score":91,"metric":"percent"},{"benchmark":"math500","model":"telechat3-36b-thinking","score":95,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b","score":80.4,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b-thinking-2507","score":76.7,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-120b","score":73.3,"metric":"percent"},{"benchmark":"aime-2024","model":"telechat3-105b-a4.7b-thinking","score":71.1,"metric":"percent"},{"benchmark":"aime-2024","model":"telechat3-36b-thinking","score":73.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b","score":70.9,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":83.3,"metric":"percent"},{"benchmark":"aime-2025","model":"telechat3-105b-a4.7b-thinking","score":69.7,"metric":"percent"},{"benchmark":"aime-2025","model":"telechat3-36b-thinking","score":73.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b","score":63.11,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-thinking-2507","score":66.89,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b","score":69,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":74.01,"metric":"percent"},{"benchmark":"livecodebench","model":"telechat3-105b-a4.7b-thinking","score":66.5,"metric":"percent"},{"benchmark":"livecodebench","model":"telechat3-36b-thinking","score":69,"metric":"percent"},{"benchmark":"ifeval-code","model":"qwen3-30b-a3b","score":20.95,"metric":"percent"},{"benchmark":"ifeval-code","model":"qwen3-30b-a3b-thinking-2507","score":20.45,"metric":"percent"},{"benchmark":"ifeval-code","model":"qwen3-32b","score":28,"metric":"percent"},{"benchmark":"ifeval-code","model":"gpt-oss-120b","score":25.73,"metric":"percent"},{"benchmark":"ifeval-code","model":"telechat3-105b-a4.7b-thinking","score":23,"metric":"percent"},{"benchmark":"ifeval-code","model":"telechat3-36b-thinking","score":26,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen3-30b-a3b","score":84.88,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen3-30b-a3b-thinking-2507","score":88.29,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen3-32b","score":76.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"gpt-oss-120b","score":89.76,"metric":"percent"},{"benchmark":"humaneval-x","model":"telechat3-105b-a4.7b-thinking","score":87.3,"metric":"percent"},{"benchmark":"humaneval-x","model":"telechat3-36b-thinking","score":92.67,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-30b-a3b","score":21,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-30b-a3b-thinking-2507","score":26,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-32b","score":28,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-120b","score":44,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"telechat3-105b-a4.7b-thinking","score":42,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"telechat3-36b-thinking","score":51,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-30b-a3b","score":69.1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gpt-oss-120b","score":65.25,"metric":"percent"},{"benchmark":"bfcl-v3","model":"telechat3-105b-a4.7b-thinking","score":65.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"telechat3-36b-thinking","score":68,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-2-30b-a3b-mid-2601","score":75.44,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-2-30b-a3b-base-2601","score":74.83,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-1.5-32.5b-base","score":76.76,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b","score":81.14,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kanana-2-30b-a3b-mid-2601","score":56.14,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kanana-2-30b-a3b-base-2601","score":52.61,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kanana-1.5-32.5b-base","score":52.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b","score":61.83,"metric":"percent"},{"benchmark":"bbh","model":"kanana-2-30b-a3b-mid-2601","score":79.76,"metric":"percent"},{"benchmark":"bbh","model":"kanana-2-30b-a3b-base-2601","score":76.46,"metric":"percent"},{"benchmark":"bbh","model":"kanana-1.5-32.5b-base","score":81.54,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-30b-a3b","score":79.97,"metric":"percent"},{"benchmark":"simpleqa","model":"kanana-2-30b-a3b-mid-2601","score":29.7,"metric":"percent"},{"benchmark":"simpleqa","model":"kanana-2-30b-a3b-base-2601","score":29.13,"metric":"percent"},{"benchmark":"simpleqa","model":"kanana-1.5-32.5b-base","score":26.95,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-30b-a3b","score":26.47,"metric":"percent"},{"benchmark":"math","model":"kanana-2-30b-a3b-mid-2601","score":54.4,"metric":"percent"},{"benchmark":"math","model":"kanana-2-30b-a3b-base-2601","score":48.86,"metric":"percent"},{"benchmark":"math","model":"kanana-1.5-32.5b-base","score":47.68,"metric":"percent"},{"benchmark":"math","model":"qwen3-30b-a3b","score":62.58,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-2-30b-a3b-mid-2601","score":82.71,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-2-30b-a3b-base-2601","score":76.57,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-1.5-32.5b-base","score":85.14,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b","score":88.1,"metric":"percent"},{"benchmark":"humaneval","model":"kanana-2-30b-a3b-mid-2601","score":75.29,"metric":"percent"},{"benchmark":"humaneval","model":"kanana-2-30b-a3b-base-2601","score":71.34,"metric":"percent"},{"benchmark":"humaneval","model":"kanana-1.5-32.5b-base","score":75.59,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-30b-a3b","score":53.32,"metric":"percent"},{"benchmark":"mbpp","model":"kanana-2-30b-a3b-mid-2601","score":62.39,"metric":"percent"},{"benchmark":"mbpp","model":"kanana-2-30b-a3b-base-2601","score":60.21,"metric":"percent"},{"benchmark":"mbpp","model":"kanana-1.5-32.5b-base","score":65.96,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-30b-a3b","score":72.58,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-2-30b-a3b-mid-2601","score":62.15,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-2-30b-a3b-base-2601","score":61.98,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-1.5-32.5b-base","score":61.56,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen3-30b-a3b","score":62.25,"metric":"percent"},{"benchmark":"kosimpleqa","model":"kanana-2-30b-a3b-mid-2601","score":49.7,"metric":"percent"},{"benchmark":"kosimpleqa","model":"kanana-2-30b-a3b-base-2601","score":49.4,"metric":"percent"},{"benchmark":"kosimpleqa","model":"kanana-1.5-32.5b-base","score":45.7,"metric":"percent"},{"benchmark":"kosimpleqa","model":"qwen3-30b-a3b","score":26.33,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-2-30b-a3b-mid-2601","score":88.73,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-2-30b-a3b-base-2601","score":88.91,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-1.5-32.5b-base","score":90.65,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"qwen3-30b-a3b","score":72.04,"metric":"percent"},{"benchmark":"math-ko","model":"kanana-2-30b-a3b-mid-2601","score":54.07,"metric":"percent"},{"benchmark":"math-ko","model":"kanana-2-30b-a3b-base-2601","score":45.58,"metric":"percent"},{"benchmark":"math-ko","model":"kanana-1.5-32.5b-base","score":47.42,"metric":"percent"},{"benchmark":"math-ko","model":"qwen3-30b-a3b","score":58.2,"metric":"percent"},{"benchmark":"gsm8k-ko","model":"kanana-2-30b-a3b-mid-2601","score":77.48,"metric":"percent"},{"benchmark":"gsm8k-ko","model":"kanana-2-30b-a3b-base-2601","score":70.43,"metric":"percent"},{"benchmark":"gsm8k-ko","model":"kanana-1.5-32.5b-base","score":81.43,"metric":"percent"},{"benchmark":"gsm8k-ko","model":"qwen3-30b-a3b","score":88.1,"metric":"percent"},{"benchmark":"mbpp-ko","model":"kanana-2-30b-a3b-mid-2601","score":61.55,"metric":"percent"},{"benchmark":"mbpp-ko","model":"kanana-2-30b-a3b-base-2601","score":57.29,"metric":"percent"},{"benchmark":"mbpp-ko","model":"kanana-1.5-32.5b-base","score":65.41,"metric":"percent"},{"benchmark":"mbpp-ko","model":"qwen3-30b-a3b","score":66.84,"metric":"percent"},{"benchmark":"ruler-4k","model":"kanana-2-30b-a3b-mid-2601","score":93.09,"metric":"percent"},{"benchmark":"ruler-4k","model":"kanana-2-30b-a3b-base-2601","score":92.49,"metric":"percent"},{"benchmark":"ruler-4k","model":"kanana-1.5-32.5b-base","score":86.39,"metric":"percent"},{"benchmark":"ruler-4k","model":"qwen3-30b-a3b","score":94.32,"metric":"percent"},{"benchmark":"ruler-8k","model":"kanana-2-30b-a3b-mid-2601","score":92.29,"metric":"percent"},{"benchmark":"ruler-8k","model":"kanana-2-30b-a3b-base-2601","score":92.14,"metric":"percent"},{"benchmark":"ruler-8k","model":"kanana-1.5-32.5b-base","score":90.16,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen3-30b-a3b","score":92.16,"metric":"percent"},{"benchmark":"ruler-16k","model":"kanana-2-30b-a3b-mid-2601","score":90.73,"metric":"percent"},{"benchmark":"ruler-16k","model":"kanana-2-30b-a3b-base-2601","score":90.01,"metric":"percent"},{"benchmark":"ruler-16k","model":"kanana-1.5-32.5b-base","score":85.88,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen3-30b-a3b","score":91.28,"metric":"percent"},{"benchmark":"ruler-32k","model":"kanana-2-30b-a3b-mid-2601","score":88.63,"metric":"percent"},{"benchmark":"ruler-32k","model":"kanana-2-30b-a3b-base-2601","score":87.92,"metric":"percent"},{"benchmark":"ruler-32k","model":"kanana-1.5-32.5b-base","score":81.62,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen3-30b-a3b","score":88.32,"metric":"percent"},{"benchmark":"mt-bench","model":"kanana-2-30b-a3b-instruct-2601","score":8.3,"metric":"score"},{"benchmark":"mt-bench","model":"kanana-2-30b-a3b-instruct","score":8.42,"metric":"score"},{"benchmark":"mt-bench","model":"kanana-1.5-32.5b-instruct","score":8.23,"metric":"score"},{"benchmark":"mt-bench","model":"qwen3-30b-a3b-instruct-2507","score":8.71,"metric":"score"},{"benchmark":"mt-bench","model":"qwen3-30b-a3b","score":8.38,"metric":"score"},{"benchmark":"komt-bench","model":"kanana-2-30b-a3b-instruct-2601","score":8.21,"metric":"score"},{"benchmark":"komt-bench","model":"kanana-2-30b-a3b-instruct","score":8.24,"metric":"score"},{"benchmark":"komt-bench","model":"kanana-1.5-32.5b-instruct","score":7.94,"metric":"score"},{"benchmark":"komt-bench","model":"qwen3-30b-a3b-instruct-2507","score":8.49,"metric":"score"},{"benchmark":"komt-bench","model":"qwen3-30b-a3b","score":7.89,"metric":"score"},{"benchmark":"ifeval","model":"kanana-2-30b-a3b-instruct-2601","score":87.25,"metric":"percent"},{"benchmark":"ifeval","model":"kanana-2-30b-a3b-instruct","score":84.47,"metric":"percent"},{"benchmark":"ifeval","model":"kanana-1.5-32.5b-instruct","score":79.48,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-instruct-2507","score":82.62,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b","score":84.1,"metric":"percent"},{"benchmark":"ifbench","model":"kanana-2-30b-a3b-instruct-2601","score":48.3,"metric":"percent"},{"benchmark":"ifbench","model":"kanana-2-30b-a3b-instruct","score":41.84,"metric":"percent"},{"benchmark":"ifbench","model":"kanana-1.5-32.5b-instruct","score":38.78,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b-instruct-2507","score":30.27,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b","score":29.25,"metric":"percent"},{"benchmark":"multi-if","model":"kanana-2-30b-a3b-instruct-2601","score":77.88,"metric":"percent"},{"benchmark":"multi-if","model":"kanana-2-30b-a3b-instruct","score":75.81,"metric":"percent"},{"benchmark":"multi-if","model":"kanana-1.5-32.5b-instruct","score":68.51,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-30b-a3b-instruct-2507","score":77.93,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-30b-a3b","score":81.03,"metric":"percent"},{"benchmark":"multichallenge","model":"kanana-2-30b-a3b-instruct-2601","score":35.16,"metric":"percent"},{"benchmark":"multichallenge","model":"kanana-2-30b-a3b-instruct","score":34.8,"metric":"percent"},{"benchmark":"multichallenge","model":"kanana-1.5-32.5b-instruct","score":19.05,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-30b-a3b-instruct-2507","score":41.76,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-30b-a3b","score":27.84,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"kanana-2-30b-a3b-instruct-2601","score":76.66,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"kanana-2-30b-a3b-instruct","score":74.3,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"kanana-1.5-32.5b-instruct","score":68.74,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"qwen3-30b-a3b-instruct-2507","score":73.93,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"qwen3-30b-a3b","score":69.14,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kanana-2-30b-a3b-instruct-2601","score":38.63,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kanana-2-30b-a3b-instruct","score":35.38,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kanana-1.5-32.5b-instruct","score":11.38,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3-30b-a3b-instruct-2507","score":38.77,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3-30b-a3b","score":11.88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kanana-2-30b-a3b-instruct-2601","score":81.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kanana-2-30b-a3b-instruct","score":79.88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kanana-1.5-32.5b-instruct","score":79.88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-30b-a3b-instruct-2507","score":86.59,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-30b-a3b","score":87.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kanana-2-30b-a3b-instruct-2601","score":73.02,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kanana-2-30b-a3b-instruct","score":73.81,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kanana-1.5-32.5b-instruct","score":71.96,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-30b-a3b-instruct-2507","score":75.13,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-30b-a3b","score":75.13,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-2-30b-a3b-instruct-2601","score":93.1,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-2-30b-a3b-instruct","score":91.89,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-1.5-32.5b-instruct","score":91.58,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b-instruct-2507","score":93.56,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b","score":93.33,"metric":"percent"},{"benchmark":"math","model":"kanana-2-30b-a3b-instruct-2601","score":88.56,"metric":"percent"},{"benchmark":"math","model":"kanana-2-30b-a3b-instruct","score":86.26,"metric":"percent"},{"benchmark":"math","model":"kanana-1.5-32.5b-instruct","score":77.92,"metric":"percent"},{"benchmark":"math","model":"qwen3-30b-a3b-instruct-2507","score":90.96,"metric":"percent"},{"benchmark":"math","model":"qwen3-30b-a3b","score":87.2,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-2-30b-a3b-instruct-2601","score":81.61,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-2-30b-a3b-instruct","score":80.8,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-1.5-32.5b-instruct","score":82.75,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b","score":85.6,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-2-30b-a3b-instruct-2601","score":68.26,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-2-30b-a3b-instruct","score":67.32,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-1.5-32.5b-instruct","score":65.75,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen3-30b-a3b-instruct-2507","score":67.56,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen3-30b-a3b","score":63.49,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kanana-2-30b-a3b-instruct-2601","score":52.53,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kanana-2-30b-a3b-instruct","score":42.93,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kanana-1.5-32.5b-instruct","score":42.42,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-instruct-2507","score":54.55,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b","score":50.51,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-2-30b-a3b-instruct-2601","score":75.57,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-2-30b-a3b-instruct","score":75.57,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-1.5-32.5b-instruct","score":65.34,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"qwen3-30b-a3b-instruct-2507","score":53.41,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"qwen3-30b-a3b","score":57.39,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kanana-2-30b-a3b-thinking-2601","score":74.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kanana-2-30b-a3b-thinking","score":75.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-thinking-2507","score":80.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b","score":78.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kanana-2-30b-a3b-thinking-2601","score":57.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kanana-2-30b-a3b-thinking","score":61.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-thinking-2507","score":70.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b","score":62.6,"metric":"percent"},{"benchmark":"aime-2025","model":"kanana-2-30b-a3b-thinking-2601","score":74,"metric":"percent"},{"benchmark":"aime-2025","model":"kanana-2-30b-a3b-thinking","score":72.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-thinking-2507","score":82.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b","score":70.7,"metric":"percent"},{"benchmark":"aime-2024","model":"kanana-2-30b-a3b-thinking-2601","score":79,"metric":"percent"},{"benchmark":"aime-2024","model":"kanana-2-30b-a3b-thinking","score":78.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b-thinking-2507","score":91,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b","score":82.7,"metric":"percent"},{"benchmark":"aime-2024-ko","model":"kanana-2-30b-a3b-thinking-2601","score":75,"metric":"percent"},{"benchmark":"aime-2024-ko","model":"kanana-2-30b-a3b-thinking","score":25.3,"metric":"percent"},{"benchmark":"aime-2024-ko","model":"qwen3-30b-a3b-thinking-2507","score":80.3,"metric":"percent"},{"benchmark":"aime-2024-ko","model":"qwen3-30b-a3b","score":72.3,"metric":"percent"},{"benchmark":"livecodebench","model":"kanana-2-30b-a3b-thinking-2601","score":58.8,"metric":"percent"},{"benchmark":"livecodebench","model":"kanana-2-30b-a3b-thinking","score":60.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-thinking-2507","score":68.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b","score":62.3,"metric":"percent"},{"benchmark":"livecodebench-ko","model":"kanana-2-30b-a3b-thinking-2601","score":51.2,"metric":"percent"},{"benchmark":"livecodebench-ko","model":"kanana-2-30b-a3b-thinking","score":9.4,"metric":"percent"},{"benchmark":"livecodebench-ko","model":"qwen3-30b-a3b-thinking-2507","score":66.3,"metric":"percent"},{"benchmark":"livecodebench-ko","model":"qwen3-30b-a3b","score":61.5,"metric":"percent"},{"benchmark":"ifeval","model":"kanana-2-30b-a3b-thinking-2601","score":82.2,"metric":"percent"},{"benchmark":"ifeval","model":"kanana-2-30b-a3b-thinking","score":82.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-thinking-2507","score":87.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b","score":86.1,"metric":"percent"},{"benchmark":"ifbench","model":"kanana-2-30b-a3b-thinking-2601","score":47.8,"metric":"percent"},{"benchmark":"ifbench","model":"kanana-2-30b-a3b-thinking","score":42.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b-thinking-2507","score":47.6,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b","score":36.7,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"kanana-2-30b-a3b-thinking-2601","score":75.9,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"kanana-2-30b-a3b-thinking","score":75.6,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"qwen3-30b-a3b-thinking-2507","score":82.9,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"qwen3-30b-a3b","score":80.3,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kanana-2-30b-a3b-thinking-2601","score":43.7,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kanana-2-30b-a3b-thinking","score":34.3,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3-30b-a3b-thinking-2507","score":53.6,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3-30b-a3b","score":35.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.5-358b-swe-agent","score":64.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-480b-a35b-mini-swe-agent","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.5-358b-mini-swe-agent","score":54.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4-moatless-tools","score":70.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4-swe-agent","score":66.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4-r2e-gym","score":66.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-r2e-gym","score":65.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-4o-r2e-gym","score":29.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2.5-1.2b-thinking","score":37.86,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-1.2b-thinking","score":49.65,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-1.2b-thinking","score":88.42,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-1.2b-thinking","score":44.85,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-1.2b-thinking","score":69.33,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2.5-1.2b-thinking","score":85.6,"metric":"percent"},{"benchmark":"math500","model":"lfm2.5-1.2b-thinking","score":87.96,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2.5-1.2b-thinking","score":31.73,"metric":"percent"},{"benchmark":"bfcl-v3","model":"lfm2.5-1.2b-thinking","score":56.97,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-1.7b-thinking","score":36.93,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b-thinking","score":56.68,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-1.7b-thinking","score":71.65,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-1.7b-thinking","score":25.88,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-1.7b-thinking","score":60.33,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-1.7b-thinking","score":85.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-1.7b-thinking","score":81.92,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-1.7b-thinking","score":36.27,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-1.7b-thinking","score":55.41,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2.5-1.2b-instruct","score":38.89,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2.5-1.2b-instruct","score":64.52,"metric":"percent"},{"benchmark":"math500","model":"lfm2.5-1.2b-instruct","score":63.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-1.7b","score":34.85,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-1.7b","score":33.66,"metric":"percent"},{"benchmark":"math500","model":"qwen3-1.7b","score":70.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"granite-4.0-h-1b","score":24.34,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-h-1b","score":27.64,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-1b","score":80.08,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.0-h-1b","score":24.93,"metric":"percent"},{"benchmark":"multi-if","model":"granite-4.0-h-1b","score":47.56,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-h-1b","score":69.6,"metric":"percent"},{"benchmark":"math500","model":"granite-4.0-h-1b","score":47.2,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-4.0-h-1b","score":1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.0-h-1b","score":50.69,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"granite-4.0-1b","score":24.24,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-1b","score":73.42,"metric":"percent"},{"benchmark":"math500","model":"granite-4.0-1b","score":44.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-1b-it","score":24.24,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-1b-it","score":42.15,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-1b-it","score":45.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.2-1b-instruct","score":16.57,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-1b-instruct","score":20.8,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.2-1b-instruct","score":52.37,"metric":"percent"},{"benchmark":"ifbench","model":"llama-3.2-1b-instruct","score":15.93,"metric":"percent"},{"benchmark":"multi-if","model":"llama-3.2-1b-instruct","score":30.16,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-1b-instruct","score":39.04,"metric":"percent"},{"benchmark":"math500","model":"llama-3.2-1b-instruct","score":23.4,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.2-1b-instruct","score":0.33,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llama-3.2-1b-instruct","score":21.44,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.2-thinking","score":87.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-5.2-thinking","score":95,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-5.2-thinking","score":90.5,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-5.2-thinking","score":92.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.2-thinking","score":35.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.2-thinking","score":87.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5.2-thinking","score":99.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.2-thinking","score":86.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.2-thinking","score":80,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5.2-thinking","score":45.5,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.2-thinking","score":75.4,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5.2-thinking","score":57.9,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-5.2-thinking","score":80.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.2-thinking","score":63.1,"metric":"percent"},{"benchmark":"vitabench","model":"gpt-5.2-thinking","score":38.2,"metric":"percent"},{"benchmark":"deep-planning","model":"gpt-5.2-thinking","score":44.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.2-thinking","score":72.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.5","score":89.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-opus-4.5","score":95.6,"metric":"percent"},{"benchmark":"c-eval","model":"claude-opus-4.5","score":92.2,"metric":"percent"},{"benchmark":"gpqa","model":"claude-opus-4.5","score":87,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.5","score":30.8,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.5","score":84.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.5","score":84,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-opus-4.5","score":43.2,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-opus-4.5","score":54.2,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"claude-opus-4.5","score":76.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"claude-opus-4.5","score":77.5,"metric":"percent"},{"benchmark":"vitabench","model":"claude-opus-4.5","score":56.3,"metric":"percent"},{"benchmark":"deep-planning","model":"claude-opus-4.5","score":33.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3-pro","score":89.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemini-3-pro","score":95.9,"metric":"percent"},{"benchmark":"c-eval","model":"gemini-3-pro","score":93.4,"metric":"percent"},{"benchmark":"gpqa","model":"gemini-3-pro","score":91.9,"metric":"percent"},{"benchmark":"hle","model":"gemini-3-pro","score":37.5,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gemini-3-pro","score":45.8,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-3-pro","score":70.4,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-3-pro","score":64.2,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemini-3-pro","score":81.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemini-3-pro","score":72.5,"metric":"percent"},{"benchmark":"vitabench","model":"gemini-3-pro","score":51.6,"metric":"percent"},{"benchmark":"deep-planning","model":"gemini-3-pro","score":23.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-3-pro","score":70.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3.2","score":94.5,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3.2","score":92.9,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v3.2","score":82.4,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v3.2","score":25.1,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2","score":80.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"deepseek-v3.2","score":40.8,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v3.2","score":60.7,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v3.2","score":47.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"deepseek-v3.2","score":66.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"deepseek-v3.2","score":61.2,"metric":"percent"},{"benchmark":"vitabench","model":"deepseek-v3.2","score":44.1,"metric":"percent"},{"benchmark":"deep-planning","model":"deepseek-v3.2","score":21.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-max-thinking","score":85.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-max-thinking","score":92.8,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-max-thinking","score":93.7,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-max-thinking","score":87.4,"metric":"percent"},{"benchmark":"hle","model":"qwen3-max-thinking","score":30.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-max-thinking","score":85.9,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-max-thinking","score":98,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-max-thinking","score":94.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-max-thinking","score":83.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-max-thinking","score":75.3,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3-max-thinking","score":49.8,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-max-thinking","score":70.9,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-max-thinking","score":63.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-max-thinking","score":90.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-max-thinking","score":67.7,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3-max-thinking","score":40.9,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3-max-thinking","score":28.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-max-thinking","score":68.7,"metric":"percent"},{"benchmark":"hle","model":"kimi-k2.5-thinking","score":30.1,"metric":"percent"},{"benchmark":"hle-with-tools","model":"kimi-k2.5-thinking","score":50.2,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2.5-thinking","score":96.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"kimi-k2.5-thinking","score":95.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2.5-thinking","score":81.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.5-thinking","score":87.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2.5-thinking","score":87.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k2.5-thinking","score":78.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"kimi-k2.5-thinking","score":77.5,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-k2.5-thinking","score":84.2,"metric":"percent"},{"benchmark":"mathvista","model":"kimi-k2.5-thinking","score":90.1,"metric":"percent"},{"benchmark":"zerobench","model":"kimi-k2.5-thinking","score":9,"metric":"percent"},{"benchmark":"ocrbench","model":"kimi-k2.5-thinking","score":92.3,"metric":"percent"},{"benchmark":"omnidocbench","model":"kimi-k2.5-thinking","score":88.8,"metric":"percent"},{"benchmark":"infovqa","model":"kimi-k2.5-thinking","score":92.6,"metric":"percent"},{"benchmark":"simplevqa","model":"kimi-k2.5-thinking","score":71.2,"metric":"percent"},{"benchmark":"worldvqa","model":"kimi-k2.5-thinking","score":46.3,"metric":"percent"},{"benchmark":"videommmu","model":"kimi-k2.5-thinking","score":86.6,"metric":"percent"},{"benchmark":"mmvu","model":"kimi-k2.5-thinking","score":80.4,"metric":"percent"},{"benchmark":"motionbench","model":"kimi-k2.5-thinking","score":70.4,"metric":"percent"},{"benchmark":"videomme","model":"kimi-k2.5-thinking","score":87.4,"metric":"percent"},{"benchmark":"longvideobench","model":"kimi-k2.5-thinking","score":79.8,"metric":"percent"},{"benchmark":"lvbench","model":"kimi-k2.5-thinking","score":75.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.5-thinking","score":76.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k2.5-thinking","score":50.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2.5-thinking","score":73,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-k2.5-thinking","score":50.8,"metric":"percent"},{"benchmark":"paperbench","model":"kimi-k2.5-thinking","score":63.5,"metric":"percent"},{"benchmark":"cybergym","model":"kimi-k2.5-thinking","score":41.3,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k2.5-thinking","score":48.7,"metric":"percent"},{"benchmark":"ojbench","model":"kimi-k2.5-thinking","score":57.4,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2.5-thinking","score":85,"metric":"percent"},{"benchmark":"longbench-v2","model":"kimi-k2.5-thinking","score":61,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2.5-thinking","score":70,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2.5-thinking","score":60.6,"metric":"percent"},{"benchmark":"wide-search","model":"kimi-k2.5-thinking","score":72.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"kimi-k2.5-thinking","score":77.1,"metric":"percent"},{"benchmark":"finsearchcomp","model":"kimi-k2.5-thinking","score":67.8,"metric":"percent"},{"benchmark":"seal-0","model":"kimi-k2.5-thinking","score":57.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.2-thinking-xhigh","score":34.5,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5.2-thinking-xhigh","score":45.5,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.2-thinking-xhigh","score":100,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5.2-thinking-xhigh","score":99.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.2-thinking-xhigh","score":86.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2-thinking-xhigh","score":92.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.2-thinking-xhigh","score":86.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.2-thinking-xhigh","score":79.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.2-thinking-xhigh","score":82.1,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.2-thinking-xhigh","score":83,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5.2-thinking-xhigh","score":82.8,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5.2-thinking-xhigh","score":9,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5.2-thinking-xhigh","score":80.7,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-5.2-thinking-xhigh","score":85.7,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-5.2-thinking-xhigh","score":84,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5.2-thinking-xhigh","score":55.8,"metric":"percent"},{"benchmark":"worldvqa","model":"gpt-5.2-thinking-xhigh","score":28,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5.2-thinking-xhigh","score":85.9,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5.2-thinking-xhigh","score":80.8,"metric":"percent"},{"benchmark":"motionbench","model":"gpt-5.2-thinking-xhigh","score":64.8,"metric":"percent"},{"benchmark":"videomme","model":"gpt-5.2-thinking-xhigh","score":86,"metric":"percent"},{"benchmark":"longvideobench","model":"gpt-5.2-thinking-xhigh","score":76.5,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.2-thinking-xhigh","score":55.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.2-thinking-xhigh","score":72,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5.2-thinking-xhigh","score":54,"metric":"percent"},{"benchmark":"paperbench","model":"gpt-5.2-thinking-xhigh","score":63.7,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.2-thinking-xhigh","score":52.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5.2-thinking-xhigh","score":54.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.2-thinking-xhigh","score":72.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-5.2-thinking-xhigh","score":71.3,"metric":"percent"},{"benchmark":"seal-0","model":"gpt-5.2-thinking-xhigh","score":45,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.5-thinking","score":30.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-opus-4.5-thinking","score":43.2,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.5-thinking","score":92.8,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"claude-opus-4.5-thinking","score":92.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.5-thinking","score":78.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.5-thinking","score":87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.5-thinking","score":89.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.5-thinking","score":74,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.5-thinking","score":67.2,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.5-thinking","score":77.1,"metric":"percent"},{"benchmark":"mathvista","model":"claude-opus-4.5-thinking","score":80.2,"metric":"percent"},{"benchmark":"zerobench","model":"claude-opus-4.5-thinking","score":3,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-opus-4.5-thinking","score":86.5,"metric":"percent"},{"benchmark":"omnidocbench","model":"claude-opus-4.5-thinking","score":87.7,"metric":"percent"},{"benchmark":"infovqa","model":"claude-opus-4.5-thinking","score":76.9,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-opus-4.5-thinking","score":69.7,"metric":"percent"},{"benchmark":"worldvqa","model":"claude-opus-4.5-thinking","score":36.8,"metric":"percent"},{"benchmark":"videommmu","model":"claude-opus-4.5-thinking","score":84.4,"metric":"percent"},{"benchmark":"mmvu","model":"claude-opus-4.5-thinking","score":77.3,"metric":"percent"},{"benchmark":"motionbench","model":"claude-opus-4.5-thinking","score":60.3,"metric":"percent"},{"benchmark":"longvideobench","model":"claude-opus-4.5-thinking","score":67.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.5-thinking","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.5-thinking","score":77.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4.5-thinking","score":59.3,"metric":"percent"},{"benchmark":"paperbench","model":"claude-opus-4.5-thinking","score":72.9,"metric":"percent"},{"benchmark":"cybergym","model":"claude-opus-4.5-thinking","score":50.6,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.5-thinking","score":49.5,"metric":"percent"},{"benchmark":"ojbench","model":"claude-opus-4.5-thinking","score":54.6,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.5-thinking","score":82.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-opus-4.5-thinking","score":64.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-opus-4.5-thinking","score":71.3,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-opus-4.5-thinking","score":37,"metric":"percent"},{"benchmark":"wide-search","model":"claude-opus-4.5-thinking","score":76.2,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-4.5-thinking","score":76.1,"metric":"percent"},{"benchmark":"finsearchcomp","model":"claude-opus-4.5-thinking","score":66.2,"metric":"percent"},{"benchmark":"seal-0","model":"claude-opus-4.5-thinking","score":47.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemini-3-pro","score":97.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3-pro","score":83.1,"metric":"percent"},{"benchmark":"zerobench","model":"gemini-3-pro","score":8,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-3-pro","score":90.3,"metric":"percent"},{"benchmark":"omnidocbench","model":"gemini-3-pro","score":88.5,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-3-pro","score":57.2,"metric":"percent"},{"benchmark":"worldvqa","model":"gemini-3-pro","score":47.4,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-3-pro","score":77.5,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-3-pro","score":77.7,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3-pro","score":73.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemini-3-pro","score":65,"metric":"percent"},{"benchmark":"cybergym","model":"gemini-3-pro","score":39.9,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3-pro","score":56.1,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-3-pro","score":68.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-pro","score":87.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-3-pro","score":68.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-3-pro","score":65.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gemini-3-pro","score":63.2,"metric":"percent"},{"benchmark":"finsearchcomp","model":"gemini-3-pro","score":49.9,"metric":"percent"},{"benchmark":"seal-0","model":"gemini-3-pro","score":45.5,"metric":"percent"},{"benchmark":"hle-with-tools","model":"deepseek-v3.2-thinking","score":40.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-v3.2-thinking","score":46.4,"metric":"percent"},{"benchmark":"paperbench","model":"deepseek-v3.2-thinking","score":47.1,"metric":"percent"},{"benchmark":"cybergym","model":"deepseek-v3.2-thinking","score":17.3,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v3.2-thinking","score":38.9,"metric":"percent"},{"benchmark":"ojbench","model":"deepseek-v3.2-thinking","score":54.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v3.2-thinking","score":59.8,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v3.2-thinking","score":64.3,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v3.2-thinking","score":32.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v3.2-thinking","score":60.9,"metric":"percent"},{"benchmark":"finsearchcomp","model":"deepseek-v3.2-thinking","score":59.1,"metric":"percent"},{"benchmark":"seal-0","model":"deepseek-v3.2-thinking","score":49.5,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-235b-a22b-thinking","score":85.8,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3-vl-235b-a22b-thinking","score":4,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-235b-a22b-thinking","score":87.5,"metric":"percent"},{"benchmark":"omnidocbench","model":"qwen3-vl-235b-a22b-thinking","score":82,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-235b-a22b-thinking","score":56.8,"metric":"percent"},{"benchmark":"worldvqa","model":"qwen3-vl-235b-a22b-thinking","score":23.5,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3-vl-235b-a22b-thinking","score":71.1,"metric":"percent"},{"benchmark":"videomme","model":"qwen3-vl-235b-a22b-thinking","score":79,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-vl-235b-a22b-thinking","score":65.6,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"deepseek-ocr","score":0.129,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"deepseek-ocr-2","score":0.1,"metric":"edit_distance"},{"benchmark":"omnidocbench","model":"marker-1.8.2","score":71.3,"metric":"percent"},{"benchmark":"omnidocbench","model":"mineru2-pp","score":71.51,"metric":"percent"},{"benchmark":"omnidocbench","model":"dolphin","score":74.67,"metric":"percent"},{"benchmark":"omnidocbench","model":"dolphin-1.5","score":83.21,"metric":"percent"},{"benchmark":"omnidocbench","model":"pp-structurev3","score":86.73,"metric":"percent"},{"benchmark":"omnidocbench","model":"monkeyocr-pro-1.2b","score":86.96,"metric":"percent"},{"benchmark":"omnidocbench","model":"monkeyocr-3b","score":87.13,"metric":"percent"},{"benchmark":"omnidocbench","model":"monkeyocr-pro-3b","score":88.85,"metric":"percent"},{"benchmark":"omnidocbench","model":"mineru2.5","score":90.67,"metric":"percent"},{"benchmark":"omnidocbench","model":"paddleocr-vl","score":92.86,"metric":"percent"},{"benchmark":"omnidocbench","model":"ocrflux","score":74.82,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-4o","score":75.02,"metric":"percent"},{"benchmark":"omnidocbench","model":"internvl3","score":80.33,"metric":"percent"},{"benchmark":"omnidocbench","model":"points-reader","score":80.98,"metric":"percent"},{"benchmark":"omnidocbench","model":"olmocr","score":81.79,"metric":"percent"},{"benchmark":"omnidocbench","model":"internvl3.5-241b","score":82.67,"metric":"percent"},{"benchmark":"omnidocbench","model":"mineru2-vlm","score":85.56,"metric":"percent"},{"benchmark":"omnidocbench","model":"nanonets-ocr-s","score":85.59,"metric":"percent"},{"benchmark":"omnidocbench","model":"qwen2.5-vl-72b","score":87.02,"metric":"percent"},{"benchmark":"omnidocbench","model":"gemini-2.5-pro","score":88.03,"metric":"percent"},{"benchmark":"omnidocbench","model":"dots.ocr","score":88.41,"metric":"percent"},{"benchmark":"omnidocbench","model":"ocrverse","score":88.56,"metric":"percent"},{"benchmark":"omnidocbench","model":"qwen3-vl-235b-a22b","score":89.15,"metric":"percent"},{"benchmark":"omnidocbench","model":"deepseek-ocr","score":87.36,"metric":"percent"},{"benchmark":"omnidocbench","model":"deepseek-ocr-2","score":91.09,"metric":"percent"},{"benchmark":"mmlu","model":"llama-4-maverick","score":85.5,"metric":"percent"},{"benchmark":"mmlu","model":"trinity-large-preview","score":87.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trinity-large-preview","score":75.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"trinity-large-preview","score":63.3,"metric":"percent"},{"benchmark":"aime-2025","model":"trinity-large-preview","score":24,"metric":"percent"},{"benchmark":"mbpp-plus","model":"trinity-large-base","score":88.62,"metric":"percent"},{"benchmark":"math500","model":"trinity-large-base","score":65.2,"metric":"percent"},{"benchmark":"hellaswag","model":"trinity-large-base","score":90.11,"metric":"percent"},{"benchmark":"winogrande","model":"trinity-large-base","score":80.82,"metric":"percent"},{"benchmark":"mmlu","model":"trinity-large-base","score":82.58,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trinity-large-base","score":66.02,"metric":"percent"},{"benchmark":"triviaqa","model":"trinity-large-base","score":83.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"trinity-large-base","score":65.44,"metric":"percent"},{"benchmark":"bbh","model":"trinity-large-base","score":65.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"trinity-large-base","score":43.94,"metric":"percent"},{"benchmark":"gsm8k","model":"trinity-large-base","score":91.36,"metric":"percent"},{"benchmark":"arc-challenge","model":"trinity-large-truebase","score":62.37,"metric":"percent"},{"benchmark":"bbh","model":"trinity-large-truebase","score":57.84,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"trinity-large-truebase","score":40.91,"metric":"percent"},{"benchmark":"gsm8k","model":"trinity-large-truebase","score":80.36,"metric":"percent"},{"benchmark":"hellaswag","model":"trinity-large-truebase","score":88.13,"metric":"percent"},{"benchmark":"humaneval-plus","model":"trinity-large-truebase","score":51.83,"metric":"percent"},{"benchmark":"mbpp-plus","model":"trinity-large-truebase","score":80.95,"metric":"percent"},{"benchmark":"math500","model":"trinity-large-truebase","score":48.2,"metric":"percent"},{"benchmark":"mmlu","model":"trinity-large-truebase","score":78.45,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trinity-large-truebase","score":51.6,"metric":"percent"},{"benchmark":"triviaqa","model":"trinity-large-truebase","score":80.96,"metric":"percent"},{"benchmark":"winogrande","model":"trinity-large-truebase","score":81.45,"metric":"percent"},{"benchmark":"tau2-airline","model":"longcat-flash-lite","score":58,"metric":"percent"},{"benchmark":"tau2-retail","model":"longcat-flash-lite","score":73.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"longcat-flash-lite","score":72.8,"metric":"percent"},{"benchmark":"swe-bench","model":"longcat-flash-lite","score":54.4,"metric":"percent"},{"benchmark":"terminal-bench","model":"longcat-flash-lite","score":33.75,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"longcat-flash-lite","score":38.1,"metric":"percent"},{"benchmark":"prdbench","model":"longcat-flash-lite","score":39.63,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"longcat-flash-lite","score":66.78,"metric":"percent"},{"benchmark":"mmlu","model":"longcat-flash-lite","score":85.52,"metric":"percent"},{"benchmark":"mmlu-pro","model":"longcat-flash-lite","score":78.29,"metric":"percent"},{"benchmark":"c-eval","model":"longcat-flash-lite","score":86.55,"metric":"percent"},{"benchmark":"cmmlu","model":"longcat-flash-lite","score":82.48,"metric":"percent"},{"benchmark":"math500","model":"longcat-flash-lite","score":96.8,"metric":"percent"},{"benchmark":"aime-2024","model":"longcat-flash-lite","score":72.19,"metric":"percent"},{"benchmark":"aime-2025","model":"longcat-flash-lite","score":63.23,"metric":"percent"},{"benchmark":"tau2-airline","model":"kimi-linear-instruct","score":44,"metric":"percent"},{"benchmark":"tau2-retail","model":"kimi-linear-instruct","score":18.86,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-linear-instruct","score":15.68,"metric":"percent"},{"benchmark":"swe-bench","model":"kimi-linear-instruct","score":32.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"kimi-linear-instruct","score":20,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-linear-instruct","score":37.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-linear-instruct","score":69.89,"metric":"percent"},{"benchmark":"mmlu","model":"kimi-linear-instruct","score":79.91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-linear-instruct","score":67.22,"metric":"percent"},{"benchmark":"c-eval","model":"kimi-linear-instruct","score":78.48,"metric":"percent"},{"benchmark":"cmmlu","model":"kimi-linear-instruct","score":76.26,"metric":"percent"},{"benchmark":"math500","model":"kimi-linear-instruct","score":94.2,"metric":"percent"},{"benchmark":"aime-2024","model":"kimi-linear-instruct","score":70.52,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-linear-instruct","score":59.58,"metric":"percent"},{"benchmark":"swe-bench","model":"qwen3-next-80b-a3b-instruct","score":37.6,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-next-80b-a3b-instruct","score":15.19,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3-next-80b-a3b-instruct","score":31.3,"metric":"percent"},{"benchmark":"prdbench","model":"qwen3-next-80b-a3b-instruct","score":15.36,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-next-80b-a3b-instruct","score":74.33,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-next-80b-a3b-instruct","score":89.28,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-next-80b-a3b-instruct","score":82.93,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-next-80b-a3b-instruct","score":90.91,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-next-80b-a3b-instruct","score":86.5,"metric":"percent"},{"benchmark":"math500","model":"qwen3-next-80b-a3b-instruct","score":98,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-next-80b-a3b-instruct","score":81.35,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-next-80b-a3b-instruct","score":68.44,"metric":"percent"},{"benchmark":"tau2-airline","model":"gemini-2.5-flash-lite","score":35,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemini-2.5-flash-lite","score":37.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash-lite","score":21.93,"metric":"percent"},{"benchmark":"swe-bench","model":"gemini-2.5-flash-lite","score":41.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-flash-lite","score":20,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash-lite","score":70.2,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-2.5-flash-lite","score":84.68,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-flash-lite","score":78.95,"metric":"percent"},{"benchmark":"c-eval","model":"gemini-2.5-flash-lite","score":75.16,"metric":"percent"},{"benchmark":"cmmlu","model":"gemini-2.5-flash-lite","score":72.06,"metric":"percent"},{"benchmark":"math500","model":"gemini-2.5-flash-lite","score":95.2,"metric":"percent"},{"benchmark":"aime-2024","model":"gemini-2.5-flash-lite","score":63.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash-lite","score":50.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.5","score":78.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4.5","score":76,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.2","score":70.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.7","score":74.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m2.1","score":74.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.5","score":73.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-next","score":70.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.5","score":71.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-sonnet-4.5","score":67.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v3.2","score":62.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-4.7","score":63.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"minimax-m2.1","score":66.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2.5","score":63.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3-coder-next","score":62.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.5","score":46.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-sonnet-4.5","score":44.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v3.2","score":40.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"glm-4.7","score":40.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"minimax-m2.1","score":34.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k2.5","score":39.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3-coder-next","score":44.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-coder-next","score":66.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3.2","score":69.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"glm-4.7","score":52.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"minimax-m2.1","score":61,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-coder-next","score":36.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v3.2","score":39.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-4.7","score":37.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"minimax-m2.1","score":32.6,"metric":"percent"},{"benchmark":"browsecomp","model":"step-3.5-flash-20260204","score":51.6,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2-thinking","score":41.5,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2.5","score":60.6,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"step-3.5-flash-20260204","score":69,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"kimi-k2.5","score":74.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"step-3.5-flash-20260204","score":66.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"kimi-k2.5","score":62.3,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"minimax-m2.1","score":47.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"mimo-v2-flash","score":51.2,"metric":"percent"},{"benchmark":"browsecomp-zh-with-content-manager","model":"step-3.5-flash-20260204","score":73.7,"metric":"percent"},{"benchmark":"gaia-no-file","model":"step-3.5-flash-20260204","score":84.5,"metric":"percent"},{"benchmark":"gaia-no-file","model":"deepseek-v3.2","score":75.1,"metric":"percent"},{"benchmark":"gaia-no-file","model":"kimi-k2-thinking","score":75.6,"metric":"percent"},{"benchmark":"gaia-no-file","model":"kimi-k2.5","score":75.9,"metric":"percent"},{"benchmark":"gaia-no-file","model":"glm-4.7","score":61.9,"metric":"percent"},{"benchmark":"gaia-no-file","model":"minimax-m2.1","score":64.3,"metric":"percent"},{"benchmark":"gaia-no-file","model":"mimo-v2-flash","score":78.2,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"step-3.5-flash-20260204","score":83.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"deepseek-v3.2","score":78,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"kimi-k2-thinking","score":76,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"kimi-k2.5","score":76.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"glm-4.7","score":72,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"minimax-m2.1","score":68.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"mimo-v2-flash","score":69.3,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"step-3.5-flash-20260204","score":56.3,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"deepseek-v3.2","score":55.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"glm-4.7","score":52.3,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"minimax-m2.1","score":43,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"mimo-v2-flash","score":44,"metric":"avg@3"},{"benchmark":"researchrubrics","model":"step-3.5-flash-20260204","score":65.3,"metric":"percent"},{"benchmark":"researchrubrics","model":"deepseek-v3.2","score":55.8,"metric":"percent"},{"benchmark":"researchrubrics","model":"kimi-k2-thinking","score":56.2,"metric":"percent"},{"benchmark":"researchrubrics","model":"kimi-k2.5","score":59.5,"metric":"percent"},{"benchmark":"researchrubrics","model":"glm-4.7","score":62,"metric":"percent"},{"benchmark":"researchrubrics","model":"minimax-m2.1","score":60.2,"metric":"percent"},{"benchmark":"researchrubrics","model":"mimo-v2-flash","score":54.3,"metric":"percent"},{"benchmark":"aime-2025","model":"step-3.5-flash-20260204","score":97.3,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2.5","score":96.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"step-3.5-flash-20260204","score":98.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"kimi-k2.5","score":95.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"minimax-m2.1","score":71,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"step-3.5-flash-20260204","score":94,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"minimax-m2.1","score":74.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"mimo-v2-flash","score":91,"metric":"percent"},{"benchmark":"imo-answerbench","model":"step-3.5-flash-20260204","score":85.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2.5","score":81.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"minimax-m2.1","score":60.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"mimo-v2-flash","score":80.9,"metric":"percent"},{"benchmark":"livecodebench","model":"step-3.5-flash-20260204","score":86.4,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2.5","score":85,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"step-3.5-flash-20260204","score":74.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.5","score":76.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"step-3.5-flash-20260204","score":51,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2.5","score":50.8,"metric":"percent"},{"benchmark":"scireasoner","model":"intern-s1-pro","score":55.5,"metric":"percent"},{"benchmark":"scireasoner","model":"qwen3-vl-235b-a22b-thinking","score":11.9,"metric":"percent"},{"benchmark":"scireasoner","model":"kimi-k2.5","score":15.3,"metric":"percent"},{"benchmark":"scireasoner","model":"gpt-5.2","score":13.6,"metric":"percent"},{"benchmark":"scireasoner","model":"gemini-3-pro","score":14.7,"metric":"percent"},{"benchmark":"sfe","model":"intern-s1-pro","score":52.7,"metric":"percent"},{"benchmark":"sfe","model":"qwen3-vl-235b-a22b-thinking","score":41.4,"metric":"percent"},{"benchmark":"sfe","model":"kimi-k2.5","score":53.7,"metric":"percent"},{"benchmark":"sfe","model":"gpt-5.2","score":47.5,"metric":"percent"},{"benchmark":"sfe","model":"gemini-3-pro","score":58.9,"metric":"percent"},{"benchmark":"smolinstruct","model":"intern-s1-pro","score":74.8,"metric":"percent"},{"benchmark":"smolinstruct","model":"qwen3-vl-235b-a22b-thinking","score":36.6,"metric":"percent"},{"benchmark":"smolinstruct","model":"kimi-k2.5","score":53.5,"metric":"percent"},{"benchmark":"smolinstruct","model":"gpt-5.2","score":48.2,"metric":"percent"},{"benchmark":"smolinstruct","model":"gemini-3-pro","score":58.3,"metric":"percent"},{"benchmark":"matbench","model":"intern-s1-pro","score":72.8,"metric":"percent"},{"benchmark":"matbench","model":"qwen3-vl-235b-a22b-thinking","score":49.7,"metric":"percent"},{"benchmark":"matbench","model":"kimi-k2.5","score":60,"metric":"percent"},{"benchmark":"matbench","model":"gpt-5.2","score":53.6,"metric":"percent"},{"benchmark":"matbench","model":"gemini-3-pro","score":64.9,"metric":"percent"},{"benchmark":"mol-instructions","model":"intern-s1-pro","score":48.8,"metric":"percent"},{"benchmark":"mol-instructions","model":"qwen3-vl-235b-a22b-thinking","score":8.9,"metric":"percent"},{"benchmark":"mol-instructions","model":"kimi-k2.5","score":20,"metric":"percent"},{"benchmark":"mol-instructions","model":"gpt-5.2","score":12.3,"metric":"percent"},{"benchmark":"mol-instructions","model":"gemini-3-pro","score":34.6,"metric":"percent"},{"benchmark":"microvqa","model":"intern-s1-pro","score":63.3,"metric":"percent"},{"benchmark":"microvqa","model":"qwen3-vl-235b-a22b-thinking","score":53.8,"metric":"percent"},{"benchmark":"microvqa","model":"kimi-k2.5","score":55.4,"metric":"percent"},{"benchmark":"microvqa","model":"gpt-5.2","score":60.4,"metric":"percent"},{"benchmark":"microvqa","model":"gemini-3-pro","score":69,"metric":"percent"},{"benchmark":"biology-instruction","model":"intern-s1-pro","score":52.5,"metric":"percent"},{"benchmark":"biology-instruction","model":"qwen3-vl-235b-a22b-thinking","score":6.2,"metric":"percent"},{"benchmark":"biology-instruction","model":"kimi-k2.5","score":10.7,"metric":"percent"},{"benchmark":"biology-instruction","model":"gpt-5.2","score":10.2,"metric":"percent"},{"benchmark":"biology-instruction","model":"gemini-3-pro","score":12,"metric":"percent"},{"benchmark":"xlrs-bench","model":"intern-s1-pro","score":52.8,"metric":"percent"},{"benchmark":"xlrs-bench","model":"qwen3-vl-235b-a22b-thinking","score":51.2,"metric":"percent"},{"benchmark":"xlrs-bench","model":"kimi-k2.5","score":46.4,"metric":"percent"},{"benchmark":"xlrs-bench","model":"gpt-5.2","score":50.4,"metric":"percent"},{"benchmark":"xlrs-bench","model":"gemini-3-pro","score":51.8,"metric":"percent"},{"benchmark":"msearth-mcq","model":"intern-s1-pro","score":65.2,"metric":"percent"},{"benchmark":"msearth-mcq","model":"qwen3-vl-235b-a22b-thinking","score":52.7,"metric":"percent"},{"benchmark":"msearth-mcq","model":"kimi-k2.5","score":61.9,"metric":"percent"},{"benchmark":"msearth-mcq","model":"gpt-5.2","score":62.6,"metric":"percent"},{"benchmark":"msearth-mcq","model":"gemini-3-pro","score":65.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"intern-s1-pro","score":72.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-235b-a22b-thinking","score":69.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k2.5","score":78.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.2","score":79.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-s1-pro","score":86.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-vl-235b-a22b-thinking","score":83.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2.5","score":87.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.2","score":85.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3-pro","score":89.3,"metric":"percent"},{"benchmark":"aime-2025","model":"intern-s1-pro","score":93.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-235b-a22b-thinking","score":90,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.2","score":100,"metric":"percent"},{"benchmark":"imo-answerbench","model":"intern-s1-pro","score":77.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-vl-235b-a22b-thinking","score":72.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.2","score":86.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3-pro","score":81.3,"metric":"percent"},{"benchmark":"refcoco","model":"intern-s1-pro","score":91.9,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-235b-a22b-thinking","score":91.1,"metric":"percent"},{"benchmark":"refcoco","model":"kimi-k2.5","score":87.8,"metric":"percent"},{"benchmark":"refcoco","model":"gpt-5.2","score":54.9,"metric":"percent"},{"benchmark":"refcoco","model":"gemini-3-pro","score":76.2,"metric":"percent"},{"benchmark":"ifbench","model":"intern-s1-pro","score":71.2,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-vl-235b-a22b-thinking","score":58.7,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.5","score":69.7,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.2","score":75.4,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"intern-s1-pro","score":60.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"kimi-k2.5","score":64.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gpt-5.2","score":56.4,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemini-3-pro","score":68,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"intern-s1-pro","score":60.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-235b-a22b-thinking","score":63.8,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"kimi-k2.5","score":57.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gpt-5.2","score":54.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gemini-3-pro","score":52.5,"metric":"percent"},{"benchmark":"sarena-icon","model":"intern-s1-pro","score":83.5,"metric":"percent"},{"benchmark":"sarena-icon","model":"qwen3-vl-235b-a22b-thinking","score":76.3,"metric":"percent"},{"benchmark":"sarena-icon","model":"kimi-k2.5","score":77.3,"metric":"percent"},{"benchmark":"sarena-icon","model":"gpt-5.2","score":55.5,"metric":"percent"},{"benchmark":"sarena-icon","model":"gemini-3-pro","score":82.6,"metric":"percent"},{"benchmark":"livecodebench","model":"intern-s1-pro","score":74.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-235b-a22b-thinking","score":72,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.2","score":87.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-pro","score":86.9,"metric":"percent"},{"benchmark":"gaia","model":"intern-s1-pro","score":77.4,"metric":"percent"},{"benchmark":"gaia","model":"qwen3-vl-235b-a22b-thinking","score":47.8,"metric":"percent"},{"benchmark":"gaia","model":"kimi-k2.5","score":79.9,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.2","score":71.1,"metric":"percent"},{"benchmark":"gaia","model":"gemini-3-pro","score":75.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"intern-s1-pro","score":93.6,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-235b-a22b-thinking","score":92.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"kimi-k2.5","score":92.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gpt-5.2","score":49.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gemini-3-pro","score":94.7,"metric":"percent"},{"benchmark":"hle-with-tools","model":"glm-5","score":50.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-opus-4.5","score":43.4,"metric":"avg@3"},{"benchmark":"hle","model":"glm-5","score":30.5,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.2-thinking-xhigh","score":35.4,"metric":"avg@3"},{"benchmark":"swe-bench-verified","model":"glm-5","score":77.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5","score":73.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.5","score":77.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-5","score":56.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2-thinking-xhigh","score":54,"metric":"percent"},{"benchmark":"vending-bench-2","model":"glm-4.7","score":2377,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"glm-5","score":4432,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"claude-opus-4.5","score":4967,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"gpt-5.2-thinking-xhigh","score":3591,"metric":"net_worth_mean"},{"benchmark":"aicodeking-non-agentic","model":"claude-opus-4.6","score":100,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gemini-3-pro","score":100,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"glm-5","score":100,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"claude-opus-4.5-max","score":74,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gpt-5.2-thinking-xhigh","score":65,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"kimi-k2.5","score":64,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"deepseek-v3.1-thinking","score":43,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gpt-5-mini","score":43,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gpt-5-mini-high","score":43,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gemini-2.5-pro","score":42,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gpt-5.2","score":42,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"deepseek-v3.2-thinking","score":41,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"sonoma-sky","score":41,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gemini-3-flash-preview","score":40,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gpt-5.2-high","score":40,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"kimi-k2-0905","score":40,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"qwen3-max","score":40,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"grok-code-fast-1","score":38,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"gpt-5.1-codex-mini-high","score":36,"metric":"percent"},{"benchmark":"aicodeking-non-agentic","model":"sonic","score":36,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-2507","score":57.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b","score":49.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-14b","score":55.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b","score":55.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-2507","score":66,"metric":"percent"},{"benchmark":"livecodebench","model":"nanbeige4-3b-thinking-2511","score":46,"metric":"percent"},{"benchmark":"livecodebench","model":"nanbeige4.1-3b","score":76.9,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-4b-2507","score":40.2,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-8b","score":41.2,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-14b","score":33,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-32b","score":42.3,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-30b-a3b-2507","score":60.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nanbeige4-3b-thinking-2511","score":40.2,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nanbeige4.1-3b","score":81.4,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-4b-2507","score":5.3,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-8b","score":3.5,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-14b","score":1.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-32b","score":3.5,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-30b-a3b-2507","score":3.5,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nanbeige4-3b-thinking-2511","score":5.3,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nanbeige4.1-3b","score":28.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-4b-2507","score":81.46,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-8b","score":70.42,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-14b","score":76.46,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-32b","score":75.83,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-30b-a3b-2507","score":87.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nanbeige4-3b-thinking-2511","score":84.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nanbeige4.1-3b","score":87.4,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-4b-2507","score":68.33,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-8b","score":48.33,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-14b","score":56.67,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-32b","score":57.08,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-30b-a3b-2507","score":71.25,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"nanbeige4-3b-thinking-2511","score":66.67,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"nanbeige4.1-3b","score":77.92,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-4b-2507","score":48,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-8b","score":36.56,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-14b","score":41.81,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-32b","score":43.94,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-30b-a3b-2507","score":54.34,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nanbeige4-3b-thinking-2511","score":38.25,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nanbeige4.1-3b","score":53.38,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b-2507","score":65.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-14b","score":63.38,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-2507","score":73.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nanbeige4.1-3b","score":83.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-4b-2507","score":6.72,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-8b","score":5.28,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-14b","score":7,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-32b","score":9.31,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-30b-a3b-2507","score":11.77,"metric":"percent"},{"benchmark":"hle-text-only","model":"nanbeige4-3b-thinking-2511","score":10.98,"metric":"percent"},{"benchmark":"hle-text-only","model":"nanbeige4.1-3b","score":12.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-4b-2507","score":34.9,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-8b","score":26.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-14b","score":36.9,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-32b","score":56,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-30b-a3b-2507","score":60.2,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"nanbeige4.1-3b","score":73.2,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-4b-2507","score":41.14,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-8b","score":36.3,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-14b","score":36.97,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-32b","score":38.72,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-30b-a3b-2507","score":49.4,"metric":"percent"},{"benchmark":"multichallenge","model":"nanbeige4.1-3b","score":52.21,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-4b-2507","score":44.87,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-14b","score":45.14,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-30b-a3b-2507","score":48.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nanbeige4.1-3b","score":56.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.3-codex","score":77.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2-codex","score":64,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2","score":62.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.3-codex","score":64.7,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.2-codex","score":38.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.2","score":37.9,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.3-codex","score":56.8,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.2-codex","score":56.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.2","score":55.6,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.3-codex","score":70.9,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.2-high","score":70.9,"metric":"percent"},{"benchmark":"cybersecurity-ctf","model":"gpt-5.3-codex","score":77.6,"metric":"percent"},{"benchmark":"cybersecurity-ctf","model":"gpt-5.2-codex","score":67.4,"metric":"percent"},{"benchmark":"cybersecurity-ctf","model":"gpt-5.2","score":67.7,"metric":"percent"},{"benchmark":"swe-lancer-ic-diamond","model":"gpt-5.3-codex","score":81.4,"metric":"percent"},{"benchmark":"swe-lancer-ic-diamond","model":"gpt-5.2-codex","score":76,"metric":"percent"},{"benchmark":"swe-lancer-ic-diamond","model":"gpt-5.2","score":74.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.6","score":65.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.5","score":59.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-pro","score":56.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.6","score":80.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.2","score":80,"metric":"percent"},{"benchmark":"osworld","model":"claude-opus-4.6","score":72.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4.6","score":91.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-5.2","score":82,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.6","score":99.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.2","score":98.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.6","score":59.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.2","score":60.6,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-opus-4.6","score":84,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-opus-4.5","score":67.8,"metric":"percent"},{"benchmark":"browsecomp","model":"gemini-3-pro","score":59.2,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.2","score":77.9,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.6","score":40,"metric":"avg@3"},{"benchmark":"hle","model":"claude-opus-4.5","score":30.8,"metric":"avg@3"},{"benchmark":"hle","model":"claude-sonnet-4.5","score":17.7,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.2","score":36.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-opus-4.6","score":53.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.2","score":50,"metric":"avg@3"},{"benchmark":"financeagent","model":"claude-opus-4.6","score":60.7,"metric":"percent"},{"benchmark":"financeagent","model":"claude-opus-4.5","score":55.9,"metric":"percent"},{"benchmark":"financeagent","model":"claude-sonnet-4.5","score":54.2,"metric":"percent"},{"benchmark":"financeagent","model":"gemini-3-pro","score":44.1,"metric":"percent"},{"benchmark":"financeagent","model":"gpt-5.1","score":56.6,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"claude-opus-4.6","score":1606,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"claude-opus-4.5","score":1416,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"claude-sonnet-4.5","score":1277,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gemini-3-pro","score":1195,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gpt-5.2","score":1462,"metric":"elo"},{"benchmark":"arc-agi-2","model":"claude-opus-4.6","score":68.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-pro","score":45.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2","score":54.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.6","score":91.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2","score":93.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.6","score":73.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.5","score":70.6,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"claude-opus-4.6","score":77.3,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"claude-opus-4.5","score":73.9,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.2","score":80.4,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-opus-4.6","score":91.1,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5.2","score":89.6,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-8b-non-thinking","score":48.01,"metric":"percent"},{"benchmark":"gpqa","model":"ling-mini-2.0","score":59.41,"metric":"percent"},{"benchmark":"gpqa","model":"llada2.0-mini","score":47.76,"metric":"percent"},{"benchmark":"gpqa","model":"llada2.1-mini-s","score":48.36,"metric":"percent"},{"benchmark":"gpqa","model":"llada2.1-mini-q","score":53.28,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b-non-thinking","score":65.83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-mini-2.0","score":67.18,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.0-mini","score":64.27,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.1-mini-s","score":63.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.1-mini-q","score":64.84,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-8b-non-thinking","score":80.6,"metric":"percent"},{"benchmark":"c-eval","model":"ling-mini-2.0","score":82.17,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.0-mini","score":81.8,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.1-mini-s","score":78.4,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.1-mini-q","score":78.59,"metric":"percent"},{"benchmark":"phybench","model":"qwen3-8b-non-thinking","score":9.76,"metric":"percent"},{"benchmark":"phybench","model":"ling-mini-2.0","score":14.59,"metric":"percent"},{"benchmark":"phybench","model":"llada2.0-mini","score":11.7,"metric":"percent"},{"benchmark":"phybench","model":"llada2.1-mini-s","score":12.75,"metric":"percent"},{"benchmark":"phybench","model":"llada2.1-mini-q","score":13.05,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3-8b-non-thinking","score":52.51,"metric":"percent"},{"benchmark":"triviaqa","model":"ling-mini-2.0","score":55.63,"metric":"percent"},{"benchmark":"triviaqa","model":"llada2.0-mini","score":51.33,"metric":"percent"},{"benchmark":"triviaqa","model":"llada2.1-mini-s","score":53.33,"metric":"percent"},{"benchmark":"triviaqa","model":"llada2.1-mini-q","score":54.24,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-8b-non-thinking","score":79.48,"metric":"percent"},{"benchmark":"bbh","model":"ling-mini-2.0","score":83.7,"metric":"percent"},{"benchmark":"bbh","model":"llada2.0-mini","score":78.21,"metric":"percent"},{"benchmark":"bbh","model":"llada2.1-mini-s","score":78.42,"metric":"percent"},{"benchmark":"bbh","model":"llada2.1-mini-q","score":80.58,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"qwen3-8b-non-thinking","score":18.27,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"ling-mini-2.0","score":14.81,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"llada2.0-mini","score":16.47,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"llada2.1-mini-s","score":15.3,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"llada2.1-mini-q","score":15.78,"metric":"percent"},{"benchmark":"bbh-zh","model":"qwen3-8b-non-thinking","score":80.09,"metric":"percent"},{"benchmark":"bbh-zh","model":"ling-mini-2.0","score":66.11,"metric":"percent"},{"benchmark":"bbh-zh","model":"llada2.0-mini","score":75.75,"metric":"percent"},{"benchmark":"bbh-zh","model":"llada2.1-mini-s","score":67.65,"metric":"percent"},{"benchmark":"bbh-zh","model":"llada2.1-mini-q","score":70.4,"metric":"percent"},{"benchmark":"musr","model":"qwen3-8b-non-thinking","score":70.02,"metric":"percent"},{"benchmark":"musr","model":"ling-mini-2.0","score":71.36,"metric":"percent"},{"benchmark":"musr","model":"llada2.0-mini","score":71.48,"metric":"percent"},{"benchmark":"musr","model":"llada2.1-mini-s","score":70.43,"metric":"percent"},{"benchmark":"musr","model":"llada2.1-mini-q","score":71.89,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-8b-non-thinking","score":37.48,"metric":"percent"},{"benchmark":"zebralogic","model":"ling-mini-2.0","score":79.85,"metric":"percent"},{"benchmark":"zebralogic","model":"llada2.0-mini","score":64.2,"metric":"percent"},{"benchmark":"zebralogic","model":"llada2.1-mini-s","score":68.5,"metric":"percent"},{"benchmark":"zebralogic","model":"llada2.1-mini-q","score":77.1,"metric":"percent"},{"benchmark":"prontoqa","model":"qwen3-8b-non-thinking","score":93.12,"metric":"percent"},{"benchmark":"prontoqa","model":"ling-mini-2.0","score":96.06,"metric":"percent"},{"benchmark":"prontoqa","model":"llada2.0-mini","score":86,"metric":"percent"},{"benchmark":"prontoqa","model":"llada2.1-mini-s","score":87.5,"metric":"percent"},{"benchmark":"prontoqa","model":"llada2.1-mini-q","score":84.5,"metric":"percent"},{"benchmark":"piqa","model":"qwen3-8b-non-thinking","score":88.3,"metric":"percent"},{"benchmark":"piqa","model":"ling-mini-2.0","score":87.54,"metric":"percent"},{"benchmark":"piqa","model":"llada2.0-mini","score":86.51,"metric":"percent"},{"benchmark":"piqa","model":"llada2.1-mini-s","score":84.87,"metric":"percent"},{"benchmark":"piqa","model":"llada2.1-mini-q","score":86.89,"metric":"percent"},{"benchmark":"ocnli","model":"qwen3-8b-non-thinking","score":61.49,"metric":"percent"},{"benchmark":"ocnli","model":"ling-mini-2.0","score":60.17,"metric":"percent"},{"benchmark":"ocnli","model":"llada2.0-mini","score":64.51,"metric":"percent"},{"benchmark":"ocnli","model":"llada2.1-mini-s","score":61.02,"metric":"percent"},{"benchmark":"ocnli","model":"llada2.1-mini-q","score":61.59,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-8b-non-thinking","score":79.56,"metric":"percent"},{"benchmark":"hellaswag","model":"ling-mini-2.0","score":69.02,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.0-mini","score":79.01,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.1-mini-s","score":75.71,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.1-mini-q","score":76.19,"metric":"percent"},{"benchmark":"kor-bench","model":"qwen3-8b-non-thinking","score":54.96,"metric":"percent"},{"benchmark":"kor-bench","model":"ling-mini-2.0","score":63.2,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.0-mini","score":49.92,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.1-mini-s","score":46.64,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.1-mini-q","score":48,"metric":"percent"},{"benchmark":"drop","model":"qwen3-8b-non-thinking","score":84.56,"metric":"percent"},{"benchmark":"drop","model":"ling-mini-2.0","score":78.8,"metric":"percent"},{"benchmark":"drop","model":"llada2.0-mini","score":81.89,"metric":"percent"},{"benchmark":"drop","model":"llada2.1-mini-s","score":81.55,"metric":"percent"},{"benchmark":"drop","model":"llada2.1-mini-q","score":82.37,"metric":"percent"},{"benchmark":"squad-v2.0","model":"qwen3-8b-non-thinking","score":85.21,"metric":"percent"},{"benchmark":"squad-v2.0","model":"ling-mini-2.0","score":75.56,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llada2.0-mini","score":86.5,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llada2.1-mini-s","score":84.51,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llada2.1-mini-q","score":85.13,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b-non-thinking","score":26.76,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-mini-2.0","score":42.29,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.0-mini","score":31.83,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.1-mini-s","score":28.85,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.1-mini-q","score":30.4,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-8b-non-thinking","score":74.06,"metric":"percent"},{"benchmark":"crux-o","model":"ling-mini-2.0","score":76.12,"metric":"percent"},{"benchmark":"crux-o","model":"llada2.0-mini","score":71.62,"metric":"percent"},{"benchmark":"crux-o","model":"llada2.1-mini-s","score":70.62,"metric":"percent"},{"benchmark":"crux-o","model":"llada2.1-mini-q","score":73.75,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-8b-non-thinking","score":72.69,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ling-mini-2.0","score":77.25,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llada2.0-mini","score":78.24,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llada2.1-mini-s","score":78.84,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llada2.1-mini-q","score":74.07,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-8b-non-thinking","score":79.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-mini-2.0","score":80.03,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llada2.0-mini","score":81.71,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llada2.1-mini-s","score":80.49,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llada2.1-mini-q","score":82.93,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3-8b-non-thinking","score":61.7,"metric":"percent"},{"benchmark":"multipl-e","model":"ling-mini-2.0","score":67.09,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.0-mini","score":67.46,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.1-mini-s","score":64.16,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.1-mini-q","score":67.17,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-8b-non-thinking","score":36.05,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"ling-mini-2.0","score":35,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llada2.0-mini","score":32.89,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llada2.1-mini-s","score":30.18,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llada2.1-mini-q","score":34.39,"metric":"pass@1"},{"benchmark":"aider-code-editing","model":"qwen3-8b-non-thinking","score":55.64,"metric":"percent"},{"benchmark":"aider-code-editing","model":"ling-mini-2.0","score":49.62,"metric":"percent"},{"benchmark":"aider-code-editing","model":"llada2.0-mini","score":39.85,"metric":"percent"},{"benchmark":"aider-code-editing","model":"llada2.1-mini-s","score":43.61,"metric":"percent"},{"benchmark":"aider-code-editing","model":"llada2.1-mini-q","score":45.11,"metric":"percent"},{"benchmark":"bird-sql","model":"qwen3-8b-non-thinking","score":36.11,"metric":"percent"},{"benchmark":"bird-sql","model":"ling-mini-2.0","score":39.67,"metric":"percent"},{"benchmark":"bird-sql","model":"llada2.0-mini","score":39.34,"metric":"percent"},{"benchmark":"bird-sql","model":"llada2.1-mini-s","score":37.32,"metric":"percent"},{"benchmark":"bird-sql","model":"llada2.1-mini-q","score":38.4,"metric":"percent"},{"benchmark":"spider","model":"qwen3-8b-non-thinking","score":72.8,"metric":"percent"},{"benchmark":"spider","model":"ling-mini-2.0","score":76.43,"metric":"percent"},{"benchmark":"spider","model":"llada2.0-mini","score":76.76,"metric":"percent"},{"benchmark":"spider","model":"llada2.1-mini-s","score":75.78,"metric":"percent"},{"benchmark":"spider","model":"llada2.1-mini-q","score":77.55,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b-non-thinking","score":22.08,"metric":"percent"},{"benchmark":"aime-2025","model":"ling-mini-2.0","score":47.66,"metric":"percent"},{"benchmark":"aime-2025","model":"llada2.0-mini","score":36.67,"metric":"percent"},{"benchmark":"aime-2025","model":"llada2.1-mini-s","score":36.67,"metric":"percent"},{"benchmark":"aime-2025","model":"llada2.1-mini-q","score":43.33,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen3-8b-non-thinking","score":55.33,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-mini-2.0","score":72.3,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.0-mini","score":67.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.1-mini-s","score":64.3,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.1-mini-q","score":66.67,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3-8b-non-thinking","score":85.56,"metric":"percent"},{"benchmark":"gsm-plus","model":"ling-mini-2.0","score":87.18,"metric":"percent"},{"benchmark":"gsm-plus","model":"llada2.0-mini","score":86.5,"metric":"percent"},{"benchmark":"gsm-plus","model":"llada2.1-mini-s","score":85.88,"metric":"percent"},{"benchmark":"gsm-plus","model":"llada2.1-mini-q","score":86.55,"metric":"percent"},{"benchmark":"cmath","model":"qwen3-8b-non-thinking","score":95.42,"metric":"percent"},{"benchmark":"cmath","model":"ling-mini-2.0","score":96.4,"metric":"percent"},{"benchmark":"cmath","model":"llada2.0-mini","score":95.72,"metric":"percent"},{"benchmark":"cmath","model":"llada2.1-mini-s","score":95.63,"metric":"percent"},{"benchmark":"cmath","model":"llada2.1-mini-q","score":94.99,"metric":"percent"},{"benchmark":"omni-math","model":"qwen3-8b-non-thinking","score":33.2,"metric":"percent"},{"benchmark":"omni-math","model":"ling-mini-2.0","score":48.8,"metric":"percent"},{"benchmark":"omni-math","model":"llada2.0-mini","score":41.7,"metric":"percent"},{"benchmark":"omni-math","model":"llada2.1-mini-s","score":41.7,"metric":"percent"},{"benchmark":"omni-math","model":"llada2.1-mini-q","score":43.6,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen3-8b-non-thinking","score":84.29,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"ling-mini-2.0","score":76.16,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llada2.0-mini","score":80.78,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llada2.1-mini-s","score":81.33,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llada2.1-mini-q","score":83.18,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-8b-non-thinking","score":70.12,"metric":"percent"},{"benchmark":"bfcl-v3","model":"ling-mini-2.0","score":53.75,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llada2.0-mini","score":70.72,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llada2.1-mini-s","score":72.06,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llada2.1-mini-q","score":73.61,"metric":"percent"},{"benchmark":"codeif-bench","model":"qwen3-8b-non-thinking","score":50,"metric":"percent"},{"benchmark":"codeif-bench","model":"ling-mini-2.0","score":46,"metric":"percent"},{"benchmark":"codeif-bench","model":"llada2.0-mini","score":46,"metric":"percent"},{"benchmark":"codeif-bench","model":"llada2.1-mini-s","score":42,"metric":"percent"},{"benchmark":"codeif-bench","model":"llada2.1-mini-q","score":48,"metric":"percent"},{"benchmark":"nexus","model":"qwen3-8b-non-thinking","score":37.71,"metric":"percent"},{"benchmark":"nexus","model":"ling-mini-2.0","score":34.38,"metric":"percent"},{"benchmark":"nexus","model":"llada2.0-mini","score":35.18,"metric":"percent"},{"benchmark":"nexus","model":"llada2.1-mini-s","score":31.59,"metric":"percent"},{"benchmark":"nexus","model":"llada2.1-mini-q","score":33.69,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-30b-a3b-instruct-2507","score":54.14,"metric":"percent"},{"benchmark":"gpqa","model":"ling-flash-2.0","score":69.16,"metric":"percent"},{"benchmark":"gpqa","model":"llada2.0-flash","score":62.31,"metric":"percent"},{"benchmark":"gpqa","model":"llada2.1-flash-s","score":66.67,"metric":"percent"},{"benchmark":"gpqa","model":"llada2.1-flash-q","score":67.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-instruct-2507","score":74.21,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-flash-2.0","score":77.55,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.0-flash","score":74.79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.1-flash-s","score":75.31,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.1-flash-q","score":76.59,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-30b-a3b-instruct-2507","score":88.12,"metric":"percent"},{"benchmark":"c-eval","model":"ling-flash-2.0","score":87.54,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.0-flash","score":85.21,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.1-flash-s","score":86.93,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.1-flash-q","score":86.71,"metric":"percent"},{"benchmark":"phybench","model":"qwen3-30b-a3b-instruct-2507","score":29.84,"metric":"percent"},{"benchmark":"phybench","model":"ling-flash-2.0","score":27.67,"metric":"percent"},{"benchmark":"phybench","model":"llada2.0-flash","score":30.06,"metric":"percent"},{"benchmark":"phybench","model":"llada2.1-flash-s","score":26.04,"metric":"percent"},{"benchmark":"phybench","model":"llada2.1-flash-q","score":28.23,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3-30b-a3b-instruct-2507","score":65.61,"metric":"percent"},{"benchmark":"triviaqa","model":"ling-flash-2.0","score":69.76,"metric":"percent"},{"benchmark":"triviaqa","model":"llada2.0-flash","score":66.88,"metric":"percent"},{"benchmark":"triviaqa","model":"llada2.1-flash-s","score":72.55,"metric":"percent"},{"benchmark":"triviaqa","model":"llada2.1-flash-q","score":72.93,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-30b-a3b-instruct-2507","score":85.54,"metric":"percent"},{"benchmark":"bbh","model":"ling-flash-2.0","score":89.36,"metric":"percent"},{"benchmark":"bbh","model":"llada2.0-flash","score":86.75,"metric":"percent"},{"benchmark":"bbh","model":"llada2.1-flash-s","score":87.82,"metric":"percent"},{"benchmark":"bbh","model":"llada2.1-flash-q","score":88.69,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"qwen3-30b-a3b-instruct-2507","score":37.8,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"ling-flash-2.0","score":23.24,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"llada2.0-flash","score":27.86,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"llada2.1-flash-s","score":33.51,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"llada2.1-flash-q","score":35.77,"metric":"percent"},{"benchmark":"bbh-zh","model":"qwen3-30b-a3b-instruct-2507","score":86.18,"metric":"percent"},{"benchmark":"bbh-zh","model":"ling-flash-2.0","score":75.09,"metric":"percent"},{"benchmark":"bbh-zh","model":"llada2.0-flash","score":87.52,"metric":"percent"},{"benchmark":"bbh-zh","model":"llada2.1-flash-s","score":82.55,"metric":"percent"},{"benchmark":"bbh-zh","model":"llada2.1-flash-q","score":86.23,"metric":"percent"},{"benchmark":"musr","model":"qwen3-30b-a3b-instruct-2507","score":79.15,"metric":"percent"},{"benchmark":"musr","model":"ling-flash-2.0","score":82.72,"metric":"percent"},{"benchmark":"musr","model":"llada2.0-flash","score":82.72,"metric":"percent"},{"benchmark":"musr","model":"llada2.1-flash-s","score":80.1,"metric":"percent"},{"benchmark":"musr","model":"llada2.1-flash-q","score":79.84,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-30b-a3b-instruct-2507","score":90.97,"metric":"percent"},{"benchmark":"zebralogic","model":"ling-flash-2.0","score":87.6,"metric":"percent"},{"benchmark":"zebralogic","model":"llada2.0-flash","score":82.3,"metric":"percent"},{"benchmark":"zebralogic","model":"llada2.1-flash-s","score":84.2,"metric":"percent"},{"benchmark":"zebralogic","model":"llada2.1-flash-q","score":88.9,"metric":"percent"},{"benchmark":"prontoqa","model":"qwen3-30b-a3b-instruct-2507","score":97.12,"metric":"percent"},{"benchmark":"prontoqa","model":"ling-flash-2.0","score":97.88,"metric":"percent"},{"benchmark":"prontoqa","model":"llada2.0-flash","score":96.5,"metric":"percent"},{"benchmark":"prontoqa","model":"llada2.1-flash-s","score":95,"metric":"percent"},{"benchmark":"prontoqa","model":"llada2.1-flash-q","score":97,"metric":"percent"},{"benchmark":"piqa","model":"qwen3-30b-a3b-instruct-2507","score":91.57,"metric":"percent"},{"benchmark":"piqa","model":"ling-flash-2.0","score":91.95,"metric":"percent"},{"benchmark":"piqa","model":"llada2.0-flash","score":96.5,"metric":"percent"},{"benchmark":"piqa","model":"llada2.1-flash-s","score":92.44,"metric":"percent"},{"benchmark":"piqa","model":"llada2.1-flash-q","score":92.17,"metric":"percent"},{"benchmark":"ocnli","model":"qwen3-30b-a3b-instruct-2507","score":71.59,"metric":"percent"},{"benchmark":"ocnli","model":"ling-flash-2.0","score":65.36,"metric":"percent"},{"benchmark":"ocnli","model":"llada2.0-flash","score":71.63,"metric":"percent"},{"benchmark":"ocnli","model":"llada2.1-flash-s","score":72.17,"metric":"percent"},{"benchmark":"ocnli","model":"llada2.1-flash-q","score":72.75,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.1-flash-s","score":85.6,"metric":"percent"},{"benchmark":"hellaswag","model":"llada2.1-flash-q","score":85.31,"metric":"percent"},{"benchmark":"kor-bench","model":"qwen3-30b-a3b-instruct-2507","score":69.2,"metric":"percent"},{"benchmark":"kor-bench","model":"ling-flash-2.0","score":69.44,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.0-flash","score":63.04,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.1-flash-s","score":62.8,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.1-flash-q","score":65.12,"metric":"percent"},{"benchmark":"drop","model":"llada2.1-flash-s","score":87.55,"metric":"percent"},{"benchmark":"drop","model":"llada2.1-flash-q","score":87.86,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llada2.1-flash-s","score":90.65,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llada2.1-flash-q","score":90.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-instruct-2507","score":46.42,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-flash-2.0","score":52.48,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.0-flash","score":42.51,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.1-flash-s","score":44.05,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.1-flash-q","score":45.37,"metric":"percent"},{"benchmark":"crux-o","model":"qwen3-30b-a3b-instruct-2507","score":86.75,"metric":"percent"},{"benchmark":"crux-o","model":"ling-flash-2.0","score":82.75,"metric":"percent"},{"benchmark":"crux-o","model":"llada2.0-flash","score":85.12,"metric":"percent"},{"benchmark":"crux-o","model":"llada2.1-flash-s","score":85.25,"metric":"percent"},{"benchmark":"crux-o","model":"llada2.1-flash-q","score":87.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-30b-a3b-instruct-2507","score":78.21,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ling-flash-2.0","score":80.89,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llada2.0-flash","score":79.37,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llada2.1-flash-s","score":76.72,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llada2.1-flash-q","score":77.25,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-30b-a3b-instruct-2507","score":87.88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-flash-2.0","score":87.58,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llada2.0-flash","score":88.41,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llada2.1-flash-s","score":89.63,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llada2.1-flash-q","score":89.63,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.1-flash-s","score":70.89,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.1-flash-q","score":73.34,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-30b-a3b-instruct-2507","score":41.49,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"ling-flash-2.0","score":40.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llada2.0-flash","score":41.58,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llada2.1-flash-s","score":37.11,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llada2.1-flash-q","score":39.21,"metric":"pass@1"},{"benchmark":"bird-sql","model":"qwen3-30b-a3b-instruct-2507","score":47.75,"metric":"percent"},{"benchmark":"bird-sql","model":"ling-flash-2.0","score":47.49,"metric":"percent"},{"benchmark":"bird-sql","model":"llada2.0-flash","score":45.76,"metric":"percent"},{"benchmark":"bird-sql","model":"llada2.1-flash-s","score":42.18,"metric":"percent"},{"benchmark":"bird-sql","model":"llada2.1-flash-q","score":44.04,"metric":"percent"},{"benchmark":"spider","model":"llada2.1-flash-s","score":79.18,"metric":"percent"},{"benchmark":"spider","model":"llada2.1-flash-q","score":81.04,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-instruct-2507","score":61.88,"metric":"percent"},{"benchmark":"aime-2025","model":"ling-flash-2.0","score":55.89,"metric":"percent"},{"benchmark":"aime-2025","model":"llada2.0-flash","score":60,"metric":"percent"},{"benchmark":"aime-2025","model":"llada2.1-flash-s","score":63.33,"metric":"percent"},{"benchmark":"aime-2025","model":"llada2.1-flash-q","score":63.33,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.1-flash-s","score":75.85,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.1-flash-q","score":76.59,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3-30b-a3b-instruct-2507","score":89.41,"metric":"percent"},{"benchmark":"gsm-plus","model":"ling-flash-2.0","score":89.71,"metric":"percent"},{"benchmark":"gsm-plus","model":"llada2.0-flash","score":89.74,"metric":"percent"},{"benchmark":"gsm-plus","model":"llada2.1-flash-s","score":89.23,"metric":"percent"},{"benchmark":"gsm-plus","model":"llada2.1-flash-q","score":89.69,"metric":"percent"},{"benchmark":"cmath","model":"qwen3-30b-a3b-instruct-2507","score":96.58,"metric":"percent"},{"benchmark":"cmath","model":"ling-flash-2.0","score":96.52,"metric":"percent"},{"benchmark":"cmath","model":"llada2.0-flash","score":96.9,"metric":"percent"},{"benchmark":"cmath","model":"llada2.1-flash-s","score":96.54,"metric":"percent"},{"benchmark":"cmath","model":"llada2.1-flash-q","score":96.63,"metric":"percent"},{"benchmark":"omni-math","model":"qwen3-30b-a3b-instruct-2507","score":54,"metric":"percent"},{"benchmark":"omni-math","model":"ling-flash-2.0","score":53,"metric":"percent"},{"benchmark":"omni-math","model":"llada2.0-flash","score":50.3,"metric":"percent"},{"benchmark":"omni-math","model":"llada2.1-flash-s","score":52.3,"metric":"percent"},{"benchmark":"omni-math","model":"llada2.1-flash-q","score":54.1,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen3-30b-a3b-instruct-2507","score":83.73,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"ling-flash-2.0","score":81.15,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llada2.0-flash","score":82.62,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llada2.1-flash-s","score":83.36,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llada2.1-flash-q","score":83.55,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-30b-a3b-instruct-2507","score":73.41,"metric":"percent"},{"benchmark":"bfcl-v3","model":"ling-flash-2.0","score":67.69,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llada2.0-flash","score":74.94,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llada2.1-flash-s","score":74.86,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llada2.1-flash-q","score":75.61,"metric":"percent"},{"benchmark":"nexus","model":"qwen3-30b-a3b-instruct-2507","score":49.93,"metric":"percent"},{"benchmark":"nexus","model":"ling-flash-2.0","score":36.25,"metric":"percent"},{"benchmark":"nexus","model":"llada2.0-flash","score":50.45,"metric":"percent"},{"benchmark":"nexus","model":"llada2.1-flash-s","score":44.83,"metric":"percent"},{"benchmark":"nexus","model":"llada2.1-flash-q","score":47.65,"metric":"percent"},{"benchmark":"cmmlu","model":"hy-1.8b","score":55.07,"metric":"percent"},{"benchmark":"c-eval","model":"hy-1.8b","score":54.27,"metric":"percent"},{"benchmark":"arc-challenge","model":"hy-1.8b","score":70.5,"metric":"percent"},{"benchmark":"bbh","model":"hy-1.8b","score":79.08,"metric":"percent"},{"benchmark":"gsm8k","model":"hy-1.8b","score":84.08,"metric":"percent"},{"benchmark":"humaneval","model":"hy-1.8b","score":94.51,"metric":"percent"},{"benchmark":"livecodebench","model":"hy-1.8b","score":31.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hy-1.8b","score":68.18,"metric":"percent"},{"benchmark":"cmmlu","model":"hy-0.5b","score":37.08,"metric":"percent"},{"benchmark":"c-eval","model":"hy-0.5b","score":35.98,"metric":"percent"},{"benchmark":"arc-challenge","model":"hy-0.5b","score":49.89,"metric":"percent"},{"benchmark":"bbh","model":"hy-0.5b","score":58.1,"metric":"percent"},{"benchmark":"gsm8k","model":"hy-0.5b","score":55.04,"metric":"percent"},{"benchmark":"humaneval","model":"hy-0.5b","score":67.07,"metric":"percent"},{"benchmark":"livecodebench","model":"hy-0.5b","score":12.11,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hy-0.5b","score":46.97,"metric":"percent"},{"benchmark":"cmmlu","model":"hy-1.8b-int4gptq","score":50.8,"metric":"percent"},{"benchmark":"c-eval","model":"hy-1.8b-int4gptq","score":48.67,"metric":"percent"},{"benchmark":"arc-challenge","model":"hy-1.8b-int4gptq","score":68.83,"metric":"percent"},{"benchmark":"bbh","model":"hy-1.8b-int4gptq","score":74.8,"metric":"percent"},{"benchmark":"gsm8k","model":"hy-1.8b-int4gptq","score":78.7,"metric":"percent"},{"benchmark":"humaneval","model":"hy-1.8b-int4gptq","score":89.02,"metric":"percent"},{"benchmark":"livecodebench","model":"hy-1.8b-int4gptq","score":30.08,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hy-1.8b-int4gptq","score":65.56,"metric":"percent"},{"benchmark":"cmmlu","model":"hy-1.8b-2bit","score":49.32,"metric":"percent"},{"benchmark":"c-eval","model":"hy-1.8b-2bit","score":47.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"hy-1.8b-2bit","score":64.45,"metric":"percent"},{"benchmark":"bbh","model":"hy-1.8b-2bit","score":75.54,"metric":"percent"},{"benchmark":"gsm8k","model":"hy-1.8b-2bit","score":77.33,"metric":"percent"},{"benchmark":"humaneval","model":"hy-1.8b-2bit","score":93.29,"metric":"percent"},{"benchmark":"livecodebench","model":"hy-1.8b-2bit","score":32.73,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hy-1.8b-2bit","score":65.15,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ring-1t-2.5","score":86.69,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ring-1t-2.5","score":93.75,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"ring-1t-2.5","score":97.34,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-1t-2.5","score":87.89,"metric":"percent"},{"benchmark":"gaia2","model":"ring-1t-2.5","score":75,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ring-1t-2.5","score":72.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"ring-1t-2.5","score":19.31,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ring-1t-2.5-heavy-thinking","score":90,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ring-1t-2.5-heavy-thinking","score":95,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"ring-1t-2.5-heavy-thinking","score":98.33,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-1t-2.5-heavy-thinking","score":89.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.5-thinking","score":90.62,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"kimi-k2.5-thinking","score":91.51,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2.5-thinking","score":85,"metric":"percent"},{"benchmark":"gaia2","model":"kimi-k2.5-thinking","score":55.21,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k2.5-thinking","score":16.25,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v3.2-thinking","score":92.71,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-thinking","score":82.71,"metric":"percent"},{"benchmark":"gaia2","model":"deepseek-v3.2-thinking","score":68.96,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v3.2-thinking","score":7.22,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m2.5","score":80.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"minimax-m2.5","score":55.4,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"minimax-m2.5","score":51.3,"metric":"percent"},{"benchmark":"vibe-average","model":"minimax-m2.5","score":54.2,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"minimax-m2.5","score":76.3,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"minimax-m2.5","score":76.8,"metric":"percent"},{"benchmark":"mewc","model":"minimax-m2.5","score":74.4,"metric":"percent"},{"benchmark":"gdpval","model":"minimax-m2.5","score":59,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m2.1","score":74,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"minimax-m2.1","score":49.7,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"minimax-m2.1","score":47.2,"metric":"percent"},{"benchmark":"vibe-average","model":"minimax-m2.1","score":42.4,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"minimax-m2.1","score":62,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"minimax-m2.1","score":37.4,"metric":"percent"},{"benchmark":"mewc","model":"minimax-m2.1","score":55.6,"metric":"percent"},{"benchmark":"gdpval","model":"minimax-m2.1","score":24.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.5","score":56.9,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"claude-opus-4.5","score":50,"metric":"percent"},{"benchmark":"vibe-average","model":"claude-opus-4.5","score":55.2,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"claude-opus-4.5","score":67.8,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"claude-opus-4.5","score":68,"metric":"percent"},{"benchmark":"mewc","model":"claude-opus-4.5","score":82.1,"metric":"percent"},{"benchmark":"gdpval","model":"claude-opus-4.5","score":61.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.6","score":55.4,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"claude-opus-4.6","score":50.3,"metric":"percent"},{"benchmark":"vibe-average","model":"claude-opus-4.6","score":55.6,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"claude-opus-4.6","score":84,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"claude-opus-4.6","score":63.3,"metric":"percent"},{"benchmark":"mewc","model":"claude-opus-4.6","score":89.8,"metric":"percent"},{"benchmark":"gdpval","model":"claude-opus-4.6","score":73.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3-pro","score":78,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemini-3-pro","score":54.1,"metric":"percent"},{"benchmark":"vibe-average","model":"gemini-3-pro","score":36.9,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"gemini-3-pro","score":61,"metric":"percent"},{"benchmark":"mewc","model":"gemini-3-pro","score":78.7,"metric":"percent"},{"benchmark":"gdpval","model":"gemini-3-pro","score":28.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.2","score":80,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.2","score":55.6,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"gpt-5.2","score":65.8,"metric":"percent"},{"benchmark":"mewc","model":"gpt-5.2","score":41.3,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.2","score":54.5,"metric":"percent"},{"benchmark":"core","model":"nanbeige4.1-3b","score":53.47,"metric":"percent"},{"benchmark":"core","model":"qwen3-vl-8b-thinking","score":47.52,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nanbeige4.1-3b","score":53.4,"metric":"percent"},{"benchmark":"multichallenge","model":"nanbeige4.1-3b","score":52.2,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"nanbeige4.1-3b","score":39,"metric":"percent"},{"benchmark":"gaia-text-only","model":"nanbeige4.1-3b","score":69.9,"metric":"percent"},{"benchmark":"bridgebench","model":"claude-opus-4.6","score":60.1,"metric":"percent"},{"benchmark":"bridgebench","model":"minimax-m2.5","score":59.7,"metric":"percent"},{"benchmark":"bridgebench","model":"gpt-5.2-codex","score":58.3,"metric":"percent"},{"benchmark":"bridgebench","model":"glm-5","score":41.5,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-8b","score":81.68,"metric":"percent"},{"benchmark":"cmmlu","model":"nemotron-nano-v2-9b","score":61.59,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm4.1-8b","score":84.72,"metric":"percent"},{"benchmark":"cmmlu","model":"ministral-3-r-8b","score":71.74,"metric":"percent"},{"benchmark":"cmmlu","model":"falcon-h1r-7b","score":63.55,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-sala","score":81.55,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b","score":73.26,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-nano-v2-9b","score":71.79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minicpm4.1-8b","score":72.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ministral-3-r-8b","score":68.75,"metric":"percent"},{"benchmark":"mmlu-pro","model":"falcon-h1r-7b","score":70.98,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minicpm-sala","score":67.04,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-8b","score":93.9,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-nano-v2-9b","score":93.9,"metric":"percent"},{"benchmark":"humaneval","model":"minicpm4.1-8b","score":91.46,"metric":"percent"},{"benchmark":"humaneval","model":"ministral-3-r-8b","score":96.95,"metric":"percent"},{"benchmark":"humaneval","model":"falcon-h1r-7b","score":96.34,"metric":"percent"},{"benchmark":"humaneval","model":"minicpm-sala","score":95.12,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-8b","score":56.89,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nemotron-nano-v2-9b","score":68.26,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"minicpm4.1-8b","score":56.89,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"ministral-3-r-8b","score":65.87,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"falcon-h1r-7b","score":67.66,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"minicpm-sala","score":60.48,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b","score":48.57,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-nano-v2-9b","score":60,"metric":"percent"},{"benchmark":"livecodebench","model":"minicpm4.1-8b","score":51.43,"metric":"percent"},{"benchmark":"livecodebench","model":"ministral-3-r-8b","score":53.71,"metric":"percent"},{"benchmark":"livecodebench","model":"falcon-h1r-7b","score":57.71,"metric":"percent"},{"benchmark":"livecodebench","model":"minicpm-sala","score":52,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-8b","score":81.32,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-nano-v2-9b","score":93.39,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm4.1-8b","score":91.05,"metric":"percent"},{"benchmark":"mbpp","model":"ministral-3-r-8b","score":94.16,"metric":"percent"},{"benchmark":"mbpp","model":"falcon-h1r-7b","score":91.05,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm-sala","score":89.11,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-8b","score":73.33,"metric":"percent"},{"benchmark":"aime-2024","model":"nemotron-nano-v2-9b","score":71.67,"metric":"percent"},{"benchmark":"aime-2024","model":"minicpm4.1-8b","score":80.83,"metric":"percent"},{"benchmark":"aime-2024","model":"ministral-3-r-8b","score":81.46,"metric":"percent"},{"benchmark":"aime-2024","model":"falcon-h1r-7b","score":86.67,"metric":"percent"},{"benchmark":"aime-2024","model":"minicpm-sala","score":83.75,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b","score":66.67,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-nano-v2-9b","score":56.67,"metric":"percent"},{"benchmark":"aime-2025","model":"minicpm4.1-8b","score":72.08,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-3-r-8b","score":75,"metric":"percent"},{"benchmark":"aime-2025","model":"falcon-h1r-7b","score":81.04,"metric":"percent"},{"benchmark":"aime-2025","model":"minicpm-sala","score":78.33,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-8b","score":74.17,"metric":"percent"},{"benchmark":"bbh","model":"nemotron-nano-v2-9b","score":74.28,"metric":"percent"},{"benchmark":"bbh","model":"minicpm4.1-8b","score":82.68,"metric":"percent"},{"benchmark":"bbh","model":"ministral-3-r-8b","score":64.39,"metric":"percent"},{"benchmark":"bbh","model":"falcon-h1r-7b","score":63.17,"metric":"percent"},{"benchmark":"bbh","model":"minicpm-sala","score":81.55,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-8b","score":84.66,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-nano-v2-9b","score":86.69,"metric":"percent"},{"benchmark":"ifeval","model":"minicpm4.1-8b","score":77.45,"metric":"percent"},{"benchmark":"ifeval","model":"ministral-3-r-8b","score":70.06,"metric":"percent"},{"benchmark":"ifeval","model":"falcon-h1r-7b","score":86.32,"metric":"percent"},{"benchmark":"ifeval","model":"minicpm-sala","score":76.34,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen3-30b-a3b-instruct-2507","score":89.1,"metric":"percent"},{"benchmark":"ruler-512k","model":"qwen3-30b-a3b-instruct-2507","score":78.4,"metric":"percent"},{"benchmark":"ruler-1m","model":"qwen3-30b-a3b-instruct-2507","score":72.8,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen3-235b-a22b-instruct-2507","score":93.9,"metric":"percent"},{"benchmark":"ruler-512k","model":"qwen3-235b-a22b-instruct-2507","score":90.9,"metric":"percent"},{"benchmark":"ruler-1m","model":"qwen3-235b-a22b-instruct-2507","score":84.5,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen3-next-80b-a3b-instruct","score":96,"metric":"percent"},{"benchmark":"ruler-512k","model":"qwen3-next-80b-a3b-instruct","score":86.9,"metric":"percent"},{"benchmark":"ruler-1m","model":"qwen3-next-80b-a3b-instruct","score":80.3,"metric":"percent"},{"benchmark":"ruler-128k","model":"minicpm-sala","score":89.4,"metric":"percent"},{"benchmark":"ruler-512k","model":"minicpm-sala","score":87.1,"metric":"percent"},{"benchmark":"ruler-1m","model":"minicpm-sala","score":86.3,"metric":"percent"},{"benchmark":"ruler-2048k","model":"minicpm-sala","score":81.6,"metric":"percent"},{"benchmark":"ruler-64k","model":"qwen3-8b","score":80.53,"metric":"percent"},{"benchmark":"ruler-64k","model":"nemotron-nano-v2-9b","score":88.77,"metric":"percent"},{"benchmark":"ruler-64k","model":"ministral-3-r-8b","score":70.66,"metric":"percent"},{"benchmark":"ruler-64k","model":"falcon-h1r-7b","score":56.5,"metric":"percent"},{"benchmark":"ruler-64k","model":"minicpm-sala","score":92.65,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen3-8b","score":71.74,"metric":"percent"},{"benchmark":"ruler-128k","model":"nemotron-nano-v2-9b","score":68.01,"metric":"percent"},{"benchmark":"ruler-128k","model":"ministral-3-r-8b","score":45.09,"metric":"percent"},{"benchmark":"ruler-128k","model":"falcon-h1r-7b","score":36.33,"metric":"percent"},{"benchmark":"ruler-128k","model":"minicpm-sala","score":89.37,"metric":"percent"},{"benchmark":"mrcr-64k-2n","model":"qwen3-8b","score":29.2,"metric":"percent"},{"benchmark":"mrcr-64k-2n","model":"nemotron-nano-v2-9b","score":20.91,"metric":"percent"},{"benchmark":"mrcr-64k-2n","model":"ministral-3-r-8b","score":44.02,"metric":"percent"},{"benchmark":"mrcr-64k-2n","model":"falcon-h1r-7b","score":13.18,"metric":"percent"},{"benchmark":"mrcr-64k-2n","model":"minicpm-sala","score":29.77,"metric":"percent"},{"benchmark":"mrcr-64k-4n","model":"qwen3-8b","score":21.56,"metric":"percent"},{"benchmark":"mrcr-64k-4n","model":"nemotron-nano-v2-9b","score":13.69,"metric":"percent"},{"benchmark":"mrcr-64k-4n","model":"ministral-3-r-8b","score":35.8,"metric":"percent"},{"benchmark":"mrcr-64k-4n","model":"falcon-h1r-7b","score":9.06,"metric":"percent"},{"benchmark":"mrcr-64k-4n","model":"minicpm-sala","score":20.57,"metric":"percent"},{"benchmark":"mrcr-64k-8n","model":"qwen3-8b","score":17.82,"metric":"percent"},{"benchmark":"mrcr-64k-8n","model":"nemotron-nano-v2-9b","score":13.24,"metric":"percent"},{"benchmark":"mrcr-64k-8n","model":"ministral-3-r-8b","score":17.23,"metric":"percent"},{"benchmark":"mrcr-64k-8n","model":"falcon-h1r-7b","score":6.93,"metric":"percent"},{"benchmark":"mrcr-64k-8n","model":"minicpm-sala","score":16.56,"metric":"percent"},{"benchmark":"mrcr-128k-2n","model":"qwen3-8b","score":26.5,"metric":"percent"},{"benchmark":"mrcr-128k-2n","model":"nemotron-nano-v2-9b","score":14.61,"metric":"percent"},{"benchmark":"mrcr-128k-2n","model":"ministral-3-r-8b","score":50.3,"metric":"percent"},{"benchmark":"mrcr-128k-2n","model":"falcon-h1r-7b","score":9.17,"metric":"percent"},{"benchmark":"mrcr-128k-2n","model":"minicpm-sala","score":28.62,"metric":"percent"},{"benchmark":"mrcr-128k-4n","model":"qwen3-8b","score":14.75,"metric":"percent"},{"benchmark":"mrcr-128k-4n","model":"nemotron-nano-v2-9b","score":12.2,"metric":"percent"},{"benchmark":"mrcr-128k-4n","model":"ministral-3-r-8b","score":22.66,"metric":"percent"},{"benchmark":"mrcr-128k-4n","model":"falcon-h1r-7b","score":8.22,"metric":"percent"},{"benchmark":"mrcr-128k-4n","model":"minicpm-sala","score":19.62,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"qwen3-8b","score":12.15,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"nemotron-nano-v2-9b","score":7.55,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"ministral-3-r-8b","score":14.47,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"falcon-h1r-7b","score":7.54,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"minicpm-sala","score":10.12,"metric":"percent"},{"benchmark":"nolima-32k","model":"qwen3-8b","score":43.4,"metric":"percent"},{"benchmark":"nolima-32k","model":"nemotron-nano-v2-9b","score":19.69,"metric":"percent"},{"benchmark":"nolima-32k","model":"ministral-3-r-8b","score":3.78,"metric":"percent"},{"benchmark":"nolima-32k","model":"falcon-h1r-7b","score":14.89,"metric":"percent"},{"benchmark":"nolima-32k","model":"minicpm-sala","score":54.54,"metric":"percent"},{"benchmark":"nolima-64k","model":"qwen3-8b","score":23.35,"metric":"percent"},{"benchmark":"nolima-64k","model":"nemotron-nano-v2-9b","score":11.82,"metric":"percent"},{"benchmark":"nolima-64k","model":"ministral-3-r-8b","score":2.48,"metric":"percent"},{"benchmark":"nolima-64k","model":"falcon-h1r-7b","score":9.87,"metric":"percent"},{"benchmark":"nolima-64k","model":"minicpm-sala","score":42.95,"metric":"percent"},{"benchmark":"nolima-128k","model":"qwen3-8b","score":11.25,"metric":"percent"},{"benchmark":"nolima-128k","model":"nemotron-nano-v2-9b","score":5.8,"metric":"percent"},{"benchmark":"nolima-128k","model":"ministral-3-r-8b","score":3.48,"metric":"percent"},{"benchmark":"nolima-128k","model":"falcon-h1r-7b","score":4.73,"metric":"percent"},{"benchmark":"nolima-128k","model":"minicpm-sala","score":23.86,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-deep-think","score":84.6,"metric":"percent"},{"benchmark":"hle","model":"gemini-3-deep-think","score":48.4,"metric":"avg@3"},{"benchmark":"mmmu-pro","model":"gemini-3-deep-think","score":81.5,"metric":"percent"},{"benchmark":"codeforces","model":"gemini-3-deep-think","score":3455,"metric":"ELO"},{"benchmark":"mmbench-v1.1-en","model":"ovis2.6-30b-a3b","score":88.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis2.6-30b-a3b","score":87.7,"metric":"percent"},{"benchmark":"mmstar","model":"ovis2.6-30b-a3b","score":77.3,"metric":"percent"},{"benchmark":"mmvet","model":"ovis2.6-30b-a3b","score":78,"metric":"percent"},{"benchmark":"mmmu","model":"ovis2.6-30b-a3b","score":77.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"ovis2.6-30b-a3b","score":65.6,"metric":"percent"},{"benchmark":"mathvista","model":"ovis2.6-30b-a3b","score":86,"metric":"percent"},{"benchmark":"mathverse","model":"ovis2.6-30b-a3b","score":79.9,"metric":"percent"},{"benchmark":"mathvision","model":"ovis2.6-30b-a3b","score":68,"metric":"percent"},{"benchmark":"logicvista","model":"ovis2.6-30b-a3b","score":71.6,"metric":"percent"},{"benchmark":"wemath","model":"ovis2.6-30b-a3b","score":75,"metric":"percent"},{"benchmark":"dynamath","model":"ovis2.6-30b-a3b","score":55.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"ovis2.6-30b-a3b","score":68,"metric":"percent"},{"benchmark":"miabench","model":"ovis2.6-30b-a3b","score":95.1,"metric":"percent"},{"benchmark":"refcoco","model":"ovis2.6-30b-a3b","score":88.3,"metric":"percent"},{"benchmark":"countbench","model":"ovis2.6-30b-a3b","score":91.8,"metric":"percent"},{"benchmark":"blink","model":"ovis2.6-30b-a3b","score":70.2,"metric":"percent"},{"benchmark":"muirbench","model":"ovis2.6-30b-a3b","score":78.5,"metric":"percent"},{"benchmark":"videomme-nosub","model":"ovis2.6-30b-a3b","score":71.1,"metric":"percent"},{"benchmark":"mlvu","model":"ovis2.6-30b-a3b","score":77.5,"metric":"percent"},{"benchmark":"ocrbench","model":"ovis2.6-30b-a3b","score":89.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"ovis2.6-30b-a3b","score":72.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"ovis2.6-30b-a3b","score":67.1,"metric":"percent"},{"benchmark":"chartqa-pro","model":"ovis2.6-30b-a3b","score":66.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"ovis2.6-30b-a3b","score":67.7,"metric":"percent"},{"benchmark":"docvqa","model":"ovis2.6-30b-a3b","score":96.7,"metric":"percent"},{"benchmark":"infovqa","model":"ovis2.6-30b-a3b","score":91.2,"metric":"percent"},{"benchmark":"textvqa","model":"ovis2.6-30b-a3b","score":90.7,"metric":"percent"},{"benchmark":"ai2d","model":"ovis2.6-30b-a3b","score":89.6,"metric":"percent"},{"benchmark":"omnidocbench","model":"ovis2.6-30b-a3b","score":92.6,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"ovis2.6-30b-a3b","score":52,"metric":"percent"},{"benchmark":"v-star","model":"ovis2.6-30b-a3b","score":93.2,"metric":"percent"},{"benchmark":"hrbench4k","model":"ovis2.6-30b-a3b","score":84,"metric":"percent"},{"benchmark":"hrbench8k","model":"ovis2.6-30b-a3b","score":80.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-vl-30b-a3b-instruct","score":88.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-30b-a3b-instruct","score":75.5,"metric":"percent"},{"benchmark":"mmvet","model":"qwen3-vl-30b-a3b-instruct","score":75.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-30b-a3b-instruct","score":76,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-30b-a3b-instruct","score":63,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-30b-a3b-instruct","score":81.9,"metric":"percent"},{"benchmark":"mathverse","model":"qwen3-vl-30b-a3b-instruct","score":79.6,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-30b-a3b-instruct","score":65.7,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3-vl-30b-a3b-instruct","score":65.3,"metric":"percent"},{"benchmark":"wemath","model":"qwen3-vl-30b-a3b-instruct","score":66.1,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3-vl-30b-a3b-instruct","score":48.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-30b-a3b-instruct","score":66,"metric":"percent"},{"benchmark":"miabench","model":"qwen3-vl-30b-a3b-instruct","score":91.6,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-30b-a3b-instruct","score":89.7,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3-vl-30b-a3b-instruct","score":77.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-30b-a3b-instruct","score":74.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-30b-a3b-instruct","score":63.2,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-30b-a3b-instruct","score":60.4,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3-vl-30b-a3b-instruct","score":59.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-30b-a3b-instruct","score":56.6,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-30b-a3b-instruct","score":86,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-30b-a3b-instruct","score":67,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-30b-a3b-instruct","score":86.9,"metric":"percent"},{"benchmark":"omnidocbench","model":"qwen3-vl-30b-a3b-instruct","score":73.1,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-30b-a3b-instruct","score":51.5,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-30b-a3b-instruct","score":81.2,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-30b-a3b-instruct","score":77.8,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-30b-a3b-instruct","score":71.3,"metric":"percent"},{"benchmark":"mmvet","model":"glm-4.6v","score":78.8,"metric":"percent"},{"benchmark":"mathverse","model":"glm-4.6v","score":76,"metric":"percent"},{"benchmark":"mathvision","model":"glm-4.6v","score":62.3,"metric":"percent"},{"benchmark":"logicvista","model":"glm-4.6v","score":64,"metric":"percent"},{"benchmark":"hallusionbench","model":"glm-4.6v","score":61.1,"metric":"percent"},{"benchmark":"miabench","model":"glm-4.6v","score":94.1,"metric":"percent"},{"benchmark":"countbench","model":"glm-4.6v","score":92.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"glm-4.6v","score":65.6,"metric":"percent"},{"benchmark":"mlvu","model":"glm-4.6v","score":61.6,"metric":"percent"},{"benchmark":"docvqa","model":"glm-4.6v","score":96.5,"metric":"percent"},{"benchmark":"infovqa","model":"glm-4.6v","score":89.8,"metric":"percent"},{"benchmark":"textvqa","model":"glm-4.6v","score":88,"metric":"percent"},{"benchmark":"omnidocbench","model":"glm-4.6v","score":87.5,"metric":"percent"},{"benchmark":"v-star","model":"glm-4.6v","score":87.4,"metric":"percent"},{"benchmark":"hrbench4k","model":"glm-4.6v","score":79.9,"metric":"percent"},{"benchmark":"hrbench8k","model":"glm-4.6v","score":74.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-5-mini","score":86.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-5-mini","score":86.2,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-mini","score":73.2,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-5-mini","score":74.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-mini","score":67.3,"metric":"percent"},{"benchmark":"mathverse","model":"gpt-5-mini","score":78.8,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-mini","score":71.9,"metric":"percent"},{"benchmark":"logicvista","model":"gpt-5-mini","score":69.1,"metric":"percent"},{"benchmark":"wemath","model":"gpt-5-mini","score":65.1,"metric":"percent"},{"benchmark":"dynamath","model":"gpt-5-mini","score":52.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5-mini","score":62.5,"metric":"percent"},{"benchmark":"miabench","model":"gpt-5-mini","score":94.8,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5-mini","score":85.8,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-mini","score":63.8,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-5-mini","score":71.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-5-mini","score":78.9,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5-mini","score":83.3,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5-mini","score":82.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gpt-5-mini","score":52.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gpt-5-mini","score":45.1,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gpt-5-mini","score":64.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5-mini","score":68.6,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5-mini","score":90,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-5-mini","score":78,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-5-mini","score":87.2,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-mini","score":86.7,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-5-mini","score":76.9,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gpt-5-mini","score":50.3,"metric":"percent"},{"benchmark":"v-star","model":"gpt-5-mini","score":74.3,"metric":"percent"},{"benchmark":"hrbench4k","model":"gpt-5-mini","score":75.1,"metric":"percent"},{"benchmark":"hrbench8k","model":"gpt-5-mini","score":71,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.5-pro","score":88.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.5-pro","score":88.3,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-pro","score":73.6,"metric":"percent"},{"benchmark":"mmvet","model":"gemini-2.5-pro","score":83.3,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-pro","score":80.9,"metric":"percent"},{"benchmark":"mathverse","model":"gemini-2.5-pro","score":82.9,"metric":"percent"},{"benchmark":"wemath","model":"gemini-2.5-pro","score":74.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.5-pro","score":64.1,"metric":"percent"},{"benchmark":"miabench","model":"gemini-2.5-pro","score":96,"metric":"percent"},{"benchmark":"countbench","model":"gemini-2.5-pro","score":91.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemini-2.5-pro","score":61.9,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gemini-2.5-pro","score":57.6,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gemini-2.5-pro","score":69.5,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-pro","score":92.2,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-2.5-pro","score":84.4,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-2.5-pro","score":90.6,"metric":"percent"},{"benchmark":"omnidocbench","model":"gemini-2.5-pro","score":88,"metric":"percent"},{"benchmark":"v-star","model":"gemini-2.5-pro","score":79,"metric":"percent"},{"benchmark":"hrbench4k","model":"gemini-2.5-pro","score":86.9,"metric":"percent"},{"benchmark":"hrbench8k","model":"gemini-2.5-pro","score":84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.2-high","score":85.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.5","score":89.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed2.0-pro","score":87,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.2-high","score":29.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-4.5","score":14.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4.5","score":23.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3-pro","score":33.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"seed2.0-pro","score":32.4,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.2-high","score":36.8,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-sonnet-4.5","score":29.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-opus-4.5","score":48.6,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"seed2.0-pro","score":36,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-5.2-high","score":63.3,"metric":"percent"},{"benchmark":"healthbench","model":"claude-sonnet-4.5","score":28.7,"metric":"percent"},{"benchmark":"healthbench","model":"claude-opus-4.5","score":36.3,"metric":"percent"},{"benchmark":"healthbench","model":"gemini-3-pro","score":37.9,"metric":"percent"},{"benchmark":"healthbench","model":"seed2.0-pro","score":57.7,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gpt-5.2-high","score":42,"metric":"percent"},{"benchmark":"healthbench-hard","model":"claude-sonnet-4.5","score":10.9,"metric":"percent"},{"benchmark":"healthbench-hard","model":"claude-opus-4.5","score":11,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gemini-3-pro","score":15,"metric":"percent"},{"benchmark":"healthbench-hard","model":"seed2.0-pro","score":29.1,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5.2-high","score":67.9,"metric":"percent"},{"benchmark":"supergpqa","model":"claude-sonnet-4.5","score":65.5,"metric":"percent"},{"benchmark":"supergpqa","model":"claude-opus-4.5","score":70.6,"metric":"percent"},{"benchmark":"supergpqa","model":"gemini-3-pro","score":73.8,"metric":"percent"},{"benchmark":"supergpqa","model":"seed2.0-pro","score":68.7,"metric":"percent"},{"benchmark":"lpfqa","model":"gpt-5.2-high","score":54.4,"metric":"percent"},{"benchmark":"lpfqa","model":"claude-sonnet-4.5","score":54.9,"metric":"percent"},{"benchmark":"lpfqa","model":"claude-opus-4.5","score":52.6,"metric":"percent"},{"benchmark":"lpfqa","model":"gemini-3-pro","score":51.2,"metric":"percent"},{"benchmark":"lpfqa","model":"seed2.0-pro","score":52.6,"metric":"percent"},{"benchmark":"encyclo-k","model":"gpt-5.2-high","score":61,"metric":"percent"},{"benchmark":"encyclo-k","model":"claude-sonnet-4.5","score":58,"metric":"percent"},{"benchmark":"encyclo-k","model":"claude-opus-4.5","score":63.3,"metric":"percent"},{"benchmark":"encyclo-k","model":"gemini-3-pro","score":64.9,"metric":"percent"},{"benchmark":"encyclo-k","model":"seed2.0-pro","score":65.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.2-high","score":97.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-sonnet-4.5","score":82.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.5","score":92.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3-pro","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"seed2.0-pro","score":94.2,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.2-high","score":99,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.5","score":91.3,"metric":"percent"},{"benchmark":"aime-2025","model":"seed2.0-pro","score":98.3,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5.2-high","score":100,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"claude-opus-4.5","score":92.9,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"seed2.0-pro","score":97.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5.2-high","score":100,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"claude-opus-4.5","score":93.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"seed2.0-pro","score":93.3,"metric":"percent"},{"benchmark":"matharena-apex","model":"gpt-5.2-high","score":80.1,"metric":"percent"},{"benchmark":"matharena-apex","model":"claude-sonnet-4.5","score":26,"metric":"percent"},{"benchmark":"matharena-apex","model":"claude-opus-4.5","score":47.4,"metric":"percent"},{"benchmark":"matharena-apex","model":"gemini-3-pro","score":71.4,"metric":"percent"},{"benchmark":"matharena-apex","model":"seed2.0-pro","score":82.1,"metric":"percent"},{"benchmark":"beyondaime","model":"gpt-5.2-high","score":86,"metric":"percent"},{"benchmark":"beyondaime","model":"claude-sonnet-4.5","score":57,"metric":"percent"},{"benchmark":"beyondaime","model":"claude-opus-4.5","score":69,"metric":"percent"},{"benchmark":"beyondaime","model":"seed2.0-pro","score":86.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.2-high","score":86.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-sonnet-4.5","score":60.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.5","score":72.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"seed2.0-pro","score":89.3,"metric":"percent"},{"benchmark":"codeforces","model":"gpt-5.2-high","score":3148,"metric":"ELO"},{"benchmark":"codeforces","model":"claude-sonnet-4.5","score":1485,"metric":"ELO"},{"benchmark":"codeforces","model":"claude-opus-4.5","score":1701,"metric":"ELO"},{"benchmark":"codeforces","model":"gemini-3-pro","score":2726,"metric":"ELO"},{"benchmark":"codeforces","model":"seed2.0-pro","score":3020,"metric":"ELO"},{"benchmark":"aethercode","model":"gpt-5.2-high","score":73.8,"metric":"percent"},{"benchmark":"aethercode","model":"claude-sonnet-4.5","score":16.4,"metric":"percent"},{"benchmark":"aethercode","model":"claude-opus-4.5","score":31.6,"metric":"percent"},{"benchmark":"aethercode","model":"gemini-3-pro","score":57.8,"metric":"percent"},{"benchmark":"aethercode","model":"seed2.0-pro","score":60.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.2-high","score":87.7,"metric":"percent"},{"benchmark":"livecodebench","model":"seed2.0-pro","score":87.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2-high","score":92.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-sonnet-4.5","score":84.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.5","score":86.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed2.0-pro","score":88.9,"metric":"percent"},{"benchmark":"superchem","model":"gpt-5.2-high","score":58,"metric":"percent"},{"benchmark":"superchem","model":"claude-sonnet-4.5","score":32.4,"metric":"percent"},{"benchmark":"superchem","model":"claude-opus-4.5","score":43.2,"metric":"percent"},{"benchmark":"superchem","model":"gemini-3-pro","score":63.2,"metric":"percent"},{"benchmark":"superchem","model":"seed2.0-pro","score":51.6,"metric":"percent"},{"benchmark":"babe","model":"gpt-5.2-high","score":58.1,"metric":"percent"},{"benchmark":"babe","model":"claude-sonnet-4.5","score":44.7,"metric":"percent"},{"benchmark":"babe","model":"claude-opus-4.5","score":49.3,"metric":"percent"},{"benchmark":"babe","model":"gemini-3-pro","score":51.3,"metric":"percent"},{"benchmark":"babe","model":"seed2.0-pro","score":50,"metric":"percent"},{"benchmark":"phybench","model":"gpt-5.2-high","score":74,"metric":"percent"},{"benchmark":"phybench","model":"claude-sonnet-4.5","score":48,"metric":"percent"},{"benchmark":"phybench","model":"claude-opus-4.5","score":69,"metric":"percent"},{"benchmark":"phybench","model":"gemini-3-pro","score":80,"metric":"percent"},{"benchmark":"phybench","model":"seed2.0-pro","score":74,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.2-high","score":25,"metric":"percent"},{"benchmark":"frontierscience-research","model":"claude-sonnet-4.5","score":16.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"claude-opus-4.5","score":21.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gemini-3-pro","score":15,"metric":"percent"},{"benchmark":"frontierscience-research","model":"seed2.0-pro","score":25,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.2-high","score":75,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"claude-sonnet-4.5","score":60,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"claude-opus-4.5","score":71,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gemini-3-pro","score":73,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"seed2.0-pro","score":74,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-high","score":89.9,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4.5","score":70.9,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.5","score":84,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-pro","score":85,"metric":"percent"},{"benchmark":"arc-agi-1","model":"seed2.0-pro","score":85.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-high","score":57.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.5","score":29.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"seed2.0-pro","score":37.5,"metric":"percent"},{"benchmark":"korbench","model":"gpt-5.2-high","score":79.2,"metric":"percent"},{"benchmark":"korbench","model":"claude-sonnet-4.5","score":73,"metric":"percent"},{"benchmark":"korbench","model":"claude-opus-4.5","score":77.4,"metric":"percent"},{"benchmark":"korbench","model":"gemini-3-pro","score":73.9,"metric":"percent"},{"benchmark":"korbench","model":"seed2.0-pro","score":77.5,"metric":"percent"},{"benchmark":"procbench","model":"gpt-5.2-high","score":95,"metric":"percent"},{"benchmark":"procbench","model":"claude-sonnet-4.5","score":87.5,"metric":"percent"},{"benchmark":"procbench","model":"claude-opus-4.5","score":92.5,"metric":"percent"},{"benchmark":"procbench","model":"gemini-3-pro","score":90,"metric":"percent"},{"benchmark":"procbench","model":"seed2.0-pro","score":96.6,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gpt-5.2-high","score":89.4,"metric":"percent"},{"benchmark":"mrcr-v2","model":"claude-sonnet-4.5","score":47.1,"metric":"percent"},{"benchmark":"mrcr-v2","model":"claude-opus-4.5","score":56.2,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gemini-3-pro","score":79.7,"metric":"percent"},{"benchmark":"mrcr-v2","model":"seed2.0-pro","score":54,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gpt-5.2-high","score":98,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"claude-sonnet-4.5","score":80.5,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"claude-opus-4.5","score":92,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gemini-3-pro","score":79.9,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"seed2.0-pro","score":68.9,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gpt-5.2-high","score":99.7,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"claude-sonnet-4.5","score":99,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"claude-opus-4.5","score":96.2,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gemini-3-pro","score":99.7,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"seed2.0-pro","score":97.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5.2-high","score":63.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-sonnet-4.5","score":62,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-opus-4.5","score":65,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-3-pro","score":67.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"seed2.0-pro","score":63.8,"metric":"percent"},{"benchmark":"frames","model":"gpt-5.2-high","score":84,"metric":"percent"},{"benchmark":"frames","model":"claude-sonnet-4.5","score":78.7,"metric":"percent"},{"benchmark":"frames","model":"claude-opus-4.5","score":84.7,"metric":"percent"},{"benchmark":"frames","model":"gemini-3-pro","score":81.9,"metric":"percent"},{"benchmark":"frames","model":"seed2.0-pro","score":84.5,"metric":"percent"},{"benchmark":"der2-bench","model":"gpt-5.2-high","score":69,"metric":"percent"},{"benchmark":"der2-bench","model":"claude-sonnet-4.5","score":58.9,"metric":"percent"},{"benchmark":"der2-bench","model":"claude-opus-4.5","score":60.4,"metric":"percent"},{"benchmark":"der2-bench","model":"gemini-3-pro","score":66.1,"metric":"percent"},{"benchmark":"der2-bench","model":"seed2.0-pro","score":58.2,"metric":"percent"},{"benchmark":"cl-bench","model":"gpt-5.2-high","score":23.9,"metric":"percent"},{"benchmark":"cl-bench","model":"claude-sonnet-4.5","score":18.1,"metric":"percent"},{"benchmark":"cl-bench","model":"claude-opus-4.5","score":22.6,"metric":"percent"},{"benchmark":"cl-bench","model":"gemini-3-pro","score":15.6,"metric":"percent"},{"benchmark":"cl-bench","model":"seed2.0-pro","score":20.8,"metric":"percent"},{"benchmark":"global-piqa","model":"gpt-5.2-high","score":93.2,"metric":"percent"},{"benchmark":"global-piqa","model":"claude-sonnet-4.5","score":93.9,"metric":"percent"},{"benchmark":"global-piqa","model":"claude-opus-4.5","score":93.9,"metric":"percent"},{"benchmark":"global-piqa","model":"gemini-3-pro","score":95,"metric":"percent"},{"benchmark":"global-piqa","model":"seed2.0-pro","score":92.3,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5.2-high","score":90.3,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-sonnet-4.5","score":89.9,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-opus-4.5","score":91,"metric":"percent"},{"benchmark":"mmmlu","model":"seed2.0-pro","score":88.1,"metric":"percent"},{"benchmark":"discox","model":"gpt-5.2-high","score":76.3,"metric":"percent"},{"benchmark":"discox","model":"claude-sonnet-4.5","score":70.3,"metric":"percent"},{"benchmark":"discox","model":"claude-opus-4.5","score":78.6,"metric":"percent"},{"benchmark":"discox","model":"gemini-3-pro","score":76.8,"metric":"percent"},{"benchmark":"discox","model":"seed2.0-pro","score":82,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5.2-high","score":59.5,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-sonnet-4.5","score":57.3,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-opus-4.5","score":59,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-3-pro","score":68.7,"metric":"percent"},{"benchmark":"multichallenge","model":"seed2.0-pro","score":68.3,"metric":"percent"},{"benchmark":"collie","model":"gpt-5.2-high","score":96.9,"metric":"percent"},{"benchmark":"collie","model":"claude-sonnet-4.5","score":77.3,"metric":"percent"},{"benchmark":"collie","model":"claude-opus-4.5","score":79.8,"metric":"percent"},{"benchmark":"collie","model":"gemini-3-pro","score":95,"metric":"percent"},{"benchmark":"collie","model":"seed2.0-pro","score":93.9,"metric":"percent"},{"benchmark":"mars-bench","model":"gpt-5.2-high","score":87.9,"metric":"percent"},{"benchmark":"mars-bench","model":"claude-sonnet-4.5","score":72.9,"metric":"percent"},{"benchmark":"mars-bench","model":"claude-opus-4.5","score":87.7,"metric":"percent"},{"benchmark":"mars-bench","model":"gemini-3-pro","score":85.6,"metric":"percent"},{"benchmark":"mars-bench","model":"seed2.0-pro","score":85.6,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"gpt-5.2-high","score":72.3,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"claude-sonnet-4.5","score":69.3,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"claude-opus-4.5","score":72.4,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"gemini-3-pro","score":79.6,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"seed2.0-pro","score":78.9,"metric":"percent"},{"benchmark":"longfact-objects","model":"gpt-5.2-high","score":99.2,"metric":"percent"},{"benchmark":"longfact-objects","model":"claude-sonnet-4.5","score":98.8,"metric":"percent"},{"benchmark":"longfact-objects","model":"claude-opus-4.5","score":99,"metric":"percent"},{"benchmark":"longfact-objects","model":"gemini-3-pro","score":98.1,"metric":"percent"},{"benchmark":"longfact-objects","model":"seed2.0-pro","score":92.9,"metric":"percent"},{"benchmark":"longfact-concepts","model":"gpt-5.2-high","score":99.7,"metric":"percent"},{"benchmark":"longfact-concepts","model":"claude-sonnet-4.5","score":98.5,"metric":"percent"},{"benchmark":"longfact-concepts","model":"claude-opus-4.5","score":98.8,"metric":"percent"},{"benchmark":"longfact-concepts","model":"gemini-3-pro","score":98.5,"metric":"percent"},{"benchmark":"longfact-concepts","model":"seed2.0-pro","score":92.8,"metric":"percent"},{"benchmark":"factscore","model":"gpt-5.2-high","score":91.9,"metric":"percent"},{"benchmark":"factscore","model":"claude-sonnet-4.5","score":90.6,"metric":"percent"},{"benchmark":"factscore","model":"claude-opus-4.5","score":91.1,"metric":"percent"},{"benchmark":"factscore","model":"gemini-3-pro","score":92.6,"metric":"percent"},{"benchmark":"factscore","model":"seed2.0-pro","score":71.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5-mini-high","score":84.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3-flash","score":87.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed2.0-mini","score":83.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed2.0-lite","score":87.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5-mini-high","score":17.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3-flash","score":31.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"seed2.0-mini","score":13.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"seed2.0-lite","score":28.2,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5-mini-high","score":26,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-3-flash","score":65.4,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"seed2.0-mini","score":18.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"seed2.0-lite","score":24,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-5-mini-high","score":62.5,"metric":"percent"},{"benchmark":"healthbench","model":"gemini-3-flash","score":51.6,"metric":"percent"},{"benchmark":"healthbench","model":"seed2.0-mini","score":30,"metric":"percent"},{"benchmark":"healthbench","model":"seed2.0-lite","score":51.2,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gpt-5-mini-high","score":38.6,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gemini-3-flash","score":21.5,"metric":"percent"},{"benchmark":"healthbench-hard","model":"seed2.0-mini","score":15.3,"metric":"percent"},{"benchmark":"healthbench-hard","model":"seed2.0-lite","score":20,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5-mini-high","score":60.5,"metric":"percent"},{"benchmark":"supergpqa","model":"gemini-3-flash","score":72.7,"metric":"percent"},{"benchmark":"supergpqa","model":"seed2.0-mini","score":61.6,"metric":"percent"},{"benchmark":"supergpqa","model":"seed2.0-lite","score":67.5,"metric":"percent"},{"benchmark":"lpfqa","model":"gpt-5-mini-high","score":50.7,"metric":"percent"},{"benchmark":"lpfqa","model":"gemini-3-flash","score":51.6,"metric":"percent"},{"benchmark":"lpfqa","model":"seed2.0-mini","score":47.2,"metric":"percent"},{"benchmark":"lpfqa","model":"seed2.0-lite","score":50.9,"metric":"percent"},{"benchmark":"encyclo-k","model":"gpt-5-mini-high","score":53,"metric":"percent"},{"benchmark":"encyclo-k","model":"gemini-3-flash","score":60,"metric":"percent"},{"benchmark":"encyclo-k","model":"seed2.0-mini","score":52.1,"metric":"percent"},{"benchmark":"encyclo-k","model":"seed2.0-lite","score":64.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5-mini-high","score":92.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3-flash","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"seed2.0-mini","score":86.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"seed2.0-lite","score":88.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-mini-high","score":90.3,"metric":"percent"},{"benchmark":"aime-2025","model":"seed2.0-mini","score":87,"metric":"percent"},{"benchmark":"aime-2025","model":"seed2.0-lite","score":93,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5-mini-high","score":93.3,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemini-3-flash","score":100,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"seed2.0-mini","score":70,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"seed2.0-lite","score":90,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5-mini-high","score":96.7,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gemini-3-flash","score":96.7,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"seed2.0-mini","score":80,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"seed2.0-lite","score":86.7,"metric":"percent"},{"benchmark":"matharena-apex","model":"gpt-5-mini-high","score":43.4,"metric":"percent"},{"benchmark":"matharena-apex","model":"gemini-3-flash","score":71.9,"metric":"percent"},{"benchmark":"matharena-apex","model":"seed2.0-mini","score":31.1,"metric":"percent"},{"benchmark":"matharena-apex","model":"seed2.0-lite","score":52.6,"metric":"percent"},{"benchmark":"beyondaime","model":"gpt-5-mini-high","score":72,"metric":"percent"},{"benchmark":"beyondaime","model":"gemini-3-flash","score":82,"metric":"percent"},{"benchmark":"beyondaime","model":"seed2.0-mini","score":69,"metric":"percent"},{"benchmark":"beyondaime","model":"seed2.0-lite","score":76,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5-mini-high","score":72.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3-flash","score":84.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"seed2.0-mini","score":71.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"seed2.0-lite","score":81.6,"metric":"percent"},{"benchmark":"codeforces","model":"gpt-5-mini-high","score":1985,"metric":"ELO"},{"benchmark":"codeforces","model":"gemini-3-flash","score":2727,"metric":"ELO"},{"benchmark":"codeforces","model":"seed2.0-mini","score":1644,"metric":"ELO"},{"benchmark":"codeforces","model":"seed2.0-lite","score":2233,"metric":"ELO"},{"benchmark":"aethercode","model":"gpt-5-mini-high","score":42.6,"metric":"percent"},{"benchmark":"aethercode","model":"gemini-3-flash","score":56.1,"metric":"percent"},{"benchmark":"aethercode","model":"seed2.0-mini","score":29.8,"metric":"percent"},{"benchmark":"aethercode","model":"seed2.0-lite","score":41.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini-high","score":62.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-flash","score":84.7,"metric":"percent"},{"benchmark":"livecodebench","model":"seed2.0-mini","score":64.1,"metric":"percent"},{"benchmark":"livecodebench","model":"seed2.0-lite","score":81.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-mini-high","score":82.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3-flash","score":90.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed2.0-mini","score":79,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed2.0-lite","score":85.1,"metric":"percent"},{"benchmark":"superchem","model":"gpt-5-mini-high","score":34.8,"metric":"percent"},{"benchmark":"superchem","model":"gemini-3-flash","score":54.4,"metric":"percent"},{"benchmark":"superchem","model":"seed2.0-mini","score":16.2,"metric":"percent"},{"benchmark":"superchem","model":"seed2.0-lite","score":48,"metric":"percent"},{"benchmark":"babe","model":"gpt-5-mini-high","score":49.2,"metric":"percent"},{"benchmark":"babe","model":"gemini-3-flash","score":55.2,"metric":"percent"},{"benchmark":"babe","model":"seed2.0-mini","score":40.4,"metric":"percent"},{"benchmark":"babe","model":"seed2.0-lite","score":50.2,"metric":"percent"},{"benchmark":"phybench","model":"gpt-5-mini-high","score":60,"metric":"percent"},{"benchmark":"phybench","model":"gemini-3-flash","score":77,"metric":"percent"},{"benchmark":"phybench","model":"seed2.0-mini","score":56,"metric":"percent"},{"benchmark":"phybench","model":"seed2.0-lite","score":73,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5-mini-high","score":18.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gemini-3-flash","score":11.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"seed2.0-mini","score":3.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"seed2.0-lite","score":18.3,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5-mini-high","score":69,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gemini-3-flash","score":73,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"seed2.0-mini","score":44,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"seed2.0-lite","score":70,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-high","score":54.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-flash","score":86.9,"metric":"percent"},{"benchmark":"arc-agi-1","model":"seed2.0-mini","score":43.3,"metric":"percent"},{"benchmark":"arc-agi-1","model":"seed2.0-lite","score":75.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-high","score":3.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-flash","score":34.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"seed2.0-mini","score":2.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"seed2.0-lite","score":14.8,"metric":"percent"},{"benchmark":"korbench","model":"gpt-5-mini-high","score":74.2,"metric":"percent"},{"benchmark":"korbench","model":"gemini-3-flash","score":76,"metric":"percent"},{"benchmark":"korbench","model":"seed2.0-mini","score":72.8,"metric":"percent"},{"benchmark":"korbench","model":"seed2.0-lite","score":77,"metric":"percent"},{"benchmark":"procbench","model":"gpt-5-mini-high","score":87.5,"metric":"percent"},{"benchmark":"procbench","model":"gemini-3-flash","score":90,"metric":"percent"},{"benchmark":"procbench","model":"seed2.0-mini","score":80.1,"metric":"percent"},{"benchmark":"procbench","model":"seed2.0-lite","score":92.4,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gpt-5-mini-high","score":50.1,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gemini-3-flash","score":79,"metric":"percent"},{"benchmark":"mrcr-v2","model":"seed2.0-mini","score":51.4,"metric":"percent"},{"benchmark":"mrcr-v2","model":"seed2.0-lite","score":33.6,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gpt-5-mini-high","score":85.5,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gemini-3-flash","score":84.2,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"seed2.0-mini","score":64.1,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"seed2.0-lite","score":82.5,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gpt-5-mini-high","score":96.6,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gemini-3-flash","score":99.7,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"seed2.0-mini","score":93,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"seed2.0-lite","score":100,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5-mini-high","score":56.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-3-flash","score":64,"metric":"percent"},{"benchmark":"longbench-v2","model":"seed2.0-mini","score":52.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"seed2.0-lite","score":59.6,"metric":"percent"},{"benchmark":"frames","model":"gpt-5-mini-high","score":82.9,"metric":"percent"},{"benchmark":"frames","model":"gemini-3-flash","score":83.7,"metric":"percent"},{"benchmark":"frames","model":"seed2.0-mini","score":80.5,"metric":"percent"},{"benchmark":"frames","model":"seed2.0-lite","score":83.4,"metric":"percent"},{"benchmark":"der2-bench","model":"gpt-5-mini-high","score":50.3,"metric":"percent"},{"benchmark":"der2-bench","model":"gemini-3-flash","score":66,"metric":"percent"},{"benchmark":"der2-bench","model":"seed2.0-mini","score":46.6,"metric":"percent"},{"benchmark":"der2-bench","model":"seed2.0-lite","score":57.3,"metric":"percent"},{"benchmark":"cl-bench","model":"gpt-5-mini-high","score":25.2,"metric":"percent"},{"benchmark":"cl-bench","model":"gemini-3-flash","score":16.1,"metric":"percent"},{"benchmark":"cl-bench","model":"seed2.0-mini","score":14.8,"metric":"percent"},{"benchmark":"cl-bench","model":"seed2.0-lite","score":20,"metric":"percent"},{"benchmark":"global-piqa","model":"gpt-5-mini-high","score":91.6,"metric":"percent"},{"benchmark":"global-piqa","model":"gemini-3-flash","score":95.6,"metric":"percent"},{"benchmark":"global-piqa","model":"seed2.0-mini","score":89.2,"metric":"percent"},{"benchmark":"global-piqa","model":"seed2.0-lite","score":92.1,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5-mini-high","score":86.3,"metric":"percent"},{"benchmark":"mmmlu","model":"seed2.0-mini","score":81.6,"metric":"percent"},{"benchmark":"mmmlu","model":"seed2.0-lite","score":87.7,"metric":"percent"},{"benchmark":"discox","model":"gpt-5-mini-high","score":67.7,"metric":"percent"},{"benchmark":"discox","model":"gemini-3-flash","score":71.9,"metric":"percent"},{"benchmark":"discox","model":"seed2.0-mini","score":73,"metric":"percent"},{"benchmark":"discox","model":"seed2.0-lite","score":80.3,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5-mini-high","score":59,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-3-flash","score":69.3,"metric":"percent"},{"benchmark":"multichallenge","model":"seed2.0-mini","score":61.1,"metric":"percent"},{"benchmark":"multichallenge","model":"seed2.0-lite","score":63.2,"metric":"percent"},{"benchmark":"collie","model":"gpt-5-mini-high","score":97.4,"metric":"percent"},{"benchmark":"collie","model":"gemini-3-flash","score":96.5,"metric":"percent"},{"benchmark":"collie","model":"seed2.0-mini","score":91.2,"metric":"percent"},{"benchmark":"collie","model":"seed2.0-lite","score":94,"metric":"percent"},{"benchmark":"mars-bench","model":"gpt-5-mini-high","score":66.1,"metric":"percent"},{"benchmark":"mars-bench","model":"gemini-3-flash","score":84.6,"metric":"percent"},{"benchmark":"mars-bench","model":"seed2.0-mini","score":62.4,"metric":"percent"},{"benchmark":"mars-bench","model":"seed2.0-lite","score":80.5,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"gpt-5-mini-high","score":74.8,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"gemini-3-flash","score":80.9,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"seed2.0-mini","score":69.3,"metric":"percent"},{"benchmark":"inverse-ifeval","model":"seed2.0-lite","score":77.1,"metric":"percent"},{"benchmark":"longfact-objects","model":"gpt-5-mini-high","score":99.2,"metric":"percent"},{"benchmark":"longfact-objects","model":"gemini-3-flash","score":97.9,"metric":"percent"},{"benchmark":"longfact-objects","model":"seed2.0-mini","score":87,"metric":"percent"},{"benchmark":"longfact-objects","model":"seed2.0-lite","score":92.2,"metric":"percent"},{"benchmark":"longfact-concepts","model":"gpt-5-mini-high","score":99.5,"metric":"percent"},{"benchmark":"longfact-concepts","model":"gemini-3-flash","score":98.6,"metric":"percent"},{"benchmark":"longfact-concepts","model":"seed2.0-mini","score":91.4,"metric":"percent"},{"benchmark":"longfact-concepts","model":"seed2.0-lite","score":92.4,"metric":"percent"},{"benchmark":"factscore","model":"gpt-5-mini-high","score":96.1,"metric":"percent"},{"benchmark":"factscore","model":"gemini-3-flash","score":92,"metric":"percent"},{"benchmark":"factscore","model":"seed2.0-mini","score":50.4,"metric":"percent"},{"benchmark":"factscore","model":"seed2.0-lite","score":62.4,"metric":"percent"},{"benchmark":"mmlu","model":"joyai-llm-flash","score":89.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"joyai-llm-flash","score":81.02,"metric":"percent"},{"benchmark":"cmmlu","model":"joyai-llm-flash","score":87.03,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"joyai-llm-flash","score":74.43,"metric":"percent"},{"benchmark":"supergpqa","model":"joyai-llm-flash","score":55,"metric":"percent"},{"benchmark":"livebench","model":"joyai-llm-flash","score":72.9,"metric":"percent"},{"benchmark":"ifeval","model":"joyai-llm-flash","score":86.69,"metric":"percent"},{"benchmark":"alignbench","model":"joyai-llm-flash","score":8.24,"metric":"score"},{"benchmark":"hellaswag","model":"joyai-llm-flash","score":91.79,"metric":"percent"},{"benchmark":"humaneval","model":"joyai-llm-flash","score":96.34,"metric":"percent"},{"benchmark":"livecodebench","model":"joyai-llm-flash","score":65.6,"metric":"percent"},{"benchmark":"scicode-main","model":"joyai-llm-flash","score":3.08,"metric":"percent"},{"benchmark":"scicode","model":"joyai-llm-flash","score":22.92,"metric":"percent"},{"benchmark":"gsm8k","model":"joyai-llm-flash","score":95.83,"metric":"percent"},{"benchmark":"aime-2025","model":"joyai-llm-flash","score":65.83,"metric":"percent"},{"benchmark":"math500","model":"joyai-llm-flash","score":97.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"joyai-llm-flash","score":60.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"joyai-llm-flash","score":67.55,"metric":"percent"},{"benchmark":"tau2-airline","model":"joyai-llm-flash","score":54,"metric":"percent"},{"benchmark":"tau2-telecom","model":"joyai-llm-flash","score":79.83,"metric":"percent"},{"benchmark":"ruler-128k","model":"joyai-llm-flash","score":95.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b-instruct-2507","score":86.87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-instruct-2507","score":73.88,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-30b-a3b-instruct-2507","score":85.88,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-instruct-2507","score":68.69,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-30b-a3b-instruct-2507","score":52,"metric":"percent"},{"benchmark":"livebench","model":"qwen3-30b-a3b-instruct-2507","score":59.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-instruct-2507","score":83.18,"metric":"percent"},{"benchmark":"alignbench","model":"qwen3-30b-a3b-instruct-2507","score":8.07,"metric":"score"},{"benchmark":"hellaswag","model":"qwen3-30b-a3b-instruct-2507","score":89.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-30b-a3b-instruct-2507","score":95.12,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-instruct-2507","score":39.71,"metric":"percent"},{"benchmark":"scicode-main","model":"qwen3-30b-a3b-instruct-2507","score":3.08,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-30b-a3b-instruct-2507","score":22.92,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b-instruct-2507","score":79.83,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-instruct-2507","score":62.08,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b-instruct-2507","score":89.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-30b-a3b-instruct-2507","score":24.44,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-30b-a3b-instruct-2507","score":53.51,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-30b-a3b-instruct-2507","score":32,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-30b-a3b-instruct-2507","score":4.39,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen3-30b-a3b-instruct-2507","score":89.66,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.7-flash","score":80.53,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.7-flash","score":63.62,"metric":"percent"},{"benchmark":"cmmlu","model":"glm-4.7-flash","score":75.85,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.7-flash","score":39.9,"metric":"percent"},{"benchmark":"supergpqa","model":"glm-4.7-flash","score":32,"metric":"percent"},{"benchmark":"livebench","model":"glm-4.7-flash","score":43.1,"metric":"percent"},{"benchmark":"ifeval","model":"glm-4.7-flash","score":82.44,"metric":"percent"},{"benchmark":"alignbench","model":"glm-4.7-flash","score":6.85,"metric":"score"},{"benchmark":"hellaswag","model":"glm-4.7-flash","score":60.84,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4.7-flash","score":74.39,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.7-flash","score":27.43,"metric":"percent"},{"benchmark":"scicode-main","model":"glm-4.7-flash","score":3.08,"metric":"percent"},{"benchmark":"scicode","model":"glm-4.7-flash","score":15.11,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4.7-flash","score":81.88,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.7-flash","score":24.17,"metric":"percent"},{"benchmark":"math500","model":"glm-4.7-flash","score":90.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.7-flash","score":51.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"glm-4.7-flash","score":62.28,"metric":"percent"},{"benchmark":"tau2-airline","model":"glm-4.7-flash","score":52,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-4.7-flash","score":88.6,"metric":"percent"},{"benchmark":"ruler-128k","model":"glm-4.7-flash","score":56.12,"metric":"percent"},{"benchmark":"mmlu","model":"joyai-llm-flash-base","score":84.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"joyai-llm-flash-base","score":73.14,"metric":"percent"},{"benchmark":"cmmlu","model":"joyai-llm-flash-base","score":83.09,"metric":"percent"},{"benchmark":"humaneval","model":"joyai-llm-flash-base","score":85.37,"metric":"percent"},{"benchmark":"livecodebench","model":"joyai-llm-flash-base","score":39.91,"metric":"percent"},{"benchmark":"gsm8k","model":"joyai-llm-flash-base","score":88.78,"metric":"percent"},{"benchmark":"math","model":"joyai-llm-flash-base","score":78.16,"metric":"percent"},{"benchmark":"math500","model":"joyai-llm-flash-base","score":77,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b-base","score":82.12,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-base","score":61.76,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-30b-a3b-base","score":83.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-30b-a3b-base","score":87.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-base","score":37.34,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b-base","score":90.37,"metric":"percent"},{"benchmark":"math","model":"qwen3-30b-a3b-base","score":59.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b-base","score":58,"metric":"percent"},{"benchmark":"local-agent-bench","model":"lfm2.5-1.2b-instruct","score":88,"metric":"percent"},{"benchmark":"local-agent-bench","model":"phi-4-mini-3.8b","score":88,"metric":"percent"},{"benchmark":"local-agent-bench","model":"qwen3-0.6b","score":88,"metric":"percent"},{"benchmark":"local-agent-bench","model":"qwen3-4b","score":88,"metric":"percent"},{"benchmark":"local-agent-bench","model":"qwen2.5-1.5b","score":84,"metric":"percent"},{"benchmark":"local-agent-bench","model":"bitnet-2b-4t","score":81,"metric":"percent"},{"benchmark":"local-agent-bench","model":"ministral-3-3b-base","score":80,"metric":"percent"},{"benchmark":"local-agent-bench","model":"smollm2-1.7b-instruct","score":74,"metric":"percent"},{"benchmark":"local-agent-bench","model":"deepseek-r1-distill-qwen-1.5b","score":72,"metric":"percent"},{"benchmark":"local-agent-bench","model":"smollm3-3b","score":71,"metric":"percent"},{"benchmark":"local-agent-bench","model":"qwen2.5-3b","score":67,"metric":"percent"},{"benchmark":"local-agent-bench","model":"qwen3-1.7b","score":67,"metric":"percent"},{"benchmark":"local-agent-bench","model":"granite-4.0-micro","score":67,"metric":"percent"},{"benchmark":"local-agent-bench","model":"llama-3.2-3b","score":66,"metric":"percent"},{"benchmark":"local-agent-bench","model":"qwen2.5-0.5b","score":64,"metric":"percent"},{"benchmark":"local-agent-bench","model":"functiongemma","score":64,"metric":"percent"},{"benchmark":"local-agent-bench","model":"bitnet-3b","score":60,"metric":"percent"},{"benchmark":"local-agent-bench","model":"jan-v3","score":56,"metric":"percent"},{"benchmark":"local-agent-bench","model":"gemma-3-1b","score":55,"metric":"percent"},{"benchmark":"local-agent-bench","model":"granite-3.3-2b-instruct","score":48,"metric":"percent"},{"benchmark":"local-agent-bench","model":"llama-3.2-1b","score":43,"metric":"percent"},{"benchmark":"csimpleqa","model":"ling-2.5-1t","score":78.97,"metric":"percent"},{"benchmark":"csimpleqa","model":"ling-1t","score":64.6,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v3.2","score":68.37,"metric":"percent"},{"benchmark":"csimpleqa","model":"kimi-k2.5","score":76.8,"metric":"percent"},{"benchmark":"csimpleqa","model":"gpt-5.2","score":67.77,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"ling-2.5-1t","score":37.4,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"ling-1t","score":19.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v3.2","score":23.7,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"kimi-k2.5","score":25.4,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.2","score":29.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ling-2.5-1t","score":75.57,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ling-1t","score":73.48,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3.2","score":77.11,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.5","score":80.52,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2","score":77.15,"metric":"percent"},{"benchmark":"supergpqa","model":"ling-2.5-1t","score":60.34,"metric":"percent"},{"benchmark":"supergpqa","model":"ling-1t","score":57.22,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3.2","score":61.37,"metric":"percent"},{"benchmark":"supergpqa","model":"kimi-k2.5","score":66.4,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5.2","score":60.59,"metric":"percent"},{"benchmark":"hle-text-only","model":"ling-2.5-1t","score":11.33,"metric":"percent"},{"benchmark":"hle-text-only","model":"ling-1t","score":6.92,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v3.2","score":10.47,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2.5","score":12.92,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.2","score":8.62,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-2.5-1t","score":68.17,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-1t","score":62.28,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2","score":57.71,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2.5","score":73.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.2","score":67.51,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ling-2.5-1t","score":87.08,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ling-1t","score":75.16,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v3.2","score":66.41,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.5","score":66.98,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.2","score":66.2,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"ling-2.5-1t","score":80.21,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"ling-1t","score":66.46,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"deepseek-v3.2","score":53.44,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"kimi-k2.5","score":61.2,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5.2","score":53.18,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ling-2.5-1t","score":62.31,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ling-1t","score":54.81,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v3.2","score":46.66,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2.5","score":52.56,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.2","score":43.41,"metric":"percent"},{"benchmark":"arc-agi-2","model":"ling-2.5-1t","score":47.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"ling-1t","score":43.19,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v3.2","score":20.06,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k2.5","score":31.19,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2","score":24.19,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"ling-2.5-1t","score":51.99,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"ling-1t","score":47.25,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"deepseek-v3.2","score":48.04,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"kimi-k2.5","score":48.43,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gpt-5.2","score":43.12,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ling-2.5-1t","score":69.87,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ling-1t","score":45.99,"metric":"percent"},{"benchmark":"bfcl-v4","model":"deepseek-v3.2","score":60.05,"metric":"percent"},{"benchmark":"bfcl-v4","model":"kimi-k2.5","score":62.96,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.2","score":63.05,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"ling-2.5-1t","score":31.46,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"ling-1t","score":8.99,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v3.2","score":29.21,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2.5","score":48.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2","score":23.6,"metric":"percent"},{"benchmark":"lifebench","model":"ling-2.5-1t","score":57.9,"metric":"percent"},{"benchmark":"lifebench","model":"ling-1t","score":42.3,"metric":"percent"},{"benchmark":"lifebench","model":"deepseek-v3.2","score":55.5,"metric":"percent"},{"benchmark":"lifebench","model":"kimi-k2.5","score":54.9,"metric":"percent"},{"benchmark":"lifebench","model":"gpt-5.2","score":61.7,"metric":"percent"},{"benchmark":"ifbench","model":"ling-2.5-1t","score":46.67,"metric":"percent"},{"benchmark":"ifbench","model":"ling-1t","score":36,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v3.2","score":50,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.5","score":42.53,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.2","score":71.47,"metric":"percent"},{"benchmark":"multi-if","model":"ling-2.5-1t","score":77.18,"metric":"percent"},{"benchmark":"multi-if","model":"ling-1t","score":69.93,"metric":"percent"},{"benchmark":"multi-if","model":"deepseek-v3.2","score":69.81,"metric":"percent"},{"benchmark":"multi-if","model":"kimi-k2.5","score":78.2,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-5.2","score":75.97,"metric":"percent"},{"benchmark":"longbench-v2","model":"ling-2.5-1t","score":53.68,"metric":"percent"},{"benchmark":"longbench-v2","model":"ling-1t","score":50.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v3.2","score":51.89,"metric":"percent"},{"benchmark":"longbench-v2","model":"kimi-k2.5","score":59.64,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5.2","score":52.88,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"ling-2.5-1t","score":77.92,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"ling-1t","score":74.85,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"deepseek-v3.2","score":71.04,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"kimi-k2.5","score":78.66,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-5.2","score":72.54,"metric":"percent"},{"benchmark":"multichallenge","model":"ling-2.5-1t","score":52.01,"metric":"percent"},{"benchmark":"multichallenge","model":"ling-1t","score":54.95,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v3.2","score":43.59,"metric":"percent"},{"benchmark":"multichallenge","model":"kimi-k2.5","score":53.11,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5.2","score":51.28,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.2","score":87.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-397b-a17b","score":87.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-5.2","score":95,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-k2.5","score":94.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-397b-a17b","score":94.9,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5.2","score":67.9,"metric":"percent"},{"benchmark":"supergpqa","model":"gemini-3-pro","score":74,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-max-thinking","score":67.3,"metric":"percent"},{"benchmark":"supergpqa","model":"kimi-k2.5","score":69.2,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-397b-a17b","score":70.4,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-5.2","score":90.5,"metric":"percent"},{"benchmark":"c-eval","model":"kimi-k2.5","score":94,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-397b-a17b","score":93,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-5.2","score":94.8,"metric":"percent"},{"benchmark":"ifeval","model":"claude-opus-4.5","score":90.9,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-3-pro","score":93.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-max-thinking","score":93.4,"metric":"percent"},{"benchmark":"ifeval","model":"kimi-k2.5","score":93.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-397b-a17b","score":92.6,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.5","score":70.2,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-397b-a17b","score":76.5,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5.2","score":57.9,"metric":"percent"},{"benchmark":"multichallenge","model":"kimi-k2.5","score":62.7,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-397b-a17b","score":67.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.2","score":72.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2.5","score":70,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-397b-a17b","score":68.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5.2","score":54.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-opus-4.5","score":64.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-max-thinking","score":60.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"kimi-k2.5","score":61,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-397b-a17b","score":63.2,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-5.2","score":92.4,"metric":"percent"},{"benchmark":"gpqa","model":"kimi-k2.5","score":87.6,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-397b-a17b","score":88.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.2","score":35.5,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3-max-thinking","score":30.2,"metric":"avg@3"},{"benchmark":"hle","model":"kimi-k2.5","score":30.1,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-397b-a17b","score":28.7,"metric":"avg@3"},{"benchmark":"hle-verified","model":"gpt-5.2","score":43.3,"metric":"percent"},{"benchmark":"hle-verified","model":"claude-opus-4.5","score":38.8,"metric":"percent"},{"benchmark":"hle-verified","model":"gemini-3-pro","score":48,"metric":"percent"},{"benchmark":"hle-verified","model":"qwen3-max-thinking","score":37.6,"metric":"percent"},{"benchmark":"hle-verified","model":"qwen3.5-397b-a17b","score":37.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-397b-a17b","score":83.6,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5.2","score":99.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.5-397b-a17b","score":94.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5.2","score":100,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"kimi-k2.5","score":91.1,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-397b-a17b","score":92.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-397b-a17b","score":80.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.2","score":96.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.5","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3-pro","score":90.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-max-thinking","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.5","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-397b-a17b","score":91.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.2","score":63.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"kimi-k2.5","score":68.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-397b-a17b","score":72.9,"metric":"percent"},{"benchmark":"vitabench","model":"gpt-5.2","score":38.2,"metric":"percent"},{"benchmark":"vitabench","model":"kimi-k2.5","score":41.9,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-397b-a17b","score":49.7,"metric":"percent"},{"benchmark":"deep-planning","model":"gpt-5.2","score":44.6,"metric":"percent"},{"benchmark":"deep-planning","model":"kimi-k2.5","score":14.5,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.5-397b-a17b","score":34.3,"metric":"percent"},{"benchmark":"tool-decathlon","model":"gpt-5.2","score":43.8,"metric":"percent"},{"benchmark":"tool-decathlon","model":"claude-opus-4.5","score":43.5,"metric":"percent"},{"benchmark":"tool-decathlon","model":"qwen3-max-thinking","score":18.8,"metric":"percent"},{"benchmark":"tool-decathlon","model":"kimi-k2.5","score":27.8,"metric":"percent"},{"benchmark":"tool-decathlon","model":"qwen3.5-397b-a17b","score":38.3,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5.2","score":57.5,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-opus-4.5","score":42.3,"metric":"percent"},{"benchmark":"mcpmark","model":"gemini-3-pro","score":53.9,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3-max-thinking","score":33.5,"metric":"percent"},{"benchmark":"mcpmark","model":"kimi-k2.5","score":29.5,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.5-397b-a17b","score":46.1,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5.2","score":45.5,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"qwen3-max-thinking","score":49.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"kimi-k2.5","score":50.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"qwen3.5-397b-a17b","score":48.3,"metric":"avg@3"},{"benchmark":"browsecomp","model":"gpt-5.2","score":65.8,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3-max-thinking","score":53.9,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-397b-a17b","score":69,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-5.2","score":76.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"claude-opus-4.5","score":62.4,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gemini-3-pro","score":66.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"qwen3-max-thinking","score":60.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"qwen3.5-397b-a17b","score":70.3,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5.2","score":76.8,"metric":"percent"},{"benchmark":"wide-search","model":"claude-opus-4.5","score":76.4,"metric":"percent"},{"benchmark":"wide-search","model":"gemini-3-pro","score":68,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3-max-thinking","score":57.9,"metric":"percent"},{"benchmark":"wide-search","model":"kimi-k2.5","score":72.7,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.5-397b-a17b","score":74,"metric":"percent"},{"benchmark":"seal-0","model":"gpt-5.2","score":45,"metric":"percent"},{"benchmark":"seal-0","model":"claude-opus-4.5","score":47.7,"metric":"percent"},{"benchmark":"seal-0","model":"qwen3-max-thinking","score":46.9,"metric":"percent"},{"benchmark":"seal-0","model":"kimi-k2.5","score":57.4,"metric":"percent"},{"benchmark":"seal-0","model":"qwen3.5-397b-a17b","score":46.9,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5.2","score":89.5,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-opus-4.5","score":90.1,"metric":"percent"},{"benchmark":"mmmlu","model":"gemini-3-pro","score":90.6,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-max-thinking","score":84.4,"metric":"percent"},{"benchmark":"mmmlu","model":"kimi-k2.5","score":86,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-397b-a17b","score":88.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"gpt-5.2","score":83.7,"metric":"percent"},{"benchmark":"mmlu-prox","model":"claude-opus-4.5","score":85.7,"metric":"percent"},{"benchmark":"mmlu-prox","model":"gemini-3-pro","score":87.7,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-max-thinking","score":78.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"kimi-k2.5","score":82.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-397b-a17b","score":84.7,"metric":"percent"},{"benchmark":"nova-63","model":"gpt-5.2","score":54.6,"metric":"percent"},{"benchmark":"nova-63","model":"claude-opus-4.5","score":56.7,"metric":"percent"},{"benchmark":"nova-63","model":"gemini-3-pro","score":56.7,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3-max-thinking","score":54.2,"metric":"percent"},{"benchmark":"nova-63","model":"kimi-k2.5","score":56,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.5-397b-a17b","score":59.1,"metric":"percent"},{"benchmark":"include","model":"gpt-5.2","score":87.5,"metric":"percent"},{"benchmark":"include","model":"claude-opus-4.5","score":86.2,"metric":"percent"},{"benchmark":"include","model":"gemini-3-pro","score":90.5,"metric":"percent"},{"benchmark":"include","model":"qwen3-max-thinking","score":82.3,"metric":"percent"},{"benchmark":"include","model":"kimi-k2.5","score":83.3,"metric":"percent"},{"benchmark":"include","model":"qwen3.5-397b-a17b","score":85.6,"metric":"percent"},{"benchmark":"global-piqa","model":"gpt-5.2","score":90.9,"metric":"percent"},{"benchmark":"global-piqa","model":"claude-opus-4.5","score":91.6,"metric":"percent"},{"benchmark":"global-piqa","model":"gemini-3-pro","score":93.2,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-max-thinking","score":86,"metric":"percent"},{"benchmark":"global-piqa","model":"kimi-k2.5","score":89.3,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.5-397b-a17b","score":89.8,"metric":"percent"},{"benchmark":"polymath","model":"gpt-5.2","score":62.5,"metric":"percent"},{"benchmark":"polymath","model":"claude-opus-4.5","score":79,"metric":"percent"},{"benchmark":"polymath","model":"gemini-3-pro","score":81.6,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-max-thinking","score":64.7,"metric":"percent"},{"benchmark":"polymath","model":"kimi-k2.5","score":43.1,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.5-397b-a17b","score":73.3,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gpt-5.2","score":78.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"claude-opus-4.5","score":79.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gemini-3-pro","score":80.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-max-thinking","score":77.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"kimi-k2.5","score":77.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-397b-a17b","score":78.9,"metric":"percent"},{"benchmark":"maxife","model":"gpt-5.2","score":88.4,"metric":"percent"},{"benchmark":"maxife","model":"claude-opus-4.5","score":79.2,"metric":"percent"},{"benchmark":"maxife","model":"gemini-3-pro","score":87.5,"metric":"percent"},{"benchmark":"maxife","model":"qwen3-max-thinking","score":84,"metric":"percent"},{"benchmark":"maxife","model":"kimi-k2.5","score":72.8,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.5-397b-a17b","score":88.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-397b-a17b","score":76.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.2","score":72,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3-max-thinking","score":66.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2.5","score":73,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-397b-a17b","score":69.3,"metric":"percent"},{"benchmark":"seccodebench","model":"gpt-5.2","score":68.7,"metric":"percent"},{"benchmark":"seccodebench","model":"claude-opus-4.5","score":68.6,"metric":"percent"},{"benchmark":"seccodebench","model":"gemini-3-pro","score":62.4,"metric":"percent"},{"benchmark":"seccodebench","model":"qwen3-max-thinking","score":57.5,"metric":"percent"},{"benchmark":"seccodebench","model":"kimi-k2.5","score":61.3,"metric":"percent"},{"benchmark":"seccodebench","model":"qwen3.5-397b-a17b","score":68.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2","score":54,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-max-thinking","score":22.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-397b-a17b","score":52.5,"metric":"percent"},{"benchmark":"tau2-bench","model":"gpt-5.2","score":87.1,"metric":"percent"},{"benchmark":"tau2-bench","model":"claude-opus-4.5","score":91.6,"metric":"percent"},{"benchmark":"tau2-bench","model":"gemini-3-pro","score":85.4,"metric":"percent"},{"benchmark":"tau2-bench","model":"qwen3-max-thinking","score":84.6,"metric":"percent"},{"benchmark":"tau2-bench","model":"kimi-k2.5","score":77,"metric":"percent"},{"benchmark":"tau2-bench","model":"qwen3.5-397b-a17b","score":86.7,"metric":"percent"},{"benchmark":"tau2-bench","model":"ling-2.5-1t","score":59.78,"metric":"percent"},{"benchmark":"tau2-bench","model":"ling-1t","score":34.58,"metric":"percent"},{"benchmark":"tau2-bench","model":"deepseek-v3.2","score":68.1,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5.2","score":86.7,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-3-pro","score":87.2,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-235b-a22b","score":80.6,"metric":"percent"},{"benchmark":"mmmu","model":"kimi-k2.5","score":84.3,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-397b-a17b","score":85,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-235b-a22b","score":69.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-397b-a17b","score":79,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.2","score":83,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.5","score":74.3,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3-pro","score":86.6,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-235b-a22b","score":74.6,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-k2.5","score":84.2,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-397b-a17b","score":88.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-5.2","score":83.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-opus-4.5","score":80,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-3-pro","score":87.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-235b-a22b","score":85.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"kimi-k2.5","score":90.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-397b-a17b","score":90.3,"metric":"percent"},{"benchmark":"wemath","model":"gpt-5.2","score":79,"metric":"percent"},{"benchmark":"wemath","model":"claude-opus-4.5","score":70,"metric":"percent"},{"benchmark":"wemath","model":"gemini-3-pro","score":86.9,"metric":"percent"},{"benchmark":"wemath","model":"qwen3-vl-235b-a22b","score":74.8,"metric":"percent"},{"benchmark":"wemath","model":"kimi-k2.5","score":84.7,"metric":"percent"},{"benchmark":"wemath","model":"qwen3.5-397b-a17b","score":87.9,"metric":"percent"},{"benchmark":"dynamath","model":"gpt-5.2","score":86.8,"metric":"percent"},{"benchmark":"dynamath","model":"claude-opus-4.5","score":79.7,"metric":"percent"},{"benchmark":"dynamath","model":"gemini-3-pro","score":85.1,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3-vl-235b-a22b","score":82.8,"metric":"percent"},{"benchmark":"dynamath","model":"kimi-k2.5","score":84.4,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-397b-a17b","score":86.3,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5.2","score":9,"metric":"percent"},{"benchmark":"zerobench","model":"claude-opus-4.5","score":3,"metric":"percent"},{"benchmark":"zerobench","model":"gemini-3-pro","score":10,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3-vl-235b-a22b","score":4,"metric":"percent"},{"benchmark":"zerobench","model":"kimi-k2.5","score":9,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-397b-a17b","score":12,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gpt-5.2","score":33.2,"metric":"percent"},{"benchmark":"zerobench-sub","model":"claude-opus-4.5","score":28.4,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemini-3-pro","score":39,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-235b-a22b","score":28.4,"metric":"percent"},{"benchmark":"zerobench-sub","model":"kimi-k2.5","score":33.5,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-397b-a17b","score":41,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.2","score":34.4,"metric":"percent"},{"benchmark":"babyvision","model":"claude-opus-4.5","score":14.2,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3-pro","score":49.7,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-vl-235b-a22b","score":22.2,"metric":"percent"},{"benchmark":"babyvision","model":"kimi-k2.5","score":36.5,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.5-397b-a17b","score":52.3,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5.2","score":83.3,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-opus-4.5","score":77,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-3-pro","score":83.3,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-235b-a22b","score":81.3,"metric":"percent"},{"benchmark":"realworldqa","model":"kimi-k2.5","score":81,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-397b-a17b","score":83.9,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5.2","score":77.1,"metric":"percent"},{"benchmark":"mmstar","model":"claude-opus-4.5","score":73.2,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-235b-a22b","score":78.7,"metric":"percent"},{"benchmark":"mmstar","model":"kimi-k2.5","score":80.5,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-397b-a17b","score":83.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5.2","score":65.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-opus-4.5","score":64.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-3-pro","score":68.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-235b-a22b","score":66.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"kimi-k2.5","score":69.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-397b-a17b","score":71.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gpt-5.2","score":88.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"claude-opus-4.5","score":89.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemini-3-pro","score":93.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-235b-a22b","score":89.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"kimi-k2.5","score":94.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-397b-a17b","score":93.7,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5.2","score":55.8,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-opus-4.5","score":65.7,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3-pro","score":73.2,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-235b-a22b","score":61.3,"metric":"percent"},{"benchmark":"simplevqa","model":"kimi-k2.5","score":71.2,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-397b-a17b","score":67.1,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.2","score":85.7,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"claude-opus-4.5","score":87.7,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gemini-3-pro","score":88.5,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"qwen3-vl-235b-a22b","score":84.5,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"kimi-k2.5","score":88.8,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"qwen3.5-397b-a17b","score":90.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.2","score":82.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.5","score":68.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-235b-a22b","score":66.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"kimi-k2.5","score":77.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-397b-a17b","score":80.8,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"claude-opus-4.5","score":61.9,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gemini-3-pro","score":60.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-235b-a22b","score":56.2,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"kimi-k2.5","score":58.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-397b-a17b","score":61.5,"metric":"percent"},{"benchmark":"cc-ocr","model":"gpt-5.2","score":70.3,"metric":"percent"},{"benchmark":"cc-ocr","model":"claude-opus-4.5","score":76.9,"metric":"percent"},{"benchmark":"cc-ocr","model":"gemini-3-pro","score":79,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-235b-a22b","score":81.5,"metric":"percent"},{"benchmark":"cc-ocr","model":"kimi-k2.5","score":79.7,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-397b-a17b","score":82,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5.2","score":92.2,"metric":"percent"},{"benchmark":"ai2d","model":"claude-opus-4.5","score":87.7,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-3-pro","score":94.1,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-235b-a22b","score":89.2,"metric":"percent"},{"benchmark":"ai2d","model":"kimi-k2.5","score":90.8,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-397b-a17b","score":93.9,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5.2","score":80.7,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-opus-4.5","score":85.8,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-3-pro","score":90.4,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-235b-a22b","score":87.5,"metric":"percent"},{"benchmark":"ocrbench","model":"kimi-k2.5","score":92.3,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-397b-a17b","score":93.1,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.2","score":59.8,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-4.5","score":46.8,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-235b-a22b","score":52.5,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-397b-a17b","score":67.5,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5.2","score":91.9,"metric":"percent"},{"benchmark":"countbench","model":"claude-opus-4.5","score":90.6,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-235b-a22b","score":93.7,"metric":"percent"},{"benchmark":"countbench","model":"kimi-k2.5","score":94.1,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-397b-a17b","score":97.2,"metric":"percent"},{"benchmark":"odinw-13","model":"gemini-3-pro","score":46.3,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-235b-a22b","score":43.2,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-397b-a17b","score":47,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5.2","score":81.3,"metric":"percent"},{"benchmark":"embspatialbench","model":"claude-opus-4.5","score":75.7,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-3-pro","score":61.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-235b-a22b","score":84.3,"metric":"percent"},{"benchmark":"embspatialbench","model":"kimi-k2.5","score":77.4,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-397b-a17b","score":84.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-235b-a22b","score":69.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-397b-a17b","score":73.6,"metric":"percent"},{"benchmark":"lingoqa","model":"gpt-5.2","score":68.8,"metric":"percent"},{"benchmark":"lingoqa","model":"claude-opus-4.5","score":78.8,"metric":"percent"},{"benchmark":"lingoqa","model":"gemini-3-pro","score":72.8,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3-vl-235b-a22b","score":66.8,"metric":"percent"},{"benchmark":"lingoqa","model":"kimi-k2.5","score":68.2,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.5-397b-a17b","score":81.6,"metric":"percent"},{"benchmark":"v-star","model":"gpt-5.2","score":75.9,"metric":"percent"},{"benchmark":"v-star","model":"claude-opus-4.5","score":67,"metric":"percent"},{"benchmark":"v-star","model":"gemini-3-pro","score":88,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-235b-a22b","score":85.9,"metric":"percent"},{"benchmark":"v-star","model":"kimi-k2.5","score":77,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.5-397b-a17b","score":95.8,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-235b-a22b","score":11,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3.5-397b-a17b","score":12.5,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-235b-a22b","score":34.9,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3.5-397b-a17b","score":38.3,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3-vl-235b-a22b","score":13.9,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3.5-397b-a17b","score":16,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5.2","score":86,"metric":"percent"},{"benchmark":"videomme-sub","model":"claude-opus-4.5","score":77.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-3-pro","score":88.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3-vl-235b-a22b","score":83.8,"metric":"percent"},{"benchmark":"videomme-sub","model":"kimi-k2.5","score":87.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.5-397b-a17b","score":87.5,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-5.2","score":85.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"claude-opus-4.5","score":81.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-3-pro","score":87.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-235b-a22b","score":79,"metric":"percent"},{"benchmark":"videomme-nosub","model":"kimi-k2.5","score":83.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-397b-a17b","score":83.7,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5.2","score":85.9,"metric":"percent"},{"benchmark":"videommmu","model":"claude-opus-4.5","score":84.4,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-235b-a22b","score":80,"metric":"percent"},{"benchmark":"videommmu","model":"kimi-k2.5","score":86.6,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.5-397b-a17b","score":84.7,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5.2","score":85.6,"metric":"percent"},{"benchmark":"mlvu","model":"claude-opus-4.5","score":81.7,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-3-pro","score":83,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-235b-a22b","score":83.8,"metric":"percent"},{"benchmark":"mlvu","model":"kimi-k2.5","score":85,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-397b-a17b","score":86.7,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-5.2","score":78.1,"metric":"percent"},{"benchmark":"mvbench","model":"claude-opus-4.5","score":67.2,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-3-pro","score":74.1,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-235b-a22b","score":75.2,"metric":"percent"},{"benchmark":"mvbench","model":"kimi-k2.5","score":73.5,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-397b-a17b","score":77.6,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-5.2","score":73.7,"metric":"percent"},{"benchmark":"lvbench","model":"claude-opus-4.5","score":57.3,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3-pro","score":76.2,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-235b-a22b","score":63.6,"metric":"percent"},{"benchmark":"lvbench","model":"kimi-k2.5","score":75.9,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-397b-a17b","score":75.5,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5.2","score":80.8,"metric":"percent"},{"benchmark":"mmvu","model":"claude-opus-4.5","score":77.3,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3-vl-235b-a22b","score":71.1,"metric":"percent"},{"benchmark":"mmvu","model":"kimi-k2.5","score":80.4,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-397b-a17b","score":75.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-opus-4.5","score":45.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-235b-a22b","score":62,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-397b-a17b","score":65.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.2","score":38.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-opus-4.5","score":66.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3-vl-235b-a22b","score":38.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"kimi-k2.5","score":63.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-397b-a17b","score":62.2,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3-vl-235b-a22b","score":63.7,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.5-397b-a17b","score":66.8,"metric":"percent"},{"benchmark":"slake","model":"gpt-5.2","score":76.9,"metric":"percent"},{"benchmark":"slake","model":"claude-opus-4.5","score":76.4,"metric":"percent"},{"benchmark":"slake","model":"gemini-3-pro","score":81.3,"metric":"percent"},{"benchmark":"slake","model":"qwen3-vl-235b-a22b","score":54.7,"metric":"percent"},{"benchmark":"slake","model":"kimi-k2.5","score":81.6,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-397b-a17b","score":79.9,"metric":"percent"},{"benchmark":"pmc-vqa","model":"gpt-5.2","score":58.9,"metric":"percent"},{"benchmark":"pmc-vqa","model":"claude-opus-4.5","score":59.9,"metric":"percent"},{"benchmark":"pmc-vqa","model":"gemini-3-pro","score":62.3,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3-vl-235b-a22b","score":41.2,"metric":"percent"},{"benchmark":"pmc-vqa","model":"kimi-k2.5","score":63.3,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-397b-a17b","score":64.2,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gpt-5.2","score":73.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"claude-opus-4.5","score":63.6,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemini-3-pro","score":76,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3-vl-235b-a22b","score":47.6,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"kimi-k2.5","score":65.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-397b-a17b","score":70,"metric":"percent"},{"benchmark":"global-mmlu","model":"tiny-aya-global","score":44.9,"metric":"percent"},{"benchmark":"include","model":"tiny-aya-global","score":45.1,"metric":"percent"},{"benchmark":"global-piqa","model":"tiny-aya-global","score":68.3,"metric":"percent"},{"benchmark":"mdolly","model":"tiny-aya-global","score":86.9,"metric":"percent"},{"benchmark":"marena-hard","model":"tiny-aya-global","score":67.4,"metric":"percent"},{"benchmark":"global-mgsm","model":"tiny-aya-global","score":52.8,"metric":"percent"},{"benchmark":"flores","model":"tiny-aya-global","score":43.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"tiny-aya-global","score":45.4,"metric":"percent"},{"benchmark":"mdolly","model":"gemma-3-4b","score":77.5,"metric":"percent"},{"benchmark":"marena-hard","model":"gemma-3-4b","score":65.8,"metric":"percent"},{"benchmark":"global-mgsm","model":"gemma-3-4b","score":55.4,"metric":"percent"},{"benchmark":"flores","model":"gemma-3-4b","score":38.9,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gemma-3-4b","score":40.5,"metric":"percent"},{"benchmark":"mdolly","model":"qwen3-4b","score":67.3,"metric":"percent"},{"benchmark":"marena-hard","model":"qwen3-4b","score":70.1,"metric":"percent"},{"benchmark":"global-mgsm","model":"qwen3-4b","score":60.9,"metric":"percent"},{"benchmark":"flores","model":"qwen3-4b","score":30.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-4b","score":32.6,"metric":"percent"},{"benchmark":"mdolly","model":"ministral-3-3b-base","score":61.6,"metric":"percent"},{"benchmark":"marena-hard","model":"ministral-3-3b-base","score":63.7,"metric":"percent"},{"benchmark":"global-mgsm","model":"ministral-3-3b-base","score":49.6,"metric":"percent"},{"benchmark":"flores","model":"ministral-3-3b-base","score":32,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"ministral-3-3b-base","score":30.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-sonnet-4.6","score":59.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-sonnet-4.5","score":51,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2","score":64.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-4.6","score":79.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3-pro","score":78,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-sonnet-4.6","score":72.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-sonnet-4.5","score":61.4,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-opus-4.6","score":72.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-sonnet-4.6","score":91.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-sonnet-4.5","score":86.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-sonnet-4.6","score":97.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-sonnet-4.5","score":98,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-sonnet-4.6","score":61.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-sonnet-4.5","score":43.8,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-sonnet-4.6","score":74.7,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-sonnet-4.5","score":43.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-4.6","score":33.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-4.5","score":17.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4.6","score":40,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4.5","score":30.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.2","score":36.6,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-sonnet-4.6","score":49,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-sonnet-4.5","score":33.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-opus-4.6","score":53,"metric":"avg@3"},{"benchmark":"financeagent-v1.1","model":"claude-sonnet-4.6","score":63.3,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"claude-sonnet-4.5","score":54.5,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"claude-opus-4.6","score":60.1,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"claude-opus-4.5","score":58.8,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gemini-3-pro","score":55.2,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.2","score":59,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"claude-sonnet-4.6","score":1633,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"claude-sonnet-4.5","score":1276,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gemini-3-pro","score":1201,"metric":"elo"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4.6","score":58.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-sonnet-4.6","score":89.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-sonnet-4.6","score":74.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-sonnet-4.5","score":63.4,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"claude-sonnet-4.6","score":75.6,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"claude-sonnet-4.5","score":68.9,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-sonnet-4.6","score":89.3,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-sonnet-4.5","score":89.5,"metric":"percent"},{"benchmark":"hle","model":"gemini-3.1-pro","score":44.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemini-3.1-pro","score":51.4,"metric":"avg@3"},{"benchmark":"arc-agi-2","model":"gemini-3.1-pro","score":77.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3.1-pro","score":94.3,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"gemini-3.1-pro","score":68.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3.1-pro","score":80.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-3.1-pro","score":54.2,"metric":"percent"},{"benchmark":"livecodebench-pro","model":"gemini-3.1-pro","score":2887,"metric":"elo"},{"benchmark":"scicode","model":"gemini-3.1-pro","score":59,"metric":"percent"},{"benchmark":"apex-agents","model":"gemini-3.1-pro","score":33.5,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"gemini-3.1-pro","score":1317,"metric":"elo"},{"benchmark":"tau2-retail","model":"gemini-3.1-pro","score":90.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-3.1-pro","score":99.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3.1-pro","score":69.2,"metric":"percent"},{"benchmark":"browsecomp","model":"gemini-3.1-pro","score":85.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-pro","score":80.5,"metric":"percent"},{"benchmark":"mmmlu","model":"gemini-3.1-pro","score":92.6,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-3.1-pro","score":84.9,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-3.1-pro","score":26.3,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"gemini-3-pro","score":56.9,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-3-pro","score":43.3,"metric":"percent"},{"benchmark":"apex-agents","model":"gemini-3-pro","score":18.4,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-3-pro","score":77,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4.6","score":33.2,"metric":"avg@3"},{"benchmark":"terminal-bench-terminus","model":"claude-sonnet-4.6","score":59.1,"metric":"percent"},{"benchmark":"scicode","model":"claude-sonnet-4.6","score":47,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"claude-sonnet-4.6","score":84.9,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"claude-opus-4.6","score":65.4,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.6","score":52,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-4.6","score":29.8,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"claude-opus-4.6","score":84,"metric":"percent"},{"benchmark":"livecodebench-pro","model":"gpt-5.2","score":2393,"metric":"elo"},{"benchmark":"scicode","model":"gpt-5.2","score":52,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.2","score":23,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.2","score":83.8,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"gpt-5.2-codex","score":54,"metric":"percent"},{"benchmark":"terminal-bench-terminus","model":"gpt-5.3-codex","score":64.7,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.2-codex","score":27.6,"metric":"percent"},{"benchmark":"apex-agents","model":"gemini-3-flash","score":24,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.1-codex","score":20.6,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5-codex","score":20,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-4.5","score":18.4,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5","score":18.3,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.1","score":17.5,"metric":"percent"},{"benchmark":"apex-agents","model":"grok-4","score":15.2,"metric":"percent"},{"benchmark":"apex-agents","model":"kimi-k2.5","score":14.4,"metric":"percent"},{"benchmark":"apex-agents","model":"minimax-m2.5","score":6.2,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-oss-120b","score":4.7,"metric":"percent"},{"benchmark":"apex-agents","model":"kimi-k2-thinking","score":4,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-4.7","score":3.1,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-4.6","score":3,"metric":"percent"},{"model":"claude-opus-4.6","benchmark":"terminal-bench-2.0","score":65.4},{"model":"claude-opus-4.5","benchmark":"terminal-bench-2.0","score":59.8},{"model":"claude-sonnet-4.5","benchmark":"terminal-bench-2.0","score":51},{"model":"gemini-3-pro","benchmark":"terminal-bench-2.0","score":56.2},{"model":"gpt-5.2","benchmark":"terminal-bench-2.0","score":64.7},{"model":"claude-opus-4.6","benchmark":"swe-bench-verified","score":80.8},{"model":"claude-opus-4.5","benchmark":"swe-bench-verified","score":80.9},{"model":"claude-sonnet-4.5","benchmark":"swe-bench-verified","score":77.2},{"model":"gemini-3-pro","benchmark":"swe-bench-verified","score":76.2},{"model":"gpt-5.2","benchmark":"swe-bench-verified","score":80},{"model":"claude-opus-4.6","benchmark":"osworld","score":72.7},{"model":"claude-opus-4.5","benchmark":"osworld","score":66.3},{"model":"claude-sonnet-4.5","benchmark":"osworld","score":61.4},{"model":"claude-opus-4.6","benchmark":"tau2-retail","score":91.9},{"model":"claude-opus-4.5","benchmark":"tau2-retail","score":88.9},{"model":"claude-sonnet-4.5","benchmark":"tau2-retail","score":86.2},{"model":"gemini-3-pro","benchmark":"tau2-retail","score":85.3},{"model":"gpt-5.2","benchmark":"tau2-retail","score":82},{"model":"claude-opus-4.6","benchmark":"tau2-telecom","score":99.3},{"model":"claude-opus-4.5","benchmark":"tau2-telecom","score":98.2},{"model":"claude-sonnet-4.5","benchmark":"tau2-telecom","score":98},{"model":"gemini-3-pro","benchmark":"tau2-telecom","score":98},{"model":"gpt-5.2","benchmark":"tau2-telecom","score":98.7},{"model":"claude-opus-4.6","benchmark":"mcp-atlas","score":59.5},{"model":"claude-opus-4.5","benchmark":"mcp-atlas","score":62.3},{"model":"claude-sonnet-4.5","benchmark":"mcp-atlas","score":43.8},{"model":"gemini-3-pro","benchmark":"mcp-atlas","score":54.1},{"model":"gpt-5.2","benchmark":"mcp-atlas","score":60.6},{"model":"claude-opus-4.6","benchmark":"browsecomp","score":84},{"model":"claude-opus-4.5","benchmark":"browsecomp","score":67.8},{"model":"claude-sonnet-4.5","benchmark":"browsecomp","score":43.9},{"model":"gemini-deepresearch","benchmark":"browsecomp","score":59.2},{"model":"gpt-5.2","benchmark":"browsecomp","score":77.9},{"model":"claude-opus-4.6","benchmark":"hle","score":40},{"model":"claude-opus-4.5","benchmark":"hle","score":30.8},{"model":"claude-sonnet-4.5","benchmark":"hle","score":17.7},{"model":"gemini-3-pro","benchmark":"hle","score":37.5},{"model":"gpt-5.2","benchmark":"hle","score":36.6},{"model":"claude-opus-4.6","benchmark":"hle-with-tools","score":53.1},{"model":"claude-opus-4.5","benchmark":"hle-with-tools","score":43.4},{"model":"claude-sonnet-4.5","benchmark":"hle-with-tools","score":33.6},{"model":"gemini-3-pro","benchmark":"hle-with-tools","score":45.8},{"model":"gpt-5.2","benchmark":"hle-with-tools","score":50},{"model":"claude-opus-4.6","benchmark":"financeagent","score":60.7},{"model":"claude-opus-4.5","benchmark":"financeagent","score":55.9},{"model":"claude-sonnet-4.5","benchmark":"financeagent","score":54.2},{"model":"gemini-3-pro","benchmark":"financeagent","score":44.1},{"model":"gpt-5.1","benchmark":"financeagent","score":56.6},{"model":"claude-opus-4.6","benchmark":"gdpval-aa-elo","score":1606},{"model":"claude-opus-4.5","benchmark":"gdpval-aa-elo","score":1416},{"model":"claude-sonnet-4.5","benchmark":"gdpval-aa-elo","score":1277},{"model":"gemini-3-pro","benchmark":"gdpval-aa-elo","score":1195},{"model":"gpt-5.2","benchmark":"gdpval-aa-elo","score":1462},{"model":"claude-opus-4.6","benchmark":"arc-agi-2","score":68.8},{"model":"claude-opus-4.5","benchmark":"arc-agi-2","score":37.6},{"model":"claude-sonnet-4.5","benchmark":"arc-agi-2","score":13.6},{"model":"gemini-3-pro","benchmark":"arc-agi-2","score":45.1},{"model":"gpt-5.2","benchmark":"arc-agi-2","score":54.2},{"model":"claude-opus-4.6","benchmark":"gpqa-diamond","score":91.3},{"model":"claude-opus-4.5","benchmark":"gpqa-diamond","score":87},{"model":"claude-sonnet-4.5","benchmark":"gpqa-diamond","score":83.4},{"model":"gemini-3-pro","benchmark":"gpqa-diamond","score":91.9},{"model":"gpt-5.2","benchmark":"gpqa-diamond","score":93.2},{"model":"claude-opus-4.6","benchmark":"mmmu-pro","score":73.9},{"model":"claude-opus-4.5","benchmark":"mmmu-pro","score":70.6},{"model":"claude-sonnet-4.5","benchmark":"mmmu-pro","score":63.4},{"model":"gemini-3-pro","benchmark":"mmmu-pro","score":81},{"model":"gpt-5.2","benchmark":"mmmu-pro","score":79.5},{"model":"claude-opus-4.6","benchmark":"mmmu-pro-with-tools","score":77.3},{"model":"claude-opus-4.5","benchmark":"mmmu-pro-with-tools","score":73.9},{"model":"claude-sonnet-4.5","benchmark":"mmmu-pro-with-tools","score":68.9},{"model":"gpt-5.2","benchmark":"mmmu-pro-with-tools","score":80.4},{"model":"claude-opus-4.6","benchmark":"mmmlu","score":91.1},{"model":"claude-opus-4.5","benchmark":"mmmlu","score":90.8},{"model":"claude-sonnet-4.5","benchmark":"mmmlu","score":89.5},{"model":"gemini-3-pro","benchmark":"mmmlu","score":91.8},{"model":"gpt-5.2","benchmark":"mmmlu","score":89.6},{"model":"gpt-5.3-codex","benchmark":"terminal-bench-2.0","score":77.3},{"model":"gpt-5.2-codex","benchmark":"terminal-bench-2.0","score":64},{"model":"gpt-5.2","benchmark":"terminal-bench-2.0","score":62.2},{"model":"gpt-5.3-codex","benchmark":"osworld-verified","score":64.7},{"model":"gpt-5.2-codex","benchmark":"osworld-verified","score":38.2},{"model":"gpt-5.2","benchmark":"osworld-verified","score":37.9},{"model":"gpt-5.3-codex","benchmark":"swe-bench-pro-public","score":56.8},{"model":"gpt-5.2-codex","benchmark":"swe-bench-pro-public","score":56.4},{"model":"gpt-5.2","benchmark":"swe-bench-pro-public","score":55.6},{"model":"gpt-5.3-codex","benchmark":"gdpval","score":70.9},{"model":"gpt-5.2","benchmark":"gdpval","score":70.9},{"model":"gpt-5.3-codex","benchmark":"cybersecurity-capture-the-flag-challenges","score":77.6},{"model":"gpt-5.2-codex","benchmark":"cybersecurity-capture-the-flag-challenges","score":67.4},{"model":"gpt-5.2","benchmark":"cybersecurity-capture-the-flag-challenges","score":67.7},{"model":"gpt-5.3-codex","benchmark":"swe-lancer-diamond","score":81.4},{"model":"gpt-5.2-codex","benchmark":"swe-lancer-diamond","score":76},{"model":"gpt-5.2","benchmark":"swe-lancer-diamond","score":74.6},{"benchmark":"mmlu-pro","model":"gpt-5-mini","score":83.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-a22b","score":84.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-122b-a10b","score":86.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-27b","score":86.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-35b-a3b","score":85.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-5-mini","score":93.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-oss-120b","score":91,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-235b-a22b","score":93.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-122b-a10b","score":94,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-27b","score":93.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-35b-a3b","score":93.3,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-5-mini","score":82.2,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-oss-120b","score":76.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-235b-a22b","score":92.1,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-122b-a10b","score":91.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-27b","score":90.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-35b-a3b","score":90.2,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5-mini","score":58.6,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-oss-120b","score":54.6,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-235b-a22b","score":64.9,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-122b-a10b","score":67.1,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-27b","score":65.6,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-35b-a3b","score":63.4,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-5-mini","score":93.9,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-120b","score":88.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-235b-a22b","score":87.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-122b-a10b","score":93.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-27b","score":95,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-35b-a3b","score":91.9,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5-mini","score":75.4,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-235b-a22b","score":51.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-122b-a10b","score":76.1,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-27b","score":76.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-35b-a3b","score":70.2,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5-mini","score":59,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-oss-120b","score":45.3,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-235b-a22b","score":50.2,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-122b-a10b","score":61.5,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-27b","score":60.8,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-35b-a3b","score":60,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5-mini","score":68,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-235b-a22b","score":60,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-122b-a10b","score":66.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-27b","score":66.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-35b-a3b","score":58.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5-mini","score":56.8,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-oss-120b","score":48.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-235b-a22b","score":54.8,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-122b-a10b","score":60.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-27b","score":60.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-35b-a3b","score":59,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5-mini","score":19.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-oss-120b","score":14.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-235b-a22b","score":18.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-122b-a10b","score":25.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-27b","score":24.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-35b-a3b","score":22.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-mini","score":82.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-122b-a10b","score":86.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-27b","score":85.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-35b-a3b","score":84.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5-mini","score":89.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-oss-120b","score":90,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-235b-a22b","score":85.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.5-122b-a10b","score":91.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.5-27b","score":92,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.5-35b-a3b","score":89,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5-mini","score":84.2,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-oss-120b","score":90,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-235b-a22b","score":89.5,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-122b-a10b","score":90.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-27b","score":89.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-35b-a3b","score":89.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-mini","score":72,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-120b","score":62,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-122b-a10b","score":72,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-27b","score":72.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-35b-a3b","score":69.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-122b-a10b","score":49.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-27b","score":41.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-35b-a3b","score":40.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini","score":80.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":82.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b","score":75.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-122b-a10b","score":78.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-27b","score":80.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-35b-a3b","score":74.6,"metric":"percent"},{"benchmark":"codeforces","model":"gpt-5-mini","score":2160,"metric":"ELO"},{"benchmark":"codeforces","model":"gpt-oss-120b","score":2157,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen3-235b-a22b","score":2146,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen3.5-122b-a10b","score":2100,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen3.5-27b","score":1899,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen3.5-35b-a3b","score":2028,"metric":"ELO"},{"benchmark":"ojbench","model":"gpt-5-mini","score":40.4,"metric":"percent"},{"benchmark":"ojbench","model":"gpt-oss-120b","score":41.5,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-235b-a22b","score":32.7,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-122b-a10b","score":39.5,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-27b","score":40.1,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-35b-a3b","score":36,"metric":"percent"},{"benchmark":"fullstackbench","model":"gpt-5-mini","score":30.6,"metric":"percent"},{"benchmark":"fullstackbench","model":"gpt-oss-120b","score":58.9,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3-235b-a22b","score":61.1,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3.5-122b-a10b","score":62.6,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3.5-27b","score":60.1,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3.5-35b-a3b","score":58.1,"metric":"percent"},{"benchmark":"fullstackbench-zh","model":"gpt-5-mini","score":35.2,"metric":"percent"},{"benchmark":"fullstackbench-zh","model":"gpt-oss-120b","score":60.4,"metric":"percent"},{"benchmark":"fullstackbench-zh","model":"qwen3-235b-a22b","score":63.1,"metric":"percent"},{"benchmark":"fullstackbench-zh","model":"qwen3.5-122b-a10b","score":58.7,"metric":"percent"},{"benchmark":"fullstackbench-zh","model":"qwen3.5-27b","score":57.4,"metric":"percent"},{"benchmark":"fullstackbench-zh","model":"qwen3.5-35b-a3b","score":55,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5-mini","score":55.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-235b-a22b","score":54.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-122b-a10b","score":72.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-27b","score":68.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-35b-a3b","score":67.3,"metric":"percent"},{"benchmark":"vitabench","model":"gpt-5-mini","score":13.9,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3-235b-a22b","score":31.6,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-122b-a10b","score":33.6,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-27b","score":41.9,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-35b-a3b","score":31.9,"metric":"percent"},{"benchmark":"deep-planning","model":"gpt-5-mini","score":17.9,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3-235b-a22b","score":17.1,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.5-122b-a10b","score":24.1,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.5-27b","score":22.6,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.5-35b-a3b","score":22.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5-mini","score":35.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-oss-120b","score":19,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.5-122b-a10b","score":47.5,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.5-27b","score":48.5,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.5-35b-a3b","score":47.4,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5-mini","score":48.1,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-oss-120b","score":41.1,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-122b-a10b","score":63.8,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-27b","score":61,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-35b-a3b","score":61,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-5-mini","score":49.5,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-oss-120b","score":42.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"qwen3.5-122b-a10b","score":69.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"qwen3.5-27b","score":62.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"qwen3.5-35b-a3b","score":69.5,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5-mini","score":47.2,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-oss-120b","score":40.4,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.5-122b-a10b","score":60.5,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.5-27b","score":61.1,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.5-35b-a3b","score":57.1,"metric":"percent"},{"benchmark":"seal-0","model":"gpt-5-mini","score":34.2,"metric":"percent"},{"benchmark":"seal-0","model":"gpt-oss-120b","score":45.1,"metric":"percent"},{"benchmark":"seal-0","model":"qwen3.5-122b-a10b","score":44.1,"metric":"percent"},{"benchmark":"seal-0","model":"qwen3.5-27b","score":47.2,"metric":"percent"},{"benchmark":"seal-0","model":"qwen3.5-35b-a3b","score":41.4,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5-mini","score":86.2,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-oss-120b","score":78.2,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-235b-a22b","score":83.4,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-122b-a10b","score":86.7,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-27b","score":85.9,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-35b-a3b","score":85.2,"metric":"percent"},{"benchmark":"mmlu-prox","model":"gpt-5-mini","score":78.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"gpt-oss-120b","score":74.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-235b-a22b","score":77.9,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-122b-a10b","score":82.2,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-27b","score":82.2,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-35b-a3b","score":81,"metric":"percent"},{"benchmark":"nova-63","model":"gpt-5-mini","score":51.9,"metric":"percent"},{"benchmark":"nova-63","model":"gpt-oss-120b","score":51.1,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3-235b-a22b","score":55.4,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.5-122b-a10b","score":58.6,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.5-27b","score":58.1,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.5-35b-a3b","score":57.1,"metric":"percent"},{"benchmark":"include","model":"gpt-5-mini","score":81.8,"metric":"percent"},{"benchmark":"include","model":"gpt-oss-120b","score":74,"metric":"percent"},{"benchmark":"include","model":"qwen3-235b-a22b","score":81,"metric":"percent"},{"benchmark":"include","model":"qwen3.5-122b-a10b","score":82.8,"metric":"percent"},{"benchmark":"include","model":"qwen3.5-27b","score":81.6,"metric":"percent"},{"benchmark":"include","model":"qwen3.5-35b-a3b","score":79.7,"metric":"percent"},{"benchmark":"global-piqa","model":"gpt-5-mini","score":88.5,"metric":"percent"},{"benchmark":"global-piqa","model":"gpt-oss-120b","score":84.1,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-235b-a22b","score":85.7,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.5-122b-a10b","score":88.4,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.5-27b","score":87.5,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.5-35b-a3b","score":86.6,"metric":"percent"},{"benchmark":"polymath","model":"gpt-5-mini","score":67.3,"metric":"percent"},{"benchmark":"polymath","model":"gpt-oss-120b","score":54,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-235b-a22b","score":60.1,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.5-122b-a10b","score":68.9,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.5-27b","score":71.2,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.5-35b-a3b","score":64.4,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gpt-5-mini","score":80.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gpt-oss-120b","score":74.4,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-235b-a22b","score":75.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-122b-a10b","score":78.3,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-27b","score":77.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-35b-a3b","score":76.3,"metric":"percent"},{"benchmark":"maxife","model":"gpt-5-mini","score":85.3,"metric":"percent"},{"benchmark":"maxife","model":"gpt-oss-120b","score":83.7,"metric":"percent"},{"benchmark":"maxife","model":"qwen3-235b-a22b","score":83.2,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.5-122b-a10b","score":87.9,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.5-27b","score":88,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.5-35b-a3b","score":86.6,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-mini","score":79,"metric":"percent"},{"benchmark":"mmmu","model":"claude-sonnet-4.5","score":79.6,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-122b-a10b","score":83.9,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-27b","score":82.3,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-35b-a3b","score":81.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-sonnet-4.5","score":68.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-122b-a10b","score":76.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-27b","score":75,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-35b-a3b","score":75.1,"metric":"percent"},{"benchmark":"mathvision","model":"claude-sonnet-4.5","score":71.1,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-122b-a10b","score":86.2,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-27b","score":86,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-35b-a3b","score":83.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-5-mini","score":79.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-sonnet-4.5","score":79.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-122b-a10b","score":87.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-27b","score":87.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-35b-a3b","score":86.2,"metric":"percent"},{"benchmark":"dynamath","model":"gpt-5-mini","score":81.4,"metric":"percent"},{"benchmark":"dynamath","model":"claude-sonnet-4.5","score":78.8,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-122b-a10b","score":85.9,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-27b","score":87.7,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-35b-a3b","score":85,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5-mini","score":3,"metric":"percent"},{"benchmark":"zerobench","model":"claude-sonnet-4.5","score":4,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-122b-a10b","score":9,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-27b","score":10,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-35b-a3b","score":8,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gpt-5-mini","score":27.3,"metric":"percent"},{"benchmark":"zerobench-sub","model":"claude-sonnet-4.5","score":26.3,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-122b-a10b","score":36.2,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-27b","score":36.2,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-35b-a3b","score":34.1,"metric":"percent"},{"benchmark":"vlmsareblind","model":"gpt-5-mini","score":75.8,"metric":"percent"},{"benchmark":"vlmsareblind","model":"claude-sonnet-4.5","score":85.5,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3-vl-235b-a22b","score":79.5,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.5-122b-a10b","score":96.7,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.5-27b","score":96.9,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.5-35b-a3b","score":97,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5-mini","score":20.9,"metric":"percent"},{"benchmark":"babyvision","model":"claude-sonnet-4.5","score":18.6,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.5-122b-a10b","score":40.2,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.5-27b","score":44.6,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.5-35b-a3b","score":38.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5-mini","score":79,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-sonnet-4.5","score":70.3,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-122b-a10b","score":85.1,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-27b","score":83.7,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-35b-a3b","score":84.1,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-mini","score":74.1,"metric":"percent"},{"benchmark":"mmstar","model":"claude-sonnet-4.5","score":73.8,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-122b-a10b","score":82.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-27b","score":81,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-35b-a3b","score":81.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gpt-5-mini","score":86.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"claude-sonnet-4.5","score":88.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-122b-a10b","score":92.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-27b","score":92.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-35b-a3b","score":91.5,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5-mini","score":56.8,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-sonnet-4.5","score":57.6,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-122b-a10b","score":61.7,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-27b","score":56,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-35b-a3b","score":58.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5-mini","score":63.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-sonnet-4.5","score":59.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-122b-a10b","score":67.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-27b","score":70,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-35b-a3b","score":67.9,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5-mini","score":77,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"claude-sonnet-4.5","score":85.8,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"qwen3.5-122b-a10b","score":89.8,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"qwen3.5-27b","score":88.9,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"qwen3.5-35b-a3b","score":89.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-sonnet-4.5","score":67.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-122b-a10b","score":77.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-27b","score":79.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-35b-a3b","score":77.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-122b-a10b","score":59,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-27b","score":60.2,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-35b-a3b","score":59.5,"metric":"percent"},{"benchmark":"cc-ocr","model":"gpt-5-mini","score":70.8,"metric":"percent"},{"benchmark":"cc-ocr","model":"claude-sonnet-4.5","score":68.1,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-122b-a10b","score":81.8,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-27b","score":81,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-35b-a3b","score":80.7,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-mini","score":88.2,"metric":"percent"},{"benchmark":"ai2d","model":"claude-sonnet-4.5","score":87,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-122b-a10b","score":93.3,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-27b","score":92.9,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-35b-a3b","score":92.6,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5-mini","score":82.1,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-sonnet-4.5","score":76.6,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-122b-a10b","score":92.1,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-27b","score":89.4,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-35b-a3b","score":91,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5-mini","score":54,"metric":"percent"},{"benchmark":"erqa","model":"claude-sonnet-4.5","score":45,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-122b-a10b","score":62,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-27b","score":60.5,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-35b-a3b","score":64.8,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5-mini","score":91,"metric":"percent"},{"benchmark":"countbench","model":"claude-sonnet-4.5","score":90,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-122b-a10b","score":97,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-27b","score":97.8,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-35b-a3b","score":97.8,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-122b-a10b","score":44.5,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-27b","score":41.1,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-35b-a3b","score":42.6,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5-mini","score":80.7,"metric":"percent"},{"benchmark":"embspatialbench","model":"claude-sonnet-4.5","score":71.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-122b-a10b","score":83.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-27b","score":84.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-35b-a3b","score":83.1,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5-mini","score":9,"metric":"percent"},{"benchmark":"refspatialbench","model":"claude-sonnet-4.5","score":2.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-122b-a10b","score":69.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-27b","score":67.7,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-35b-a3b","score":63.5,"metric":"percent"},{"benchmark":"lingoqa","model":"gpt-5-mini","score":62.4,"metric":"percent"},{"benchmark":"lingoqa","model":"claude-sonnet-4.5","score":12.8,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.5-122b-a10b","score":80.8,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.5-27b","score":82,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.5-35b-a3b","score":79.2,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3.5-122b-a10b","score":12.7,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3.5-27b","score":13,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3.5-35b-a3b","score":13.1,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3.5-122b-a10b","score":36.2,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3.5-27b","score":35.4,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3.5-35b-a3b","score":33.4,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3.5-122b-a10b","score":15.4,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3.5-27b","score":15.2,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3.5-35b-a3b","score":14.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5-mini","score":83.5,"metric":"percent"},{"benchmark":"videomme-sub","model":"claude-sonnet-4.5","score":81.1,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.5-122b-a10b","score":87.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.5-27b","score":87,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.5-35b-a3b","score":86.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"claude-sonnet-4.5","score":75.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-122b-a10b","score":83.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-27b","score":82.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-35b-a3b","score":82.5,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5-mini","score":82.5,"metric":"percent"},{"benchmark":"videommmu","model":"claude-sonnet-4.5","score":77.6,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.5-122b-a10b","score":82,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.5-27b","score":82.3,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.5-35b-a3b","score":80.4,"metric":"percent"},{"benchmark":"mlvu","model":"claude-sonnet-4.5","score":72.8,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-122b-a10b","score":87.3,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-27b","score":85.9,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-35b-a3b","score":85.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-122b-a10b","score":76.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-27b","score":74.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-35b-a3b","score":74.8,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-122b-a10b","score":74.4,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-27b","score":73.6,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-35b-a3b","score":71.4,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5-mini","score":69.8,"metric":"percent"},{"benchmark":"mmvu","model":"claude-sonnet-4.5","score":70.6,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-122b-a10b","score":74.7,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-27b","score":73.3,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-35b-a3b","score":72.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-sonnet-4.5","score":36.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-122b-a10b","score":70.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-27b","score":70.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-35b-a3b","score":68.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-122b-a10b","score":58,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-27b","score":56.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-35b-a3b","score":54.5,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.5-122b-a10b","score":66.4,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.5-27b","score":64.2,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.5-35b-a3b","score":71.1,"metric":"percent"},{"benchmark":"tir-bench","model":"gpt-5-mini","score":24.6,"metric":"percent"},{"benchmark":"tir-bench","model":"claude-sonnet-4.5","score":27.6,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3-vl-235b-a22b","score":29.8,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3.5-122b-a10b","score":53.2,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3.5-27b","score":59.8,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3.5-35b-a3b","score":55.5,"metric":"percent"},{"benchmark":"v-star","model":"gpt-5-mini","score":71.7,"metric":"percent"},{"benchmark":"v-star","model":"claude-sonnet-4.5","score":58.6,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.5-122b-a10b","score":93.2,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.5-27b","score":93.7,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.5-35b-a3b","score":92.7,"metric":"percent"},{"benchmark":"slake","model":"gpt-5-mini","score":70.5,"metric":"percent"},{"benchmark":"slake","model":"claude-sonnet-4.5","score":73.6,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-122b-a10b","score":81.6,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-27b","score":80,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-35b-a3b","score":78.7,"metric":"percent"},{"benchmark":"pmc-vqa","model":"gpt-5-mini","score":36.3,"metric":"percent"},{"benchmark":"pmc-vqa","model":"claude-sonnet-4.5","score":55.9,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-122b-a10b","score":63.3,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-27b","score":62.4,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-35b-a3b","score":62,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gpt-5-mini","score":34.4,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"claude-sonnet-4.5","score":54,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-122b-a10b","score":67.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-27b","score":62.4,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-35b-a3b","score":61.4,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-5.2-instant","score":55.4,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-5.3-instant","score":54.1,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gpt-5.2-instant","score":26.8,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gpt-5.3-instant","score":25.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-mythos-preview","score":77.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-mythos-preview","score":93.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-mythos-preview","score":87.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-mythos-preview","score":82,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-mythos-preview","score":94.6,"metric":"percent"},{"benchmark":"hle","model":"claude-mythos-preview","score":56.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-mythos-preview","score":64.7,"metric":"avg@3"},{"benchmark":"browsecomp","model":"claude-mythos-preview","score":86.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-mythos-preview","score":79.6,"metric":"percent"},{"benchmark":"cybergym","model":"claude-mythos-preview","score":83.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-mythos-preview","score":86.1,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-mythos-preview","score":92.7,"metric":"percent"},{"benchmark":"usamo-2026","model":"claude-mythos-preview","score":97.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.7","score":64.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.7","score":87.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.7","score":80.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.7","score":69.4,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.7","score":46.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-opus-4.7","score":54.7,"metric":"avg@3"},{"benchmark":"browsecomp","model":"claude-opus-4.7","score":79.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.7","score":77.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-opus-4.7","score":78,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"claude-opus-4.7","score":64.4,"metric":"percent"},{"benchmark":"cybergym","model":"claude-opus-4.7","score":73.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.7","score":94.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.7","score":82.1,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-opus-4.7","score":91.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-opus-4.7","score":79.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.7","score":75.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.7","score":92,"metric":"percent"},{"benchmark":"usamo-2026","model":"claude-opus-4.7","score":69.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-4.7","score":89.1,"metric":"percent"},{"benchmark":"figqa","model":"claude-opus-4.7","score":78.6,"metric":"percent"},{"benchmark":"vending-bench-2","model":"claude-opus-4.7","score":10937,"metric":"net_worth_mean"},{"benchmark":"gdpval-aa-elo","model":"claude-opus-4.7","score":1753,"metric":"elo"},{"benchmark":"global-mmlu","model":"claude-opus-4.7","score":89.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.8","score":69.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.8","score":88.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.8","score":84.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.8","score":74.6,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.8","score":49.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-opus-4.8","score":57.9,"metric":"avg@3"},{"benchmark":"osworld-verified","model":"claude-opus-4.8","score":83.4,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"claude-opus-4.8","score":1890,"metric":"elo"},{"benchmark":"financeagent-v2","model":"claude-opus-4.8","score":53.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.8","score":93.6,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-opus-4.8","score":84.3,"metric":"percent"},{"benchmark":"chartqa-pro","model":"claude-opus-4.8","score":69.4,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-opus-4.8","score":75.8,"metric":"percent"},{"benchmark":"figqa","model":"claude-opus-4.8","score":80.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.8","score":80.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-opus-4.8","score":82.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.8","score":82.2,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-4.8","score":15.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-4.8","score":93.1,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-opus-4.8","score":59.9,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-opus-4.8","score":55.8,"metric":"percent"},{"benchmark":"global-mmlu","model":"claude-opus-4.8","score":90.4,"metric":"percent"},{"benchmark":"usamo-2026","model":"claude-opus-4.8","score":96.7,"metric":"percent"},{"benchmark":"cybergym","model":"claude-opus-4.8","score":78.8,"metric":"percent"},{"benchmark":"vending-bench-2","model":"claude-opus-4.8","score":5787.43,"metric":"net_worth_mean"},{"benchmark":"swe-bench-pro","model":"claude-fable-5","score":80,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-fable-5","score":95,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-fable-5","score":84.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-fable-5","score":85,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"claude-fable-5","score":1932,"metric":"elo"},{"benchmark":"frontiercode-diamond","model":"claude-fable-5","score":29.3,"metric":"percent"},{"benchmark":"gdp-pdf","model":"claude-fable-5","score":29.8,"metric":"percent"},{"benchmark":"blueprint-bench-2","model":"claude-fable-5","score":38.6,"metric":"percent"},{"benchmark":"automationbench","model":"claude-fable-5","score":17.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-fable-5","score":83.3,"metric":"percent"},{"benchmark":"financeagent-v2","model":"claude-fable-5","score":56.31,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-fable-5","score":61.7,"metric":"percent"},{"benchmark":"vending-bench-2","model":"claude-fable-5","score":5680.26,"metric":"net_worth_mean"},{"benchmark":"swe-bench-pro","model":"claude-mythos-5","score":80.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-mythos-5","score":95.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-mythos-5","score":92.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-mythos-5","score":88,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-mythos-5","score":88,"metric":"percent"},{"benchmark":"hle","model":"claude-mythos-5","score":59,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-mythos-5","score":64.5,"metric":"avg@3"},{"benchmark":"charxiv-rq","model":"claude-mythos-5","score":88.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-mythos-5","score":85,"metric":"percent"},{"benchmark":"critpt","model":"claude-mythos-5","score":28.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-mythos-5","score":94.1,"metric":"percent"},{"benchmark":"usamo-2026","model":"claude-mythos-5","score":99.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-mythos-5","score":94.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-mythos-5","score":87.3,"metric":"percent"},{"benchmark":"chartqa-pro","model":"claude-mythos-5","score":71.6,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-mythos-5","score":85.9,"metric":"percent"},{"benchmark":"figqa","model":"claude-mythos-5","score":88.9,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-mythos-5","score":61.7,"metric":"percent"},{"benchmark":"healthbench","model":"claude-mythos-5","score":62.7,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-mythos-5","score":66,"metric":"percent"},{"benchmark":"global-mmlu","model":"claude-mythos-5","score":93.2,"metric":"percent"},{"benchmark":"cybergym","model":"claude-mythos-5","score":83.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-sonnet-5","score":63.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-sonnet-5","score":85.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-sonnet-5","score":78.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-sonnet-5","score":80.4,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-5","score":43.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-sonnet-5","score":57.4,"metric":"avg@3"},{"benchmark":"osworld-verified","model":"claude-sonnet-5","score":81.2,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-5","score":1618,"metric":"elo"},{"benchmark":"browsecomp","model":"claude-sonnet-5","score":84.7,"metric":"percent"},{"benchmark":"automationbench","model":"claude-sonnet-5","score":13.5,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-sonnet-5","score":57.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-sonnet-5","score":77,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-sonnet-5","score":70.1,"metric":"percent"},{"benchmark":"usamo-2026","model":"claude-sonnet-5","score":79.5,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-sonnet-5","score":54.3,"metric":"percent"},{"benchmark":"cybergym","model":"claude-sonnet-5","score":52.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-5","score":96,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-5","score":79.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-5","score":89.5,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-opus-5","score":59.4,"metric":"percent"},{"benchmark":"deepswe","model":"claude-opus-5","score":68.8,"metric":"percent"},{"benchmark":"frontiercode","model":"claude-opus-5","score":53.4,"metric":"percent"},{"benchmark":"frontierbench","model":"claude-opus-5","score":43.3,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-opus-5","score":90.8,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-5","score":56.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-opus-5","score":64.7,"metric":"avg@3"},{"benchmark":"osworld-2.0","model":"claude-opus-5","score":70.6,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-opus-5","score":59.8,"metric":"percent"},{"benchmark":"healthbench","model":"claude-opus-5","score":67.1,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-5","score":1861,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-opus-5","score":1720,"metric":"elo"},{"benchmark":"automationbench","model":"claude-opus-5","score":26,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-5","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5","score":90.4,"metric":"percent"},{"benchmark":"arc-agi-3","model":"claude-opus-5","score":30.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-5","score":85.8,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-opus-5","score":80.6,"metric":"percent"},{"benchmark":"chartography","model":"claude-opus-5","score":29.6,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-opus-5","score":83,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"claude-fable-5.1","score":52.6,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-fable-5.1","score":55.8,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5.1","score":1853,"metric":"elo"},{"benchmark":"osworld-2.0","model":"claude-fable-5.1","score":77.9,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"claude-fable-5.1","score":41.7,"metric":"percent"},{"benchmark":"hle","model":"claude-fable-5.1","score":60.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-fable-5.1","score":65,"metric":"avg@3"},{"benchmark":"automationbench","model":"claude-fable-5.1","score":31.4,"metric":"percent"},{"benchmark":"cursorbench-3.2","model":"claude-fable-5.1","score":73.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-fable-5.1","score":81.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-fable-5.1","score":89.1,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-fable-5.1","score":54.7,"metric":"percent"},{"benchmark":"deepswe","model":"claude-fable-5.1","score":67.4,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-fable-5.1","score":62.1,"metric":"percent"},{"benchmark":"healthbench","model":"claude-fable-5.1","score":66.7,"metric":"percent"},{"benchmark":"aa-briefcase","model":"claude-fable-5.1","score":1694,"metric":"elo"},{"benchmark":"arc-agi-1","model":"claude-fable-5.1","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5.1","score":90,"metric":"percent"},{"benchmark":"global-mmlu","model":"claude-fable-5.1","score":94,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-fable-5.1","score":77.8,"metric":"percent"},{"benchmark":"chartography","model":"claude-fable-5.1","score":42.6,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-fable-5.1","score":86.2,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-mythos-5.1","score":60.9,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-opus-5.5","score":66.4,"metric":"percent"},{"benchmark":"frontiercode","model":"claude-opus-5.5","score":54.4,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"claude-opus-5.5","score":57.8,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-5.5","score":1846,"metric":"elo"},{"benchmark":"automationbench","model":"claude-opus-5.5","score":40,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-opus-5.5","score":67.7,"metric":"avg@3"},{"benchmark":"hle","model":"claude-opus-5.5","score":64.4,"metric":"avg@3"},{"benchmark":"terminal-bench-science","model":"claude-opus-5.5","score":58.7,"metric":"percent"},{"benchmark":"osworld-2.1","model":"claude-opus-5.5","score":81.8,"metric":"percent"},{"benchmark":"osworld-2.1-strict","model":"claude-opus-5.5","score":48.7,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-opus-5.5","score":89,"metric":"percent"},{"benchmark":"chartography","model":"claude-opus-5.5","score":64.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-5.5","score":89.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-5.5","score":93.9,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-opus-5.5","score":61.4,"metric":"percent"},{"benchmark":"deepswe","model":"claude-opus-5.5","score":74.2,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-opus-5.5","score":65.6,"metric":"percent"},{"benchmark":"aa-briefcase","model":"claude-opus-5.5","score":1822,"metric":"elo"},{"benchmark":"global-mmlu","model":"claude-opus-5.5","score":94.3,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-opus-5.5","score":77.8,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-sonnet-5.5","score":70.6,"metric":"percent"},{"benchmark":"frontiercode","model":"claude-sonnet-5.5","score":46.2,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"claude-sonnet-5.5","score":55.5,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-5.5","score":1844,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-sonnet-5.5","score":1811,"metric":"elo"},{"benchmark":"hle-with-tools","model":"claude-sonnet-5.5","score":64.5,"metric":"avg@3"},{"benchmark":"hle","model":"claude-sonnet-5.5","score":56.9,"metric":"avg@3"},{"benchmark":"osworld-2.1","model":"claude-sonnet-5.5","score":80.1,"metric":"percent"},{"benchmark":"osworld-2.1-strict","model":"claude-sonnet-5.5","score":43.5,"metric":"percent"},{"benchmark":"chartography","model":"claude-sonnet-5.5","score":61.6,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-sonnet-5.5","score":90.2,"metric":"percent"},{"benchmark":"automationbench","model":"claude-sonnet-5.5","score":44.7,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"claude-sonnet-5.5","score":59.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-sonnet-5.5","score":81.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-sonnet-5.5","score":90.3,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-sonnet-5.5","score":54.3,"metric":"percent"},{"benchmark":"deepswe","model":"claude-sonnet-5.5","score":71,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-sonnet-5.5","score":69.2,"metric":"percent"},{"benchmark":"global-mmlu","model":"claude-sonnet-5.5","score":92.1,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-sonnet-5.5","score":77.8,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-haiku-5.5","score":1620,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-haiku-5.5","score":1578,"metric":"elo"},{"benchmark":"hle","model":"claude-haiku-5.5","score":45.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-haiku-5.5","score":57.4,"metric":"avg@3"},{"benchmark":"terminal-bench-4.0","model":"claude-haiku-5.5","score":39.2,"metric":"percent"},{"benchmark":"frontiercode","model":"claude-haiku-5.5","score":46.4,"metric":"percent"},{"benchmark":"chartography","model":"claude-haiku-5.5","score":46.4,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-haiku-5.5","score":86.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-haiku-5.5","score":64.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-haiku-5.5","score":83.7,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-haiku-5.5","score":30.7,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-haiku-5.5","score":64.8,"metric":"percent"},{"benchmark":"global-mmlu","model":"claude-haiku-5.5","score":87.8,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"claude-haiku-5.5","score":20.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.3-codex-spark","score":51.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.3-codex-spark","score":58.4,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.4","score":83,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.4","score":56,"metric":"percent"},{"benchmark":"officeqa","model":"gpt-5.4","score":68.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.4","score":57.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.4","score":75.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.4","score":75,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.4","score":81.2,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.4","score":82.1,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.4","score":0.109,"metric":"edit_distance"},{"benchmark":"webarena-verified","model":"gpt-5.4","score":67.3,"metric":"percent"},{"benchmark":"online-mind2web","model":"gpt-5.4","score":92.8,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.4","score":82.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.4","score":67.2,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.4","score":54.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.4","score":98.9,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.4","score":33,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.4","score":47.6,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.4","score":27.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4","score":92.8,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.4","score":39.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.4","score":52.1,"metric":"avg@3"},{"benchmark":"graphwalks-bfs","model":"gpt-5.4","score":93,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gpt-5.4","score":89.8,"metric":"percent"},{"benchmark":"mrcr-64k-8n","model":"gpt-5.4","score":90.5,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.4","score":86,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4","score":93.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4","score":73.3,"metric":"percent"},{"benchmark":"genebench","model":"gpt-5.4","score":19,"metric":"percent"},{"benchmark":"bixbench","model":"gpt-5.4","score":74,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.4","score":53.2,"metric":"percent"},{"benchmark":"cybergym","model":"gpt-5.4","score":79,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.4-pro","score":82,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.4-pro","score":61.5,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.4-pro","score":89.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.4-pro","score":36.7,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.4-pro","score":38,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.4-pro","score":50,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4-pro","score":94.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.4-pro","score":42.7,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.4-pro","score":58.7,"metric":"avg@3"},{"benchmark":"arc-agi-1","model":"gpt-5.4-pro","score":94.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-pro","score":83.3,"metric":"percent"},{"benchmark":"genebench","model":"gpt-5.4-pro","score":25.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.4-mini","score":54.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.4-mini","score":60,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.4-mini","score":57.7,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.4-mini","score":42.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.4-mini","score":93.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4-mini","score":88,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5.4-mini","score":41.5,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4-mini","score":28.2,"metric":"avg@3"},{"benchmark":"osworld-verified","model":"gpt-5.4-mini","score":72.1,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.4-mini","score":78,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.4-mini","score":76.6,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.4-mini","score":0.1263,"metric":"edit_distance"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.4-mini","score":47.7,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gpt-5.4-mini","score":76.3,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gpt-5.4-mini","score":71.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.4-nano","score":52.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.4-nano","score":46.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.4-nano","score":56.1,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.4-nano","score":35.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.4-nano","score":92.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4-nano","score":82.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5.4-nano","score":37.7,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4-nano","score":24.3,"metric":"avg@3"},{"benchmark":"osworld-verified","model":"gpt-5.4-nano","score":39,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.4-nano","score":69.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.4-nano","score":66.1,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.4-nano","score":0.2419,"metric":"edit_distance"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.4-nano","score":44.2,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gpt-5.4-nano","score":73.4,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gpt-5.4-nano","score":50.8,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.5","score":58.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.5","score":82.7,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.5","score":84.9,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.5","score":60,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.5","score":54.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.5","score":78.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.5","score":81.2,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.5","score":83.2,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.5","score":84.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.5","score":75.3,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.5","score":55.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.5","score":98,"metric":"percent"},{"benchmark":"genebench","model":"gpt-5.5","score":25,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.5","score":51.7,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.5","score":35.4,"metric":"percent"},{"benchmark":"bixbench","model":"gpt-5.5","score":80.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.5","score":93.6,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.5","score":41.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.5","score":52.2,"metric":"avg@3"},{"benchmark":"cybergym","model":"gpt-5.5","score":81.8,"metric":"percent"},{"benchmark":"mrcr-64k-8n","model":"gpt-5.5","score":90,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.5","score":83.1,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.5","score":95,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.5","score":85,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.5-pro","score":82.3,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.5-pro","score":90.1,"metric":"percent"},{"benchmark":"genebench","model":"gpt-5.5-pro","score":33.2,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.5-pro","score":52.4,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.5-pro","score":39.6,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.5-pro","score":43.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.5-pro","score":57.2,"metric":"avg@3"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol","score":52.7,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1747.8,"metric":"elo"},{"benchmark":"swe-bench-pro","model":"gpt-5.6-sol","score":64.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-sol","score":72.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-sol","score":88.8,"metric":"percent"},{"benchmark":"genebench-pro","model":"gpt-5.6-sol","score":28.7,"metric":"percent"},{"benchmark":"lifescibench","model":"gpt-5.6-sol","score":59.9,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gpt-5.6-sol","score":60.5,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-5.6-sol","score":62.6,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.6-sol","score":90.4,"metric":"percent"},{"benchmark":"benchcad","model":"gpt-5.6-sol","score":70.6,"metric":"percent"},{"benchmark":"cybersecurity-capture-the-flag-challenges","model":"gpt-5.6-sol","score":96.7,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"gpt-5.6-sol","score":71.2,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.6-sol","score":73.5,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-5.6-sol","score":33.7,"metric":"percent"},{"benchmark":"posttrainbench-lite","model":"gpt-5.6-sol","score":50.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.6-sol","score":83,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.6-sol","score":84.6,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-5.6-sol","score":30.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.6-sol","score":94.6,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.6-sol","score":89,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.6-sol","score":83,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-sol","score":18.1,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.6-sol","score":58,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"gpt-5.6-sol","score":90.7,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"gpt-5.6-sol","score":77.1,"metric":"percent"},{"benchmark":"arc-agi-3","model":"gpt-5.6-sol","score":7.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-sol","score":92.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-sol","score":97.5,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-5.6-sol","score":37.3,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"gpt-5.6-sol","score":22.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5.6-sol","score":76.9,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-5.6-sol","score":47.5,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-5.6-sol","score":60.6,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-5.6-sol","score":65.7,"metric":"percent"},{"benchmark":"sre-bench","model":"gpt-5.6-sol","score":55.9,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-terra","score":50.4,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-terra","score":1593,"metric":"elo"},{"benchmark":"swe-bench-pro","model":"gpt-5.6-terra","score":63.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-terra","score":69.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-terra","score":87.4,"metric":"percent"},{"benchmark":"genebench-pro","model":"gpt-5.6-terra","score":23.3,"metric":"percent"},{"benchmark":"lifescibench","model":"gpt-5.6-terra","score":56,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gpt-5.6-terra","score":57.7,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-5.6-terra","score":50.2,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.6-terra","score":87.5,"metric":"percent"},{"benchmark":"benchcad","model":"gpt-5.6-terra","score":62.3,"metric":"percent"},{"benchmark":"cybersecurity-capture-the-flag-challenges","model":"gpt-5.6-terra","score":91.8,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"gpt-5.6-terra","score":57.7,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.6-terra","score":52.9,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-5.6-terra","score":23.2,"metric":"percent"},{"benchmark":"posttrainbench-lite","model":"gpt-5.6-terra","score":51.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.6-terra","score":80.7,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.6-terra","score":82,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-5.6-terra","score":24.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.6-terra","score":92.9,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.6-terra","score":84.9,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.6-terra","score":68.3,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-terra","score":15.2,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.6-terra","score":53.1,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"gpt-5.6-terra","score":76.9,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"gpt-5.6-terra","score":71.2,"metric":"percent"},{"benchmark":"arc-agi-3","model":"gpt-5.6-terra","score":0.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-luna","score":50.3,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-luna","score":1591.8,"metric":"elo"},{"benchmark":"swe-bench-pro","model":"gpt-5.6-luna","score":62.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-luna","score":67.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-luna","score":84.7,"metric":"percent"},{"benchmark":"genebench-pro","model":"gpt-5.6-luna","score":10.8,"metric":"percent"},{"benchmark":"lifescibench","model":"gpt-5.6-luna","score":51.2,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gpt-5.6-luna","score":55.7,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-5.6-luna","score":45.6,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.6-luna","score":83.3,"metric":"percent"},{"benchmark":"benchcad","model":"gpt-5.6-luna","score":63.1,"metric":"percent"},{"benchmark":"cybersecurity-capture-the-flag-challenges","model":"gpt-5.6-luna","score":85.2,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"gpt-5.6-luna","score":48.9,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.6-luna","score":33.2,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-5.6-luna","score":12.4,"metric":"percent"},{"benchmark":"posttrainbench-lite","model":"gpt-5.6-luna","score":29.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.6-luna","score":78.4,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.6-luna","score":79.5,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-5.6-luna","score":22.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.6-luna","score":92.3,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.6-luna","score":78.6,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.6-luna","score":58.5,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-luna","score":14.9,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.6-luna","score":53.4,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"gpt-5.6-luna","score":81.3,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"gpt-5.6-luna","score":51.2,"metric":"percent"},{"benchmark":"arc-agi-3","model":"gpt-5.6-luna","score":0.18,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-5.6-cyber","score":32.1,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.6-cyber","score":73,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra","score":59.3,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-6-astra","score":72.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-6-astra","score":92.7,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-6-astra","score":41.4,"metric":"percent"},{"benchmark":"benchcad","model":"gpt-6-astra","score":95.9,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-6-astra","score":91.5,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-6-astra","score":57.9,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-6-astra","score":74.1,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-6-astra","score":64.5,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-6-astra","score":53.3,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"gpt-6-astra","score":64.6,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-6-astra","score":97.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-6-astra","score":96,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-6-astra","score":57.2,"metric":"avg@3"},{"benchmark":"genebench-pro","model":"gpt-6-astra","score":37.1,"metric":"percent"},{"benchmark":"lifescibench","model":"gpt-6-astra","score":60.3,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gpt-6-astra","score":63.4,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-6-astra","score":100,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-6-astra","score":42.4,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"gpt-6-astra","score":85.4,"metric":"percent"},{"benchmark":"sre-bench","model":"gpt-6-astra","score":88,"metric":"percent"},{"benchmark":"arc-agi-3","model":"gpt-6-astra","score":99.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-astra","score":95,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-astra","score":98.5,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-6-sol","score":33.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-sol","score":56.4,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-6-sol","score":49.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-6-sol","score":68.8,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-6-sol","score":64.4,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"gpt-6-sol","score":27.6,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-6-sol","score":28,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-6-luna","score":20.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-luna","score":50.9,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-6-luna","score":42.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-6-luna","score":66.6,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-6-luna","score":52.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-6.1-sol","score":75.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-6.1-sol","score":32,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-6.1-sol","score":36.1,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-6.1-sol","score":71.4,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"gpt-6.1-sol","score":57,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol","score":53.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-fable-5","score":48.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5","score":55.5,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"claude-opus-5","score":70.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-fable-5","score":87.3,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-5","score":26.9,"metric":"percent"},{"benchmark":"benchcad","model":"gpt-5.6-sol","score":83.3,"metric":"percent"},{"benchmark":"benchcad","model":"claude-fable-5.1","score":84.3,"metric":"percent"},{"benchmark":"benchcad","model":"claude-fable-5","score":67.5,"metric":"percent"},{"benchmark":"benchcad","model":"claude-opus-5","score":82.1,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-fable-5","score":87.4,"metric":"percent"},{"benchmark":"openscore-string-quartets","model":"gpt-6-astra","score":0.84,"metric":"score"},{"benchmark":"openscore-string-quartets","model":"gpt-5.6-sol","score":0.19,"metric":"score"},{"benchmark":"openai-internal-design-tasks","model":"gpt-6-astra","score":50,"metric":"percent"},{"benchmark":"openai-internal-design-tasks","model":"gpt-5.6-sol","score":47.4,"metric":"percent"},{"benchmark":"openai-internal-design-tasks","model":"claude-fable-5","score":35.8,"metric":"percent"},{"benchmark":"openai-internal-data-science-tasks","model":"gpt-6-astra","score":40.9,"metric":"percent"},{"benchmark":"openai-internal-data-science-tasks","model":"gpt-5.6-sol","score":30.5,"metric":"percent"},{"benchmark":"openai-internal-data-science-tasks","model":"claude-fable-5","score":34.7,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-fable-5","score":44.5,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-opus-5","score":52.6,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gemini-3.8-flash","score":19.1,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-fable-5","score":69.9,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-5","score":73.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.8-flash","score":73.8,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-fable-5.1","score":63.6,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-fable-5","score":64.9,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-opus-5","score":63.6,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gemini-3.8-flash","score":56.3,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-fable-5.1","score":50.9,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-fable-5","score":53.5,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gemini-3.8-flash","score":43.6,"metric":"percent"},{"benchmark":"openai-internal-db-migration-tasks","model":"gpt-6-astra","score":63.9,"metric":"percent"},{"benchmark":"openai-internal-db-migration-tasks","model":"gpt-5.6-sol","score":42.7,"metric":"percent"},{"benchmark":"openai-internal-db-migration-tasks","model":"claude-fable-5.1","score":57.8,"metric":"percent"},{"benchmark":"openai-internal-db-migration-tasks","model":"claude-fable-5","score":50.3,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"claude-fable-5","score":21.4,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"claude-opus-5","score":30,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"claude-fable-5.1","score":87.8,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"claude-fable-5","score":90.2,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"claude-opus-5","score":73.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-fable-5.1","score":93.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-fable-5","score":92.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-5","score":93.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3.8-flash","score":95.3,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-fable-5","score":63.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-opus-5","score":63.6,"metric":"avg@3"},{"benchmark":"genebench-pro","model":"gpt-5.6-sol","score":32.3,"metric":"percent"},{"benchmark":"medchembench-internal","model":"gpt-6-astra","score":49.3,"metric":"percent"},{"benchmark":"medchembench-internal","model":"gpt-5.6-sol","score":47.4,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-fable-5.1","score":58.1,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-fable-5","score":60.9,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-opus-5","score":56.4,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gemini-3.8-flash","score":52.1,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.6-sol","score":78.5,"metric":"percent"},{"benchmark":"exploitbench","model":"claude-opus-5","score":70,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-5.6-sol","score":30.3,"metric":"percent"},{"benchmark":"exploitgym","model":"claude-fable-5.1","score":30.4,"metric":"percent"},{"benchmark":"exploitgym","model":"claude-fable-5","score":28.4,"metric":"percent"},{"benchmark":"exploitgym","model":"claude-opus-5","score":22,"metric":"percent"},{"benchmark":"exploitbench-2026-jun-aug","model":"gpt-6-astra","score":39,"metric":"percent"},{"benchmark":"exploitbench-2026-jun-aug","model":"gpt-5.6-sol","score":5.5,"metric":"percent"},{"benchmark":"sre-bench","model":"claude-opus-5","score":12.5,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"gpt-5.6-sol","score":79.1,"metric":"percent"},{"benchmark":"openai-internal-cua-safety","model":"gpt-6-astra","score":2.4,"metric":"percent"},{"benchmark":"openai-internal-cua-safety","model":"gpt-5.6-sol","score":22,"metric":"percent"},{"benchmark":"openai-internal-cua-safety","model":"claude-fable-5.1","score":9.5,"metric":"percent"},{"benchmark":"openai-internal-cua-safety","model":"claude-fable-5","score":18.3,"metric":"percent"},{"benchmark":"openai-internal-cua-safety","model":"claude-opus-5","score":11.5,"metric":"percent"},{"benchmark":"openai-internal-cua-safety-autoreview","model":"gpt-6-astra","score":1.8,"metric":"percent"},{"benchmark":"openai-internal-cua-safety-autoreview","model":"gpt-5.6-sol","score":4.3,"metric":"percent"},{"benchmark":"openai-internal-circumvention","model":"gpt-6-astra","score":0,"metric":"percent"},{"benchmark":"openai-internal-circumvention","model":"gpt-5.6-sol","score":0.29,"metric":"percent"},{"benchmark":"exploitgym-honeypot","model":"gpt-6-astra","score":0,"metric":"percent"},{"benchmark":"exploitgym-honeypot","model":"gpt-5.6-sol","score":48.2,"metric":"percent"},{"benchmark":"impossible-exploitgym","model":"gpt-6-astra","score":100,"metric":"percent"},{"benchmark":"openai-internal-hallucination","model":"gpt-6-astra","score":4.2,"metric":"percent"},{"benchmark":"openai-internal-hallucination","model":"gpt-5.6-sol","score":12.2,"metric":"percent"},{"benchmark":"mrcr-512k-8n","model":"gpt-6-astra","score":100,"metric":"percent"},{"benchmark":"mrcr-512k-8n","model":"gpt-5.6-sol","score":91.5,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"gpt-6-astra","score":96.3,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"gpt-5.6-sol","score":73.8,"metric":"percent"},{"benchmark":"arc-agi-3","model":"gpt-5.6-sol","score":7.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5","score":89.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5","score":98.5,"metric":"percent"},{"benchmark":"hle","model":"glm-5.1","score":31,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.6-plus","score":28.8,"metric":"avg@3"},{"benchmark":"hle","model":"minimax-m2.7","score":28,"metric":"avg@3"},{"benchmark":"hle","model":"kimi-k2.5-thinking","score":31.5,"metric":"avg@3"},{"benchmark":"hle","model":"claude-opus-4.6","score":36.7,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-3.1-pro","score":45,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"glm-5.1","score":52.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"qwen3.6-plus","score":50.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"kimi-k2.5-thinking","score":51.8,"metric":"avg@3"},{"benchmark":"aime-2026-i","model":"glm-5.1","score":95.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"glm-5","score":95.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-plus","score":95.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minimax-m2.7","score":89.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v3.2-thinking","score":95.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.5-thinking","score":94.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.6","score":95.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3.1-pro","score":98.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.4","score":98.7,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-5.1","score":94,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-5","score":96.9,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.6-plus","score":94.6,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"minimax-m2.7","score":81,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"kimi-k2.5-thinking","score":91.1,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"claude-opus-4.6","score":96.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gemini-3.1-pro","score":94.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5.4","score":95.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"glm-5.1","score":82.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"glm-5","score":82.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.6-plus","score":87.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"minimax-m2.7","score":72.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v3.2-thinking","score":79.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"kimi-k2.5-thinking","score":81.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-opus-4.6","score":84.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemini-3.1-pro","score":87.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.4","score":91.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"glm-5.1","score":83.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"glm-5","score":82.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.6-plus","score":83.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"minimax-m2.7","score":66.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.6","score":75.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3.1-pro","score":81,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.4","score":91.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5.1","score":86.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5","score":86,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-plus","score":90.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m2.7","score":87,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4","score":92,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"glm-5.1","score":58.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"glm-5","score":55.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.6-plus","score":56.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"minimax-m2.7","score":56.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"kimi-k2.5-thinking","score":53.8,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-opus-4.6","score":57.3,"metric":"percent"},{"benchmark":"nl2repo","model":"glm-5.1","score":42.7,"metric":"percent"},{"benchmark":"nl2repo","model":"glm-5","score":35.9,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.6-plus","score":37.9,"metric":"percent"},{"benchmark":"nl2repo","model":"minimax-m2.7","score":39.8,"metric":"percent"},{"benchmark":"nl2repo","model":"kimi-k2.5-thinking","score":32,"metric":"percent"},{"benchmark":"nl2repo","model":"claude-opus-4.6","score":49.8,"metric":"percent"},{"benchmark":"nl2repo","model":"gemini-3.1-pro","score":33.4,"metric":"percent"},{"benchmark":"nl2repo","model":"gpt-5.4","score":41.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-5.1","score":63.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.6-plus","score":61.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v3.2-thinking","score":39.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2.5-thinking","score":50.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3.1-pro","score":68.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-5.1","score":69,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"minimax-m2.7","score":57,"metric":"percent"},{"benchmark":"cybergym","model":"glm-5.1","score":68.7,"metric":"percent"},{"benchmark":"cybergym","model":"glm-5","score":48.3,"metric":"percent"},{"benchmark":"cybergym","model":"claude-opus-4.6","score":66.6,"metric":"percent"},{"benchmark":"cybergym","model":"gemini-3.1-pro","score":38.8,"metric":"percent"},{"benchmark":"cybergym","model":"gpt-5.4","score":66.3,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5.1","score":68,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5","score":62,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"glm-5.1","score":79.3,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"glm-5","score":75.9,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"kimi-k2.5-thinking","score":74.9,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"gemini-3.1-pro","score":85.9,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"gpt-5.4","score":82.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5.1","score":71.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5","score":69.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.6-plus","score":74.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"minimax-m2.7","score":48.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v3.2-thinking","score":62.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k2.5-thinking","score":63.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.6","score":73.8,"metric":"percent"},{"benchmark":"toolathlon","model":"glm-5.1","score":40.7,"metric":"percent"},{"benchmark":"toolathlon","model":"glm-5","score":38,"metric":"percent"},{"benchmark":"toolathlon","model":"qwen3.6-plus","score":39.8,"metric":"percent"},{"benchmark":"toolathlon","model":"minimax-m2.7","score":46.3,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v3.2-thinking","score":35.2,"metric":"percent"},{"benchmark":"toolathlon","model":"kimi-k2.5-thinking","score":27.8,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-opus-4.6","score":47.2,"metric":"percent"},{"benchmark":"toolathlon","model":"gemini-3.1-pro","score":48.8,"metric":"percent"},{"benchmark":"vending-bench-2","model":"glm-5.1","score":5634.41,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"glm-5","score":4432.12,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"qwen3.6-plus","score":5114.87,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"deepseek-v3.2-thinking","score":1034,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"kimi-k2.5-thinking","score":1198.46,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"claude-opus-4.6","score":8017.59,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"gemini-3.1-pro","score":911.21,"metric":"net_worth_mean"},{"benchmark":"vending-bench-2","model":"gpt-5.4","score":6144.18,"metric":"net_worth_mean"},{"benchmark":"hle","model":"glm-5.2","score":40.5,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.7-max","score":41.4,"metric":"avg@3"},{"benchmark":"hle","model":"minimax-m3","score":37,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-pro","score":37.7,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"glm-5.2","score":54.7,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"qwen3.7-max","score":53.5,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-pro","score":48.2,"metric":"avg@3"},{"benchmark":"critpt","model":"glm-5.2","score":20.9,"metric":"percent"},{"benchmark":"critpt","model":"glm-5.1","score":4.6,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.7-max","score":13.4,"metric":"percent"},{"benchmark":"critpt","model":"minimax-m3","score":3.7,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v4-pro","score":12.9,"metric":"percent"},{"benchmark":"critpt","model":"claude-opus-4.8","score":20.9,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5.5","score":27.1,"metric":"percent"},{"benchmark":"critpt","model":"gemini-3.1-pro","score":17.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"glm-5.2","score":99.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.7-max","score":97,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-pro","score":94.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.8","score":95.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.5","score":98.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-5.2","score":94.4,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.7-max","score":95,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"minimax-m3","score":84.4,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"deepseek-v4-pro","score":94.4,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"claude-opus-4.8","score":96.5,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5.5","score":96.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"glm-5.2","score":92.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.7-max","score":97.1,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"minimax-m3","score":84.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-pro","score":95.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-opus-4.8","score":96.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.5","score":96.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"glm-5.2","score":91,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.7-max","score":90,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-pro","score":89.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.8","score":83.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5.2","score":91.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.7-max","score":90,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m3","score":93,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-pro","score":90.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"glm-5.2","score":62.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.7-max","score":60.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"minimax-m3","score":59,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-pro","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-opus-4.8","score":69.2,"metric":"percent"},{"benchmark":"nl2repo","model":"glm-5.2","score":48.9,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.7-max","score":47.2,"metric":"percent"},{"benchmark":"nl2repo","model":"minimax-m3","score":42.1,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-pro","score":35.5,"metric":"percent"},{"benchmark":"nl2repo","model":"claude-opus-4.8","score":69.7,"metric":"percent"},{"benchmark":"nl2repo","model":"gpt-5.5","score":50.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.2","score":46.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.1","score":18,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.7-max","score":18,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"minimax-m3","score":20,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro","score":8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-4.8","score":58,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.5","score":70,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.1-pro","score":10,"metric":"percent"},{"benchmark":"programbench","model":"glm-5.2","score":63.7,"metric":"percent"},{"benchmark":"programbench","model":"glm-5.1","score":50.9,"metric":"percent"},{"benchmark":"programbench","model":"deepseek-v4-pro","score":47.8,"metric":"percent"},{"benchmark":"programbench","model":"claude-opus-4.8","score":71.9,"metric":"percent"},{"benchmark":"programbench","model":"gpt-5.5","score":70.8,"metric":"percent"},{"benchmark":"programbench","model":"gemini-3.1-pro","score":39.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.2","score":81,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.1","score":63.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.7-max","score":75,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minimax-m3","score":65,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro","score":64,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.8","score":85,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.5","score":84,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.1-pro","score":74,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.2","score":82.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.1","score":69,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.8","score":78.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.5","score":83.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.1-pro","score":70.7,"metric":"percent"},{"benchmark":"frontierswe","model":"glm-5.2","score":74.4,"metric":"percent"},{"benchmark":"frontierswe","model":"glm-5.1","score":30.5,"metric":"percent"},{"benchmark":"frontierswe","model":"deepseek-v4-pro","score":29,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-opus-4.8","score":75.1,"metric":"percent"},{"benchmark":"frontierswe","model":"gpt-5.5","score":72.6,"metric":"percent"},{"benchmark":"frontierswe","model":"gemini-3.1-pro","score":39.6,"metric":"percent"},{"benchmark":"posttrainbench","model":"glm-5.2","score":34.3,"metric":"percent"},{"benchmark":"posttrainbench","model":"glm-5.1","score":20.1,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-4.8","score":37.2,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.5","score":28.4,"metric":"percent"},{"benchmark":"posttrainbench","model":"gemini-3.1-pro","score":21.6,"metric":"percent"},{"benchmark":"swe-marathon","model":"glm-5.2","score":13,"metric":"percent"},{"benchmark":"swe-marathon","model":"glm-5.1","score":1,"metric":"percent"},{"benchmark":"swe-marathon","model":"claude-opus-4.8","score":26,"metric":"percent"},{"benchmark":"swe-marathon","model":"gpt-5.5","score":12,"metric":"percent"},{"benchmark":"swe-marathon","model":"gemini-3.1-pro","score":4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5.2","score":76.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.7-max","score":76.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"minimax-m3","score":74.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-pro","score":73.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.8","score":77.8,"metric":"percent"},{"benchmark":"toolathlon","model":"glm-5.2","score":48.2,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v4-pro","score":52.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.3","score":88.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k3","score":88.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro-0813","score":87.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-max","score":86.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-fable-5","score":88,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"glm-5.3","score":28.3,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"glm-5.2","score":4.6,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"kimi-k3","score":17.4,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-opus-4.8","score":21.1,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-fable-5","score":33.7,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"gpt-5.6-sol","score":34.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.3","score":66.9,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k3","score":67.5,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro-0813","score":62.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-max","score":56.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-fable-5","score":69.7,"metric":"percent"},{"benchmark":"nl2repo","model":"glm-5.3","score":58,"metric":"percent"},{"benchmark":"nl2repo","model":"kimi-k3","score":58,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-pro-0813","score":61.1,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.8-max","score":55.9,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"glm-5.3","score":19,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"glm-5.2","score":9.5,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"kimi-k3","score":17.5,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"qwen3.8-max","score":10.5,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"claude-opus-4.8","score":15.5,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"claude-fable-5","score":33,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"gpt-5.6-sol","score":23,"metric":"percent"},{"benchmark":"frontierswe","model":"glm-5.3","score":78.1,"metric":"percent"},{"benchmark":"frontierswe","model":"glm-5.2","score":67.5,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-opus-4.8","score":66.5,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-fable-5","score":88.2,"metric":"percent"},{"benchmark":"swe-marathon-v1.1","model":"glm-5.3","score":42.5,"metric":"percent"},{"benchmark":"swe-marathon-v1.1","model":"glm-5.2","score":19.4,"metric":"percent"},{"benchmark":"swe-marathon-v1.1","model":"kimi-k3","score":48.1,"metric":"percent"},{"benchmark":"swe-marathon-v1.1","model":"claude-opus-4.8","score":48.8,"metric":"percent"},{"benchmark":"swe-marathon-v1.1","model":"claude-fable-5","score":33.1,"metric":"percent"},{"benchmark":"swe-marathon-v1.1","model":"gpt-5.6-sol","score":42.5,"metric":"percent"},{"benchmark":"posttrainbench","model":"glm-5.3","score":39.8,"metric":"percent"},{"benchmark":"posttrainbench","model":"glm-5.2","score":31.7,"metric":"percent"},{"benchmark":"posttrainbench","model":"kimi-k3","score":32,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-4.8","score":32.9,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-fable-5","score":41.8,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.6-sol","score":36.2,"metric":"percent"},{"benchmark":"cybergym","model":"glm-5.3","score":84.5,"metric":"percent"},{"benchmark":"cybergym","model":"glm-5.2","score":77.2,"metric":"percent"},{"benchmark":"cybergym","model":"kimi-k3","score":80,"metric":"percent"},{"benchmark":"cybergym","model":"deepseek-v4-pro-0813","score":83.3,"metric":"percent"},{"benchmark":"cybergym","model":"qwen3.8-max","score":78.5,"metric":"percent"},{"benchmark":"cybergym","model":"claude-opus-4.8","score":78.1,"metric":"percent"},{"benchmark":"cybergym","model":"claude-fable-5","score":83.8,"metric":"percent"},{"benchmark":"cybergym","model":"gpt-5.6-sol","score":83.6,"metric":"percent"},{"benchmark":"exploitbench","model":"glm-5.3","score":54.4,"metric":"percent"},{"benchmark":"exploitbench","model":"glm-5.2","score":24.4,"metric":"percent"},{"benchmark":"exploitbench","model":"kimi-k3","score":32.2,"metric":"percent"},{"benchmark":"exploitbench","model":"qwen3.8-max","score":28.8,"metric":"percent"},{"benchmark":"exploitbench","model":"claude-opus-4.8","score":40,"metric":"percent"},{"benchmark":"exploitbench","model":"claude-fable-5","score":78,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.6-sol","score":76.5,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"glm-5.3","score":73,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"glm-5.2","score":59.9,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"kimi-k3","score":76.5,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-pro-0813","score":74.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.8-max","score":72.5,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"claude-opus-4.8","score":76.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"claude-fable-5","score":74.7,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gpt-5.6-sol","score":74.9,"metric":"percent"},{"benchmark":"automationbench","model":"glm-5.3","score":48.2,"metric":"percent"},{"benchmark":"automationbench","model":"glm-5.2","score":26.2,"metric":"percent"},{"benchmark":"automationbench","model":"kimi-k3","score":46.7,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-pro-0813","score":43.2,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.8-max","score":39.8,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-4.8","score":41,"metric":"percent"},{"benchmark":"automationbench","model":"claude-fable-5","score":46.2,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-sol","score":45.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"glm-5.3","score":28.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"glm-5.2","score":23.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"kimi-k3","score":27.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4-pro-0813","score":25.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.8-max","score":27,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.8","score":25.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-fable-5","score":23.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol","score":28.6,"metric":"percent"},{"benchmark":"hle-with-tools","model":"glm-5.3","score":62.5,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"kimi-k3","score":59.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-pro-0813","score":60,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"qwen3.8-max","score":56.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-fable-5","score":63.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.6-sol","score":64.5,"metric":"avg@3"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.3","score":1769,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.2","score":1508,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"kimi-k3","score":1682,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4-pro-0813","score":1590,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.8-max","score":1739,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-4.8","score":1588,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5","score":1743,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1730,"metric":"elo"},{"benchmark":"terminal-bench-2.1","model":"glm-5.3-flash","score":84.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash-vision-exp","score":83.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.7-flash","score":85.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.3-flash","score":63.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-flash-vision-exp","score":59.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.7-flash","score":65.3,"metric":"percent"},{"benchmark":"nl2repo","model":"glm-5.3-flash","score":56.3,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-flash-vision-exp","score":57.7,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"glm-5.3-flash","score":78.4,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-flash-vision-exp","score":75.9,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gpt-5.6-terra","score":74.9,"metric":"percent"},{"benchmark":"automationbench","model":"glm-5.3-flash","score":48.8,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-flash-vision-exp","score":38.8,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-terra","score":37.2,"metric":"percent"},{"benchmark":"automationbench","model":"gemini-3.7-flash","score":52.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"glm-5.3-flash","score":26.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"glm-5.2","score":20.4,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4-flash-vision-exp","score":27.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.8","score":27,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-terra","score":28,"metric":"percent"},{"benchmark":"hle-with-tools","model":"glm-5.3-flash","score":55.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-flash-vision-exp","score":55.1,"metric":"avg@3"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.3-flash","score":1773,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.2","score":1504,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4-flash-vision-exp","score":1675,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-4.8","score":1582,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-terra","score":1571,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.7-flash","score":1527,"metric":"elo"},{"benchmark":"officeqa-pro","model":"glm-5.3-flash","score":62.4,"metric":"percent"},{"benchmark":"officeqa-pro","model":"deepseek-v4-flash-vision-exp","score":57.9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-opus-4.8","score":48.9,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"glm-5.3-flash","score":89.4,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"deepseek-v4-flash-vision-exp","score":80.4,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-opus-4.8","score":89.9,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-5.6-terra","score":88,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gemini-3.7-flash","score":88.7,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"glm-5.3-flash","score":78,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"deepseek-v4-flash-vision-exp","score":64.3,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-opus-4.8","score":75,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"gpt-5.6-terra","score":68,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"gemini-3.7-flash","score":65,"metric":"percent"},{"benchmark":"babyvision","model":"glm-5.3-flash","score":53.4,"metric":"percent"},{"benchmark":"babyvision","model":"deepseek-v4-flash-vision-exp","score":35.1,"metric":"percent"},{"benchmark":"babyvision","model":"claude-opus-4.8","score":46.8,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.6-terra","score":61.6,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3.7-flash","score":70.9,"metric":"percent"},{"benchmark":"mvbench","model":"glm-5.3-flash","score":77.8,"metric":"percent"},{"benchmark":"mvbench","model":"deepseek-v4-flash-vision-exp","score":69.4,"metric":"percent"},{"benchmark":"mvbench","model":"claude-opus-4.8","score":67.1,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-5.6-terra","score":75,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-3.7-flash","score":82.2,"metric":"percent"},{"benchmark":"mmvu","model":"glm-5.3-flash","score":80.5,"metric":"percent"},{"benchmark":"mmvu","model":"deepseek-v4-flash-vision-exp","score":72.7,"metric":"percent"},{"benchmark":"mmvu","model":"claude-opus-4.8","score":67.4,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5.6-terra","score":75.8,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-3.7-flash","score":82.3,"metric":"percent"},{"benchmark":"osworld-2.0","model":"glm-5.3-flash","score":59.1,"metric":"percent"},{"benchmark":"osworld-2.0","model":"deepseek-v4-flash-vision-exp","score":54.9,"metric":"percent"},{"benchmark":"osworld-2.0","model":"claude-opus-4.8","score":54.8,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gemini-3.7-flash","score":47.9,"metric":"percent"},{"benchmark":"vision2web","model":"glm-5.3-flash","score":77.8,"metric":"percent"},{"benchmark":"vision2web","model":"deepseek-v4-flash-vision-exp","score":67.6,"metric":"percent"},{"benchmark":"vision2web","model":"claude-opus-4.8","score":76.1,"metric":"percent"},{"benchmark":"vision2web","model":"gpt-5.6-terra","score":67.5,"metric":"percent"},{"benchmark":"vision2web","model":"gemini-3.7-flash","score":76.5,"metric":"percent"},{"benchmark":"mmlu","model":"glm-5-base","score":88.3,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v4-flash-base","score":88.5,"metric":"percent"},{"benchmark":"mmlu","model":"glm-5.3-flash-base","score":88.1,"metric":"percent"},{"benchmark":"bbh","model":"glm-5-base","score":87.4,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v4-flash-base","score":84.9,"metric":"percent"},{"benchmark":"bbh","model":"glm-5.3-flash-base","score":86.6,"metric":"percent"},{"benchmark":"hellaswag","model":"glm-5-base","score":88.1,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v4-flash-base","score":85.3,"metric":"percent"},{"benchmark":"hellaswag","model":"glm-5.3-flash-base","score":87.1,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-5-base","score":34.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-base","score":29.9,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-5.3-flash-base","score":37.6,"metric":"percent"},{"benchmark":"simpleqa","model":"glm-5-base","score":36,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v4-flash-base","score":31.2,"metric":"percent"},{"benchmark":"simpleqa","model":"glm-5.3-flash-base","score":33.5,"metric":"percent"},{"benchmark":"design2code","model":"glm-5v-turbo","score":94.8,"metric":"percent"},{"benchmark":"design2code","model":"kimi-k2.5-thinking","score":91.3,"metric":"percent"},{"benchmark":"design2code","model":"claude-opus-4.6","score":77.3,"metric":"percent"},{"benchmark":"flame-react-eval","model":"glm-5v-turbo","score":93.8,"metric":"percent"},{"benchmark":"flame-react-eval","model":"kimi-k2.5-thinking","score":88.8,"metric":"percent"},{"benchmark":"flame-react-eval","model":"claude-opus-4.6","score":98.8,"metric":"percent"},{"benchmark":"vision2web","model":"glm-5v-turbo","score":31,"metric":"percent"},{"benchmark":"vision2web","model":"kimi-k2.5-thinking","score":33.2,"metric":"percent"},{"benchmark":"vision2web","model":"claude-opus-4.6","score":43.5,"metric":"percent"},{"benchmark":"imagemining","model":"glm-5v-turbo","score":30.7,"metric":"percent"},{"benchmark":"imagemining","model":"kimi-k2.5-thinking","score":24.4,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"glm-5v-turbo","score":51.9,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"kimi-k2.5-thinking","score":42.9,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"claude-opus-4.6","score":35.9,"metric":"percent"},{"benchmark":"mmsearch","model":"glm-5v-turbo","score":72.9,"metric":"percent"},{"benchmark":"mmsearch","model":"kimi-k2.5-thinking","score":58.7,"metric":"percent"},{"benchmark":"mmsearch","model":"claude-opus-4.6","score":63.8,"metric":"percent"},{"benchmark":"mmsearch-plus","model":"glm-5v-turbo","score":30,"metric":"percent"},{"benchmark":"mmsearch-plus","model":"kimi-k2.5-thinking","score":25.6,"metric":"percent"},{"benchmark":"mmsearch-plus","model":"claude-opus-4.6","score":25.6,"metric":"percent"},{"benchmark":"simplevqa","model":"glm-5v-turbo","score":78.2,"metric":"percent"},{"benchmark":"simplevqa","model":"kimi-k2.5-thinking","score":71.5,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-opus-4.6","score":63.2,"metric":"percent"},{"benchmark":"v-star","model":"glm-5v-turbo","score":89,"metric":"percent"},{"benchmark":"v-star","model":"kimi-k2.5-thinking","score":84.3,"metric":"percent"},{"benchmark":"v-star","model":"claude-opus-4.6","score":66.5,"metric":"percent"},{"benchmark":"osworld","model":"glm-5v-turbo","score":62.3,"metric":"percent"},{"benchmark":"osworld","model":"kimi-k2.5-thinking","score":63.3,"metric":"percent"},{"benchmark":"osworld","model":"claude-opus-4.6","score":72.2,"metric":"percent"},{"benchmark":"androidworld","model":"glm-5v-turbo","score":75.7,"metric":"percent"},{"benchmark":"androidworld","model":"kimi-k2.5-thinking","score":43.1,"metric":"percent"},{"benchmark":"androidworld","model":"claude-opus-4.6","score":62,"metric":"percent"},{"benchmark":"webvoyager","model":"glm-5v-turbo","score":88.5,"metric":"percent"},{"benchmark":"webvoyager","model":"kimi-k2.5-thinking","score":84.3,"metric":"percent"},{"benchmark":"webvoyager","model":"claude-opus-4.6","score":88,"metric":"percent"},{"benchmark":"cc-bench-v2-backend","model":"glm-5v-turbo","score":22.8,"metric":"percent"},{"benchmark":"cc-bench-v2-backend","model":"glm-5-turbo","score":20.5,"metric":"percent"},{"benchmark":"cc-bench-v2-backend","model":"kimi-k2.5-thinking","score":25.3,"metric":"percent"},{"benchmark":"cc-bench-v2-backend","model":"claude-opus-4.6","score":26.9,"metric":"percent"},{"benchmark":"cc-bench-v2-frontend","model":"glm-5v-turbo","score":68.4,"metric":"percent"},{"benchmark":"cc-bench-v2-frontend","model":"glm-5-turbo","score":69.4,"metric":"percent"},{"benchmark":"cc-bench-v2-frontend","model":"kimi-k2.5-thinking","score":62.3,"metric":"percent"},{"benchmark":"cc-bench-v2-frontend","model":"claude-opus-4.6","score":75.9,"metric":"percent"},{"benchmark":"cc-bench-v2-repo-exploration","model":"glm-5v-turbo","score":72.2,"metric":"percent"},{"benchmark":"cc-bench-v2-repo-exploration","model":"glm-5-turbo","score":68.9,"metric":"percent"},{"benchmark":"cc-bench-v2-repo-exploration","model":"kimi-k2.5-thinking","score":66.7,"metric":"percent"},{"benchmark":"cc-bench-v2-repo-exploration","model":"claude-opus-4.6","score":74.4,"metric":"percent"},{"benchmark":"pinchbench-best","model":"glm-5v-turbo","score":87,"metric":"percent"},{"benchmark":"pinchbench-best","model":"glm-5-turbo","score":86.5,"metric":"percent"},{"benchmark":"pinchbench-best","model":"kimi-k2.5-thinking","score":84.8,"metric":"percent"},{"benchmark":"pinchbench-best","model":"claude-opus-4.6","score":93.3,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"glm-5v-turbo","score":80.7,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"glm-5-turbo","score":81.1,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"kimi-k2.5-thinking","score":79.2,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"claude-opus-4.6","score":82.9,"metric":"percent"},{"benchmark":"claweval-pass3","model":"glm-5v-turbo","score":57.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"glm-5-turbo","score":51,"metric":"percent"},{"benchmark":"claweval-pass3","model":"kimi-k2.5-thinking","score":52.9,"metric":"percent"},{"benchmark":"claweval-pass3","model":"claude-opus-4.6","score":66.3,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"glm-5v-turbo","score":75,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"glm-5-turbo","score":72.1,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"kimi-k2.5-thinking","score":73.1,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"claude-opus-4.6","score":77.9,"metric":"percent"},{"benchmark":"zclawbench","model":"glm-5v-turbo","score":57.6,"metric":"percent"},{"benchmark":"zclawbench","model":"glm-5-turbo","score":60.6,"metric":"percent"},{"benchmark":"zclawbench","model":"kimi-k2.5-thinking","score":49.1,"metric":"percent"},{"benchmark":"zclawbench","model":"claude-opus-4.6","score":62.3,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v3.2-base","score":80.1,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v4-flash-base","score":82.6,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v4-pro-base","score":83.1,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3.2-base","score":87.8,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v4-flash-base","score":88.7,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v4-pro-base","score":90.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3.2-base","score":87.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v4-flash-base","score":89.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v4-pro-base","score":90.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.2-base","score":65.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-flash-base","score":68.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-pro-base","score":73.5,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v3.2-base","score":87.9,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v4-flash-base","score":88.8,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v4-pro-base","score":90.3,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3.2-base","score":90.4,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v4-flash-base","score":92.1,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v4-pro-base","score":93.1,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v3.2-base","score":88.9,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v4-flash-base","score":90.4,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v4-pro-base","score":90.8,"metric":"percent"},{"benchmark":"multiloko","model":"deepseek-v3.2-base","score":38.7,"metric":"percent"},{"benchmark":"multiloko","model":"deepseek-v4-flash-base","score":42.2,"metric":"percent"},{"benchmark":"multiloko","model":"deepseek-v4-pro-base","score":51.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v3.2-base","score":28.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-flash-base","score":30.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-pro-base","score":55.2,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3.2-base","score":45,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v4-flash-base","score":46.5,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v4-pro-base","score":53.9,"metric":"percent"},{"benchmark":"facts-parametric","model":"deepseek-v3.2-base","score":27.1,"metric":"percent"},{"benchmark":"facts-parametric","model":"deepseek-v4-flash-base","score":33.9,"metric":"percent"},{"benchmark":"facts-parametric","model":"deepseek-v4-pro-base","score":62.6,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v3.2-base","score":83.3,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v4-flash-base","score":82.8,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v4-pro-base","score":85.6,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3.2-base","score":87.6,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v4-flash-base","score":86.9,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v4-pro-base","score":87.5,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v3.2-base","score":88.2,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v4-flash-base","score":88.6,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v4-pro-base","score":88.7,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v3.2-base","score":86.4,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v4-flash-base","score":85.7,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v4-pro-base","score":88,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v3.2-base","score":78.9,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v4-flash-base","score":79.5,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v4-pro-base","score":81.5,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v3.2-base","score":83.5,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v4-flash-base","score":82.2,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v4-pro-base","score":85.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-v3.2-base","score":63.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v4-flash-base","score":56.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v4-pro-base","score":59.2,"metric":"pass@1"},{"benchmark":"humaneval","model":"deepseek-v3.2-base","score":62.8,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v4-flash-base","score":69.5,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v4-pro-base","score":76.8,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3.2-base","score":91.1,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v4-flash-base","score":90.8,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v4-pro-base","score":92.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3.2-base","score":60.5,"metric":"percent"},{"benchmark":"math","model":"deepseek-v4-flash-base","score":57.4,"metric":"percent"},{"benchmark":"math","model":"deepseek-v4-pro-base","score":64.5,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v3.2-base","score":81.3,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v4-flash-base","score":85.7,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v4-pro-base","score":84.4,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v3.2-base","score":92.6,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v4-flash-base","score":93.6,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v4-pro-base","score":90.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v3.2-base","score":40.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v4-flash-base","score":44.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v4-pro-base","score":51.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.6","score":89.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.4","score":87.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3.1-pro","score":91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2.6-thinking","score":87.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-5.1","score":86,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-pro-thinking-max","score":87.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-opus-4.6","score":46.2,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.4","score":45.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-3.1-pro","score":75.6,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"kimi-k2.6-thinking","score":36.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"glm-5.1","score":38.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-pro-thinking-max","score":57.9,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"claude-opus-4.6","score":76.4,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"gpt-5.4","score":76.8,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"gemini-3.1-pro","score":85.9,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"kimi-k2.6-thinking","score":75.9,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"glm-5.1","score":75,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v4-pro-thinking-max","score":84.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4","score":93,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.6-thinking","score":90.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-pro-thinking-max","score":90.1,"metric":"percent"},{"benchmark":"hle","model":"kimi-k2.6-thinking","score":36.4,"metric":"avg@3"},{"benchmark":"hle","model":"glm-5.1","score":34.7,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-pro-thinking-max","score":37.7,"metric":"avg@3"},{"benchmark":"livecodebench","model":"claude-opus-4.6","score":88.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3.1-pro","score":91.7,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2.6-thinking","score":89.6,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-pro-thinking-max","score":93.5,"metric":"percent"},{"benchmark":"codeforces","model":"gpt-5.4","score":3168,"metric":"ELO"},{"benchmark":"codeforces","model":"gemini-3.1-pro","score":3052,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v4-pro-thinking-max","score":3206,"metric":"ELO"},{"benchmark":"hmmt-feb-2026","model":"claude-opus-4.6","score":96.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.4","score":97.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemini-3.1-pro","score":94.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"kimi-k2.6-thinking","score":92.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"glm-5.1","score":89.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-pro-thinking-max","score":95.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2.6-thinking","score":86,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-pro-thinking-max","score":89.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"claude-opus-4.6","score":34.5,"metric":"percent"},{"benchmark":"matharena-apex","model":"gpt-5.4","score":54.1,"metric":"percent"},{"benchmark":"matharena-apex","model":"gemini-3.1-pro","score":60.9,"metric":"percent"},{"benchmark":"matharena-apex","model":"kimi-k2.6-thinking","score":24,"metric":"percent"},{"benchmark":"matharena-apex","model":"glm-5.1","score":11.5,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-pro-thinking-max","score":38.3,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"claude-opus-4.6","score":85.9,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"gpt-5.4","score":78.1,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"gemini-3.1-pro","score":89.1,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"kimi-k2.6-thinking","score":75.5,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"glm-5.1","score":72.4,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-pro-thinking-max","score":90.2,"metric":"percent"},{"benchmark":"mrcr-1m","model":"claude-opus-4.6","score":92.9,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-3.1-pro","score":76.3,"metric":"percent"},{"benchmark":"mrcr-1m","model":"deepseek-v4-pro-thinking-max","score":83.5,"metric":"percent"},{"benchmark":"corpusqa","model":"claude-opus-4.6","score":71.7,"metric":"percent"},{"benchmark":"corpusqa","model":"gemini-3.1-pro","score":53.8,"metric":"percent"},{"benchmark":"corpusqa","model":"deepseek-v4-pro-thinking-max","score":62,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2.6-thinking","score":66.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v4-pro-thinking-max","score":67.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.6-thinking","score":80.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-pro-thinking-max","score":80.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"kimi-k2.6-thinking","score":58.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-pro-thinking-max","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.6","score":77.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2.6-thinking","score":76.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.1","score":73.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-pro-thinking-max","score":76.2,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-opus-4.6","score":83.7,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2.6-thinking","score":83.2,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5.1","score":79.3,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-pro-thinking-max","score":83.4,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5.4","score":52,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemini-3.1-pro","score":51.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"kimi-k2.6-thinking","score":54,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"glm-5.1","score":50.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-pro-thinking-max","score":48.2,"metric":"avg@3"},{"benchmark":"gdpval-aa-elo","model":"claude-opus-4.6","score":1619,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gpt-5.4","score":1674,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gemini-3.1-pro","score":1314,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"kimi-k2.6-thinking","score":1482,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"glm-5.1","score":1535,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"deepseek-v4-pro-thinking-max","score":1554,"metric":"elo"},{"benchmark":"mcp-atlas","model":"kimi-k2.6-thinking","score":66.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-pro-thinking-max","score":73.6,"metric":"percent"},{"benchmark":"toolathlon","model":"kimi-k2.6-thinking","score":50,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v4-pro-thinking-max","score":51.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-flash","score":83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-flash-thinking","score":86.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-flash-thinking-max","score":86.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-pro","score":82.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-pro-thinking","score":87.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-flash","score":23.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-flash-thinking","score":28.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-flash-thinking-max","score":34.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-pro","score":45,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-pro-thinking","score":46.2,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v4-flash","score":71.5,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v4-flash-thinking","score":73.2,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v4-flash-thinking-max","score":78.9,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v4-pro","score":75.8,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v4-pro-thinking","score":77.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash","score":71.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash-thinking","score":87.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash-thinking-max","score":88.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-pro","score":72.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-pro-thinking","score":89.1,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v4-flash","score":8.1,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-flash-thinking","score":29.4,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-flash-thinking-max","score":34.8,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-pro","score":7.7,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-pro-thinking","score":34.5,"metric":"avg@3"},{"benchmark":"livecodebench","model":"deepseek-v4-flash","score":55.2,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-thinking","score":88.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-thinking-max","score":91.6,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-pro","score":56.8,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-pro-thinking","score":89.8,"metric":"percent"},{"benchmark":"codeforces","model":"deepseek-v4-flash-thinking","score":2816,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v4-flash-thinking-max","score":3052,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v4-pro-thinking","score":2919,"metric":"ELO"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-flash","score":40.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-flash-thinking","score":91.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-flash-thinking-max","score":94.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-pro","score":31.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-pro-thinking","score":94,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-flash","score":41.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-flash-thinking","score":85.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-flash-thinking-max","score":88.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-pro","score":35.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-pro-thinking","score":88,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-flash","score":1,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-flash-thinking","score":19.1,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-flash-thinking-max","score":33,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-pro","score":0.4,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-pro-thinking","score":27.4,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-flash","score":9.3,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-flash-thinking","score":72.1,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-flash-thinking-max","score":85.7,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-pro","score":9.2,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-pro-thinking","score":85.5,"metric":"percent"},{"benchmark":"mrcr-1m","model":"deepseek-v4-flash","score":37.5,"metric":"percent"},{"benchmark":"mrcr-1m","model":"deepseek-v4-flash-thinking","score":76.9,"metric":"percent"},{"benchmark":"mrcr-1m","model":"deepseek-v4-flash-thinking-max","score":78.7,"metric":"percent"},{"benchmark":"mrcr-1m","model":"deepseek-v4-pro","score":44.7,"metric":"percent"},{"benchmark":"mrcr-1m","model":"deepseek-v4-pro-thinking","score":83.3,"metric":"percent"},{"benchmark":"corpusqa","model":"deepseek-v4-flash","score":15.5,"metric":"percent"},{"benchmark":"corpusqa","model":"deepseek-v4-flash-thinking","score":59.3,"metric":"percent"},{"benchmark":"corpusqa","model":"deepseek-v4-flash-thinking-max","score":60.5,"metric":"percent"},{"benchmark":"corpusqa","model":"deepseek-v4-pro","score":35.6,"metric":"percent"},{"benchmark":"corpusqa","model":"deepseek-v4-pro-thinking","score":56.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v4-flash","score":49.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v4-flash-thinking","score":56.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v4-flash-thinking-max","score":56.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v4-pro","score":59.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v4-pro-thinking","score":63.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-flash","score":73.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-flash-thinking","score":78.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-flash-thinking-max","score":79,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-pro","score":73.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-pro-thinking","score":79.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-flash","score":49.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-flash-thinking","score":52.3,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-flash-thinking-max","score":52.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-pro","score":52.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-pro-thinking","score":54.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-flash","score":69.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-flash-thinking","score":70.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-flash-thinking-max","score":73.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-pro","score":69.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-pro-thinking","score":74.1,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-flash-thinking","score":53.5,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-flash-thinking-max","score":73.2,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-pro-thinking","score":80.4,"metric":"percent"},{"benchmark":"hle-with-tools","model":"deepseek-v4-flash-thinking","score":40.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-flash-thinking-max","score":45.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-pro-thinking","score":44.7,"metric":"avg@3"},{"benchmark":"mcp-atlas","model":"deepseek-v4-flash","score":64,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-flash-thinking","score":67.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-flash-thinking-max","score":69,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-pro","score":69.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-pro-thinking","score":74.2,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"deepseek-v4-flash-thinking-max","score":1395,"metric":"elo"},{"benchmark":"toolathlon","model":"deepseek-v4-flash","score":40.7,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v4-flash-thinking","score":43.5,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v4-flash-thinking-max","score":47.8,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v4-pro","score":46.3,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v4-pro-thinking","score":49,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash-0731","score":82.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash-thinking-max","score":61.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro-thinking-max","score":72.1,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-flash-0731","score":54.2,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-flash-thinking-max","score":39.4,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-pro-thinking-max","score":38.5,"metric":"percent"},{"benchmark":"cybergym","model":"deepseek-v4-flash-0731","score":76.7,"metric":"percent"},{"benchmark":"cybergym","model":"deepseek-v4-flash-thinking-max","score":38.7,"metric":"percent"},{"benchmark":"cybergym","model":"deepseek-v4-pro-thinking-max","score":52.7,"metric":"percent"},{"benchmark":"cybergym","model":"claude-opus-4.8","score":83.1,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-flash-0731","score":54.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-flash-thinking-max","score":7.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro-thinking-max","score":12.8,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-flash-0731","score":70.3,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-flash-thinking-max","score":49.7,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-pro-thinking-max","score":55.9,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4-flash-0731","score":25.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4-flash-thinking-max","score":15.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4-pro-thinking-max","score":16.5,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-flash-0731","score":25.1,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-flash-thinking-max","score":10.8,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-pro-thinking-max","score":12.8,"metric":"percent"},{"benchmark":"automationbench","model":"glm-5.2","score":12.9,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-4.8","score":27.2,"metric":"percent"},{"benchmark":"dsbench-fullstack","model":"deepseek-v4-flash-0731","score":68.7,"metric":"percent"},{"benchmark":"dsbench-fullstack","model":"deepseek-v4-flash-thinking-max","score":37,"metric":"percent"},{"benchmark":"dsbench-fullstack","model":"deepseek-v4-pro-thinking-max","score":41.8,"metric":"percent"},{"benchmark":"dsbench-fullstack","model":"glm-5.2","score":61.8,"metric":"percent"},{"benchmark":"dsbench-fullstack","model":"claude-opus-4.8","score":71.6,"metric":"percent"},{"benchmark":"dsbench-hard","model":"deepseek-v4-flash-0731","score":59.6,"metric":"percent"},{"benchmark":"dsbench-hard","model":"deepseek-v4-flash-thinking-max","score":25.8,"metric":"percent"},{"benchmark":"dsbench-hard","model":"deepseek-v4-pro-thinking-max","score":31.1,"metric":"percent"},{"benchmark":"dsbench-hard","model":"glm-5.2","score":54.5,"metric":"percent"},{"benchmark":"dsbench-hard","model":"claude-opus-4.8","score":71.7,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v4-pro-0813","score":42.7,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-flash-0731","score":37.8,"metric":"avg@3"},{"benchmark":"hle","model":"kimi-k3","score":43.5,"metric":"avg@3"},{"benchmark":"hle","model":"claude-fable-5","score":53.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-flash-0731","score":51.5,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"kimi-k3","score":56,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-fable-5","score":63,"metric":"avg@3"},{"benchmark":"nl2repo","model":"deepseek-v4-pro-0813","score":61.5,"metric":"percent"},{"benchmark":"cybergym","model":"claude-opus-4.8","score":78.3,"metric":"percent"},{"benchmark":"cybergym","model":"claude-fable-5","score":83.1,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-fable-5","score":70,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"claude-fable-5","score":77.9,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-pro-0813","score":31.8,"metric":"percent"},{"benchmark":"automationbench","model":"kimi-k3","score":30.8,"metric":"percent"},{"benchmark":"automationbench","model":"claude-fable-5","score":29.1,"metric":"percent"},{"benchmark":"dsbench-fullstack","model":"deepseek-v4-pro-0813","score":71.1,"metric":"percent"},{"benchmark":"dsbench-fullstack","model":"kimi-k3","score":73.7,"metric":"percent"},{"benchmark":"dsbench-fullstack","model":"claude-fable-5","score":77.2,"metric":"percent"},{"benchmark":"dsbench-hard","model":"deepseek-v4-pro-0813","score":67.2,"metric":"percent"},{"benchmark":"dsbench-hard","model":"kimi-k3","score":63,"metric":"percent"},{"benchmark":"dsbench-hard","model":"claude-fable-5","score":68.3,"metric":"percent"},{"benchmark":"cybergym","model":"deepseek-v4-flash-vision-exp","score":75.3,"metric":"percent"},{"benchmark":"dsbench-hard","model":"deepseek-v4-flash-vision-exp","score":63.6,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-flash-vision-exp","score":25.7,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-opus-4.8","score":65,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"deepseek-v4-flash-vision-exp","score":35,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"claude-opus-4.8","score":34,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v4-flash-base","score":83.9,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v4-pro-base","score":84.4,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v4.1-flash-base","score":83.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4.1-flash-base","score":74.1,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v4.1-flash-base","score":92.1,"metric":"percent"},{"benchmark":"multiloko","model":"deepseek-v4-flash-base","score":42.6,"metric":"percent"},{"benchmark":"multiloko","model":"deepseek-v4-pro-base","score":50.9,"metric":"percent"},{"benchmark":"multiloko","model":"deepseek-v4.1-flash-base","score":45.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4.1-flash-base","score":42.3,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v4.1-flash-base","score":53.1,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v4.1-flash-base","score":86.1,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"deepseek-v4-flash-base","score":25.4,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"deepseek-v4-pro-base","score":29.8,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"deepseek-v4.1-flash-base","score":27.2,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v4.1-flash-base","score":87.9,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v4.1-flash-base","score":87.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-v4.1-flash-base","score":60.6,"metric":"pass@1"},{"benchmark":"humaneval","model":"deepseek-v4.1-flash-base","score":79.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v4.1-flash-base","score":93,"metric":"percent"},{"benchmark":"math","model":"deepseek-v4.1-flash-base","score":61.1,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v4.1-flash-base","score":80.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v4.1-flash-base","score":45.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"deepseek-v4.1-flash-base","score":56.5,"metric":"percent"},{"benchmark":"cv-bench","model":"deepseek-v4.1-flash-base","score":77.9,"metric":"percent"},{"benchmark":"docvqa","model":"deepseek-v4.1-flash-base","score":95.6,"metric":"percent"},{"benchmark":"refcoco","model":"deepseek-v4.1-flash-base","score":86,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-5","score":93.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.6-sol","score":94.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k3","score":92.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5.3","score":88.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-pro-0813","score":92.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash-0731","score":89.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4.1-flash","score":90.9,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.6-sol","score":44.5,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4.1-flash","score":36.8,"metric":"avg@3"},{"benchmark":"hle-text-only","model":"glm-5.3","score":42,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-pro-0813","score":42.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-flash-0731","score":37.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4.1-flash","score":39.1,"metric":"percent"},{"benchmark":"codeforces","model":"deepseek-v4-pro-0813","score":3348,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v4-flash-0731","score":3289,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v4.1-flash","score":3471,"metric":"ELO"},{"benchmark":"matharena-apex","model":"kimi-k3","score":65.6,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-pro-0813","score":65.3,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-flash-0731","score":58.6,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4.1-flash","score":65.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-5","score":89.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4.1-flash","score":90.6,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-opus-5","score":43.3,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"gpt-5.6-sol","score":34.4,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"kimi-k3","score":17.7,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"deepseek-v4-pro-0813","score":11.8,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"deepseek-v4-flash-0731","score":7.6,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"deepseek-v4.1-flash","score":30,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-opus-5","score":51.8,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-5.6-sol","score":39.9,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"kimi-k3","score":12.6,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"glm-5.3","score":37.9,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"deepseek-v4-pro-0813","score":12.4,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"deepseek-v4-flash-0731","score":7,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"deepseek-v4.1-flash","score":31.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-5","score":74,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-sol","score":73,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4.1-flash","score":74.2,"metric":"percent"},{"benchmark":"programbench","model":"claude-opus-5","score":37,"metric":"percent"},{"benchmark":"programbench","model":"gpt-5.6-sol","score":23,"metric":"percent"},{"benchmark":"programbench","model":"kimi-k3","score":17.5,"metric":"percent"},{"benchmark":"programbench","model":"glm-5.3","score":19,"metric":"percent"},{"benchmark":"programbench","model":"deepseek-v4-pro-0813","score":15.5,"metric":"percent"},{"benchmark":"programbench","model":"deepseek-v4.1-flash","score":20.3,"metric":"percent"},{"benchmark":"nl2repo","model":"claude-opus-5","score":75.3,"metric":"percent"},{"benchmark":"nl2repo","model":"gpt-5.6-sol","score":56.8,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4.1-flash","score":64,"metric":"percent"},{"benchmark":"cybergym","model":"gpt-5.6-sol","score":84.5,"metric":"percent"},{"benchmark":"cybergym","model":"deepseek-v4.1-flash","score":88.1,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"gpt-5.6-sol","score":74.3,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"deepseek-v4-pro-0813","score":56.4,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"deepseek-v4-flash-0731","score":30.9,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"deepseek-v4.1-flash","score":62.8,"metric":"percent"},{"benchmark":"exploitgym","model":"claude-opus-5","score":22.1,"metric":"percent"},{"benchmark":"exploitgym","model":"glm-5.3","score":15,"metric":"percent"},{"benchmark":"exploitgym","model":"deepseek-v4-pro-0813","score":5.4,"metric":"percent"},{"benchmark":"exploitgym","model":"deepseek-v4-flash-0731","score":1.8,"metric":"percent"},{"benchmark":"exploitgym","model":"deepseek-v4.1-flash","score":15.3,"metric":"percent"},{"benchmark":"hle-with-tools","model":"deepseek-v4.1-flash","score":63.9,"metric":"avg@3"},{"benchmark":"automationbench","model":"claude-opus-5","score":50.3,"metric":"percent"},{"benchmark":"automationbench","model":"glm-5.3","score":48.8,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-flash-0731","score":37.7,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4.1-flash","score":54.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5","score":28.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol","score":26.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4.1-flash","score":31.8,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-opus-5","score":84,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"gpt-5.6-sol","score":79.9,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"kimi-k3","score":68.1,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"deepseek-v4.1-flash","score":78.9,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"claude-opus-5","score":94.1,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"gpt-5.6-sol","score":88.9,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"kimi-k3","score":85.7,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"deepseek-v4.1-flash","score":89.6,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"claude-opus-5","score":52,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"gpt-5.6-sol","score":53,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"kimi-k3","score":41,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"deepseek-v4.1-flash","score":49,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2.5-350m","score":30.64,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2-350m","score":27.58,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"granite-4-h-300m","score":22.32,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"granite-4-300m","score":25.91,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-0.8b","score":27.41,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-0.8b-thinking","score":19.29,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-1b","score":23.89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-350m","score":20.01,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2-350m","score":19.29,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4-h-300m","score":13.14,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4-300m","score":12.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-0.8b","score":37.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-1b","score":14.04,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-350m","score":76.96,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-350m","score":64.96,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4-h-300m","score":61.27,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4-300m","score":53.48,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-0.8b","score":59.94,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-0.8b-thinking","score":32.93,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-1b","score":63.49,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-350m","score":40.69,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-350m","score":18.2,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4-h-300m","score":17.22,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4-300m","score":15.98,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-0.8b","score":22.87,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-0.8b-thinking","score":22,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-3-1b","score":20.33,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-350m","score":44.92,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2-350m","score":32.92,"metric":"percent"},{"benchmark":"multi-if","model":"granite-4-h-300m","score":28.7,"metric":"percent"},{"benchmark":"multi-if","model":"granite-4-300m","score":24.21,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-0.8b","score":41.68,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-0.8b-thinking","score":26.44,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-3-1b","score":44.25,"metric":"percent"},{"benchmark":"casereportbench","model":"lfm2.5-350m","score":32.45,"metric":"percent"},{"benchmark":"casereportbench","model":"lfm2-350m","score":11.67,"metric":"percent"},{"benchmark":"casereportbench","model":"granite-4-h-300m","score":12.44,"metric":"percent"},{"benchmark":"casereportbench","model":"granite-4-300m","score":0.84,"metric":"percent"},{"benchmark":"casereportbench","model":"qwen3.5-0.8b","score":13.83,"metric":"percent"},{"benchmark":"casereportbench","model":"qwen3.5-0.8b-thinking","score":0.39,"metric":"percent"},{"benchmark":"casereportbench","model":"gemma-3-1b","score":2.28,"metric":"percent"},{"benchmark":"bfcl-v3","model":"lfm2.5-350m","score":44.11,"metric":"percent"},{"benchmark":"bfcl-v3","model":"lfm2-350m","score":22.95,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4-h-300m","score":43.07,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4-300m","score":39.58,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.5-0.8b","score":35.08,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.5-0.8b-thinking","score":39.64,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemma-3-1b","score":16.61,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-350m","score":21.86,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2-350m","score":12.29,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4-h-300m","score":13.28,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4-300m","score":13.73,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-0.8b","score":18.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-0.8b-thinking","score":25.39,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-3-1b","score":7.17,"metric":"percent"},{"benchmark":"tau2-telecom","model":"lfm2.5-350m","score":18.86,"metric":"percent"},{"benchmark":"tau2-telecom","model":"lfm2-350m","score":10.82,"metric":"percent"},{"benchmark":"tau2-telecom","model":"granite-4-h-300m","score":13.74,"metric":"percent"},{"benchmark":"tau2-telecom","model":"granite-4-300m","score":2.92,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-0.8b","score":12.57,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-0.8b-thinking","score":14.33,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemma-3-1b","score":9.36,"metric":"percent"},{"benchmark":"tau2-retail","model":"lfm2.5-350m","score":17.84,"metric":"percent"},{"benchmark":"tau2-retail","model":"lfm2-350m","score":5.56,"metric":"percent"},{"benchmark":"tau2-retail","model":"granite-4-h-300m","score":6.14,"metric":"percent"},{"benchmark":"tau2-retail","model":"granite-4-300m","score":6.14,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.5-0.8b","score":6.14,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.5-0.8b-thinking","score":7.02,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemma-3-1b","score":6.43,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2.5-230m","score":25.41,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-230m","score":20.25,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-230m","score":71.71,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-230m","score":38.4,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-230m","score":37.7,"metric":"percent"},{"benchmark":"casereportbench","model":"lfm2.5-230m","score":22.51,"metric":"percent"},{"benchmark":"bfcl-v3","model":"lfm2.5-230m","score":43.26,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-230m","score":21.03,"metric":"percent"},{"benchmark":"tau2-telecom","model":"lfm2.5-230m","score":5.26,"metric":"percent"},{"benchmark":"tau2-retail","model":"lfm2.5-230m","score":13.68,"metric":"percent"},{"benchmark":"aa-omniscience","model":"lfm2-8b-a1b","score":-78.42,"metric":"index"},{"benchmark":"aa-omniscience","model":"lfm2.5-8b-a1b","score":-24.7,"metric":"index"},{"benchmark":"aa-omniscience-accuracy","model":"lfm2-8b-a1b","score":7.33,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"lfm2.5-8b-a1b","score":8.67,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"lfm2-8b-a1b","score":7.46,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"lfm2.5-8b-a1b","score":63.47,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-8b-a1b","score":79.44,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-8b-a1b","score":91.84,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-8b-a1b","score":26,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-8b-a1b","score":56.47,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2-8b-a1b","score":58.54,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-8b-a1b","score":79.93,"metric":"percent"},{"benchmark":"math500","model":"lfm2-8b-a1b","score":74.8,"metric":"percent"},{"benchmark":"math500","model":"lfm2.5-8b-a1b","score":88.76,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2-8b-a1b","score":20,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2.5-8b-a1b","score":42.53,"metric":"percent"},{"benchmark":"bfcl-v3","model":"lfm2-8b-a1b","score":45.07,"metric":"percent"},{"benchmark":"bfcl-v3","model":"lfm2.5-8b-a1b","score":64.36,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2-8b-a1b","score":25.52,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-8b-a1b","score":48.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"lfm2-8b-a1b","score":13.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"lfm2.5-8b-a1b","score":88.07,"metric":"percent"},{"benchmark":"tau2-retail","model":"lfm2-8b-a1b","score":7.02,"metric":"percent"},{"benchmark":"tau2-retail","model":"lfm2.5-8b-a1b","score":39.82,"metric":"percent"},{"benchmark":"aa-omniscience","model":"granite-4.0-h-tiny","score":-75.5,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3.5-4b","score":-51.53,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3-30b-a3b-thinking-2507","score":-51.31,"metric":"index"},{"benchmark":"aa-omniscience","model":"gemma-4-e2b-it","score":-72,"metric":"index"},{"benchmark":"aa-omniscience","model":"gemma-4-e4b-it","score":-50.67,"metric":"index"},{"benchmark":"aa-omniscience","model":"gemma-4-26b-a4b-it","score":-62.07,"metric":"index"},{"benchmark":"aa-omniscience","model":"gpt-oss-20b","score":-49.17,"metric":"index"},{"benchmark":"aa-omniscience-accuracy","model":"granite-4.0-h-tiny","score":9.37,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.5-4b","score":17.2,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3-30b-a3b-thinking-2507","score":18.8,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gemma-4-e2b-it","score":7,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gemma-4-e4b-it","score":8.1,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gemma-4-26b-a4b-it","score":14.37,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gpt-oss-20b","score":14.57,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"granite-4.0-h-tiny","score":6.38,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"qwen3.5-4b","score":16.99,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"qwen3-30b-a3b-thinking-2507","score":13.87,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"gemma-4-e2b-it","score":15.05,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"gemma-4-e4b-it","score":36.06,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"gemma-4-26b-a4b-it","score":10.75,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"gpt-oss-20b","score":24.5,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.0-h-tiny","score":82.23,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-4b","score":87.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-thinking-2507","score":90.82,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e2b-it","score":82.93,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e4b-it","score":87.74,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-26b-a4b-it","score":91.4,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-20b","score":86.73,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.0-h-tiny","score":21.28,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":50.38,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b-thinking-2507","score":51.11,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e2b-it","score":33.53,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":39.48,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-26b-a4b-it","score":47.25,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b","score":58.65,"metric":"percent"},{"benchmark":"multi-if","model":"granite-4.0-h-tiny","score":59,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-4b","score":67.43,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-30b-a3b-thinking-2507","score":79.04,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e2b-it","score":69.7,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e4b-it","score":77.58,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-26b-a4b-it","score":82.06,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-oss-20b","score":76.64,"metric":"percent"},{"benchmark":"math500","model":"granite-4.0-h-tiny","score":59.2,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-4b","score":80.76,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b-thinking-2507","score":86.48,"metric":"percent"},{"benchmark":"math500","model":"gemma-4-e2b-it","score":64,"metric":"percent"},{"benchmark":"math500","model":"gemma-4-e4b-it","score":65,"metric":"percent"},{"benchmark":"math500","model":"gemma-4-26b-a4b-it","score":94.2,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-20b","score":92.4,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-4.0-h-tiny","score":4.93,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-4b","score":54.28,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-thinking-2507","score":71.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e2b-it","score":26,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e4b-it","score":34.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-26b-a4b-it","score":68.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b","score":68.53,"metric":"percent"},{"benchmark":"aime-2026-i","model":"lfm2.5-8b-a1b","score":50,"metric":"percent"},{"benchmark":"aime-2026-i","model":"granite-4.0-h-tiny","score":3.33,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-4b","score":58.33,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-30b-a3b-thinking-2507","score":66.67,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-e2b-it","score":30,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-e4b-it","score":40.67,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-26b-a4b-it","score":72,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-oss-20b","score":68.67,"metric":"percent"},{"benchmark":"bfcl-v3","model":"lfm2.5-8b-a1b","score":64.79,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.0-h-tiny","score":56.89,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.5-4b","score":71.06,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-30b-a3b-thinking-2507","score":73.39,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemma-4-e2b-it","score":56.44,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemma-4-e4b-it","score":57.31,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemma-4-26b-a4b-it","score":68.87,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gpt-oss-20b","score":62.52,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-8b-a1b","score":49.73,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4.0-h-tiny","score":28.52,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":54.01,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-30b-a3b-thinking-2507","score":50.53,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e2b-it","score":31.91,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":33.92,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-26b-a4b-it","score":55.87,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-oss-20b","score":49.88,"metric":"percent"},{"benchmark":"tau2-telecom","model":"granite-4.0-h-tiny","score":16.67,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-4b","score":87.72,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-30b-a3b-thinking-2507","score":21.93,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemma-4-e2b-it","score":22.37,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemma-4-e4b-it","score":26.75,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemma-4-26b-a4b-it","score":42.11,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-20b","score":57.24,"metric":"percent"},{"benchmark":"tau2-retail","model":"granite-4.0-h-tiny","score":18.42,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.5-4b","score":71.93,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-30b-a3b-thinking-2507","score":56.14,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemma-4-e2b-it","score":18.95,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemma-4-e4b-it","score":42.11,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemma-4-26b-a4b-it","score":55.26,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-oss-20b","score":53.51,"metric":"percent"},{"benchmark":"aa-omniscience-public","model":"lfm2.5-2.6b","score":-29.5,"metric":"index"},{"benchmark":"aa-omniscience-public","model":"gemma-4-e2b-it","score":-74.47,"metric":"index"},{"benchmark":"aa-omniscience-public","model":"gemma-4-e4b-it","score":-49.03,"metric":"index"},{"benchmark":"aa-omniscience-public","model":"qwen3.5-4b","score":-54.3,"metric":"index"},{"benchmark":"aa-omniscience-public","model":"qwen3.5-9b","score":-50.43,"metric":"index"},{"benchmark":"aime-2025","model":"lfm2.5-2.6b","score":51.87,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e2b-it","score":26.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e4b-it","score":34.27,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-4b","score":49.33,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-9b","score":56.07,"metric":"percent"},{"benchmark":"livecodebench","model":"lfm2.5-2.6b","score":59.41,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e2b-it","score":54.92,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e4b-it","score":63.77,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b","score":60.85,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-9b","score":69.86,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-2.6b","score":59.17,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e2b-it","score":34.08,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":39.24,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":48.4,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-9b","score":56.47,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-2.6b","score":80.07,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e2b-it","score":69.44,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e4b-it","score":77.35,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-4b","score":55.67,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-9b","score":62.55,"metric":"percent"},{"benchmark":"ifstruct","model":"lfm2.5-2.6b","score":85.49,"metric":"percent"},{"benchmark":"ifstruct","model":"gemma-4-e2b-it","score":64.85,"metric":"percent"},{"benchmark":"ifstruct","model":"gemma-4-e4b-it","score":76.65,"metric":"percent"},{"benchmark":"ifstruct","model":"qwen3.5-4b","score":36.25,"metric":"percent"},{"benchmark":"ifstruct","model":"qwen3.5-9b","score":78.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-2.6b","score":56.88,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e2b-it","score":36.98,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":46.39,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":50.56,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-9b","score":60.13,"metric":"percent"},{"benchmark":"toolsandbox","model":"lfm2.5-2.6b","score":77.83,"metric":"percent"},{"benchmark":"toolsandbox","model":"gemma-4-e2b-it","score":52.4,"metric":"percent"},{"benchmark":"toolsandbox","model":"gemma-4-e4b-it","score":65,"metric":"percent"},{"benchmark":"toolsandbox","model":"qwen3.5-4b","score":75.55,"metric":"percent"},{"benchmark":"toolsandbox","model":"qwen3.5-9b","score":76.44,"metric":"percent"},{"benchmark":"tau3-banking","model":"lfm2.5-2.6b","score":5.67,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-e2b-it","score":3.35,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-e4b-it","score":4.12,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-4b","score":5.45,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-9b","score":5.15,"metric":"percent"},{"benchmark":"claw-eval","model":"lfm2.5-2.6b","score":62.85,"metric":"percent"},{"benchmark":"claw-eval","model":"gemma-4-e2b-it","score":53.14,"metric":"percent"},{"benchmark":"claw-eval","model":"gemma-4-e4b-it","score":58.02,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-4b","score":62.28,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-9b","score":66.53,"metric":"percent"},{"benchmark":"pinchbench","model":"lfm2.5-2.6b","score":68.22,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-e2b-it","score":44.24,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-e4b-it","score":55.09,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-4b","score":71.26,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-9b","score":71.45,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"lfm2.5-2.6b","score":26.89,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gemma-4-e2b-it","score":8.31,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gemma-4-e4b-it","score":15.9,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"qwen3.5-4b","score":24.46,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"qwen3.5-9b","score":27.23,"metric":"percent"},{"benchmark":"automationbench","model":"lfm2.5-24b-a2b","score":27.69,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.6-35b-a3b","score":8.72,"metric":"percent"},{"benchmark":"automationbench","model":"gemma-4-26b-a4b-it","score":5.46,"metric":"percent"},{"benchmark":"automationbench","model":"nemotron-3.5-lightning-30b-a3b","score":2.61,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-24b-a2b","score":65.01,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.6-35b-a3b","score":65,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-26b-a4b-it","score":57.09,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nemotron-3.5-lightning-30b-a3b","score":53.78,"metric":"percent"},{"benchmark":"toolsandbox","model":"lfm2.5-24b-a2b","score":80.71,"metric":"percent"},{"benchmark":"toolsandbox","model":"qwen3.6-35b-a3b","score":75.02,"metric":"percent"},{"benchmark":"toolsandbox","model":"gemma-4-26b-a4b-it","score":72.09,"metric":"percent"},{"benchmark":"toolsandbox","model":"nemotron-3.5-lightning-30b-a3b","score":75.13,"metric":"percent"},{"benchmark":"liveclaw","model":"lfm2.5-24b-a2b","score":48.09,"metric":"percent"},{"benchmark":"liveclaw","model":"qwen3.6-35b-a3b","score":38.19,"metric":"percent"},{"benchmark":"liveclaw","model":"gemma-4-26b-a4b-it","score":41.25,"metric":"percent"},{"benchmark":"liveclaw","model":"nemotron-3.5-lightning-30b-a3b","score":37.72,"metric":"percent"},{"benchmark":"pinchbench","model":"lfm2.5-24b-a2b","score":83.18,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.6-35b-a3b","score":89.93,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-26b-a4b-it","score":77.12,"metric":"percent"},{"benchmark":"pinchbench","model":"nemotron-3.5-lightning-30b-a3b","score":84.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"lfm2.5-24b-a2b","score":8.04,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.6-35b-a3b","score":7.63,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-26b-a4b-it","score":4.54,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3.5-lightning-30b-a3b","score":7.01,"metric":"percent"},{"benchmark":"webarena-verified","model":"lfm2.5-24b-a2b","score":26.75,"metric":"percent"},{"benchmark":"webarena-verified","model":"qwen3.6-35b-a3b","score":37.62,"metric":"percent"},{"benchmark":"webarena-verified","model":"gemma-4-26b-a4b-it","score":25.62,"metric":"percent"},{"benchmark":"webarena-verified","model":"nemotron-3.5-lightning-30b-a3b","score":28.69,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2.5-24b-a2b","score":74.42,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-35b-a3b","score":83.69,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-26b-a4b-it","score":74.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3.5-lightning-30b-a3b","score":72.42,"metric":"percent"},{"benchmark":"aa-omniscience","model":"lfm2.5-24b-a2b","score":-24.9,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3.6-35b-a3b","score":-24.35,"metric":"index"},{"benchmark":"aa-omniscience","model":"gemma-4-26b-a4b-it","score":-59.39,"metric":"index"},{"benchmark":"aa-omniscience","model":"nemotron-3.5-lightning-30b-a3b","score":-3.58,"metric":"index"},{"benchmark":"hle","model":"lfm2.5-24b-a2b","score":7.4,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.6-35b-a3b","score":7.69,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-26b-a4b-it","score":8.57,"metric":"avg@3"},{"benchmark":"hle","model":"nemotron-3.5-lightning-30b-a3b","score":5.65,"metric":"avg@3"},{"benchmark":"ifeval","model":"lfm2.5-24b-a2b","score":96.75,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.6-35b-a3b","score":93.06,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-26b-a4b-it","score":92,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-3.5-lightning-30b-a3b","score":94.19,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-24b-a2b","score":74.69,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":64.21,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-26b-a4b-it","score":47.44,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3.5-lightning-30b-a3b","score":71.67,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-24b-a2b","score":84.38,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.6-35b-a3b","score":81.53,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-26b-a4b-it","score":82.19,"metric":"percent"},{"benchmark":"multi-if","model":"nemotron-3.5-lightning-30b-a3b","score":82.34,"metric":"percent"},{"benchmark":"math500","model":"lfm2.5-24b-a2b","score":96.04,"metric":"percent"},{"benchmark":"math500","model":"qwen3.6-35b-a3b","score":96.73,"metric":"percent"},{"benchmark":"math500","model":"gemma-4-26b-a4b-it","score":95.66,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3.5-lightning-30b-a3b","score":96.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"lfm2.5-24b-a2b","score":51,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-35b-a3b","score":66.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-26b-a4b-it","score":25.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3.5-lightning-30b-a3b","score":53.4,"metric":"percent"},{"benchmark":"scicode","model":"lfm2.5-24b-a2b","score":32.71,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-35b-a3b","score":37.35,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-26b-a4b-it","score":35.42,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3.5-lightning-30b-a3b","score":27.78,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2.5-vl-450m","score":43,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2-vl-450m","score":40.87,"metric":"percent"},{"benchmark":"mmstar","model":"smolvlm2-0.5b","score":38.2,"metric":"percent"},{"benchmark":"realworldqa","model":"lfm2.5-vl-450m","score":58.43,"metric":"percent"},{"benchmark":"realworldqa","model":"lfm2-vl-450m","score":52.03,"metric":"percent"},{"benchmark":"realworldqa","model":"smolvlm2-0.5b","score":49.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"lfm2.5-vl-450m","score":60.91,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"lfm2-vl-450m","score":56.27,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"smolvlm2-0.5b","score":52.32,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2.5-vl-450m","score":32.67,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2-vl-450m","score":34.44,"metric":"percent"},{"benchmark":"mmmu","model":"smolvlm2-0.5b","score":34.1,"metric":"percent"},{"benchmark":"pope","model":"lfm2.5-vl-450m","score":86.93,"metric":"percent"},{"benchmark":"pope","model":"lfm2-vl-450m","score":83.79,"metric":"percent"},{"benchmark":"pope","model":"smolvlm2-0.5b","score":82.67,"metric":"percent"},{"benchmark":"mmvet","model":"lfm2.5-vl-450m","score":41.1,"metric":"percent"},{"benchmark":"mmvet","model":"lfm2-vl-450m","score":33.85,"metric":"percent"},{"benchmark":"mmvet","model":"smolvlm2-0.5b","score":29.9,"metric":"percent"},{"benchmark":"blink","model":"lfm2.5-vl-450m","score":43.92,"metric":"percent"},{"benchmark":"blink","model":"lfm2-vl-450m","score":42.61,"metric":"percent"},{"benchmark":"blink","model":"smolvlm2-0.5b","score":40.7,"metric":"percent"},{"benchmark":"infovqa","model":"lfm2.5-vl-450m","score":43.02,"metric":"percent"},{"benchmark":"infovqa","model":"lfm2-vl-450m","score":44.56,"metric":"percent"},{"benchmark":"infovqa","model":"smolvlm2-0.5b","score":24.64,"metric":"percent"},{"benchmark":"ocrbench-elo","model":"lfm2.5-vl-450m","score":684,"metric":"elo"},{"benchmark":"ocrbench-elo","model":"lfm2-vl-450m","score":657,"metric":"elo"},{"benchmark":"ocrbench-elo","model":"smolvlm2-0.5b","score":609,"metric":"elo"},{"benchmark":"mm-ifeval","model":"lfm2.5-vl-450m","score":45,"metric":"percent"},{"benchmark":"mm-ifeval","model":"lfm2-vl-450m","score":33.09,"metric":"percent"},{"benchmark":"mm-ifeval","model":"smolvlm2-0.5b","score":11.27,"metric":"percent"},{"benchmark":"mmmb","model":"lfm2.5-vl-450m","score":68.09,"metric":"percent"},{"benchmark":"mmmb","model":"lfm2-vl-450m","score":54.29,"metric":"percent"},{"benchmark":"mmmb","model":"smolvlm2-0.5b","score":46.79,"metric":"percent"},{"benchmark":"countbench","model":"lfm2.5-vl-450m","score":73.31,"metric":"percent"},{"benchmark":"countbench","model":"lfm2-vl-450m","score":47.64,"metric":"percent"},{"benchmark":"countbench","model":"smolvlm2-0.5b","score":61.81,"metric":"percent"},{"benchmark":"refcoco-m","model":"lfm2.5-vl-450m","score":81.28,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2.5-vl-450m","score":25.66,"metric":"percent"},{"benchmark":"gpqa","model":"lfm2-vl-450m","score":23.13,"metric":"percent"},{"benchmark":"gpqa","model":"smolvlm2-0.5b","score":23.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-vl-450m","score":19.32,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2-vl-450m","score":17.22,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smolvlm2-0.5b","score":13.57,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-vl-450m","score":61.16,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-vl-450m","score":51.75,"metric":"percent"},{"benchmark":"ifeval","model":"smolvlm2-0.5b","score":30.14,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-vl-450m","score":34.63,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2-vl-450m","score":26.21,"metric":"percent"},{"benchmark":"multi-if","model":"smolvlm2-0.5b","score":6.82,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-vl-450m","score":21.08,"metric":"percent"},{"benchmark":"screenspot-v2","model":"lfm2.5-vl-3b","score":80.7,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gemma-4-e2b-it","score":31.1,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gemma-4-e4b-it","score":50.9,"metric":"percent"},{"benchmark":"screenspot-v2","model":"internvl3.5-4b","score":84.2,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3.5-2b","score":66.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3.5-4b","score":78.5,"metric":"percent"},{"benchmark":"refcoco","model":"lfm2.5-vl-3b","score":87.9,"metric":"percent"},{"benchmark":"refcoco","model":"lfm2-vl-3b","score":57.1,"metric":"percent"},{"benchmark":"refcoco","model":"gemma-4-e2b-it","score":67.3,"metric":"percent"},{"benchmark":"refcoco","model":"gemma-4-e4b-it","score":72.1,"metric":"percent"},{"benchmark":"refcoco","model":"internvl3.5-4b","score":88.9,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-2b","score":78.5,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-4b","score":86.6,"metric":"percent"},{"benchmark":"blink","model":"lfm2.5-vl-3b","score":61.5,"metric":"percent"},{"benchmark":"blink","model":"lfm2-vl-3b","score":50.2,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-e2b-it","score":51.8,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-e4b-it","score":56.4,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-4b","score":57.4,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-2b","score":59.3,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-4b","score":65,"metric":"percent"},{"benchmark":"muirbench","model":"lfm2.5-vl-3b","score":58.3,"metric":"percent"},{"benchmark":"muirbench","model":"lfm2-vl-3b","score":34.9,"metric":"percent"},{"benchmark":"muirbench","model":"gemma-4-e2b-it","score":40.7,"metric":"percent"},{"benchmark":"muirbench","model":"gemma-4-e4b-it","score":48.9,"metric":"percent"},{"benchmark":"muirbench","model":"internvl3.5-4b","score":53.4,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3.5-2b","score":49,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3.5-4b","score":67,"metric":"percent"},{"benchmark":"toolsandbox","model":"lfm2.5-vl-3b","score":59.5,"metric":"percent"},{"benchmark":"toolsandbox","model":"lfm2-vl-3b","score":26.4,"metric":"percent"},{"benchmark":"toolsandbox","model":"gemma-4-e2b-it","score":56.5,"metric":"percent"},{"benchmark":"toolsandbox","model":"gemma-4-e4b-it","score":61.6,"metric":"percent"},{"benchmark":"toolsandbox","model":"qwen3.5-2b","score":47.7,"metric":"percent"},{"benchmark":"toolsandbox","model":"qwen3.5-4b","score":65,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-vl-3b","score":32.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2-vl-3b","score":20.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e2b-it","score":33.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":40,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-2b","score":33.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":53.6,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2.5-vl-3b","score":63.3,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2-vl-3b","score":57.7,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-e2b-it","score":57.9,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-e4b-it","score":61.9,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-2b","score":57.5,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-4b","score":65.3,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-2b","score":67.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-4b","score":73.3,"metric":"percent"},{"benchmark":"realworldqa","model":"lfm2.5-vl-3b","score":73.1,"metric":"percent"},{"benchmark":"realworldqa","model":"lfm2-vl-3b","score":71.1,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-e2b-it","score":56.2,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-e4b-it","score":61.8,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-2b","score":61.4,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-4b","score":68.6,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-2b","score":71.4,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-4b","score":76.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"lfm2.5-vl-3b","score":87.3,"metric":"percent"},{"benchmark":"countbenchqa","model":"lfm2-vl-3b","score":92.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"gemma-4-e2b-it","score":70.8,"metric":"percent"},{"benchmark":"countbenchqa","model":"gemma-4-e4b-it","score":80.1,"metric":"percent"},{"benchmark":"countbenchqa","model":"internvl3.5-2b","score":70.6,"metric":"percent"},{"benchmark":"countbenchqa","model":"internvl3.5-4b","score":82.5,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3.5-2b","score":83.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3.5-4b","score":86.9,"metric":"percent"},{"benchmark":"mmmb","model":"lfm2.5-vl-3b","score":83,"metric":"percent"},{"benchmark":"mmmb","model":"lfm2-vl-3b","score":81.9,"metric":"percent"},{"benchmark":"mmmb","model":"gemma-4-e2b-it","score":75.7,"metric":"percent"},{"benchmark":"mmmb","model":"gemma-4-e4b-it","score":80.5,"metric":"percent"},{"benchmark":"mmmb","model":"internvl3.5-2b","score":76.4,"metric":"percent"},{"benchmark":"mmmb","model":"internvl3.5-4b","score":81.5,"metric":"percent"},{"benchmark":"mmmb","model":"qwen3.5-2b","score":73.6,"metric":"percent"},{"benchmark":"mmmb","model":"qwen3.5-4b","score":83.4,"metric":"percent"},{"benchmark":"mm-ifeval","model":"lfm2.5-vl-3b","score":60.6,"metric":"percent"},{"benchmark":"mm-ifeval","model":"lfm2-vl-3b","score":51.4,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemma-4-e2b-it","score":64.5,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemma-4-e4b-it","score":66.7,"metric":"percent"},{"benchmark":"mm-ifeval","model":"internvl3.5-2b","score":48.4,"metric":"percent"},{"benchmark":"mm-ifeval","model":"internvl3.5-4b","score":54.6,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3.5-2b","score":52.1,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3.5-4b","score":63.8,"metric":"percent"},{"benchmark":"mathvista","model":"lfm2.5-vl-3b","score":68.5,"metric":"percent"},{"benchmark":"mathvista","model":"lfm2-vl-3b","score":68.5,"metric":"percent"},{"benchmark":"mathvista","model":"gemma-4-e2b-it","score":62.1,"metric":"percent"},{"benchmark":"mathvista","model":"gemma-4-e4b-it","score":52.9,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3.5-2b","score":56.6,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3.5-4b","score":59.1,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3.5-2b","score":68.8,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3.5-4b","score":69.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"lfm2.5-vl-3b","score":30.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"lfm2-vl-3b","score":28.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-e2b-it","score":34.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-e4b-it","score":39.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl3.5-2b","score":27.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl3.5-4b","score":31.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-2b","score":43.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-4b","score":60.9,"metric":"percent"},{"benchmark":"chartqa","model":"lfm2.5-vl-3b","score":81.3,"metric":"percent"},{"benchmark":"chartqa","model":"lfm2-vl-3b","score":80.4,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-4-e2b-it","score":43.5,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-4-e4b-it","score":41.9,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-2b","score":81.8,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-4b","score":86.5,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3.5-2b","score":78.3,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3.5-4b","score":84.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"lfm2.5-vl-3b","score":47.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"lfm2-vl-3b","score":43.9,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemma-4-e2b-it","score":44.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemma-4-e4b-it","score":48.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"internvl3.5-2b","score":45.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"internvl3.5-4b","score":49.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-2b","score":48,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-4b","score":58.8,"metric":"percent"},{"benchmark":"pope","model":"lfm2.5-vl-3b","score":88.7,"metric":"percent"},{"benchmark":"pope","model":"lfm2-vl-3b","score":89.2,"metric":"percent"},{"benchmark":"pope","model":"gemma-4-e2b-it","score":84,"metric":"percent"},{"benchmark":"pope","model":"gemma-4-e4b-it","score":86.9,"metric":"percent"},{"benchmark":"pope","model":"internvl3.5-2b","score":87.3,"metric":"percent"},{"benchmark":"pope","model":"internvl3.5-4b","score":88.9,"metric":"percent"},{"benchmark":"pope","model":"qwen3.5-2b","score":88.7,"metric":"percent"},{"benchmark":"pope","model":"qwen3.5-4b","score":86,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-e2b-it","score":45.3,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-e4b-it","score":52.9,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-2b","score":57.7,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-4b","score":65.5,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-2b","score":55.1,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-4b","score":59.3,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-e2b-it","score":60,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-e4b-it","score":64.3,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-2b","score":61.6,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-4b","score":67.7,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-2b","score":65.1,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-4b","score":67.1,"metric":"percent"},{"benchmark":"simplevqa","model":"lfm2.5-vl-3b","score":35.4,"metric":"percent"},{"benchmark":"simplevqa","model":"lfm2-vl-3b","score":33,"metric":"percent"},{"benchmark":"simplevqa","model":"gemma-4-e2b-it","score":27.3,"metric":"percent"},{"benchmark":"simplevqa","model":"gemma-4-e4b-it","score":30.4,"metric":"percent"},{"benchmark":"simplevqa","model":"internvl3.5-2b","score":30.5,"metric":"percent"},{"benchmark":"simplevqa","model":"internvl3.5-4b","score":33.7,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-2b","score":35.2,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-4b","score":40.7,"metric":"percent"},{"benchmark":"seed-bench-img","model":"lfm2.5-vl-3b","score":77.7,"metric":"percent"},{"benchmark":"seed-bench-img","model":"lfm2-vl-3b","score":76.6,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gemma-4-e2b-it","score":71.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gemma-4-e4b-it","score":75.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internvl3.5-2b","score":75.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internvl3.5-4b","score":76.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen3.5-2b","score":75.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen3.5-4b","score":76.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"lfm2.5-vl-3b","score":81,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"lfm2-vl-3b","score":80,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemma-4-e2b-it","score":64.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemma-4-e4b-it","score":71.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"internvl3.5-2b","score":76.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"internvl3.5-4b","score":81.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-2b","score":73.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-4b","score":78.4,"metric":"percent"},{"benchmark":"countbenchqa","model":"gemma-4-e2b-it","score":70.4,"metric":"percent"},{"benchmark":"countbenchqa","model":"gemma-4-e4b-it","score":80.5,"metric":"percent"},{"benchmark":"countbenchqa","model":"internvl3.5-2b","score":70.4,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3.5-2b","score":83.8,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3.5-4b","score":86.7,"metric":"percent"},{"benchmark":"mmmb","model":"gemma-4-e2b-it","score":73.3,"metric":"percent"},{"benchmark":"mmmb","model":"gemma-4-e4b-it","score":80.4,"metric":"percent"},{"benchmark":"mmmb","model":"internvl3.5-2b","score":76.3,"metric":"percent"},{"benchmark":"mmmb","model":"qwen3.5-2b","score":75.9,"metric":"percent"},{"benchmark":"mmmb","model":"qwen3.5-4b","score":82,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"lfm2.5-vl-3b","score":79.5,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"lfm2-vl-3b","score":76.3,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"gemma-4-e2b-it","score":62.8,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"gemma-4-e4b-it","score":71.2,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"internvl3.5-2b","score":70.9,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"internvl3.5-4b","score":76.6,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"qwen3.5-2b","score":69.9,"metric":"percent"},{"benchmark":"multilingual-mmbench","model":"qwen3.5-4b","score":77,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemma-4-e2b-it","score":65.6,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemma-4-e4b-it","score":68.2,"metric":"percent"},{"benchmark":"mm-ifeval","model":"internvl3.5-2b","score":47.1,"metric":"percent"},{"benchmark":"mm-ifeval","model":"internvl3.5-4b","score":54.5,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3.5-2b","score":55.4,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3.5-4b","score":63.1,"metric":"percent"},{"benchmark":"logicvista","model":"lfm2.5-vl-3b","score":37.4,"metric":"percent"},{"benchmark":"logicvista","model":"lfm2-vl-3b","score":32.2,"metric":"percent"},{"benchmark":"logicvista","model":"gemma-4-e2b-it","score":29.5,"metric":"percent"},{"benchmark":"logicvista","model":"gemma-4-e4b-it","score":34.5,"metric":"percent"},{"benchmark":"logicvista","model":"internvl3.5-2b","score":30.9,"metric":"percent"},{"benchmark":"logicvista","model":"internvl3.5-4b","score":36.2,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3.5-2b","score":34,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3.5-4b","score":37.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"lfm2.5-vl-3b","score":68.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"lfm2-vl-3b","score":62.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemma-4-e2b-it","score":37.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemma-4-e4b-it","score":45.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl3.5-2b","score":56.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl3.5-4b","score":67.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-2b","score":48.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-4b","score":63.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-e2b-it","score":26.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-e4b-it","score":32.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl3.5-2b","score":21.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl3.5-4b","score":22.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-2b","score":24.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-4b","score":36,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2.5-vl-3b","score":48.4,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2-vl-3b","score":45.6,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-e2b-it","score":41.1,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-e4b-it","score":49.3,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-2b","score":52,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-4b","score":60.7,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-2b","score":44.1,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-4b","score":50.3,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-4-e2b-it","score":43.2,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-4-e4b-it","score":42.1,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-2b","score":81.7,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-4b","score":86.2,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3.5-2b","score":78.4,"metric":"percent"},{"benchmark":"docvqa","model":"lfm2.5-vl-3b","score":91.1,"metric":"percent"},{"benchmark":"docvqa","model":"lfm2-vl-3b","score":89.8,"metric":"percent"},{"benchmark":"docvqa","model":"gemma-4-e2b-it","score":85.7,"metric":"percent"},{"benchmark":"docvqa","model":"gemma-4-e4b-it","score":87.4,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-2b","score":88.4,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-4b","score":91.8,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3.5-2b","score":92.6,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3.5-4b","score":94.8,"metric":"percent"},{"benchmark":"infovqa","model":"lfm2.5-vl-3b","score":70.2,"metric":"percent"},{"benchmark":"infovqa","model":"lfm2-vl-3b","score":67.8,"metric":"percent"},{"benchmark":"infovqa","model":"gemma-4-e2b-it","score":54.4,"metric":"percent"},{"benchmark":"infovqa","model":"gemma-4-e4b-it","score":60.9,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-4b","score":76.9,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3.5-2b","score":73.5,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3.5-4b","score":80.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemma-4-e2b-it","score":44.4,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemma-4-e4b-it","score":48.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"internvl3.5-4b","score":49.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-2b","score":47.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-4b","score":58.7,"metric":"percent"},{"benchmark":"textvqa","model":"lfm2.5-vl-3b","score":84.3,"metric":"percent"},{"benchmark":"textvqa","model":"lfm2-vl-3b","score":83,"metric":"percent"},{"benchmark":"textvqa","model":"gemma-4-e2b-it","score":62.5,"metric":"percent"},{"benchmark":"textvqa","model":"gemma-4-e4b-it","score":69,"metric":"percent"},{"benchmark":"textvqa","model":"internvl3.5-2b","score":76.6,"metric":"percent"},{"benchmark":"textvqa","model":"internvl3.5-4b","score":77.5,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.5-2b","score":77.3,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.5-4b","score":81.2,"metric":"percent"},{"benchmark":"refcoco","model":"internvl3.5-2b","score":82.9,"metric":"percent"},{"benchmark":"refcoco","model":"internvl3.5-4b","score":88.8,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-e2b-it","score":45.2,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-e4b-it","score":52.2,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-2b","score":52,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-4b","score":57.2,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-2b","score":48.6,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-4b","score":58.7,"metric":"percent"},{"benchmark":"muirbench","model":"gemma-4-e2b-it","score":32.9,"metric":"percent"},{"benchmark":"muirbench","model":"gemma-4-e4b-it","score":51.8,"metric":"percent"},{"benchmark":"muirbench","model":"internvl3.5-2b","score":45,"metric":"percent"},{"benchmark":"muirbench","model":"internvl3.5-4b","score":53.5,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3.5-2b","score":48.2,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3.5-4b","score":62,"metric":"percent"},{"benchmark":"hallusionbench","model":"lfm2.5-vl-3b","score":47.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"lfm2-vl-3b","score":46.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-4-e2b-it","score":41.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-4-e4b-it","score":49.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl3.5-2b","score":47.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl3.5-4b","score":52.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-2b","score":49.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-4b","score":51.7,"metric":"percent"},{"benchmark":"pope","model":"internvl3.5-2b","score":88,"metric":"percent"},{"benchmark":"pope","model":"qwen3.5-2b","score":88.6,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-vl-3b","score":82.3,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2-vl-3b","score":72.9,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e2b-it","score":83,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e4b-it","score":87.9,"metric":"percent"},{"benchmark":"ifeval","model":"internvl3.5-2b","score":32.4,"metric":"percent"},{"benchmark":"ifeval","model":"internvl3.5-4b","score":35.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-2b","score":73.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-4b","score":86.2,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-vl-3b","score":25.8,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2-vl-3b","score":20.8,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e2b-it","score":34.1,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":39.2,"metric":"percent"},{"benchmark":"ifbench","model":"internvl3.5-2b","score":24.4,"metric":"percent"},{"benchmark":"ifbench","model":"internvl3.5-4b","score":24.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-2b","score":28.9,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":33.5,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-vl-3b","score":59.4,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2-vl-3b","score":46.5,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e2b-it","score":69.4,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e4b-it","score":77.4,"metric":"percent"},{"benchmark":"multi-if","model":"internvl3.5-2b","score":16.3,"metric":"percent"},{"benchmark":"multi-if","model":"internvl3.5-4b","score":16.9,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-2b","score":53.5,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-4b","score":66.7,"metric":"percent"},{"benchmark":"jmmlu","model":"lfm2.5-1.2b-jp","score":50.7,"metric":"percent"},{"benchmark":"jmmlu","model":"lfm2.5-1.2b-instruct","score":47.7,"metric":"percent"},{"benchmark":"jmmlu","model":"qwen3-1.7b","score":47.7,"metric":"percent"},{"benchmark":"jmmlu","model":"llama-3.2-1b-instruct","score":34,"metric":"percent"},{"benchmark":"jmmlu","model":"tinyswallow-1.5b-instruct","score":48,"metric":"percent"},{"benchmark":"jmmlu","model":"gemma-2-llama-swallow-2b-it-v0.1","score":48.1,"metric":"percent"},{"benchmark":"jmmlu","model":"gemma-3-1b","score":34.5,"metric":"percent"},{"benchmark":"jmmlu","model":"granite-4.0-h-1b","score":42.2,"metric":"percent"},{"benchmark":"jmmlu","model":"sarashina2.2-1b-instruct-v0.1","score":40.2,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"lfm2.5-1.2b-jp","score":58.1,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"lfm2.5-1.2b-instruct","score":41.8,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"qwen3-1.7b","score":40.3,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"llama-3.2-1b-instruct","score":24.1,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"tinyswallow-1.5b-instruct","score":36.5,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"gemma-2-llama-swallow-2b-it-v0.1","score":33.4,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"gemma-3-1b","score":26.3,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"granite-4.0-h-1b","score":39.3,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"sarashina2.2-1b-instruct-v0.1","score":21.9,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"lfm2.5-1.2b-jp","score":56,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"lfm2.5-1.2b-instruct","score":46.8,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"qwen3-1.7b","score":46,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"llama-3.2-1b-instruct","score":25.2,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"tinyswallow-1.5b-instruct","score":47.2,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"gemma-2-llama-swallow-2b-it-v0.1","score":34.4,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"gemma-3-1b","score":33.6,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"granite-4.0-h-1b","score":42.8,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"sarashina2.2-1b-instruct-v0.1","score":44.4,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"tinyswallow-1.5b-instruct","score":36.6,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"lfm2.5-1.2b-jp-202606","score":36.23,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"lfm2.5-1.2b-instruct","score":31.42,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"qwen3-1.7b","score":30.78,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"granite-4.0-1b","score":15.32,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"llama-3.2-1b-instruct","score":15.91,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"gemma-3-1b","score":14.12,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"sarashina2.2-1b-instruct-v0.1","score":18.3,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"tinyswallow-1.5b-instruct","score":21.51,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"llm-jp-3.1-1.8b-instruct4","score":17.44,"metric":"percent"},{"benchmark":"mmlu-prox-ja","model":"rakutenai-2.0-mini-instruct","score":11.46,"metric":"percent"},{"benchmark":"jmmlu","model":"lfm2.5-1.2b-jp-202606","score":54.19,"metric":"percent"},{"benchmark":"jmmlu","model":"lfm2.5-1.2b-instruct","score":47.61,"metric":"percent"},{"benchmark":"jmmlu","model":"qwen3-1.7b","score":47.67,"metric":"percent"},{"benchmark":"jmmlu","model":"granite-4.0-1b","score":33.93,"metric":"percent"},{"benchmark":"jmmlu","model":"llama-3.2-1b-instruct","score":33.97,"metric":"percent"},{"benchmark":"jmmlu","model":"gemma-3-1b","score":34.45,"metric":"percent"},{"benchmark":"jmmlu","model":"sarashina2.2-1b-instruct-v0.1","score":40.24,"metric":"percent"},{"benchmark":"jmmlu","model":"tinyswallow-1.5b-instruct","score":47.98,"metric":"percent"},{"benchmark":"jmmlu","model":"llm-jp-3.1-1.8b-instruct4","score":43.05,"metric":"percent"},{"benchmark":"jmmlu","model":"rakutenai-2.0-mini-instruct","score":31.84,"metric":"percent"},{"benchmark":"jculture","model":"lfm2.5-1.2b-jp-202606","score":35.77,"metric":"percent"},{"benchmark":"jculture","model":"lfm2.5-1.2b-instruct","score":28.42,"metric":"percent"},{"benchmark":"jculture","model":"qwen3-1.7b","score":33.33,"metric":"percent"},{"benchmark":"jculture","model":"granite-4.0-1b","score":34.38,"metric":"percent"},{"benchmark":"jculture","model":"llama-3.2-1b-instruct","score":22.52,"metric":"percent"},{"benchmark":"jculture","model":"gemma-3-1b","score":23.42,"metric":"percent"},{"benchmark":"jculture","model":"sarashina2.2-1b-instruct-v0.1","score":25.53,"metric":"percent"},{"benchmark":"jculture","model":"tinyswallow-1.5b-instruct","score":31.17,"metric":"percent"},{"benchmark":"jculture","model":"llm-jp-3.1-1.8b-instruct4","score":27.42,"metric":"percent"},{"benchmark":"jculture","model":"rakutenai-2.0-mini-instruct","score":29.67,"metric":"percent"},{"benchmark":"jgpqa","model":"lfm2.5-1.2b-jp-202606","score":28.69,"metric":"percent"},{"benchmark":"jgpqa","model":"lfm2.5-1.2b-instruct","score":31.72,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-1.7b","score":26.26,"metric":"percent"},{"benchmark":"jgpqa","model":"granite-4.0-1b","score":24.44,"metric":"percent"},{"benchmark":"jgpqa","model":"llama-3.2-1b-instruct","score":32.32,"metric":"percent"},{"benchmark":"jgpqa","model":"gemma-3-1b","score":24.24,"metric":"percent"},{"benchmark":"jgpqa","model":"sarashina2.2-1b-instruct-v0.1","score":26.26,"metric":"percent"},{"benchmark":"jgpqa","model":"tinyswallow-1.5b-instruct","score":29.29,"metric":"percent"},{"benchmark":"jgpqa","model":"llm-jp-3.1-1.8b-instruct4","score":17.68,"metric":"percent"},{"benchmark":"jgpqa","model":"rakutenai-2.0-mini-instruct","score":22.22,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"lfm2.5-1.2b-jp-202606","score":79.08,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"lfm2.5-1.2b-instruct","score":40.44,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"qwen3-1.7b","score":40.29,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"granite-4.0-1b","score":27.56,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"gemma-3-1b","score":26.31,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"tinyswallow-1.5b-instruct","score":36.55,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"llm-jp-3.1-1.8b-instruct4","score":33.77,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"rakutenai-2.0-mini-instruct","score":28.06,"metric":"percent"},{"benchmark":"jfbench","model":"lfm2.5-1.2b-jp-202606","score":54.77,"metric":"percent"},{"benchmark":"jfbench","model":"lfm2.5-1.2b-instruct","score":36.67,"metric":"percent"},{"benchmark":"jfbench","model":"qwen3-1.7b","score":36.61,"metric":"percent"},{"benchmark":"jfbench","model":"granite-4.0-1b","score":31.26,"metric":"percent"},{"benchmark":"jfbench","model":"llama-3.2-1b-instruct","score":21.78,"metric":"percent"},{"benchmark":"jfbench","model":"gemma-3-1b","score":31.15,"metric":"percent"},{"benchmark":"jfbench","model":"sarashina2.2-1b-instruct-v0.1","score":27.41,"metric":"percent"},{"benchmark":"jfbench","model":"tinyswallow-1.5b-instruct","score":34.25,"metric":"percent"},{"benchmark":"jfbench","model":"llm-jp-3.1-1.8b-instruct4","score":30.92,"metric":"percent"},{"benchmark":"jfbench","model":"rakutenai-2.0-mini-instruct","score":24.66,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"lfm2.5-1.2b-jp-202606","score":62.2,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"lfm2.5-1.2b-instruct","score":50.2,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"granite-4.0-1b","score":42.8,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"llm-jp-3.1-1.8b-instruct4","score":52.8,"metric":"percent"},{"benchmark":"gsm8k-ja","model":"rakutenai-2.0-mini-instruct","score":24.8,"metric":"percent"},{"benchmark":"math500-ja","model":"lfm2.5-1.2b-jp-202606","score":62.8,"metric":"percent"},{"benchmark":"math500-ja","model":"lfm2.5-1.2b-instruct","score":50,"metric":"percent"},{"benchmark":"math500-ja","model":"qwen3-1.7b","score":56.4,"metric":"percent"},{"benchmark":"math500-ja","model":"granite-4.0-1b","score":25.4,"metric":"percent"},{"benchmark":"math500-ja","model":"llama-3.2-1b-instruct","score":11.4,"metric":"percent"},{"benchmark":"math500-ja","model":"gemma-3-1b","score":15.6,"metric":"percent"},{"benchmark":"math500-ja","model":"sarashina2.2-1b-instruct-v0.1","score":24.8,"metric":"percent"},{"benchmark":"math500-ja","model":"tinyswallow-1.5b-instruct","score":22.4,"metric":"percent"},{"benchmark":"math500-ja","model":"llm-jp-3.1-1.8b-instruct4","score":17,"metric":"percent"},{"benchmark":"math500-ja","model":"rakutenai-2.0-mini-instruct","score":11.4,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"lfm2.5-1.2b-jp-202606","score":49.39,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"lfm2.5-1.2b-instruct","score":28.66,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"qwen3-1.7b","score":47.56,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"granite-4.0-1b","score":51.22,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"llama-3.2-1b-instruct","score":17.68,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"gemma-3-1b","score":25,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"sarashina2.2-1b-instruct-v0.1","score":21.95,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"tinyswallow-1.5b-instruct","score":26.83,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"llm-jp-3.1-1.8b-instruct4","score":35.37,"metric":"percent"},{"benchmark":"jhumaneval-plus","model":"rakutenai-2.0-mini-instruct","score":28.6,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"lfm2.5-1.2b-jp-202606","score":48,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"lfm2.5-1.2b-instruct","score":46.29,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"qwen3-1.7b","score":52.45,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"granite-4.0-1b","score":50.57,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"llama-3.2-1b-instruct","score":21.06,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"gemma-3-1b","score":17.26,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"sarashina2.2-1b-instruct-v0.1","score":13.86,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"tinyswallow-1.5b-instruct","score":11.7,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"llm-jp-3.1-1.8b-instruct4","score":11.76,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"rakutenai-2.0-mini-instruct","score":11.85,"metric":"percent"},{"benchmark":"voicebench-ja-elyza","model":"lfm2.5-audio-1.5b-jp","score":2.272,"metric":"score"},{"benchmark":"voicebench-ja-elyza","model":"qwen2.5-omni-3b","score":2.365,"metric":"score"},{"benchmark":"voicebench-ja-elyza","model":"llm-jp-moshi-v1","score":1,"metric":"score"},{"benchmark":"voicebench-ja-elyza","model":"j-moshi","score":1.034,"metric":"score"},{"benchmark":"voicebench-ja-spoken-elyza","model":"lfm2.5-audio-1.5b-jp","score":2.118,"metric":"score"},{"benchmark":"voicebench-ja-spoken-elyza","model":"qwen2.5-omni-3b","score":2.094,"metric":"score"},{"benchmark":"voicebench-ja-spoken-elyza","model":"llm-jp-moshi-v1","score":1.023,"metric":"score"},{"benchmark":"voicebench-ja-spoken-elyza","model":"j-moshi","score":1.012,"metric":"score"},{"benchmark":"voicebench-ja-m-ifeval","model":"lfm2.5-audio-1.5b-jp","score":0.143,"metric":"score"},{"benchmark":"voicebench-ja-m-ifeval","model":"qwen2.5-omni-3b","score":0.137,"metric":"score"},{"benchmark":"voicebench-ja-m-ifeval","model":"llm-jp-moshi-v1","score":0.11,"metric":"score"},{"benchmark":"voicebench-ja-m-ifeval","model":"j-moshi","score":0.151,"metric":"score"},{"benchmark":"asr-commonvoice-8-ja","model":"lfm2.5-audio-1.5b-jp","score":4.42,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"reazonspeech-nemo-v2","score":9.1,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"whisper-large-v3","score":8.5,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"whisper-large-v2","score":9.7,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"whisper-large","score":10,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"whisper-medium","score":11.5,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"whisper-base","score":28.6,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"whisper-small","score":15.1,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"whisper-tiny","score":53.7,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"lfm2.5-audio-1.5b-jp","score":8.07,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"reazonspeech-nemo-v2","score":7.4,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"whisper-large-v3","score":7.1,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"whisper-large-v2","score":8.2,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"whisper-large","score":8.9,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"whisper-medium","score":10,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"whisper-base","score":24.9,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"whisper-small","score":14.2,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"whisper-tiny","score":36.5,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"lfm2.5-audio-1.5b-jp","score":24.24,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"reazonspeech-nemo-v2","score":11.2,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"whisper-large-v3","score":14.9,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"whisper-large-v2","score":28.1,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"whisper-large","score":34.1,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"whisper-medium","score":33.2,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"whisper-base","score":70.4,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"whisper-small","score":41.5,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"whisper-tiny","score":137.9,"metric":"cer"},{"benchmark":"browsecomp","model":"gpt-5.2-pro","score":77.9,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.2-pro","score":36.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.2-pro","score":50,"metric":"avg@3"},{"benchmark":"arc-agi-2","model":"gemini-3-deep-think","score":45.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-pro","score":54.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2-pro","score":93.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.6","score":53.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.4","score":57.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemini-3.1-pro","score":54.2,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-opus-4.6","score":53.3,"metric":"avg@3"},{"benchmark":"mcp-atlas","model":"claude-opus-4.6","score":75.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.4","score":68.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3.1-pro","score":73.9,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gemini-3.1-pro","score":59.7,"metric":"percent"},{"benchmark":"cybergym","model":"claude-opus-4.6","score":73.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.6","score":69.1,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-opus-4.7","score":91,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-opus-4.6","score":84.7,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-mythos-preview","score":93.2,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-mythos-preview","score":59,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-opus-4.6","score":27.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.6","score":77.8,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"claude-fable-5","score":24.7,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"claude-opus-5","score":29,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-fable-5","score":42,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-opus-5","score":52.3,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5","score":1723,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-5","score":1824,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1711,"metric":"elo"},{"benchmark":"osworld-2.0","model":"claude-fable-5","score":72.9,"metric":"percent"},{"benchmark":"osworld-2.0","model":"claude-opus-5","score":75.4,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"claude-fable-5","score":36.1,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"claude-opus-5","score":39.6,"metric":"percent"},{"benchmark":"hle","model":"claude-fable-5","score":57.8,"metric":"avg@3"},{"benchmark":"hle","model":"claude-opus-5","score":56.6,"metric":"avg@3"},{"benchmark":"automationbench","model":"claude-fable-5","score":17.1,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-sol","score":19.6,"metric":"percent"},{"benchmark":"cursorbench-3.2","model":"claude-fable-5","score":70.5,"metric":"percent"},{"benchmark":"cursorbench-3.2","model":"claude-opus-5","score":70,"metric":"percent"},{"benchmark":"cursorbench-3.2","model":"gpt-5.6-sol","score":67.2,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-fable-5.1","score":50.3,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-opus-5","score":48,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"claude-fable-5.1","score":51.8,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"claude-opus-5","score":46.6,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"gpt-5.6-sol","score":41.7,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5.1","score":1735,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-5","score":1708,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-6-astra","score":1542,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1588,"metric":"elo"},{"benchmark":"automationbench","model":"gpt-5.6-sol","score":28.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-fable-5.1","score":65.6,"metric":"avg@3"},{"benchmark":"osworld-2.1","model":"claude-fable-5.1","score":80.7,"metric":"percent"},{"benchmark":"osworld-2.1","model":"claude-opus-5","score":74,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-fable-5.1","score":88.4,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"claude-opus-5","score":83.4,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-sonnet-5","score":10.3,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-sonnet-5.5","score":52.1,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-sonnet-5","score":42.4,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"claude-sonnet-5","score":34.1,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-5","score":1449,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-6-sol","score":1487,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-sonnet-5","score":1359,"metric":"elo"},{"benchmark":"aa-briefcase","model":"gpt-6-sol","score":1483,"metric":"elo"},{"benchmark":"hle-with-tools","model":"claude-sonnet-5","score":54.9,"metric":"avg@3"},{"benchmark":"osworld-2.1","model":"claude-sonnet-5","score":57,"metric":"percent"},{"benchmark":"chartography","model":"claude-sonnet-5","score":15.6,"metric":"percent"},{"benchmark":"chartography","model":"gpt-6-sol","score":53.6,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-4.5-haiku","score":735,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-6-luna","score":1437,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-5.5","score":1840,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-4.5-haiku","score":614,"metric":"elo"},{"benchmark":"aa-briefcase","model":"gpt-6-luna","score":1336,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-sonnet-5.5","score":1824,"metric":"elo"},{"benchmark":"osworld-2.1-offline","model":"claude-haiku-5.5","score":72.4,"metric":"percent"},{"benchmark":"osworld-2.1-offline","model":"claude-4.5-haiku","score":15.7,"metric":"percent"},{"benchmark":"osworld-2.1-offline","model":"gpt-6-luna","score":48.9,"metric":"percent"},{"benchmark":"osworld-2.1-offline","model":"claude-sonnet-5.5","score":83.9,"metric":"percent"},{"benchmark":"hle","model":"claude-4.5-haiku","score":10.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-4.5-haiku","score":18.7,"metric":"avg@3"},{"benchmark":"terminal-bench-4.0","model":"claude-4.5-haiku","score":0,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-6-luna","score":16.4,"metric":"percent"},{"benchmark":"chartography","model":"claude-4.5-haiku","score":6.4,"metric":"percent"},{"benchmark":"chartography","model":"gpt-6-luna","score":29.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.5","score":58.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.7","score":66.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.5","score":78.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.1-pro","score":70.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-opus-4.7","score":82.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"gemini-3.1-pro","score":76.2,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"gpt-5.5","score":1769,"metric":"elo"},{"benchmark":"financeagent-v2","model":"claude-opus-4.7","score":51.5,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gpt-5.5","score":51.8,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gemini-3.1-pro","score":43,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-sonnet-4.6","score":58.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-sonnet-4.6","score":67,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.8","score":82.7,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-4.6","score":34.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-sonnet-4.6","score":46.8,"metric":"avg@3"},{"benchmark":"osworld-verified","model":"claude-sonnet-4.6","score":78.5,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-4.6","score":1395,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-4.8","score":1615,"metric":"elo"},{"benchmark":"frontiercode-diamond","model":"claude-opus-4.8","score":13.4,"metric":"percent"},{"benchmark":"frontiercode-diamond","model":"gpt-5.5","score":5.7,"metric":"percent"},{"benchmark":"gdp-pdf","model":"claude-opus-4.8","score":22.5,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-5.5","score":24.9,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gemini-3.1-pro","score":16.7,"metric":"percent"},{"benchmark":"blueprint-bench-2","model":"claude-opus-4.8","score":14.5,"metric":"percent"},{"benchmark":"blueprint-bench-2","model":"gpt-5.5","score":36.2,"metric":"percent"},{"benchmark":"blueprint-bench-2","model":"gemini-3.1-pro","score":26.5,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.5","score":12.9,"metric":"percent"},{"benchmark":"automationbench","model":"gemini-3.1-pro","score":9.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-mythos-preview","score":85.4,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-fable-5","score":13.3,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-opus-4.8","score":10.4,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gpt-5.5","score":2.1,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gemini-3.1-pro","score":0,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"claude-mythos-5","score":46.1,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"claude-mythos-preview","score":29.6,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"claude-opus-4.8","score":40,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-mythos-5","score":83.9,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-mythos-preview","score":82.6,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-opus-4.8","score":80.4,"metric":"percent"},{"benchmark":"exploitbench","model":"claude-mythos-5","score":78,"metric":"percent"},{"benchmark":"exploitbench","model":"claude-mythos-preview","score":69,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.5","score":34,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-mythos-preview","score":64.7,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-opus-4.8","score":56.9,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gpt-5.5","score":51.8,"metric":"percent"},{"benchmark":"frontierbench","model":"claude-fable-5","score":33.7,"metric":"percent"},{"benchmark":"frontierbench","model":"claude-opus-4.8","score":21.1,"metric":"percent"},{"benchmark":"frontierbench","model":"gpt-5.6-sol","score":34.4,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5","score":1747,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-4.8","score":1593,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1736,"metric":"elo"},{"benchmark":"arc-agi-3","model":"claude-opus-4.8","score":1.5,"metric":"percent"},{"benchmark":"hle","model":"claude-fable-5","score":56.5,"metric":"avg@3"},{"benchmark":"osworld-2.0","model":"claude-fable-5","score":66.1,"metric":"percent"},{"benchmark":"osworld-2.0","model":"claude-opus-4.8","score":55.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-4.8","score":59,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-opus-4.8","score":46.5,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-4.8","score":17,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-opus-5","score":11.7,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gpt-5.6-sol","score":2.5,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-opus-4.8","score":57.4,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"claude-opus-5","score":49.4,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"claude-fable-5","score":46.5,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"claude-opus-4.8","score":42.4,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-opus-5","score":90.1,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-mythos-5","score":89,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-opus-4.8","score":88.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-mythos-preview","score":94.5,"metric":"percent"},{"benchmark":"usamo-2026","model":"claude-opus-4.6","score":66.2,"metric":"percent"},{"benchmark":"usamo-2026","model":"gpt-5.4","score":95.2,"metric":"percent"},{"benchmark":"usamo-2026","model":"gemini-3.1-pro","score":74.4,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k-1m","model":"claude-mythos-preview","score":80,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k-1m","model":"claude-opus-4.6","score":38.7,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k-1m","model":"gpt-5.4","score":21.4,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-opus-4.7","score":34.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-opus-4.6","score":57.7,"metric":"percent"},{"benchmark":"screenspot-pro-with-tools","model":"claude-opus-4.7","score":87.6,"metric":"percent"},{"benchmark":"screenspot-pro-with-tools","model":"claude-opus-4.6","score":83.1,"metric":"percent"},{"benchmark":"officeqa","model":"claude-opus-4.7","score":86.3,"metric":"percent"},{"benchmark":"officeqa","model":"claude-opus-4.6","score":73.5,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-opus-4.7","score":80.6,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-opus-4.6","score":57.1,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.4","score":51.1,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gemini-3.1-pro","score":42.9,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.4","score":57.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.6","score":93,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.1-pro","score":98,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-opus-4.8","score":38.4,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-opus-4.7","score":79.8,"metric":"percent"},{"benchmark":"chartqa-pro","model":"claude-opus-4.7","score":67.6,"metric":"percent"},{"benchmark":"chartqa-pro-with-tools","model":"claude-opus-4.8","score":72.3,"metric":"percent"},{"benchmark":"chartqa-pro-with-tools","model":"claude-opus-4.7","score":69.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"gemini-3.5-flash","score":78.4,"metric":"percent"},{"benchmark":"screenspot-pro-with-tools","model":"claude-opus-4.8","score":87.9,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gemini-3.5-flash","score":57.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.7","score":79.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3.1-pro","score":78.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3.5-flash","score":83.6,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-4.7","score":9.9,"metric":"percent"},{"benchmark":"automationbench","model":"gemini-3.5-flash","score":14.5,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"claude-opus-4.8","score":85.9,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"claude-opus-4.7","score":76.9,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"gpt-5.5","score":73.7,"metric":"percent"},{"benchmark":"graphwalks-parents-256k","model":"claude-opus-4.8","score":99.3,"metric":"percent"},{"benchmark":"graphwalks-parents-256k","model":"claude-opus-4.7","score":93.6,"metric":"percent"},{"benchmark":"graphwalks-parents-256k","model":"gpt-5.5","score":90.1,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-mythos-preview","score":87.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-mythos-preview","score":86.2,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-mythos-5","score":93.5,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-mythos-preview","score":92.5,"metric":"percent"},{"benchmark":"arxivmath","model":"claude-mythos-5","score":78.5,"metric":"percent"},{"benchmark":"arxivmath","model":"claude-mythos-preview","score":68.7,"metric":"percent"},{"benchmark":"arxivmath","model":"claude-opus-4.8","score":71.8,"metric":"percent"},{"benchmark":"arxivmath","model":"gpt-5.5","score":71.5,"metric":"percent"},{"benchmark":"arxivmath","model":"gemini-3.1-pro","score":64.8,"metric":"percent"},{"benchmark":"riemannbench","model":"claude-mythos-5","score":55,"metric":"percent"},{"benchmark":"riemannbench","model":"claude-mythos-preview","score":43,"metric":"percent"},{"benchmark":"riemannbench","model":"claude-opus-4.8","score":34,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"claude-mythos-5","score":91.1,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"claude-mythos-preview","score":85.7,"metric":"percent"},{"benchmark":"graphwalks-parents-256k","model":"claude-mythos-5","score":99.96,"metric":"percent"},{"benchmark":"graphwalks-parents-256k","model":"claude-mythos-preview","score":99.9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-fable-5","score":57.9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-opus-4.8","score":48.1,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.5","score":52.6,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gemini-3.1-pro","score":18.1,"metric":"percent"},{"benchmark":"blueprint-bench-2","model":"gemini-3.5-flash","score":33.6,"metric":"percent"},{"benchmark":"legal-agent-benchmark","model":"claude-mythos-5","score":16.9,"metric":"percent"},{"benchmark":"legal-agent-benchmark","model":"claude-mythos-preview","score":13.4,"metric":"percent"},{"benchmark":"legal-agent-benchmark","model":"claude-opus-4.8","score":9.6,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gemini-3.5-flash","score":0.8,"metric":"percent"},{"benchmark":"healthbench","model":"claude-mythos-preview","score":61.1,"metric":"percent"},{"benchmark":"healthbench","model":"claude-opus-4.8","score":59.3,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-5.5","score":56.5,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemini-3.5-flash","score":55.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.5-flash","score":76.2,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-sonnet-4.6","score":76.2,"metric":"percent"},{"benchmark":"hle","model":"gemini-3.5-flash","score":40.2,"metric":"avg@3"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.5","score":1509,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.5-flash","score":1357,"metric":"elo"},{"benchmark":"automationbench","model":"claude-sonnet-4.6","score":5.3,"metric":"percent"},{"benchmark":"legal-agent-benchmark","model":"claude-sonnet-5","score":8.9,"metric":"percent"},{"benchmark":"legal-agent-benchmark","model":"claude-sonnet-4.6","score":8,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-sonnet-5","score":5.8,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-sonnet-4.6","score":5.4,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-sonnet-4.6","score":44.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-fable-5","score":86.6,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-fable-5","score":54.1,"metric":"percent"},{"benchmark":"frontierbench","model":"claude-fable-5","score":33.8,"metric":"percent"},{"benchmark":"aa-briefcase","model":"claude-opus-4.8","score":1346,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-fable-5","score":1574,"metric":"elo"},{"benchmark":"aa-briefcase","model":"gpt-5.6-sol","score":1505,"metric":"elo"},{"benchmark":"arc-agi-1","model":"claude-opus-4.8","score":92.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.8","score":72.1,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-mythos-5","score":45,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-fable-5","score":63.3,"metric":"percent"},{"benchmark":"aa-briefcase","model":"claude-fable-5","score":1572,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-opus-5","score":1685,"metric":"elo"},{"benchmark":"aa-briefcase","model":"gpt-5.6-sol","score":1502,"metric":"elo"},{"benchmark":"arc-agi-1","model":"gpt-5.6-sol","score":96.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5","score":90.42,"metric":"percent"},{"benchmark":"osworld-2.1-strict","model":"claude-opus-5","score":37.2,"metric":"percent"},{"benchmark":"osworld-2.1-strict","model":"claude-fable-5.1","score":42.8,"metric":"percent"},{"benchmark":"aa-briefcase","model":"claude-opus-5","score":1673,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-fable-5.1","score":1678,"metric":"elo"},{"benchmark":"aa-briefcase","model":"gpt-6-astra","score":1569,"metric":"elo"},{"benchmark":"swe-bench-multimodal","model":"claude-sonnet-5","score":28.1,"metric":"percent"},{"benchmark":"hle","model":"claude-sonnet-5","score":43.1,"metric":"avg@3"},{"benchmark":"automationbench","model":"claude-sonnet-5","score":10.7,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-5.5","score":42.5,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-6-sol","score":32,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-4.5-haiku","score":67.4,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"claude-4.5-haiku","score":19.8,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-haiku-5.5","score":45.8,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-4.5-haiku","score":32.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.1-codex-mini-high","score":49,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1-codex-mini-high","score":46.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.3-codex","score":74,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.2","score":47.3,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.3-codex","score":51.9,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.2","score":46.3,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.3-codex","score":77.3,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.2-pro","score":74.1,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.3-codex","score":54,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.2","score":59.5,"metric":"percent"},{"benchmark":"openai-internal-investment-banking-modeling","model":"gpt-5.4","score":87.3,"metric":"percent"},{"benchmark":"openai-internal-investment-banking-modeling","model":"gpt-5.4-pro","score":83.6,"metric":"percent"},{"benchmark":"openai-internal-investment-banking-modeling","model":"gpt-5.3-codex","score":79.3,"metric":"percent"},{"benchmark":"openai-internal-investment-banking-modeling","model":"gpt-5.2","score":68.4,"metric":"percent"},{"benchmark":"openai-internal-investment-banking-modeling","model":"gpt-5.2-pro","score":71.7,"metric":"percent"},{"benchmark":"officeqa","model":"gpt-5.3-codex","score":65.1,"metric":"percent"},{"benchmark":"officeqa","model":"gpt-5.2","score":63.1,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.2","score":45.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.2","score":25.2,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.2","score":40.7,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.2","score":18.8,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.2-pro","score":31.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.3-codex","score":92.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.2","score":92.4,"metric":"percent"},{"benchmark":"hle","model":"gpt-5.2","score":34.5,"metric":"avg@3"},{"benchmark":"graphwalks-bfs","model":"gpt-5.2","score":94,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gpt-5.2","score":89,"metric":"percent"},{"benchmark":"graphwalks-parents-256k-1m","model":"gpt-5.4","score":32.4,"metric":"percent"},{"benchmark":"mrcr-8k-8n","model":"gpt-5.4","score":97.3,"metric":"percent"},{"benchmark":"mrcr-8k-8n","model":"gpt-5.2","score":98.2,"metric":"percent"},{"benchmark":"mrcr-16k-8n","model":"gpt-5.4","score":91.4,"metric":"percent"},{"benchmark":"mrcr-16k-8n","model":"gpt-5.2","score":89.3,"metric":"percent"},{"benchmark":"mrcr-32k-8n","model":"gpt-5.4","score":97.2,"metric":"percent"},{"benchmark":"mrcr-32k-8n","model":"gpt-5.2","score":95.3,"metric":"percent"},{"benchmark":"mrcr-64k-8n","model":"gpt-5.2","score":92,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.2","score":85.6,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"gpt-5.4","score":79.3,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"gpt-5.2","score":77,"metric":"percent"},{"benchmark":"mrcr-512k-8n","model":"gpt-5.4","score":57.5,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"gpt-5.4","score":36.6,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2","score":86.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-pro","score":90.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2","score":52.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-4.1","score":43.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5-mini-high","score":45.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5-mini-high","score":38.2,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5-mini-high","score":26.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-mini-high","score":81.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5-mini-high","score":42,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5-mini-high","score":47.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-mini-high","score":74.1,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5-mini-high","score":31.6,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5-mini-high","score":18.3,"metric":"avg@3"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5.4","score":81.5,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gpt-5-mini-high","score":74.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-mini-high","score":67.5,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5-mini-high","score":0.1791,"metric":"edit_distance"},{"benchmark":"mrcr-128k-8n","model":"gpt-5-mini-high","score":35.1,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"gpt-5.4-mini","score":33.6,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"gpt-5.4-nano","score":33.1,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"gpt-5-mini-high","score":19.4,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gpt-5.4","score":93.1,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gpt-5-mini-high","score":73.4,"metric":"percent"},{"benchmark":"graphwalks-parents","model":"gpt-5-mini-high","score":64.3,"metric":"percent"},{"benchmark":"openai-internal-expert-swe","model":"gpt-5.5","score":73.1,"metric":"percent"},{"benchmark":"openai-internal-expert-swe","model":"gpt-5.4","score":68.5,"metric":"percent"},{"benchmark":"gdpval","model":"claude-opus-4.7","score":80.3,"metric":"percent"},{"benchmark":"gdpval","model":"gemini-3.1-pro","score":67.3,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"claude-opus-4.7","score":43.8,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gemini-3.1-pro","score":36.9,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"claude-opus-4.7","score":22.9,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gemini-3.1-pro","score":16.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-opus-4.7","score":64.3,"metric":"percent"},{"benchmark":"openai-internal-investment-banking-modeling","model":"gpt-5.5","score":88.5,"metric":"percent"},{"benchmark":"openai-internal-investment-banking-modeling","model":"gpt-5.5-pro","score":88.6,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-opus-4.7","score":43.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.4","score":70.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.4","score":92.8,"metric":"percent"},{"benchmark":"cybersecurity-capture-the-flag-challenges","model":"gpt-5.5","score":88.1,"metric":"percent"},{"benchmark":"cybersecurity-capture-the-flag-challenges","model":"gpt-5.4","score":83.7,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"gpt-5.4","score":62.5,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"gpt-5.5","score":45.4,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"gpt-5.4","score":9.4,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"claude-opus-4.6","score":41.2,"metric":"percent"},{"benchmark":"graphwalks-parents-256k","model":"gpt-5.4","score":82.8,"metric":"percent"},{"benchmark":"graphwalks-parents-1m","model":"gpt-5.5","score":58.5,"metric":"percent"},{"benchmark":"graphwalks-parents-1m","model":"gpt-5.4","score":44.4,"metric":"percent"},{"benchmark":"graphwalks-parents-1m","model":"claude-opus-4.6","score":72,"metric":"percent"},{"benchmark":"mrcr-8k-8n","model":"gpt-5.5","score":98.1,"metric":"percent"},{"benchmark":"mrcr-16k-8n","model":"gpt-5.5","score":93,"metric":"percent"},{"benchmark":"mrcr-32k-8n","model":"gpt-5.5","score":96.5,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"gpt-5.5","score":87.5,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"claude-opus-4.7","score":59.2,"metric":"percent"},{"benchmark":"mrcr-512k-8n","model":"gpt-5.5","score":81.5,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"gpt-5.5","score":74,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"claude-opus-4.7","score":32.2,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.7","score":93.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.7","score":75.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.5","score":46.9,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-fable-5","score":40.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.8","score":45.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gemini-3.1-pro","score":32.1,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.5","score":1493.7,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5","score":1759.6,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-4.8","score":1600.1,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.1-pro","score":962.3,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.5-flash","score":1348.8,"metric":"elo"},{"benchmark":"openai-internal-management-consulting","model":"gpt-5.6-sol","score":43.2,"metric":"percent"},{"benchmark":"openai-internal-management-consulting","model":"gpt-5.6-terra","score":37.2,"metric":"percent"},{"benchmark":"openai-internal-management-consulting","model":"gpt-5.6-luna","score":35.4,"metric":"percent"},{"benchmark":"openai-internal-management-consulting","model":"gpt-5.5","score":31.3,"metric":"percent"},{"benchmark":"openai-internal-management-consulting","model":"claude-fable-5","score":35.5,"metric":"percent"},{"benchmark":"openai-internal-management-consulting","model":"claude-opus-4.8","score":31.6,"metric":"percent"},{"benchmark":"openai-internal-management-consulting","model":"gemini-3.1-pro","score":13.2,"metric":"percent"},{"benchmark":"big-finance-bench","model":"gpt-5.6-sol","score":53,"metric":"percent"},{"benchmark":"big-finance-bench","model":"gpt-5.6-terra","score":51,"metric":"percent"},{"benchmark":"big-finance-bench","model":"gpt-5.6-luna","score":36,"metric":"percent"},{"benchmark":"big-finance-bench","model":"gpt-5.5","score":49,"metric":"percent"},{"benchmark":"big-finance-bench","model":"claude-opus-4.8","score":44,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.5","score":59.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.5","score":67,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.1-pro","score":11.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-sol-ultra","score":91.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.5","score":85.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-fable-5","score":83.1,"metric":"percent"},{"benchmark":"genebench-pro","model":"gpt-5.5","score":12,"metric":"percent"},{"benchmark":"genebench-pro","model":"claude-opus-4.8","score":16,"metric":"percent"},{"benchmark":"genebench-pro","model":"gemini-3.1-pro","score":3.1,"metric":"percent"},{"benchmark":"genebench-pro","model":"gemini-3.5-flash","score":8.14,"metric":"percent"},{"benchmark":"lifescibench","model":"gpt-5.5","score":50.4,"metric":"percent"},{"benchmark":"lifescibench","model":"claude-opus-4.8","score":53.6,"metric":"percent"},{"benchmark":"medchembench-internal","model":"gpt-5.6-sol","score":48.3,"metric":"percent"},{"benchmark":"medchembench-internal","model":"gpt-5.6-terra","score":35,"metric":"percent"},{"benchmark":"medchembench-internal","model":"gpt-5.6-luna","score":30.4,"metric":"percent"},{"benchmark":"medchembench-internal","model":"gpt-5.5","score":35.5,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gpt-5.5","score":49.5,"metric":"percent"},{"benchmark":"healthbench-professional","model":"claude-opus-4.8","score":53,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-5.5","score":47.5,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.6-sol-ultra","score":92.2,"metric":"percent"},{"benchmark":"benchcad","model":"gpt-5.5","score":44.4,"metric":"percent"},{"benchmark":"benchcad","model":"claude-mythos-5","score":38.4,"metric":"percent"},{"benchmark":"benchcad","model":"claude-mythos-preview","score":35.5,"metric":"percent"},{"benchmark":"benchcad","model":"claude-opus-4.8","score":27.3,"metric":"percent"},{"benchmark":"benchcad-python-tool","model":"gpt-5.6-sol","score":83.4,"metric":"percent"},{"benchmark":"benchcad-python-tool","model":"gpt-5.6-terra","score":78.2,"metric":"percent"},{"benchmark":"benchcad-python-tool","model":"gpt-5.6-luna","score":73.9,"metric":"percent"},{"benchmark":"benchcad-python-tool","model":"gpt-5.5","score":55.8,"metric":"percent"},{"benchmark":"benchcad-python-tool","model":"claude-mythos-5","score":65,"metric":"percent"},{"benchmark":"benchcad-python-tool","model":"claude-mythos-preview","score":61,"metric":"percent"},{"benchmark":"benchcad-python-tool","model":"claude-opus-4.8","score":51.8,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"gpt-5.6-sol-ultra","score":74.3,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"gpt-5.5","score":45.8,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.5","score":47.9,"metric":"percent"},{"benchmark":"exploitbench","model":"claude-mythos-preview","score":74.2,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-5.5","score":15.1,"metric":"percent"},{"benchmark":"openai-internal-research-debugging","model":"gpt-5.6-sol","score":68.3,"metric":"percent"},{"benchmark":"openai-internal-research-debugging","model":"gpt-5.6-terra","score":67.8,"metric":"percent"},{"benchmark":"openai-internal-research-debugging","model":"gpt-5.6-luna","score":50.8,"metric":"percent"},{"benchmark":"openai-internal-research-debugging","model":"gpt-5.5","score":50,"metric":"percent"},{"benchmark":"kernelgen-1p","model":"gpt-5.6-sol","score":61.1,"metric":"percent"},{"benchmark":"kernelgen-1p","model":"gpt-5.6-terra","score":49.2,"metric":"percent"},{"benchmark":"kernelgen-1p","model":"gpt-5.6-luna","score":22.4,"metric":"percent"},{"benchmark":"kernelgen-1p","model":"gpt-5.5","score":29.3,"metric":"percent"},{"benchmark":"nanogpt","model":"gpt-5.6-sol","score":9.69,"metric":"percent"},{"benchmark":"nanogpt","model":"gpt-5.6-terra","score":14.5,"metric":"percent"},{"benchmark":"nanogpt","model":"gpt-5.6-luna","score":1.66,"metric":"percent"},{"benchmark":"nanogpt","model":"gpt-5.5","score":2.65,"metric":"percent"},{"benchmark":"posttrainbench-lite","model":"gpt-5.5","score":38.8,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-5.5","score":26,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.8","score":92,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.5","score":85.3,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"claude-fable-5","score":87,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"claude-opus-4.8","score":80,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gemini-3.1-pro","score":59.6,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.5","score":72.5,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"claude-fable-5","score":87.8,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"claude-opus-4.8","score":56.1,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-mythos-preview","score":61.1,"metric":"percent"},{"benchmark":"mrcr-512k-8n","model":"gpt-5.6-terra","score":89.6,"metric":"percent"},{"benchmark":"mrcr-512k-8n","model":"gpt-5.6-luna","score":41.3,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"gpt-5.6-terra","score":72.5,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"gpt-5.6-luna","score":41.3,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"claude-mythos-5","score":79.4,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"claude-mythos-preview","score":74.3,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"claude-opus-4.8","score":68.1,"metric":"percent"},{"benchmark":"arc-agi-3","model":"gpt-5.5","score":0.43,"metric":"percent"},{"benchmark":"arc-agi-3","model":"gemini-3.1-pro","score":0.42,"metric":"percent"},{"benchmark":"openai-internal-advanced-cyber-completion-rate","model":"gpt-5.6-sol","score":2,"metric":"percent"},{"benchmark":"openai-internal-advanced-cyber-completion-rate","model":"gpt-5.6-cyber","score":95,"metric":"percent"},{"benchmark":"openai-internal-advanced-cyber-completion-rate","model":"gpt-5.5-cyber","score":57.3,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-5.6-sol","score":30.8,"metric":"percent"},{"benchmark":"exploitgym","model":"gpt-5.5-cyber","score":21.2,"metric":"percent"},{"benchmark":"openai-internal-zero-day-discovery","model":"gpt-5.6-sol","score":15.8,"metric":"percent"},{"benchmark":"openai-internal-zero-day-discovery","model":"gpt-5.6-cyber","score":24.5,"metric":"percent"},{"benchmark":"openai-internal-zero-day-discovery","model":"gpt-5.5-cyber","score":17.5,"metric":"percent"},{"benchmark":"openai-internal-vuln-discovery-report-writing","model":"gpt-5.6-sol","score":17.9,"metric":"percent"},{"benchmark":"openai-internal-vuln-discovery-report-writing","model":"gpt-5.6-cyber","score":14.5,"metric":"percent"},{"benchmark":"openai-internal-vuln-discovery-report-writing","model":"gpt-5.5-cyber","score":11.8,"metric":"percent"},{"benchmark":"exploitbench","model":"gpt-5.5-cyber","score":73.9,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-luna","score":17,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5","score":55.9,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-luna","score":50.4,"metric":"percent"},{"benchmark":"openai-internal-factual-error-rate","model":"gpt-5.6-luna","score":12,"metric":"percent"},{"benchmark":"openai-internal-factual-error-rate","model":"gpt-5.6-sol","score":8.4,"metric":"percent"},{"benchmark":"openai-internal-factual-error-rate","model":"gpt-6-astra","score":3.9,"metric":"percent"},{"benchmark":"openai-internal-factual-error-rate","model":"gpt-6-luna","score":7.6,"metric":"percent"},{"benchmark":"openai-internal-factual-error-rate","model":"gpt-6-sol","score":4.5,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-5.6-luna","score":39.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-luna","score":62.2,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-5.6-luna","score":52.7,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-5.6-sol","score":66.2,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-6-astra","score":73.5,"metric":"percent"},{"benchmark":"openai-internal-coding-deception","model":"gpt-5.6-luna","score":9.5,"metric":"percent"},{"benchmark":"openai-internal-coding-deception","model":"gpt-5.6-sol","score":10.4,"metric":"percent"},{"benchmark":"openai-internal-coding-deception","model":"gpt-6-astra","score":0.5,"metric":"percent"},{"benchmark":"openai-internal-coding-deception","model":"gpt-6-luna","score":2.8,"metric":"percent"},{"benchmark":"openai-internal-coding-deception","model":"gpt-6-sol","score":1.3,"metric":"percent"},{"benchmark":"openai-internal-broken-search-nondisclosure","model":"gpt-5.6-luna","score":78.3,"metric":"percent"},{"benchmark":"openai-internal-broken-search-nondisclosure","model":"gpt-5.6-sol","score":77.5,"metric":"percent"},{"benchmark":"openai-internal-broken-search-nondisclosure","model":"gpt-6-astra","score":1.5,"metric":"percent"},{"benchmark":"openai-internal-broken-search-nondisclosure","model":"gpt-6-luna","score":28.7,"metric":"percent"},{"benchmark":"openai-internal-broken-search-nondisclosure","model":"gpt-6-sol","score":4.9,"metric":"percent"},{"benchmark":"openai-internal-reviewer-bypass","model":"gpt-5.6-luna","score":4.3,"metric":"percent"},{"benchmark":"openai-internal-reviewer-bypass","model":"gpt-5.6-sol","score":7.3,"metric":"percent"},{"benchmark":"openai-internal-reviewer-bypass","model":"gpt-6-astra","score":0,"metric":"percent"},{"benchmark":"openai-internal-reviewer-bypass","model":"gpt-6-luna","score":0.3,"metric":"percent"},{"benchmark":"openai-internal-reviewer-bypass","model":"gpt-6-sol","score":0,"metric":"percent"},{"benchmark":"openai-internal-warning-circumvention","model":"gpt-5.6-luna","score":76.5,"metric":"percent"},{"benchmark":"openai-internal-warning-circumvention","model":"gpt-5.6-sol","score":68.2,"metric":"percent"},{"benchmark":"openai-internal-warning-circumvention","model":"gpt-6-astra","score":17.4,"metric":"percent"},{"benchmark":"openai-internal-warning-circumvention","model":"gpt-6-luna","score":42.4,"metric":"percent"},{"benchmark":"openai-internal-warning-circumvention","model":"gpt-6-sol","score":64.4,"metric":"percent"},{"benchmark":"openai-internal-unauthorized-agent-interaction","model":"gpt-6-astra","score":0,"metric":"percent"},{"benchmark":"openai-internal-unauthorized-agent-interaction","model":"gpt-6-sol","score":11.3,"metric":"percent"},{"benchmark":"openai-internal-unauthorized-agent-interaction","model":"gpt-5.6-sol","score":51.9,"metric":"percent"},{"benchmark":"openai-internal-unauthorized-agent-interaction","model":"gpt-6-luna","score":0,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-6-astra","score":32.2,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"claude-opus-5.5","score":63.3,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"gpt-6-astra","score":68.1,"metric":"percent"},{"benchmark":"openai-internal-factual-error-rate","model":"gpt-6.1-sol","score":4.1,"metric":"percent"},{"benchmark":"openai-internal-broken-search-nondisclosure","model":"gpt-6.1-sol","score":2.1,"metric":"percent"},{"benchmark":"openai-internal-reviewer-bypass","model":"gpt-6.1-sol","score":0,"metric":"percent"},{"benchmark":"openai-internal-warning-circumvention","model":"gpt-6.1-sol","score":23.5,"metric":"percent"},{"benchmark":"openai-internal-cua-safety","model":"gpt-6.1-sol","score":4.3,"metric":"percent"},{"benchmark":"openai-internal-cua-safety","model":"gpt-6-sol","score":17.4,"metric":"percent"},{"benchmark":"openai-internal-cua-safety","model":"gpt-6-luna","score":13.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b","score":74.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-9b","score":82.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-4b","score":79.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-oss-20b","score":87.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-9b","score":91.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-4b","score":88.8,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-oss-20b","score":71.4,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-next-80b-a3b-thinking","score":89.7,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-30b-a3b-thinking-2507","score":87.4,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-9b","score":88.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-4b","score":85.1,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-oss-20b","score":48.5,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-9b","score":58.2,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-4b","score":52.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-next-80b-a3b-thinking","score":77.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-9b","score":81.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-4b","score":76.2,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-20b","score":88.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-9b","score":91.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-4b","score":89.8,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b","score":65.1,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-next-80b-a3b-thinking","score":61.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b-thinking-2507","score":51.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-9b","score":64.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":59.2,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-oss-20b","score":40.1,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-next-80b-a3b-thinking","score":51.3,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-30b-a3b-thinking-2507","score":46.5,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-9b","score":54.5,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-4b","score":49,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-20b","score":30.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-next-80b-a3b-thinking","score":51.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-30b-a3b-thinking-2507","score":49,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-9b","score":63,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-4b","score":57,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-oss-20b","score":45.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-next-80b-a3b-thinking","score":48,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-30b-a3b-thinking-2507","score":44.8,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-9b","score":55.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-4b","score":50,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-oss-20b","score":76.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-next-80b-a3b-thinking","score":73.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-30b-a3b-thinking-2507","score":63.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.5-9b","score":83.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.5-4b","score":74,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-oss-20b","score":81.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-next-80b-a3b-thinking","score":81.2,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-30b-a3b-thinking-2507","score":73.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-9b","score":82.9,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-4b","score":76.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b","score":74.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-9b","score":65.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b","score":55.8,"metric":"percent"},{"benchmark":"ojbench","model":"gpt-oss-20b","score":36.3,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-9b","score":29.2,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-4b","score":24.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-next-80b-a3b-thinking","score":49.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-30b-a3b-thinking-2507","score":42.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-9b","score":66.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":50.3,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3-next-80b-a3b-thinking","score":29.5,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3-30b-a3b-thinking-2507","score":14.1,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-9b","score":29.8,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-4b","score":22,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3-next-80b-a3b-thinking","score":0.4,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3-30b-a3b-thinking-2507","score":4.9,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.5-9b","score":18,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.5-4b","score":17.6,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-oss-20b","score":69.7,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-next-80b-a3b-thinking","score":81.3,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-30b-a3b-thinking-2507","score":78.4,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-9b","score":81.2,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-4b","score":76.1,"metric":"percent"},{"benchmark":"mmlu-prox","model":"gpt-oss-20b","score":67.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-next-80b-a3b-thinking","score":73.6,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-30b-a3b-thinking-2507","score":69.1,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-9b","score":76.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-4b","score":71.5,"metric":"percent"},{"benchmark":"nova-63","model":"gpt-oss-20b","score":48.7,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3-next-80b-a3b-thinking","score":53.3,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3-30b-a3b-thinking-2507","score":52.5,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.5-9b","score":55.9,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.5-4b","score":54.3,"metric":"percent"},{"benchmark":"include","model":"gpt-oss-20b","score":65.3,"metric":"percent"},{"benchmark":"include","model":"qwen3-next-80b-a3b-thinking","score":78.3,"metric":"percent"},{"benchmark":"include","model":"qwen3.5-9b","score":75.6,"metric":"percent"},{"benchmark":"include","model":"qwen3.5-4b","score":71,"metric":"percent"},{"benchmark":"global-piqa","model":"gpt-oss-20b","score":79.8,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-next-80b-a3b-thinking","score":83.5,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-30b-a3b-thinking-2507","score":80.2,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.5-9b","score":83.2,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.5-4b","score":78.9,"metric":"percent"},{"benchmark":"polymath","model":"gpt-oss-20b","score":30.9,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-next-80b-a3b-thinking","score":62.4,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.5-9b","score":57.3,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.5-4b","score":51.1,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gpt-oss-20b","score":67.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-next-80b-a3b-thinking","score":57.4,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-30b-a3b-thinking-2507","score":69.3,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-9b","score":72.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-4b","score":66.6,"metric":"percent"},{"benchmark":"maxife","model":"gpt-oss-20b","score":80.1,"metric":"percent"},{"benchmark":"maxife","model":"qwen3-next-80b-a3b-thinking","score":79.9,"metric":"percent"},{"benchmark":"maxife","model":"qwen3-30b-a3b-thinking-2507","score":77.4,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.5-9b","score":83.4,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.5-4b","score":78,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-nano","score":75.8,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-flash-lite","score":73.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-9b","score":78.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-4b","score":77.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-nano","score":57.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-flash-lite","score":59.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-9b","score":70.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-4b","score":66.3,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-nano","score":62.2,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.5-flash-lite","score":52.1,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-9b","score":78.9,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-4b","score":74.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-5-nano","score":71.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-2.5-flash-lite","score":72.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-30b-a3b-instruct","score":81.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-9b","score":85.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-4b","score":85.1,"metric":"percent"},{"benchmark":"wemath","model":"gpt-5-nano","score":62.5,"metric":"percent"},{"benchmark":"wemath","model":"gemini-2.5-flash-lite","score":32.1,"metric":"percent"},{"benchmark":"wemath","model":"qwen3-vl-30b-a3b-instruct","score":70,"metric":"percent"},{"benchmark":"wemath","model":"qwen3.5-9b","score":75.2,"metric":"percent"},{"benchmark":"wemath","model":"qwen3.5-4b","score":75.4,"metric":"percent"},{"benchmark":"dynamath","model":"gpt-5-nano","score":78,"metric":"percent"},{"benchmark":"dynamath","model":"gemini-2.5-flash-lite","score":69.9,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3-vl-30b-a3b-instruct","score":80.1,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-9b","score":83.6,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-4b","score":83.3,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5-nano","score":1,"metric":"percent"},{"benchmark":"zerobench","model":"gemini-2.5-flash-lite","score":1,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3-vl-30b-a3b-instruct","score":0,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-9b","score":3,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-4b","score":3,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gpt-5-nano","score":22.2,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemini-2.5-flash-lite","score":19.2,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-30b-a3b-instruct","score":23.7,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-9b","score":31.1,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-4b","score":26.3,"metric":"percent"},{"benchmark":"vlmsareblind","model":"gpt-5-nano","score":66.7,"metric":"percent"},{"benchmark":"vlmsareblind","model":"gemini-2.5-flash-lite","score":68.4,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3-vl-30b-a3b-instruct","score":72.5,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.5-9b","score":93.7,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.5-4b","score":92.6,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5-nano","score":14.4,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-2.5-flash-lite","score":17.5,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-vl-30b-a3b-instruct","score":18.6,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.5-9b","score":28.6,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.5-4b","score":16,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5-nano","score":71.8,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-2.5-flash-lite","score":72.2,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-30b-a3b-instruct","score":77.4,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-9b","score":80.3,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-4b","score":79.5,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-nano","score":68.6,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-flash-lite","score":69.1,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-9b","score":79.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-4b","score":78.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gpt-5-nano","score":80.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemini-2.5-flash-lite","score":82.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-30b-a3b-instruct","score":88.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-9b","score":90.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-4b","score":89.4,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5-nano","score":46,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-2.5-flash-lite","score":54.1,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-30b-a3b-instruct","score":54.3,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-9b","score":51.2,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-4b","score":43.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5-nano","score":58.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.5-flash-lite","score":64.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-9b","score":69.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-4b","score":65,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5-nano","score":55.9,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemini-2.5-flash-lite","score":79.4,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3-vl-30b-a3b-instruct","score":86.8,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3.5-9b","score":87.7,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3.5-4b","score":86.2,"metric":"edit_distance"},{"benchmark":"charxiv-rq","model":"gpt-5-nano","score":50.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-flash-lite","score":56.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-9b","score":73,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-4b","score":70.8,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gpt-5-nano","score":31.8,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"gemini-2.5-flash-lite","score":46.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-30b-a3b-instruct","score":47.4,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-9b","score":57.7,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-4b","score":54.2,"metric":"percent"},{"benchmark":"cc-ocr","model":"gpt-5-nano","score":58.9,"metric":"percent"},{"benchmark":"cc-ocr","model":"gemini-2.5-flash-lite","score":72.9,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-30b-a3b-instruct","score":77.8,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-9b","score":79.3,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-4b","score":76.7,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-nano","score":81.9,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-flash-lite","score":85.7,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-9b","score":90.2,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-4b","score":89.6,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5-nano","score":75.3,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-flash-lite","score":82.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-30b-a3b-instruct","score":83.9,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-9b","score":89.2,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-4b","score":85,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5-nano","score":45.8,"metric":"percent"},{"benchmark":"erqa","model":"gemini-2.5-flash-lite","score":44.3,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-30b-a3b-instruct","score":45.3,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-9b","score":55.5,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-4b","score":54,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5-nano","score":80,"metric":"percent"},{"benchmark":"countbench","model":"gemini-2.5-flash-lite","score":79.2,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-30b-a3b-instruct","score":90,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-9b","score":97.2,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-4b","score":96.3,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-30b-a3b-instruct","score":89.3,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-9b","score":89.7,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-4b","score":88.1,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5-nano","score":74.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-2.5-flash-lite","score":66.1,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-30b-a3b-instruct","score":80.6,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-9b","score":83,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-4b","score":81.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5-nano","score":12.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-2.5-flash-lite","score":11.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-30b-a3b-instruct","score":54.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-9b","score":58.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-4b","score":54.6,"metric":"percent"},{"benchmark":"lingoqa","model":"gpt-5-nano","score":57,"metric":"percent"},{"benchmark":"lingoqa","model":"gemini-2.5-flash-lite","score":17.8,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3-vl-30b-a3b-instruct","score":62,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.5-9b","score":80.4,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.5-4b","score":74.4,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-30b-a3b-instruct","score":11.4,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3.5-9b","score":13.5,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3.5-4b","score":12.5,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3-vl-30b-a3b-instruct","score":10.3,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3.5-9b","score":11.8,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3.5-4b","score":9.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5-nano","score":71.7,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-2.5-flash-lite","score":74.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3-vl-30b-a3b-instruct","score":79.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.5-9b","score":84.5,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.5-4b","score":83.5,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-5-nano","score":66.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-2.5-flash-lite","score":72.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-30b-a3b-instruct","score":73.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-9b","score":78.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-4b","score":76.9,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5-nano","score":63,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-2.5-flash-lite","score":69.2,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-30b-a3b-instruct","score":75,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.5-9b","score":78.9,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.5-4b","score":74.1,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5-nano","score":69.2,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-2.5-flash-lite","score":78.5,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-30b-a3b-instruct","score":78.9,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-9b","score":84.4,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-4b","score":82.8,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-30b-a3b-instruct","score":72,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-9b","score":74.4,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-4b","score":71.2,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-2.5-flash-lite","score":60.9,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-30b-a3b-instruct","score":59.2,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-9b","score":70,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-4b","score":66.4,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5-nano","score":63.1,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-2.5-flash-lite","score":65.3,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3-vl-30b-a3b-instruct","score":66.1,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-9b","score":67.8,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-4b","score":64.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-30b-a3b-instruct","score":60.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-9b","score":65.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-4b","score":60.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3-vl-30b-a3b-instruct","score":30.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-9b","score":41.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-4b","score":35.6,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3-vl-30b-a3b-instruct","score":55,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.5-9b","score":57.8,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.5-4b","score":58.6,"metric":"percent"},{"benchmark":"tir-bench","model":"gpt-5-nano","score":18.5,"metric":"percent"},{"benchmark":"tir-bench","model":"gemini-2.5-flash-lite","score":21.5,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3-vl-30b-a3b-instruct","score":22.5,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3.5-9b","score":45.6,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3.5-4b","score":38.9,"metric":"percent"},{"benchmark":"v-star","model":"gpt-5-nano","score":68.1,"metric":"percent"},{"benchmark":"v-star","model":"gemini-2.5-flash-lite","score":69.6,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-30b-a3b-instruct","score":83.2,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.5-9b","score":90.1,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.5-4b","score":84.3,"metric":"percent"},{"benchmark":"slake","model":"gpt-5-nano","score":57,"metric":"percent"},{"benchmark":"slake","model":"gemini-2.5-flash-lite","score":65,"metric":"percent"},{"benchmark":"slake","model":"qwen3-vl-30b-a3b-instruct","score":68.8,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-9b","score":79,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-4b","score":76.1,"metric":"percent"},{"benchmark":"pmc-vqa","model":"gpt-5-nano","score":37.8,"metric":"percent"},{"benchmark":"pmc-vqa","model":"gemini-2.5-flash-lite","score":48.8,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3-vl-30b-a3b-instruct","score":51.5,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-9b","score":57.9,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-4b","score":55.5,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gpt-5-nano","score":26.7,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemini-2.5-flash-lite","score":35.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3-vl-30b-a3b-instruct","score":35.5,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-9b","score":49.9,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-4b","score":42.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":40.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-1.7b","score":64.4,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-4b-instruct-2507","score":80.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-1.7b","score":61,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-1.7b","score":21,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-1.7b","score":68.2,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-4b-instruct-2507","score":64.9,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-1.7b","score":46.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b-thinking-2507","score":74,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b-thinking","score":56.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-2b","score":66.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-0.8b","score":42.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-4b-thinking-2507","score":86.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-1.7b-thinking","score":73.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-2b","score":79.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-0.8b","score":59.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-4b-thinking-2507","score":82.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-1.7b-thinking","score":68.1,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-2b","score":73.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-0.8b","score":50.5,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-4b-thinking-2507","score":47.8,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-1.7b-thinking","score":31.2,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-2b","score":37.5,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-0.8b","score":21.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b-thinking-2507","score":65.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-1.7b-thinking","score":40.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-2b","score":51.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-0.8b","score":11.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b-thinking-2507","score":87.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-1.7b-thinking","score":72.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-2b","score":78.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-0.8b","score":44,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-4b-thinking-2507","score":50.4,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-1.7b-thinking","score":26.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-2b","score":41.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-0.8b","score":21,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-4b-thinking-2507","score":41.7,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-1.7b-thinking","score":27.2,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-2b","score":33.7,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-0.8b","score":18.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-4b-thinking-2507","score":32,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-1.7b-thinking","score":6.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-2b","score":25.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-0.8b","score":4.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-4b-thinking-2507","score":42.8,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-1.7b-thinking","score":26.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-2b","score":38.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-0.8b","score":26.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-4b-thinking-2507","score":57.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-1.7b-thinking","score":10.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.5-2b","score":22.9,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-4b-thinking-2507","score":69.6,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-1.7b-thinking","score":8.9,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-2b","score":19.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-4b-thinking-2507","score":39.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-2b","score":43.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-0.8b","score":25.3,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-4b-thinking-2507","score":70.8,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-1.7b-thinking","score":57,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-2b","score":63.1,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-0.8b","score":44.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-4b-thinking-2507","score":62.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3-1.7b-thinking","score":49.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-2b","score":52.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-0.8b","score":34.6,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3-4b-thinking-2507","score":47.1,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3-1.7b-thinking","score":40.3,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.5-2b","score":46.4,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.5-0.8b","score":42.4,"metric":"percent"},{"benchmark":"include","model":"qwen3-4b-thinking-2507","score":64.4,"metric":"percent"},{"benchmark":"include","model":"qwen3-1.7b-thinking","score":51.8,"metric":"percent"},{"benchmark":"include","model":"qwen3.5-2b","score":55.4,"metric":"percent"},{"benchmark":"include","model":"qwen3.5-0.8b","score":40.6,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-4b-thinking-2507","score":73.5,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-1.7b-thinking","score":63.1,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.5-2b","score":69.3,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.5-0.8b","score":59.4,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-4b-thinking-2507","score":46.2,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-1.7b-thinking","score":25.2,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.5-2b","score":26.1,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.5-0.8b","score":8.2,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-4b-thinking-2507","score":58.9,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3-1.7b-thinking","score":39.3,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-2b","score":45.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-0.8b","score":27.2,"metric":"percent"},{"benchmark":"maxife","model":"qwen3-4b-thinking-2507","score":72.1,"metric":"percent"},{"benchmark":"maxife","model":"qwen3-1.7b-thinking","score":50.7,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.5-2b","score":60.6,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.5-0.8b","score":39.2,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-4b-thinking","score":70.8,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-2b-thinking","score":61.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-2b","score":64.2,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-0.8b","score":49,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-4b-thinking","score":57,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-2b-thinking","score":42.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-2b","score":50.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-0.8b","score":31.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-4b-thinking","score":79.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-2b-thinking","score":73.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-2b","score":76.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-0.8b","score":62.2,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3-vl-4b-thinking","score":74.4,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3-vl-2b-thinking","score":66.7,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-2b","score":73.6,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-0.8b","score":49.9,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3-vl-4b-thinking","score":0,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3-vl-2b-thinking","score":0,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-2b","score":1,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-0.8b","score":0,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-4b-thinking","score":18.9,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3-vl-2b-thinking","score":13.2,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-2b","score":17.1,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-0.8b","score":12.9,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3-vl-4b-thinking","score":68.6,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3-vl-2b-thinking","score":50,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.5-2b","score":75.8,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.5-0.8b","score":59.4,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-4b-thinking","score":73.2,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-2b-thinking","score":69.5,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-2b","score":74.5,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-0.8b","score":63.4,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-4b-thinking","score":73.2,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-2b-thinking","score":68.1,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-2b","score":71.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-0.8b","score":58.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-4b-thinking","score":86.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-2b-thinking","score":81.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-2b","score":83.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-0.8b","score":69.9,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-4b-thinking","score":48.8,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-2b-thinking","score":43.6,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-2b","score":38.5,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-0.8b","score":31.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-4b-thinking","score":64.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-2b-thinking","score":54.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-2b","score":58,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-0.8b","score":53.1,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-4b-thinking","score":44.4,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3-vl-2b-thinking","score":33.8,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-2b","score":45.4,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-0.8b","score":33.6,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-4b-thinking","score":84.9,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-2b-thinking","score":80.4,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-2b","score":83.3,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-0.8b","score":69.9,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-4b-thinking","score":73.8,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-2b-thinking","score":68.3,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-2b","score":72.9,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-0.8b","score":63.2,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"qwen3-vl-4b-thinking","score":80,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3-vl-2b-thinking","score":65.9,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3.5-2b","score":79.8,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3.5-0.8b","score":61,"metric":"edit_distance"},{"benchmark":"charxiv-rq","model":"qwen3-vl-4b-thinking","score":50.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-2b-thinking","score":37.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-2b","score":58.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-0.8b","score":41.3,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-4b-thinking","score":80.8,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-2b-thinking","score":79.2,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-2b","score":84.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-0.8b","score":74.5,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-4b-thinking","score":88.2,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-2b-thinking","score":84.8,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-2b","score":84.8,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-0.8b","score":79.3,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-4b-thinking","score":89.4,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-2b-thinking","score":84.1,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-2b","score":91.4,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-0.8b","score":77,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-4b-thinking","score":39.4,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3-vl-2b-thinking","score":36,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-2b","score":35.9,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-0.8b","score":31.6,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-4b-thinking","score":47.3,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-2b-thinking","score":41.8,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-2b","score":43.8,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-0.8b","score":34.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-4b-thinking","score":80.7,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-2b-thinking","score":75.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-2b","score":77.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-0.8b","score":68.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-4b-thinking","score":45.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-2b-thinking","score":28.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-2b","score":32.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-0.8b","score":23.5,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-4b-thinking","score":11.9,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3-vl-2b-thinking","score":11.2,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3.5-2b","score":12.4,"metric":"percent"},{"benchmark":"hypersim","model":"qwen3.5-0.8b","score":11.9,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-4b-thinking","score":28,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3-vl-2b-thinking","score":28.6,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3.5-2b","score":28.7,"metric":"percent"},{"benchmark":"sunrgbd","model":"qwen3.5-0.8b","score":26.1,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3-vl-4b-thinking","score":4.9,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3-vl-2b-thinking","score":4,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3.5-2b","score":6.9,"metric":"percent"},{"benchmark":"nuscenes","model":"qwen3.5-0.8b","score":5.7,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3-vl-4b-thinking","score":76,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3-vl-2b-thinking","score":67.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.5-2b","score":75.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.5-0.8b","score":63.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-4b-thinking","score":68.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-2b-thinking","score":62.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-2b","score":69,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-0.8b","score":57.7,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-4b-thinking","score":69.4,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-2b-thinking","score":54.1,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.5-2b","score":62.1,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.5-0.8b","score":44.3,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-4b-thinking","score":75.7,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-2b-thinking","score":69.2,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-2b","score":76.2,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-0.8b","score":65.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-4b-thinking","score":69.3,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-2b-thinking","score":64.5,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-2b","score":64.9,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-0.8b","score":55.8,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-4b-thinking","score":53.5,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-2b-thinking","score":47.6,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-2b","score":57.1,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-0.8b","score":45.1,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3-vl-4b-thinking","score":58.6,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3-vl-2b-thinking","score":48.9,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-2b","score":48.6,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-0.8b","score":34.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-4b-thinking","score":59.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-2b-thinking","score":48.5,"metric":"percent"},{"benchmark":"slake","model":"qwen3-vl-4b-thinking","score":65.9,"metric":"percent"},{"benchmark":"slake","model":"qwen3-vl-2b-thinking","score":61.1,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-2b","score":74.4,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-0.8b","score":62.6,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3-vl-4b-thinking","score":48.4,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3-vl-2b-thinking","score":42.4,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-2b","score":48.8,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-0.8b","score":40.4,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3-vl-4b-thinking","score":26.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3-vl-2b-thinking","score":13,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-2b","score":26.9,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-0.8b","score":17.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-27b","score":75,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-31b-it","score":52,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-35b-a3b","score":70,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-26b-a4b-it","score":17.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-35b-a3b","score":73.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-27b","score":69.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemma-4-31b-it","score":51.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-35b-a3b","score":60.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemma-4-26b-a4b-it","score":17.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.6-35b-a3b","score":67.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.5-27b","score":51.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemma-4-31b-it","score":35.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.5-35b-a3b","score":44.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemma-4-26b-a4b-it","score":13.8,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.6-35b-a3b","score":49.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemma-4-31b-it","score":42.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemma-4-26b-a4b-it","score":34.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.6-35b-a3b","score":51.5,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-27b","score":64.3,"metric":"percent"},{"benchmark":"claw-eval","model":"gemma-4-31b-it","score":48.5,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-35b-a3b","score":65.4,"metric":"percent"},{"benchmark":"claw-eval","model":"gemma-4-26b-a4b-it","score":58.8,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.6-35b-a3b","score":68.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.5-27b","score":46.2,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gemma-4-31b-it","score":25,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.5-35b-a3b","score":51,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gemma-4-26b-a4b-it","score":28,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.6-35b-a3b","score":50,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.5-27b","score":27.2,"metric":"percent"},{"benchmark":"skillsbench","model":"gemma-4-31b-it","score":23.6,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.5-35b-a3b","score":4.4,"metric":"percent"},{"benchmark":"skillsbench","model":"gemma-4-26b-a4b-it","score":12.3,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.6-35b-a3b","score":28.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.5-27b","score":52.2,"metric":"percent"},{"benchmark":"qwenclawbench","model":"gemma-4-31b-it","score":41.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.5-35b-a3b","score":47.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"gemma-4-26b-a4b-it","score":38.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.6-35b-a3b","score":52.6,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.5-27b","score":27.3,"metric":"percent"},{"benchmark":"nl2repo","model":"gemma-4-31b-it","score":15.5,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.5-35b-a3b","score":20.5,"metric":"percent"},{"benchmark":"nl2repo","model":"gemma-4-26b-a4b-it","score":11.6,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.6-35b-a3b","score":29.4,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-27b","score":41.8,"metric":"percent"},{"benchmark":"vitabench","model":"gemma-4-31b-it","score":43,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-35b-a3b","score":29.1,"metric":"percent"},{"benchmark":"vitabench","model":"gemma-4-26b-a4b-it","score":36.9,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.6-35b-a3b","score":35.6,"metric":"percent"},{"benchmark":"deep-planning","model":"gemma-4-31b-it","score":24,"metric":"percent"},{"benchmark":"deep-planning","model":"gemma-4-26b-a4b-it","score":16.2,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.6-35b-a3b","score":25.9,"metric":"percent"},{"benchmark":"tool-decathlon","model":"qwen3.5-27b","score":31.5,"metric":"percent"},{"benchmark":"tool-decathlon","model":"gemma-4-31b-it","score":21.2,"metric":"percent"},{"benchmark":"tool-decathlon","model":"qwen3.5-35b-a3b","score":28.7,"metric":"percent"},{"benchmark":"tool-decathlon","model":"gemma-4-26b-a4b-it","score":12,"metric":"percent"},{"benchmark":"tool-decathlon","model":"qwen3.6-35b-a3b","score":26.9,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.5-27b","score":36.3,"metric":"percent"},{"benchmark":"mcpmark","model":"gemma-4-31b-it","score":18.1,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.5-35b-a3b","score":27,"metric":"percent"},{"benchmark":"mcpmark","model":"gemma-4-26b-a4b-it","score":14.2,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.6-35b-a3b","score":37,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.5-27b","score":68.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemma-4-31b-it","score":57.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.5-35b-a3b","score":62.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemma-4-26b-a4b-it","score":50,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.6-35b-a3b","score":62.8,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.5-27b","score":66.4,"metric":"percent"},{"benchmark":"wide-search","model":"gemma-4-31b-it","score":35.2,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.5-35b-a3b","score":59.1,"metric":"percent"},{"benchmark":"wide-search","model":"gemma-4-26b-a4b-it","score":38.3,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.6-35b-a3b","score":60.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-31b-it","score":85.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-26b-a4b-it","score":82.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-35b-a3b","score":85.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-4-31b-it","score":93.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-4-26b-a4b-it","score":92.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.6-35b-a3b","score":93.3,"metric":"percent"},{"benchmark":"supergpqa","model":"gemma-4-31b-it","score":65.7,"metric":"percent"},{"benchmark":"supergpqa","model":"gemma-4-26b-a4b-it","score":61.4,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.6-35b-a3b","score":64.7,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-4-31b-it","score":82.6,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-4-26b-a4b-it","score":82.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.6-35b-a3b","score":90,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-31b-it","score":84.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-26b-a4b-it","score":82.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-35b-a3b","score":86,"metric":"percent"},{"benchmark":"hle","model":"qwen3.5-27b","score":24.3,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-31b-it","score":19.5,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-35b-a3b","score":22.4,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-26b-a4b-it","score":8.7,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.6-35b-a3b","score":21.4,"metric":"avg@3"},{"benchmark":"livecodebench","model":"gemma-4-31b-it","score":80,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-26b-a4b-it","score":77.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.6-35b-a3b","score":80.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemma-4-31b-it","score":88.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemma-4-26b-a4b-it","score":91.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.6-35b-a3b","score":90.7,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gemma-4-31b-it","score":87.5,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gemma-4-26b-a4b-it","score":87.5,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.6-35b-a3b","score":89.1,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-27b","score":84.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-31b-it","score":77.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-35b-a3b","score":78.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-26b-a4b-it","score":79,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.6-35b-a3b","score":83.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-27b","score":79.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-31b-it","score":74.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-35b-a3b","score":76.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-26b-a4b-it","score":74.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.6-35b-a3b","score":78.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-27b","score":92.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-31b-it","score":89.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-35b-a3b","score":91,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-26b-a4b-it","score":88.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-35b-a3b","score":92.7,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-31b-it","score":80.4,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-26b-a4b-it","score":78.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.6-35b-a3b","score":81.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-31b-it","score":76.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-26b-a4b-it","score":73.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.6-35b-a3b","score":75.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemma-4-31b-it","score":79.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemma-4-26b-a4b-it","score":79.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.6-35b-a3b","score":86.4,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemma-4-31b-it","score":26,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemma-4-26b-a4b-it","score":26.3,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.6-35b-a3b","score":34.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-31b-it","score":72.3,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-26b-a4b-it","score":72.2,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.6-35b-a3b","score":85.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemma-4-31b-it","score":90.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemma-4-26b-a4b-it","score":89,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.6-35b-a3b","score":92.8,"metric":"percent"},{"benchmark":"simplevqa","model":"gemma-4-31b-it","score":52.9,"metric":"percent"},{"benchmark":"simplevqa","model":"gemma-4-26b-a4b-it","score":52.2,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.6-35b-a3b","score":58.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-4-31b-it","score":67.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-4-26b-a4b-it","score":66.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.6-35b-a3b","score":69.8,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gemma-4-31b-it","score":80.1,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemma-4-26b-a4b-it","score":74.4,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3.6-35b-a3b","score":89.9,"metric":"edit_distance"},{"benchmark":"charxiv-rq","model":"gemma-4-31b-it","score":67.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemma-4-26b-a4b-it","score":69,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.6-35b-a3b","score":78,"metric":"percent"},{"benchmark":"cc-ocr","model":"gemma-4-31b-it","score":75.7,"metric":"percent"},{"benchmark":"cc-ocr","model":"gemma-4-26b-a4b-it","score":74.5,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.6-35b-a3b","score":81.9,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-4-31b-it","score":89,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-4-26b-a4b-it","score":88.3,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.6-35b-a3b","score":92.7,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-27b","score":90.9,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-35b-a3b","score":89.2,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.6-35b-a3b","score":92,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.6-35b-a3b","score":50.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.6-35b-a3b","score":84.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.6-35b-a3b","score":64.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.6-35b-a3b","score":86.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.6-35b-a3b","score":82.5,"metric":"percent"},{"benchmark":"videommmu","model":"gemma-4-31b-it","score":81.6,"metric":"percent"},{"benchmark":"videommmu","model":"gemma-4-26b-a4b-it","score":76,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.6-35b-a3b","score":83.7,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.6-35b-a3b","score":86.2,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.6-35b-a3b","score":74.6,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.6-35b-a3b","score":71.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-397b-a17b","score":76.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-27b","score":77.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.5-397b-a17b","score":50.9,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-opus-4.5","score":57.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.6-27b","score":53.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.6-27b","score":71.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.6-27b","score":59.3,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.5-397b-a17b","score":30,"metric":"percent"},{"benchmark":"skillsbench","model":"claude-opus-4.5","score":45.3,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.6-27b","score":48.2,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.5-397b-a17b","score":32.2,"metric":"percent"},{"benchmark":"nl2repo","model":"claude-opus-4.5","score":43.2,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.6-27b","score":36.2,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-397b-a17b","score":70.7,"metric":"percent"},{"benchmark":"claw-eval","model":"claude-opus-4.5","score":76.6,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.6-27b","score":72.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.5-397b-a17b","score":48.1,"metric":"percent"},{"benchmark":"claweval-pass3","model":"claude-opus-4.5","score":59.6,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.6-27b","score":60.6,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.5-397b-a17b","score":51.8,"metric":"percent"},{"benchmark":"qwenclawbench","model":"claude-opus-4.5","score":52.3,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.6-27b","score":53.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-27b","score":86.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.6-27b","score":93.5,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.6-27b","score":66,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.6-27b","score":91.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-397b-a17b","score":88.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-27b","score":87.8,"metric":"percent"},{"benchmark":"hle","model":"qwen3.6-27b","score":24,"metric":"avg@3"},{"benchmark":"livecodebench","model":"qwen3.6-27b","score":83.9,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.6-27b","score":93.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.6-27b","score":90.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-397b-a17b","score":87.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-opus-4.5","score":85.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.6-27b","score":84.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.6-27b","score":80.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-397b-a17b","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.5","score":95.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-27b","score":94.1,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.6-27b","score":82.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.6-27b","score":75.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.6-27b","score":87.4,"metric":"percent"},{"benchmark":"dynamath","model":"gemma-4-31b-it","score":79.5,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.6-35b-a3b","score":82.8,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.6-27b","score":85.6,"metric":"percent"},{"benchmark":"vlmsareblind","model":"gemma-4-31b-it","score":87.2,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.6-35b-a3b","score":96.6,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3.6-27b","score":97,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.6-27b","score":84.1,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-31b-it","score":77.3,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.6-35b-a3b","score":80.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.6-27b","score":81.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.6-27b","score":92.3,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.6-27b","score":56.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.6-27b","score":78.4,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.6-27b","score":81.2,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-4-31b-it","score":86.1,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.6-35b-a3b","score":90,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.6-27b","score":89.4,"metric":"percent"},{"benchmark":"erqa","model":"gemma-4-31b-it","score":57.5,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.6-35b-a3b","score":61.8,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.6-27b","score":62.5,"metric":"percent"},{"benchmark":"countbench","model":"gemma-4-31b-it","score":96.1,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.6-35b-a3b","score":96.1,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.6-27b","score":97.8,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-397b-a17b","score":92.3,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.6-27b","score":92.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.6-27b","score":84.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemma-4-31b-it","score":4.7,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.6-27b","score":70,"metric":"percent"},{"benchmark":"videomme-sub","model":"claude-opus-4.5","score":77.7,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.6-27b","score":87.7,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.6-27b","score":84.4,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.6-27b","score":86.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.6-27b","score":75.5,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.6-35b-a3b","score":90.1,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.6-27b","score":94.7,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.6-27b","score":70.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-plus","score":78.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.6-plus","score":73.8,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"kimi-k2.5","score":53.8,"metric":"percent"},{"benchmark":"claw-eval","model":"kimi-k2.5","score":71.6,"metric":"percent"},{"benchmark":"claw-eval","model":"glm-5","score":73,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.6-plus","score":74.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"kimi-k2.5","score":52.9,"metric":"percent"},{"benchmark":"claweval-pass3","model":"glm-5","score":57.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.6-plus","score":58.7,"metric":"percent"},{"benchmark":"skillsbench","model":"kimi-k2.5","score":42,"metric":"percent"},{"benchmark":"skillsbench","model":"glm-5","score":47.2,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.6-plus","score":45.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"kimi-k2.5","score":54.3,"metric":"percent"},{"benchmark":"qwenclawbench","model":"glm-5","score":54.1,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.6-plus","score":57.2,"metric":"percent"},{"benchmark":"nl2repo","model":"kimi-k2.5","score":32,"metric":"percent"},{"benchmark":"vitabench","model":"claude-opus-4.5","score":50.3,"metric":"percent"},{"benchmark":"vitabench","model":"kimi-k2.5","score":36,"metric":"percent"},{"benchmark":"vitabench","model":"glm-5","score":37,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-397b-a17b","score":43.7,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.6-plus","score":44.3,"metric":"percent"},{"benchmark":"deep-planning","model":"kimi-k2.5","score":14.4,"metric":"percent"},{"benchmark":"deep-planning","model":"glm-5","score":14.6,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.5-397b-a17b","score":37.6,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.6-plus","score":41.5,"metric":"percent"},{"benchmark":"tool-decathlon","model":"glm-5","score":38,"metric":"percent"},{"benchmark":"tool-decathlon","model":"qwen3.6-plus","score":39.8,"metric":"percent"},{"benchmark":"mcpmark","model":"glm-5","score":31.1,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.6-plus","score":48.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.5","score":71.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k2.5","score":59.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5","score":69.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.5-397b-a17b","score":74.2,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5","score":69.5,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.6-plus","score":74.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-5","score":85.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-plus","score":88.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"glm-5","score":94.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.6-plus","score":94.5,"metric":"percent"},{"benchmark":"supergpqa","model":"glm-5","score":66.8,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.6-plus","score":71.6,"metric":"percent"},{"benchmark":"c-eval","model":"glm-5","score":92.8,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.6-plus","score":93.3,"metric":"percent"},{"benchmark":"ifeval","model":"glm-5","score":92.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.6-plus","score":94.3,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5","score":72.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-plus","score":74.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5","score":63.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.6-plus","score":68.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"glm-5","score":60.8,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.6-plus","score":62,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.5","score":87.6,"metric":"percent"},{"benchmark":"hle","model":"glm-5","score":27.2,"metric":"avg@3"},{"benchmark":"livecodebench","model":"glm-5","score":85.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.6-plus","score":87.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"glm-5","score":97.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.6-plus","score":96.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"kimi-k2.5","score":87.1,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"glm-5","score":86.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.5","score":95.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"glm-5","score":95.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-plus","score":95.3,"metric":"percent"},{"benchmark":"mmmlu","model":"glm-5","score":86.6,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.6-plus","score":89.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"glm-5","score":83.1,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.6-plus","score":84.7,"metric":"percent"},{"benchmark":"nova-63","model":"glm-5","score":55.1,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.6-plus","score":57.9,"metric":"percent"},{"benchmark":"include","model":"glm-5","score":84.9,"metric":"percent"},{"benchmark":"include","model":"qwen3.6-plus","score":85.1,"metric":"percent"},{"benchmark":"global-piqa","model":"glm-5","score":89.4,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.6-plus","score":89.8,"metric":"percent"},{"benchmark":"polymath","model":"glm-5","score":65.2,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.6-plus","score":77.4,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"glm-5","score":82.1,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.6-plus","score":84.3,"metric":"percent"},{"benchmark":"maxife","model":"glm-5","score":85.6,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.6-plus","score":88.2,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.6-plus","score":86,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.6-plus","score":78.8,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.6-plus","score":88,"metric":"percent"},{"benchmark":"wemath","model":"qwen3.6-plus","score":89,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.6-plus","score":88,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.6-plus","score":85.4,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.6-plus","score":83.3,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.6-plus","score":67.3,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"qwen3.6-plus","score":91.2,"metric":"edit_distance"},{"benchmark":"charxiv-rq","model":"qwen3.6-plus","score":81.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.6-plus","score":62,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.6-plus","score":83.4,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.6-plus","score":94.4,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.6-plus","score":97.6,"metric":"percent"},{"benchmark":"refcoco","model":"gemini-3-pro","score":84.1,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.6-plus","score":93.5,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.6-plus","score":51.8,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.6-plus","score":65.7,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.6-plus","score":96.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.6-plus","score":87.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.6-plus","score":84.2,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.6-plus","score":84,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.6-plus","score":86.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.6-plus","score":68.2,"metric":"percent"},{"benchmark":"tir-bench","model":"claude-opus-4.5","score":32.3,"metric":"percent"},{"benchmark":"tir-bench","model":"gemini-3-pro","score":47.5,"metric":"percent"},{"benchmark":"tir-bench","model":"kimi-k2.5","score":29.2,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3.5-397b-a17b","score":62.5,"metric":"percent"},{"benchmark":"tir-bench","model":"qwen3.6-plus","score":61.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.6-plus","score":62.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.7-max","score":69.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.7-max","score":80.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"kimi-k2.6-thinking","score":59.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"glm-5.1","score":58.8,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-pro-thinking-max","score":59,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.7-max","score":78.3,"metric":"percent"},{"benchmark":"nl2repo","model":"claude-opus-4.6","score":47.6,"metric":"percent"},{"benchmark":"nl2repo","model":"kimi-k2.6-thinking","score":42.8,"metric":"percent"},{"benchmark":"nl2repo","model":"glm-5.1","score":41,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-pro-thinking-max","score":35.5,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.6-plus","score":34.4,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.6","score":51.9,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k2.6-thinking","score":52.2,"metric":"percent"},{"benchmark":"scicode","model":"glm-5.1","score":45.1,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-plus","score":41.4,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.7-max","score":53.5,"metric":"percent"},{"benchmark":"qwenclawbench","model":"claude-opus-4.6","score":65.5,"metric":"percent"},{"benchmark":"qwenclawbench","model":"kimi-k2.6-thinking","score":54.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"glm-5.1","score":58.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"deepseek-v4-pro-thinking-max","score":59.2,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.7-max","score":64.3,"metric":"percent"},{"benchmark":"skillsbench","model":"kimi-k2.6-thinking","score":56.2,"metric":"percent"},{"benchmark":"skillsbench","model":"glm-5.1","score":53.1,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-pro-thinking-max","score":52.3,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.7-max","score":59.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"claude-opus-4.6","score":76.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"kimi-k2.6-thinking","score":71.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"glm-5.1","score":70.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"deepseek-v4-pro-thinking-max","score":70.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.6-plus","score":68.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.7-max","score":75,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-opus-4.6","score":56.7,"metric":"percent"},{"benchmark":"mcpmark","model":"kimi-k2.6-thinking","score":55.9,"metric":"percent"},{"benchmark":"mcpmark","model":"glm-5.1","score":57.5,"metric":"percent"},{"benchmark":"mcpmark","model":"deepseek-v4-pro-thinking-max","score":57.1,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.7-max","score":60.8,"metric":"percent"},{"benchmark":"vitabench","model":"kimi-k2.6-thinking","score":39.1,"metric":"percent"},{"benchmark":"vitabench","model":"glm-5.1","score":45.1,"metric":"percent"},{"benchmark":"vitabench","model":"deepseek-v4-pro-thinking-max","score":51.9,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.6-plus","score":42.8,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.7-max","score":47.9,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"claude-opus-4.6","score":89.3,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"kimi-k2.6-thinking","score":84.5,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"glm-5.1","score":85.2,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"deepseek-v4-pro-thinking-max","score":84.9,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"qwen3.6-plus","score":80.2,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"qwen3.7-max","score":87,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.6-plus","score":50.2,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"qwen3.7-max","score":92.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.7-max","score":91.6,"metric":"percent"},{"benchmark":"critpt","model":"claude-opus-4.6","score":12.6,"metric":"percent"},{"benchmark":"critpt","model":"kimi-k2.6-thinking","score":8,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v4-pro-thinking-max","score":12.9,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.6-plus","score":2.9,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.7-max","score":11.4,"metric":"percent"},{"benchmark":"matharena-apex","model":"qwen3.6-plus","score":8.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"qwen3.7-max","score":44.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.6","score":89.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-5.1","score":86.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.7-max","score":89.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-opus-4.6","score":95.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-k2.6-thinking","score":95.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"glm-5.1","score":94.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v4-pro-thinking-max","score":94.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.7-max","score":95,"metric":"percent"},{"benchmark":"supergpqa","model":"claude-opus-4.6","score":72.5,"metric":"percent"},{"benchmark":"supergpqa","model":"kimi-k2.6-thinking","score":71.3,"metric":"percent"},{"benchmark":"supergpqa","model":"glm-5.1","score":68,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v4-pro-thinking-max","score":69.9,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.7-max","score":73.6,"metric":"percent"},{"benchmark":"ifeval","model":"claude-opus-4.6","score":91.9,"metric":"percent"},{"benchmark":"ifeval","model":"kimi-k2.6-thinking","score":94.5,"metric":"percent"},{"benchmark":"ifeval","model":"glm-5.1","score":94.5,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v4-pro-thinking-max","score":91.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.7-max","score":94.3,"metric":"percent"},{"benchmark":"ifbench","model":"claude-opus-4.6","score":62.5,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.6-thinking","score":76,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5.1","score":76,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-pro-thinking-max","score":77,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.7-max","score":79.1,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"kimi-k2.6-thinking","score":63.1,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"glm-5.1","score":62,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"deepseek-v4-pro-thinking-max","score":74.4,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"qwen3.6-plus","score":85.9,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"qwen3.7-max","score":90.4,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"claude-opus-4.6","score":82.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"kimi-k2.6-thinking","score":81.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"glm-5.1","score":81.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"deepseek-v4-pro-thinking-max","score":82.2,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.7-max","score":85.8,"metric":"percent"},{"benchmark":"maxife","model":"claude-opus-4.6","score":81.3,"metric":"percent"},{"benchmark":"maxife","model":"kimi-k2.6-thinking","score":87.7,"metric":"percent"},{"benchmark":"maxife","model":"glm-5.1","score":87.7,"metric":"percent"},{"benchmark":"maxife","model":"deepseek-v4-pro-thinking-max","score":88.9,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.7-max","score":89.2,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-opus-4.6","score":90.6,"metric":"percent"},{"benchmark":"mmmlu","model":"kimi-k2.6-thinking","score":87.5,"metric":"percent"},{"benchmark":"mmmlu","model":"glm-5.1","score":87.2,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v4-pro-thinking-max","score":87.9,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.7-max","score":90.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"claude-opus-4.6","score":86.1,"metric":"percent"},{"benchmark":"mmlu-prox","model":"kimi-k2.6-thinking","score":83.7,"metric":"percent"},{"benchmark":"mmlu-prox","model":"glm-5.1","score":83.9,"metric":"percent"},{"benchmark":"mmlu-prox","model":"deepseek-v4-pro-thinking-max","score":83.9,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.7-max","score":87,"metric":"percent"},{"benchmark":"nova-63","model":"claude-opus-4.6","score":59.1,"metric":"percent"},{"benchmark":"nova-63","model":"kimi-k2.6-thinking","score":56.7,"metric":"percent"},{"benchmark":"nova-63","model":"glm-5.1","score":54.6,"metric":"percent"},{"benchmark":"nova-63","model":"deepseek-v4-pro-thinking-max","score":52.8,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.7-max","score":59,"metric":"percent"},{"benchmark":"include","model":"claude-opus-4.6","score":87.4,"metric":"percent"},{"benchmark":"include","model":"kimi-k2.6-thinking","score":84.2,"metric":"percent"},{"benchmark":"include","model":"glm-5.1","score":84.3,"metric":"percent"},{"benchmark":"include","model":"deepseek-v4-pro-thinking-max","score":86.1,"metric":"percent"},{"benchmark":"include","model":"qwen3.7-max","score":86.2,"metric":"percent"},{"benchmark":"global-piqa","model":"claude-opus-4.6","score":91.2,"metric":"percent"},{"benchmark":"global-piqa","model":"kimi-k2.6-thinking","score":89.2,"metric":"percent"},{"benchmark":"global-piqa","model":"glm-5.1","score":89.5,"metric":"percent"},{"benchmark":"global-piqa","model":"deepseek-v4-pro-thinking-max","score":90.5,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.7-max","score":91.4,"metric":"percent"},{"benchmark":"polymath","model":"claude-opus-4.6","score":80.2,"metric":"percent"},{"benchmark":"polymath","model":"kimi-k2.6-thinking","score":82.7,"metric":"percent"},{"benchmark":"polymath","model":"glm-5.1","score":67.6,"metric":"percent"},{"benchmark":"polymath","model":"deepseek-v4-pro-thinking-max","score":72,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.7-max","score":86.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.7-plus","score":70.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.7-plus","score":77.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.7-plus","score":57.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.7-plus","score":75.8,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.7-plus","score":41.1,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.7-plus","score":51.3,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.7-plus","score":61.8,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.7-plus","score":54.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.7-plus","score":72.9,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.7-plus","score":58.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.7-plus","score":73.2,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.7-plus","score":45.6,"metric":"percent"},{"benchmark":"deep-planning","model":"claude-opus-4.6","score":58.9,"metric":"percent"},{"benchmark":"deep-planning","model":"kimi-k2.6-thinking","score":42.3,"metric":"percent"},{"benchmark":"deep-planning","model":"glm-5.1","score":34.1,"metric":"percent"},{"benchmark":"deep-planning","model":"deepseek-v4-pro-thinking-max","score":44.6,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.6-plus","score":40.9,"metric":"percent"},{"benchmark":"deep-planning","model":"qwen3.7-plus","score":62.3,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"qwen3.7-plus","score":86.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.7-plus","score":90.3,"metric":"percent"},{"benchmark":"hle","model":"qwen3.7-plus","score":34.7,"metric":"avg@3"},{"benchmark":"livecodebench","model":"qwen3.7-plus","score":89.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.7-plus","score":92.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.7-plus","score":86,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.7-plus","score":6,"metric":"percent"},{"benchmark":"matharena-apex","model":"qwen3.7-plus","score":22.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.7-plus","score":88.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.7-plus","score":94.5,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.7-plus","score":71.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.7-plus","score":94.6,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.7-plus","score":79.1,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"qwen3.7-plus","score":91.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.7-plus","score":84.6,"metric":"percent"},{"benchmark":"maxife","model":"qwen3.7-plus","score":88.8,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.7-plus","score":89,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.7-plus","score":85.4,"metric":"percent"},{"benchmark":"nova-63","model":"qwen3.7-plus","score":58.8,"metric":"percent"},{"benchmark":"include","model":"qwen3.7-plus","score":83,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3.7-plus","score":90.3,"metric":"percent"},{"benchmark":"polymath","model":"qwen3.7-plus","score":84,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-pro","score":81.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.7-plus","score":79,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.4","score":91,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.6","score":65.5,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.1-pro","score":87.4,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.7-plus","score":90.3,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.4","score":53.1,"metric":"percent"},{"benchmark":"babyvision","model":"claude-opus-4.6","score":12.6,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3.1-pro","score":55.9,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.6-plus","score":37.4,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.7-plus","score":70.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.4","score":84.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.6","score":66,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.1-pro","score":84.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.7-plus","score":85.9,"metric":"percent"},{"benchmark":"hipho","model":"gpt-5.4","score":65,"metric":"percent"},{"benchmark":"hipho","model":"claude-opus-4.6","score":40.8,"metric":"percent"},{"benchmark":"hipho","model":"gemini-3.1-pro","score":85.4,"metric":"percent"},{"benchmark":"hipho","model":"qwen3.6-plus","score":80.4,"metric":"percent"},{"benchmark":"hipho","model":"qwen3.7-plus","score":84.1,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.4","score":67.8,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-4.6","score":40.8,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3.1-pro","score":68,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.7-plus","score":69.8,"metric":"percent"},{"benchmark":"visfactor","model":"gpt-5.4","score":40.8,"metric":"percent"},{"benchmark":"visfactor","model":"claude-opus-4.6","score":24.4,"metric":"percent"},{"benchmark":"visfactor","model":"gemini-3.1-pro","score":39.8,"metric":"percent"},{"benchmark":"visfactor","model":"qwen3.6-plus","score":36,"metric":"percent"},{"benchmark":"visfactor","model":"qwen3.7-plus","score":42.8,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gpt-5.4","score":77.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"claude-opus-4.6","score":64.4,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemini-3.1-pro","score":80.7,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.6-plus","score":68.7,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.7-plus","score":71,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5.4","score":67.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-opus-4.6","score":49.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gemini-3.1-pro","score":68.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.7-plus","score":79,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.7-plus","score":73.3,"metric":"percent"},{"benchmark":"androidworld","model":"gemini-3.1-pro","score":70.7,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.6-plus","score":67.2,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.7-plus","score":81,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5.4","score":69.4,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-opus-4.6","score":79.6,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3.1-pro","score":76.9,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.6-plus","score":69.4,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.7-plus","score":81.7,"metric":"percent"},{"benchmark":"worldvqa","model":"gpt-5.4","score":45.9,"metric":"percent"},{"benchmark":"worldvqa","model":"claude-opus-4.6","score":65.4,"metric":"percent"},{"benchmark":"worldvqa","model":"gemini-3.1-pro","score":56.1,"metric":"percent"},{"benchmark":"worldvqa","model":"qwen3.6-plus","score":33.6,"metric":"percent"},{"benchmark":"worldvqa","model":"qwen3.7-plus","score":61.1,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5.4","score":83.8,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-opus-4.6","score":73.9,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-3.1-pro","score":83.5,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.7-plus","score":86.9,"metric":"percent"},{"benchmark":"countqa","model":"gpt-5.4","score":58.4,"metric":"percent"},{"benchmark":"countqa","model":"claude-opus-4.6","score":32.5,"metric":"percent"},{"benchmark":"countqa","model":"gemini-3.1-pro","score":72.8,"metric":"percent"},{"benchmark":"countqa","model":"qwen3.6-plus","score":71.7,"metric":"percent"},{"benchmark":"countqa","model":"qwen3.7-plus","score":77,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.4","score":85.5,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"claude-opus-4.6","score":86.6,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemini-3.1-pro","score":90,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3.7-plus","score":91.4,"metric":"edit_distance"},{"benchmark":"ocrbenchv2-en","model":"gpt-5.4","score":59.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"claude-opus-4.6","score":54.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemini-3.1-pro","score":64.6,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.6-plus","score":67,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.7-plus","score":70.7,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gpt-5.4","score":57.7,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"claude-opus-4.6","score":54.9,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gemini-3.1-pro","score":58.2,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.6-plus","score":63.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.7-plus","score":67.1,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.7-plus","score":51.1,"metric":"percent"},{"benchmark":"lingoqa","model":"gpt-5.4","score":78.2,"metric":"percent"},{"benchmark":"lingoqa","model":"claude-opus-4.6","score":77.6,"metric":"percent"},{"benchmark":"lingoqa","model":"gemini-3.1-pro","score":66.8,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.6-plus","score":76,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.7-plus","score":83.4,"metric":"percent"},{"benchmark":"surds","model":"gpt-5.4","score":64.6,"metric":"percent"},{"benchmark":"surds","model":"claude-opus-4.6","score":58.3,"metric":"percent"},{"benchmark":"surds","model":"gemini-3.1-pro","score":64,"metric":"percent"},{"benchmark":"surds","model":"qwen3.6-plus","score":73.2,"metric":"percent"},{"benchmark":"surds","model":"qwen3.7-plus","score":77.2,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5.4","score":89.5,"metric":"percent"},{"benchmark":"videomme-sub","model":"claude-opus-4.6","score":86.1,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-3.1-pro","score":88.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.7-plus","score":88,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5.4","score":82.4,"metric":"percent"},{"benchmark":"videommmu","model":"claude-opus-4.6","score":85.2,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-3.1-pro","score":85.3,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.7-plus","score":85.4,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5.4","score":86.1,"metric":"percent"},{"benchmark":"mlvu","model":"claude-opus-4.6","score":81.7,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-3.1-pro","score":84.7,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.7-plus","score":87.4,"metric":"percent"},{"benchmark":"tvbench","model":"gpt-5.4","score":82.5,"metric":"percent"},{"benchmark":"tvbench","model":"claude-opus-4.6","score":69.8,"metric":"percent"},{"benchmark":"tvbench","model":"gemini-3.1-pro","score":73,"metric":"percent"},{"benchmark":"tvbench","model":"qwen3.6-plus","score":76,"metric":"percent"},{"benchmark":"tvbench","model":"qwen3.7-plus","score":78.2,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-5.4","score":77.4,"metric":"percent"},{"benchmark":"lvbench","model":"claude-opus-4.6","score":63,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3.1-pro","score":75.1,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.6-plus","score":74.8,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.7-plus","score":76.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.8","score":84.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-fable-5","score":84.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.7-max","score":74.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-fable-5","score":80,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.6-sol","score":64.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.8-max","score":67.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.7-max","score":21.6,"metric":"percent"},{"benchmark":"nl2repo","model":"claude-opus-4.8","score":69.4,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-opus-4.8","score":70,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-fable-5","score":88.8,"metric":"percent"},{"benchmark":"frontierswe","model":"qwen3.7-max","score":40.7,"metric":"percent"},{"benchmark":"frontierswe","model":"qwen3.8-max","score":73.5,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"claude-opus-4.8","score":42.8,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"claude-fable-5","score":49.9,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"gpt-5.6-sol","score":46.2,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"qwen3.7-max","score":31.7,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"qwen3.8-max","score":41,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"claude-opus-4.8","score":80.3,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"claude-fable-5","score":88.8,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"gpt-5.6-sol","score":90.5,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"qwen3.7-max","score":64.8,"metric":"percent"},{"benchmark":"paper-bench-code-dev","model":"qwen3.8-max","score":93,"metric":"percent"},{"benchmark":"androidbench","model":"claude-opus-4.8","score":69.8,"metric":"percent"},{"benchmark":"androidbench","model":"claude-fable-5","score":84.5,"metric":"percent"},{"benchmark":"androidbench","model":"gpt-5.6-sol","score":74,"metric":"percent"},{"benchmark":"androidbench","model":"qwen3.7-max","score":56.5,"metric":"percent"},{"benchmark":"androidbench","model":"qwen3.8-max","score":75.1,"metric":"percent"},{"benchmark":"skillsbench-v1.1","model":"claude-opus-4.8","score":65.1,"metric":"percent"},{"benchmark":"skillsbench-v1.1","model":"claude-fable-5","score":70.9,"metric":"percent"},{"benchmark":"skillsbench-v1.1","model":"gpt-5.6-sol","score":73.5,"metric":"percent"},{"benchmark":"skillsbench-v1.1","model":"qwen3.7-max","score":61.2,"metric":"percent"},{"benchmark":"skillsbench-v1.1","model":"qwen3.8-max","score":70.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.8","score":45.1,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.7-max","score":31.1,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.8-max","score":52.4,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-sol","score":29.7,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.7-max","score":14.2,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.8-max","score":27.3,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.7-max","score":49.7,"metric":"percent"},{"benchmark":"wide-search","model":"claude-opus-4.8","score":72.9,"metric":"percent"},{"benchmark":"wide-search","model":"claude-fable-5","score":81.2,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.7-max","score":75.2,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.8-max","score":81.9,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-fable-5","score":64.5,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.6-sol","score":58,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"qwen3.8-max","score":92.6,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-4.8","score":45.7,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.6-sol","score":47.2,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.8-max","score":43.6,"metric":"avg@3"},{"benchmark":"ifbench","model":"claude-opus-4.8","score":62.2,"metric":"percent"},{"benchmark":"ifbench","model":"claude-fable-5","score":63.5,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.6-sol","score":72.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-max","score":82.8,"metric":"percent"},{"benchmark":"healthbench","model":"claude-opus-4.8","score":52.4,"metric":"percent"},{"benchmark":"healthbench","model":"gpt-5.6-sol","score":55.3,"metric":"percent"},{"benchmark":"healthbench","model":"qwen3.7-max","score":54.5,"metric":"percent"},{"benchmark":"healthbench","model":"qwen3.8-max","score":60.2,"metric":"percent"},{"benchmark":"plawbench","model":"claude-opus-4.8","score":69.6,"metric":"percent"},{"benchmark":"plawbench","model":"claude-fable-5","score":70.2,"metric":"percent"},{"benchmark":"plawbench","model":"gpt-5.6-sol","score":72.3,"metric":"percent"},{"benchmark":"plawbench","model":"qwen3.7-max","score":58.9,"metric":"percent"},{"benchmark":"plawbench","model":"qwen3.8-max","score":73.2,"metric":"percent"},{"benchmark":"prbench-legal","model":"claude-opus-4.8","score":52.7,"metric":"percent"},{"benchmark":"prbench-legal","model":"claude-fable-5","score":57.6,"metric":"percent"},{"benchmark":"prbench-legal","model":"gpt-5.6-sol","score":57.6,"metric":"percent"},{"benchmark":"prbench-legal","model":"qwen3.7-max","score":48.5,"metric":"percent"},{"benchmark":"prbench-legal","model":"qwen3.8-max","score":57.6,"metric":"percent"},{"benchmark":"prbench-finance","model":"claude-opus-4.8","score":51.9,"metric":"percent"},{"benchmark":"prbench-finance","model":"claude-fable-5","score":55.8,"metric":"percent"},{"benchmark":"prbench-finance","model":"gpt-5.6-sol","score":55.5,"metric":"percent"},{"benchmark":"prbench-finance","model":"qwen3.7-max","score":46.8,"metric":"percent"},{"benchmark":"prbench-finance","model":"qwen3.8-max","score":58.3,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"claude-opus-4.8","score":83.2,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"gpt-5.6-sol","score":93.8,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"qwen3.7-max","score":86.7,"metric":"percent"},{"benchmark":"mrcr-256k-8n","model":"qwen3.8-max","score":92.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-opus-4.8","score":69.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5.6-sol","score":67.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.7-max","score":65.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.8-max","score":66.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.8","score":75.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-fable-5","score":81.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.8-max","score":82.3,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.8","score":97.1,"metric":"percent"},{"benchmark":"mathvision","model":"claude-fable-5","score":98.6,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.1-pro","score":95.7,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.6-sol","score":97.8,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.8-max","score":97.7,"metric":"percent"},{"benchmark":"babyvision","model":"claude-opus-4.8","score":81.2,"metric":"percent"},{"benchmark":"babyvision","model":"claude-fable-5","score":90.5,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3.1-pro","score":68.3,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.6-sol","score":88.9,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.8-max","score":91.3,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"claude-fable-5","score":46,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"gemini-3.1-pro","score":23,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"gpt-5.6-sol","score":35,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"qwen3.7-plus","score":19,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"qwen3.8-max","score":49,"metric":"percent"},{"benchmark":"zerobench-sub","model":"claude-opus-4.8","score":31.1,"metric":"percent"},{"benchmark":"zerobench-sub","model":"claude-fable-5","score":37.1,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemini-3.1-pro","score":36.5,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gpt-5.6-sol","score":46.7,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.7-plus","score":41,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.8-max","score":48.5,"metric":"percent"},{"benchmark":"logicvista","model":"claude-opus-4.8","score":76.7,"metric":"percent"},{"benchmark":"logicvista","model":"claude-fable-5","score":85.7,"metric":"percent"},{"benchmark":"logicvista","model":"gemini-3.1-pro","score":82.6,"metric":"percent"},{"benchmark":"logicvista","model":"gpt-5.6-sol","score":89.7,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3.7-plus","score":84.3,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3.8-max","score":91.9,"metric":"percent"},{"benchmark":"hipho","model":"claude-opus-4.8","score":69.3,"metric":"percent"},{"benchmark":"hipho","model":"claude-fable-5","score":78.6,"metric":"percent"},{"benchmark":"hipho","model":"gpt-5.6-sol","score":86.8,"metric":"percent"},{"benchmark":"hipho","model":"qwen3.8-max","score":90,"metric":"percent"},{"benchmark":"phyx","model":"claude-opus-4.8","score":54.2,"metric":"percent"},{"benchmark":"phyx","model":"claude-fable-5","score":71.7,"metric":"percent"},{"benchmark":"phyx","model":"gemini-3.1-pro","score":79.4,"metric":"percent"},{"benchmark":"phyx","model":"gpt-5.6-sol","score":79.1,"metric":"percent"},{"benchmark":"phyx","model":"qwen3.7-plus","score":80,"metric":"percent"},{"benchmark":"phyx","model":"qwen3.8-max","score":83.5,"metric":"percent"},{"benchmark":"slake","model":"claude-opus-4.8","score":75.9,"metric":"percent"},{"benchmark":"slake","model":"claude-fable-5","score":86.6,"metric":"percent"},{"benchmark":"slake","model":"gemini-3.1-pro","score":82.9,"metric":"percent"},{"benchmark":"slake","model":"gpt-5.6-sol","score":85.1,"metric":"percent"},{"benchmark":"slake","model":"qwen3.7-plus","score":83.2,"metric":"percent"},{"benchmark":"slake","model":"qwen3.8-max","score":90.8,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"claude-opus-4.8","score":71.7,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"claude-fable-5","score":80,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gpt-5.6-sol","score":81.5,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.8-max","score":80.4,"metric":"percent"},{"benchmark":"pmc-vqa","model":"claude-opus-4.8","score":59.2,"metric":"percent"},{"benchmark":"pmc-vqa","model":"claude-fable-5","score":63.2,"metric":"percent"},{"benchmark":"pmc-vqa","model":"gemini-3.1-pro","score":62.5,"metric":"percent"},{"benchmark":"pmc-vqa","model":"gpt-5.6-sol","score":62.3,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.7-plus","score":63.4,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.8-max","score":66.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.6-sol","score":83.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.8-max","score":86.1,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"claude-opus-4.8","score":20.6,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"gemini-3.1-pro","score":7.8,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gemini-3.1-pro","score":30.6,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"qwen3.7-plus","score":2.8,"metric":"percent"},{"benchmark":"osworld-2.0","model":"qwen3.7-plus","score":21.5,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"qwen3.8-max","score":19.4,"metric":"percent"},{"benchmark":"osworld-2.0","model":"qwen3.8-max","score":46.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5.6-sol","score":81.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.8-max","score":84.5,"metric":"percent"},{"benchmark":"webarena-verified","model":"claude-opus-4.8","score":67.9,"metric":"percent"},{"benchmark":"webarena-verified","model":"claude-fable-5","score":71.3,"metric":"percent"},{"benchmark":"webarena-verified","model":"gemini-3.1-pro","score":64.3,"metric":"percent"},{"benchmark":"webarena-verified","model":"gpt-5.6-sol","score":69.7,"metric":"percent"},{"benchmark":"webarena-verified","model":"qwen3.7-plus","score":55.3,"metric":"percent"},{"benchmark":"webarena-verified","model":"qwen3.8-max","score":66.8,"metric":"percent"},{"benchmark":"androidworld","model":"claude-opus-4.8","score":75,"metric":"percent"},{"benchmark":"androidworld","model":"claude-fable-5","score":88.8,"metric":"percent"},{"benchmark":"androidworld","model":"gpt-5.6-sol","score":77.6,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.8-max","score":85.3,"metric":"percent"},{"benchmark":"mobileworld","model":"claude-opus-4.8","score":67.5,"metric":"percent"},{"benchmark":"mobileworld","model":"claude-fable-5","score":85.5,"metric":"percent"},{"benchmark":"mobileworld","model":"gemini-3.1-pro","score":58.1,"metric":"percent"},{"benchmark":"mobileworld","model":"gpt-5.6-sol","score":76.9,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3.7-plus","score":51.2,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3.8-max","score":77.8,"metric":"percent"},{"benchmark":"vision2web","model":"claude-opus-4.8","score":62.4,"metric":"percent"},{"benchmark":"vision2web","model":"claude-fable-5","score":70.5,"metric":"percent"},{"benchmark":"vision2web","model":"gpt-5.6-sol","score":62.1,"metric":"percent"},{"benchmark":"vision2web","model":"qwen3.7-plus","score":42.1,"metric":"percent"},{"benchmark":"vision2web","model":"qwen3.8-max","score":69,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.8","score":89.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-fable-5","score":93.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.1-pro","score":89.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.6-sol","score":89.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.8-max","score":93.5,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"claude-opus-4.8","score":86.5,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"claude-fable-5","score":89.5,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.6-sol","score":86.7,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3.8-max","score":92.1,"metric":"edit_distance"},{"benchmark":"ocrbenchv2-en","model":"claude-opus-4.8","score":53.9,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"claude-opus-4.8","score":55.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"claude-fable-5","score":65.3,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"claude-fable-5","score":58.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gpt-5.6-sol","score":69,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gpt-5.6-sol","score":57.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.8-max","score":74.2,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.8-max","score":68.3,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-opus-4.8","score":76.6,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-fable-5","score":85.9,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5.6-sol","score":83.7,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.8-max","score":88,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-4.8","score":57.2,"metric":"percent"},{"benchmark":"erqa","model":"claude-fable-5","score":70,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.6-sol","score":70,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.8-max","score":77.8,"metric":"percent"},{"benchmark":"lingoqa","model":"claude-opus-4.8","score":73.8,"metric":"percent"},{"benchmark":"lingoqa","model":"claude-fable-5","score":77.4,"metric":"percent"},{"benchmark":"lingoqa","model":"gpt-5.6-sol","score":72.6,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.8-max","score":84.8,"metric":"percent"},{"benchmark":"surds","model":"claude-opus-4.8","score":62.2,"metric":"percent"},{"benchmark":"surds","model":"claude-fable-5","score":79.4,"metric":"percent"},{"benchmark":"surds","model":"gpt-5.6-sol","score":63,"metric":"percent"},{"benchmark":"surds","model":"qwen3.8-max","score":77.8,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-opus-4.8","score":67.3,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-fable-5","score":73.4,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3.1-pro","score":73.1,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5.6-sol","score":66.6,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.7-plus","score":70.3,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.8-max","score":75,"metric":"percent"},{"benchmark":"worldvqa","model":"claude-opus-4.8","score":33.9,"metric":"percent"},{"benchmark":"worldvqa","model":"claude-fable-5","score":53.5,"metric":"percent"},{"benchmark":"worldvqa","model":"gemini-3.1-pro","score":54,"metric":"percent"},{"benchmark":"worldvqa","model":"gpt-5.6-sol","score":45.1,"metric":"percent"},{"benchmark":"worldvqa","model":"qwen3.7-plus","score":43.9,"metric":"percent"},{"benchmark":"worldvqa","model":"qwen3.8-max","score":53.2,"metric":"percent"},{"benchmark":"mmstar","model":"claude-opus-4.8","score":76.7,"metric":"percent"},{"benchmark":"mmstar","model":"claude-fable-5","score":80.5,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-3.1-pro","score":84,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5.6-sol","score":82.5,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.7-plus","score":83.2,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.8-max","score":85.9,"metric":"percent"},{"benchmark":"countqa","model":"claude-opus-4.8","score":41.3,"metric":"percent"},{"benchmark":"countqa","model":"claude-fable-5","score":63.1,"metric":"percent"},{"benchmark":"countqa","model":"gpt-5.6-sol","score":68.6,"metric":"percent"},{"benchmark":"countqa","model":"qwen3.8-max","score":82.4,"metric":"percent"},{"benchmark":"visfactor","model":"claude-opus-4.8","score":30.1,"metric":"percent"},{"benchmark":"visfactor","model":"claude-fable-5","score":54.5,"metric":"percent"},{"benchmark":"visfactor","model":"gpt-5.6-sol","score":62.8,"metric":"percent"},{"benchmark":"visfactor","model":"qwen3.8-max","score":60.8,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"claude-opus-4.8","score":43.8,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"claude-fable-5","score":61.2,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gemini-3.1-pro","score":74.1,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gpt-5.6-sol","score":59.8,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"qwen3.7-plus","score":36.6,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"qwen3.8-max","score":88.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"claude-opus-4.8","score":85.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-3.1-pro","score":86.7,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5.6-sol","score":89.5,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3.8-max","score":90.4,"metric":"percent"},{"benchmark":"videommmu","model":"claude-opus-4.8","score":75.3,"metric":"percent"},{"benchmark":"videommmu","model":"claude-fable-5","score":81.2,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5.6-sol","score":85,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.8-max","score":88.7,"metric":"percent"},{"benchmark":"mmvu","model":"claude-fable-5","score":72,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-3.1-pro","score":77.9,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5.6-sol","score":81.2,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.7-plus","score":76.6,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.8-max","score":82.4,"metric":"percent"},{"benchmark":"mlvu","model":"claude-opus-4.8","score":53.4,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5.6-sol","score":87.6,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.8-max","score":90.8,"metric":"percent"},{"benchmark":"tvbench","model":"claude-opus-4.8","score":61.5,"metric":"percent"},{"benchmark":"tvbench","model":"gpt-5.6-sol","score":83.2,"metric":"percent"},{"benchmark":"tvbench","model":"qwen3.8-max","score":81.9,"metric":"percent"},{"benchmark":"lvbench","model":"claude-opus-4.8","score":67.3,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-5.6-sol","score":78.8,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.8-max","score":81.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-27b","score":73,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-27b","score":63.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.7-plus","score":64,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.6","score":78.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.8-27b","score":61.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-opus-4.6","score":53.4,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.8-27b","score":42.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-27b","score":42.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.6-27b","score":13.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.7-plus","score":14.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.8-27b","score":42.9,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.6-27b","score":27.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.7-plus","score":33.6,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-27b","score":79.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-27b","score":69.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.8-27b","score":89.2,"metric":"percent"},{"benchmark":"hle","model":"qwen3.8-27b","score":30.8,"metric":"avg@3"},{"benchmark":"livecodebench","model":"qwen3.8-27b","score":90.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.8-27b","score":84.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.6-27b","score":63.9,"metric":"percent"},{"benchmark":"webarena-verified","model":"qwen3.8-27b","score":64.8,"metric":"percent"},{"benchmark":"webarena-verified","model":"qwen3.6-27b","score":48.8,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.8-27b","score":81.9,"metric":"percent"},{"benchmark":"vision2web","model":"qwen3.8-27b","score":62.9,"metric":"percent"},{"benchmark":"vision2web","model":"qwen3.6-27b","score":45,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.8-27b","score":94.6,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.6-27b","score":85.1,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.8-27b","score":85.6,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.6-27b","score":28.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.8-27b","score":90.2,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"qwen3.8-27b","score":91.1,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"qwen3.6-27b","score":89.4,"metric":"edit_distance"},{"benchmark":"realworldqa","model":"qwen3.8-27b","score":85.9,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.8-27b","score":65.5,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-flash-next","score":58.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.7-plus","score":16.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.8-flash-next","score":62.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.7-plus","score":55.8,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-flash-0731","score":56,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.8-flash-next","score":81,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.8-27b","score":73.8,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.8-flash-next","score":48.1,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.8-flash-next","score":51.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.8-flash-next","score":73.5,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.8-27b","score":67.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.7-plus","score":50.6,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-flash-next","score":81.3,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-flash-0731","score":79.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.8-flash-next","score":91.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash-0731","score":90.8,"metric":"percent"},{"benchmark":"hle","model":"qwen3.8-flash-next","score":35.9,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-flash-0731","score":33.8,"metric":"avg@3"},{"benchmark":"livecodebench","model":"qwen3.8-flash-next","score":91.9,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-0731","score":90.6,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.8-flash-next","score":84.5,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"qwen3.8-flash-next","score":19.4,"metric":"percent"},{"benchmark":"osworld-2.0","model":"qwen3.8-flash-next","score":52.3,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"qwen3.8-27b","score":19.4,"metric":"percent"},{"benchmark":"osworld-2.0","model":"qwen3.8-27b","score":48,"metric":"percent"},{"benchmark":"vision2web","model":"qwen3.8-flash-next","score":64,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.8-flash-next","score":72.3,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.8-flash-next","score":76.6,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.8-27b","score":72.4,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.8-flash-next","score":88.5,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.8-flash-next","score":95.7,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.7-plus","score":88.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.8-flash-next","score":90.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-omni-flash","score":57.8,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.8-omni-flash","score":63.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.8-omni-flash","score":80.5,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.8-omni-flash","score":48.9,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-omni-flash","score":81.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.8-omni-flash","score":91,"metric":"percent"},{"benchmark":"hle","model":"qwen3.8-omni-flash","score":36.5,"metric":"avg@3"},{"benchmark":"livecodebench","model":"qwen3.8-omni-flash","score":92.6,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3.8-omni-flash","score":87.1,"metric":"percent"},{"benchmark":"vision2web","model":"qwen3.8-omni-flash","score":62.9,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.8-omni-flash","score":71,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.8-omni-flash","score":76.9,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.8-omni-flash","score":87.7,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.8-omni-flash","score":96.2,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.7-plus","score":88.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.8-omni-flash","score":91.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-omni-flash","score":76.9,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-omni-plus","score":80.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-omni-flash","score":68.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-omni-plus","score":73.9,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-omni-flash","score":65.4,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-omni-plus","score":73,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-omni-flash","score":82.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-omni-plus","score":86.1,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-omni-flash","score":79.3,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-omni-plus","score":83.8,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-omni-flash","score":1,"metric":"percent"},{"benchmark":"zerobench","model":"qwen3.5-omni-plus","score":5,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-omni-flash","score":26,"metric":"percent"},{"benchmark":"zerobench-sub","model":"qwen3.5-omni-plus","score":34.4,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-omni-flash","score":77.5,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-omni-plus","score":84.1,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-omni-flash","score":75.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-omni-plus","score":79.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-omni-flash","score":88.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-omni-plus","score":92.8,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-omni-flash","score":54.4,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-omni-plus","score":65.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-omni-flash","score":64.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-omni-plus","score":72.5,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-omni-flash","score":80.8,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.5-omni-plus","score":83.4,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-omni-flash","score":89,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-omni-plus","score":91.2,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-omni-flash","score":53.6,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-omni-plus","score":57.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-omni-flash","score":89.1,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-omni-plus","score":91.3,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-omni-flash","score":50,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-omni-plus","score":54.8,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-omni-flash","score":88.2,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-omni-plus","score":95.1,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-omni-flash","score":92.6,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-omni-plus","score":95,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-omni-flash","score":46.8,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-omni-plus","score":49.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-omni-flash","score":82.7,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-omni-plus","score":85.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-omni-flash","score":77,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-omni-plus","score":81.9,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-omni-flash","score":81.9,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-omni-plus","score":86.8,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-omni-flash","score":70.8,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3.5-omni-plus","score":79,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-omni-flash","score":65.7,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-omni-plus","score":71.2,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-omni-flash","score":62.7,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-omni-plus","score":67.5,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-omni-flash","score":73.1,"metric":"percent"},{"benchmark":"slake","model":"qwen3.5-omni-plus","score":84.7,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-omni-flash","score":58.7,"metric":"percent"},{"benchmark":"pmc-vqa","model":"qwen3.5-omni-plus","score":62.7,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-omni-flash","score":44.8,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3.5-omni-plus","score":54.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-omni-flash","score":79.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-omni-plus","score":85.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-omni-flash","score":90,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-omni-plus","score":94.2,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-omni-flash","score":54.9,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-omni-plus","score":66.4,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-omni-flash","score":86,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-omni-plus","score":92,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-omni-flash","score":85.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-omni-plus","score":89.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-omni-flash","score":38.4,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-omni-plus","score":52.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-omni-flash","score":46,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-omni-plus","score":57,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-omni-flash","score":46.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-omni-plus","score":59.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-omni-flash","score":76.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-omni-plus","score":83.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-omni-flash","score":56.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-omni-plus","score":65.6,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-omni-flash","score":59,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3.5-omni-plus","score":84.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-omni-flash","score":51.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-omni-plus","score":65.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-omni-flash","score":55.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-omni-plus","score":63.3,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.6-max-preview","score":73.9,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.6-max-preview","score":59,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.6-max-preview","score":55.6,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-max-preview","score":47,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-plus","score":40.7,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-397b-a17b","score":42,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.5","score":49.5,"metric":"percent"},{"benchmark":"scicode","model":"glm-5.1","score":43.8,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.6-max-preview","score":42.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.6-max-preview","score":65.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.6-max-preview","score":57.3,"metric":"percent"},{"benchmark":"vals-index","model":"gemini-4-argon","score":68.9,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-6-astra","score":63.1,"metric":"percent"},{"benchmark":"vals-index","model":"claude-fable-5.1","score":65.8,"metric":"percent"},{"benchmark":"vals-index","model":"claude-opus-5.5","score":67,"metric":"percent"},{"benchmark":"automationbench","model":"gemini-4-argon","score":51.3,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gemini-4-argon","score":65.4,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gpt-6-astra","score":53.5,"metric":"percent"},{"benchmark":"financeagent-v2","model":"claude-fable-5.1","score":58.9,"metric":"percent"},{"benchmark":"financeagent-v2","model":"claude-opus-5.5","score":58.6,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gemini-4-argon","score":19.6,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gpt-6-astra","score":5.4,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-fable-5.1","score":6.7,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-opus-5.5","score":3.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-4-argon","score":77.9,"metric":"percent"},{"benchmark":"frontierswe","model":"gemini-4-argon","score":55,"metric":"percent"},{"benchmark":"frontierswe","model":"gpt-6-astra","score":65.5,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-fable-5.1","score":56.3,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-opus-5.5","score":62.3,"metric":"percent"},{"benchmark":"vibe-code-bench","model":"gemini-4-argon","score":91.9,"metric":"percent"},{"benchmark":"vibe-code-bench","model":"gpt-6-astra","score":89.6,"metric":"percent"},{"benchmark":"vibe-code-bench","model":"claude-fable-5.1","score":90.3,"metric":"percent"},{"benchmark":"vibe-code-bench","model":"claude-opus-5.5","score":90.3,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gemini-4-argon","score":57.4,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-6-astra","score":58.2,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-fable-5.1","score":57.9,"metric":"percent"},{"benchmark":"posttrainbench","model":"gemini-4-argon","score":45.3,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-6-astra","score":44.3,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-fable-5.1","score":40.2,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-5.5","score":49.3,"metric":"percent"},{"benchmark":"terminal-bench-science","model":"gemini-4-argon","score":57.6,"metric":"percent"},{"benchmark":"labbench2","model":"gemini-4-argon","score":88.8,"metric":"percent"},{"benchmark":"labbench2","model":"gpt-6-astra","score":85.4,"metric":"percent"},{"benchmark":"labbench2","model":"claude-fable-5.1","score":68.6,"metric":"percent"},{"benchmark":"labbench2","model":"claude-opus-5.5","score":73.1,"metric":"percent"},{"benchmark":"riemannbench","model":"gemini-4-argon","score":76,"metric":"percent"},{"benchmark":"riemannbench","model":"gpt-6-astra","score":72,"metric":"percent"},{"benchmark":"riemannbench","model":"claude-fable-5.1","score":65.6,"metric":"percent"},{"benchmark":"riemannbench","model":"claude-opus-5.5","score":69.6,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gemini-4-argon","score":99.7,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"gpt-6-astra","score":98.7,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"claude-fable-5.1","score":91.4,"metric":"percent"},{"benchmark":"graphwalks-bfs","model":"claude-opus-5.5","score":90.6,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k-1m","model":"gemini-4-argon","score":84.2,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k-1m","model":"gpt-6-astra","score":71.8,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k-1m","model":"claude-fable-5.1","score":65,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k-1m","model":"claude-opus-5.5","score":66.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gemini-4-argon","score":39.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra","score":34.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5.5","score":38.2,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gemini-4-argon","score":69.2,"metric":"percent"},{"benchmark":"chartography","model":"gemini-4-argon","score":71.6,"metric":"percent"},{"benchmark":"chartography","model":"gpt-6-astra","score":71,"metric":"percent"},{"benchmark":"chartography","model":"claude-fable-5.1","score":46.2,"metric":"percent"},{"benchmark":"chartography","model":"claude-opus-5.5","score":66.3,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-4-argon","score":91.7,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-6-astra","score":87.5,"metric":"percent"},{"benchmark":"lvbench","model":"claude-fable-5.1","score":79.7,"metric":"percent"},{"benchmark":"lvbench","model":"claude-opus-5.5","score":83.7,"metric":"percent"},{"benchmark":"cwe-bench","model":"gemini-4-argon","score":68,"metric":"percent"},{"benchmark":"cwe-bench","model":"gpt-6-astra","score":68,"metric":"percent"},{"benchmark":"cwe-bench","model":"claude-fable-5.1","score":58,"metric":"percent"},{"benchmark":"cwe-bench","model":"claude-opus-5.5","score":67,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.8-flash","score":73.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-sonnet-5","score":53.8,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.8-flash","score":1545,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.7-flash","score":1482,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-5","score":1584,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1710,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-terra","score":1528,"metric":"elo"},{"benchmark":"financeagent-v2","model":"gemini-3.8-flash","score":61.4,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gemini-3.7-flash","score":59,"metric":"percent"},{"benchmark":"financeagent-v2","model":"claude-opus-5","score":58.6,"metric":"percent"},{"benchmark":"financeagent-v2","model":"claude-sonnet-5","score":53.9,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gpt-5.6-sol","score":53.8,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gpt-5.6-terra","score":54.4,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gemini-3.8-flash","score":10,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gemini-3.7-flash","score":8.8,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-opus-5","score":6.7,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-sonnet-5","score":5,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"gpt-5.6-terra","score":0.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.8-flash","score":89.4,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gemini-3.7-flash","score":11.2,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-sonnet-5","score":12.4,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-5.6-terra","score":23.6,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gemini-3.8-flash","score":35,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gemini-3.7-flash","score":34,"metric":"percent"},{"benchmark":"gdp-pdf","model":"claude-opus-5","score":37,"metric":"percent"},{"benchmark":"gdp-pdf","model":"claude-sonnet-5","score":28,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-5.6-sol","score":40,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-5.6-terra","score":29,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.8-flash","score":86.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.7-flash","score":84.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-5","score":83.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-sonnet-5","score":70.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.6-sol","score":85.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.6-terra","score":85.9,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3.8-flash","score":87.1,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3.7-flash","score":85.4,"metric":"percent"},{"benchmark":"lvbench","model":"claude-opus-5","score":75.4,"metric":"percent"},{"benchmark":"lvbench","model":"claude-sonnet-5","score":68.5,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-5.6-sol","score":82.1,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-5.6-terra","score":78.9,"metric":"percent"},{"benchmark":"hle-verified","model":"gemini-3.8-flash","score":54.9,"metric":"percent"},{"benchmark":"hle-verified","model":"gemini-3.7-flash","score":53.6,"metric":"percent"},{"benchmark":"hle-verified","model":"claude-opus-5","score":54.4,"metric":"percent"},{"benchmark":"hle-verified","model":"claude-sonnet-5","score":31,"metric":"percent"},{"benchmark":"hle-verified","model":"gpt-5.6-sol","score":54.5,"metric":"percent"},{"benchmark":"hle-verified","model":"gpt-5.6-terra","score":51.1,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gemini-3.8-flash","score":59,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gemini-3.7-flash","score":50.6,"metric":"percent"},{"benchmark":"osworld-2.0","model":"claude-sonnet-5","score":42.6,"metric":"percent"},{"benchmark":"biomysterybench","model":"gemini-3.8-flash","score":88.8,"metric":"percent"},{"benchmark":"biomysterybench","model":"gemini-3.7-flash","score":87.1,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-sonnet-5","score":87.5,"metric":"percent"},{"benchmark":"biomysterybench","model":"gpt-5.6-sol","score":79.5,"metric":"percent"},{"benchmark":"biomysterybench","model":"gpt-5.6-terra","score":83.8,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"gemini-3.8-flash","score":56.5,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"gemini-3.7-flash","score":43.5,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"claude-sonnet-5","score":34.1,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"gpt-5.6-sol","score":44.7,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"gpt-5.6-terra","score":49.4,"metric":"percent"},{"benchmark":"labbench2","model":"gemini-3.8-flash","score":86.2,"metric":"percent"},{"benchmark":"labbench2","model":"gemini-3.7-flash","score":82.1,"metric":"percent"},{"benchmark":"labbench2","model":"claude-opus-5","score":84.2,"metric":"percent"},{"benchmark":"labbench2","model":"claude-sonnet-5","score":80.1,"metric":"percent"},{"benchmark":"labbench2","model":"gpt-5.6-sol","score":82.1,"metric":"percent"},{"benchmark":"labbench2","model":"gpt-5.6-terra","score":81.2,"metric":"percent"},{"benchmark":"cybergym","model":"gemini-3.8-flash-cyber","score":86.2,"metric":"percent"},{"benchmark":"cybergym","model":"gemini-3.5-flash-cyber","score":77.5,"metric":"percent"},{"benchmark":"cybergym","model":"gpt-5.5-cyber","score":85.6,"metric":"percent"},{"benchmark":"aa-index","model":"gemini-3.7-flash","score":56,"metric":"percent"},{"benchmark":"aa-index","model":"gemini-3.6-flash","score":52,"metric":"percent"},{"benchmark":"aa-index","model":"claude-sonnet-5","score":55,"metric":"percent"},{"benchmark":"aa-index","model":"gpt-5.6-terra","score":57,"metric":"percent"},{"benchmark":"aa-index","model":"muse-spark-1.2","score":57,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gemini-3.7-flash","score":43.6,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gemini-3.6-flash","score":34.4,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-sonnet-5","score":42.7,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-5.6-terra","score":41.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.6-flash","score":48.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-1.2","score":54.9,"metric":"percent"},{"benchmark":"webdev-arena","model":"gemini-3.7-flash","score":1588,"metric":"elo"},{"benchmark":"webdev-arena","model":"gemini-3.6-flash","score":1538,"metric":"elo"},{"benchmark":"webdev-arena","model":"claude-sonnet-5","score":1541,"metric":"elo"},{"benchmark":"webdev-arena","model":"gpt-5.6-terra","score":1523,"metric":"elo"},{"benchmark":"webdev-arena","model":"muse-spark-1.2","score":1535,"metric":"elo"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.6-flash","score":78,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"muse-spark-1.2","score":82.9,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"gemini-3.7-flash","score":14.9,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"gemini-3.6-flash","score":5.4,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-sonnet-5","score":14.6,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"gpt-5.6-terra","score":20.8,"metric":"percent"},{"benchmark":"automationbench","model":"gemini-3.7-flash","score":30.4,"metric":"percent"},{"benchmark":"automationbench","model":"gemini-3.6-flash","score":17,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-terra","score":23.6,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.7-flash","score":1525,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.6-flash","score":1422,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-5","score":1598,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-terra","score":1578,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"muse-spark-1.2","score":1628,"metric":"elo"},{"benchmark":"harvey-lab-aa","model":"gemini-3.7-flash","score":90.7,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"gemini-3.6-flash","score":85.1,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"claude-sonnet-5","score":90.1,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"gpt-5.6-terra","score":85.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gemini-3.6-flash","score":22,"metric":"percent"},{"benchmark":"gdp-pdf","model":"muse-spark-1.2","score":16,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.6-flash","score":85.2,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gemini-3.6-flash","score":89.4,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-sonnet-5","score":88.3,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3.6-flash","score":84.2,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-3.7-flash","score":97,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-3.6-flash","score":91.8,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"claude-sonnet-5","score":81.5,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.6-terra","score":93.5,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gemini-3.6-flash","score":33.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gemini-3.7-flash","score":26.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gemini-3.6-flash","score":24.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-sonnet-5","score":33.3,"metric":"percent"},{"benchmark":"hle-verified","model":"gemini-3.6-flash","score":51.2,"metric":"percent"},{"benchmark":"biomysterybench","model":"gemini-3.6-flash","score":80.6,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"gemini-3.6-flash","score":41.2,"metric":"percent"},{"benchmark":"labbench2","model":"gemini-3.6-flash","score":76.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-3.6-flash","score":58.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-3.5-flash","score":55.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-5.6-luna","score":62.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"grok-4.5","score":64.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-sonnet-5","score":63.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.6-flash","score":49,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.5-flash","score":37,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.1-pro","score":12,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-luna","score":67,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.5","score":54,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-sonnet-5","score":54,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.1-pro","score":73.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"grok-4.5","score":83.3,"metric":"percent"},{"benchmark":"mle-bench","model":"gemini-3.6-flash","score":63.9,"metric":"percent"},{"benchmark":"mle-bench","model":"gemini-3.5-flash","score":49.7,"metric":"percent"},{"benchmark":"mle-bench","model":"gemini-3.1-pro","score":42.6,"metric":"percent"},{"benchmark":"mle-bench","model":"gpt-5.6-luna","score":47.6,"metric":"percent"},{"benchmark":"mle-bench","model":"grok-4.5","score":43.2,"metric":"percent"},{"benchmark":"mle-bench","model":"claude-sonnet-5","score":66.9,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.6-flash","score":1421,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.5-flash","score":1349,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.1-pro","score":965,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-luna","score":1584,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"grok-4.5","score":1535,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-5","score":1607,"metric":"elo"},{"benchmark":"osworld-verified","model":"gemini-3.6-flash","score":83,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.6-luna","score":72.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.5-flash","score":84.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.1-pro","score":83.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.6-luna","score":82.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"grok-4.5","score":81.6,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gemini-3.5-flash","score":84.9,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gemini-3.1-pro","score":83.2,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-3.5-flash","score":77.3,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.6-luna","score":74.8,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"grok-4.5","score":81.4,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"claude-sonnet-5","score":71.6,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-3.6-flash","score":54,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-3.5-flash","score":26.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3-flash","score":58,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-3.5-flash","score":53.9,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-3-flash","score":48.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-sonnet-4.6","score":53,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3-flash","score":62,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-sonnet-4.6","score":69.5,"metric":"percent"},{"benchmark":"toolathlon","model":"gemini-3.5-flash","score":56.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"gemini-3-flash","score":65.1,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gemini-3-flash","score":42.6,"metric":"percent"},{"benchmark":"financeagent-v2","model":"claude-sonnet-4.6","score":51,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"gemini-3.5-flash","score":1656,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gemini-3-flash","score":1204,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"claude-sonnet-4.6","score":1674,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gpt-5.5","score":1773,"metric":"elo"},{"benchmark":"charxiv-rq","model":"claude-sonnet-4.6","score":70.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.5","score":84.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.5-flash","score":83.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.7","score":75.2,"metric":"percent"},{"benchmark":"blueprint-bench-2","model":"gemini-3-flash","score":0,"metric":"percent"},{"benchmark":"blueprint-bench-2","model":"claude-sonnet-4.6","score":6.7,"metric":"percent"},{"benchmark":"blueprint-bench-2","model":"claude-opus-4.7","score":24.5,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-3-flash","score":67.2,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"claude-opus-4.7","score":59.3,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.5","score":94.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.5-flash","score":72.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-3.5-flash-lite","score":54.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemini-3.1-flash-lite","score":38.3,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-4.5-haiku","score":39.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.5-flash-lite","score":54,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.1-flash-lite","score":31,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.4-mini","score":59.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-4.5-haiku","score":44.2,"metric":"percent"},{"benchmark":"mle-bench","model":"gemini-3.5-flash-lite","score":39.2,"metric":"percent"},{"benchmark":"mle-bench","model":"gemini-3.1-flash-lite","score":22,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.5-flash-lite","score":1140,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.1-flash-lite","score":642,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.4-mini","score":1171,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-4.5-haiku","score":907,"metric":"elo"},{"benchmark":"osworld-verified","model":"gemini-3.5-flash-lite","score":74,"metric":"percent"},{"benchmark":"osworld-verified","model":"gemini-3.1-flash-lite","score":54.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-4.5-haiku","score":50.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.5-flash-lite","score":74.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.1-flash-lite","score":73.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.4-mini","score":80.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-4.5-haiku","score":61.7,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gemini-3.5-flash-lite","score":76.5,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gemini-3.1-flash-lite","score":75.6,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-3.5-flash-lite","score":72.2,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-3.1-flash-lite","score":60.1,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5.4-mini","score":42.7,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"claude-4.5-haiku","score":35.3,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-3.5-flash-lite","score":21.3,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-3.1-flash-lite","score":12.3,"metric":"percent"},{"benchmark":"hle","model":"gemini-3.1-flash-lite","score":16,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-2.5-flash-lite","score":6.9,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5-mini","score":16.7,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"gemini-3.1-flash-lite","score":86.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash-lite","score":66.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-mini","score":82.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-flash-lite","score":76.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-flash-lite","score":51,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-mini","score":74.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-4.5-haiku","score":58,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-flash-lite","score":55.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"grok-4.1-fast","score":31.6,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-5-mini","score":75.5,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-3.1-flash-lite","score":84.8,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-2.5-flash-lite","score":60.7,"metric":"percent"},{"benchmark":"videommmu","model":"grok-4.1-fast","score":74.6,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-3.1-flash-lite","score":43.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-2.5-flash-lite","score":11.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5-mini","score":9.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-4.5-haiku","score":5.5,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"gemini-3.1-flash-lite","score":40.6,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"gemini-2.5-flash-lite","score":17.9,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"gpt-5-mini","score":33.7,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"claude-4.5-haiku","score":18.6,"metric":"percent"},{"benchmark":"mmmlu","model":"gemini-3.1-flash-lite","score":88.9,"metric":"percent"},{"benchmark":"mmmlu","model":"gemini-2.5-flash-lite","score":84.5,"metric":"percent"},{"benchmark":"mmmlu","model":"gpt-5-mini","score":84.9,"metric":"percent"},{"benchmark":"mmmlu","model":"claude-4.5-haiku","score":83,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3.1-flash-lite","score":72,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash","score":62.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-lite","score":34.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini","score":80.4,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-4.5-haiku","score":53.2,"metric":"percent"},{"benchmark":"livecodebench","model":"grok-4.1-fast","score":76.5,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-2.5-flash","score":54.3,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemini-2.5-flash-lite","score":30.6,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gpt-5-mini","score":52.5,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"grok-4.1-fast","score":54.6,"metric":"percent"},{"benchmark":"mrcr-1m","model":"gemini-2.5-flash-lite","score":5.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-12b-it","score":77.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-e4b-it","score":69.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-e2b-it","score":60,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-27b-it","score":67.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-12b-it","score":77.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-e4b-it","score":42.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-e2b-it","score":37.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-3-27b-it","score":20.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-12b-it","score":72,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e4b-it","score":52,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e2b-it","score":44,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-27b-it","score":29.1,"metric":"percent"},{"benchmark":"codeforces","model":"gemma-4-31b-it","score":2150,"metric":"ELO"},{"benchmark":"codeforces","model":"gemma-4-26b-a4b-it","score":1718,"metric":"ELO"},{"benchmark":"codeforces","model":"gemma-4-12b-it","score":1659,"metric":"ELO"},{"benchmark":"codeforces","model":"gemma-4-e4b-it","score":940,"metric":"ELO"},{"benchmark":"codeforces","model":"gemma-4-e2b-it","score":633,"metric":"ELO"},{"benchmark":"codeforces","model":"gemma-3-27b-it","score":110,"metric":"ELO"},{"benchmark":"gpqa-diamond","model":"gemma-4-12b-it","score":78.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e4b-it","score":58.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e2b-it","score":43.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-27b-it","score":42.4,"metric":"percent"},{"benchmark":"hle","model":"gemma-4-12b-it","score":5.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemma-4-31b-it","score":26.5,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemma-4-26b-a4b-it","score":17.2,"metric":"avg@3"},{"benchmark":"big-bench-extra-hard","model":"gemma-4-31b-it","score":74.4,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemma-4-26b-a4b-it","score":64.8,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemma-4-12b-it","score":53,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemma-4-e4b-it","score":33.1,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemma-4-e2b-it","score":21.9,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemma-3-27b-it","score":19.3,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-4-31b-it","score":88.4,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-4-26b-a4b-it","score":86.3,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-4-12b-it","score":83.4,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-4-e4b-it","score":76.6,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-4-e2b-it","score":67.4,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-3-27b-it","score":70.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-12b-it","score":69.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-e4b-it","score":52.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-e2b-it","score":44.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-3-27b-it","score":49.7,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gemma-4-31b-it","score":0.131,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemma-4-26b-a4b-it","score":0.149,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemma-4-12b-it","score":0.164,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemma-4-e4b-it","score":0.181,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemma-4-e2b-it","score":0.29,"metric":"edit_distance"},{"benchmark":"omnidocbench-1.5","model":"gemma-3-27b-it","score":0.365,"metric":"edit_distance"},{"benchmark":"mathvision","model":"gemma-4-31b-it","score":85.6,"metric":"percent"},{"benchmark":"mathvision","model":"gemma-4-26b-a4b-it","score":82.4,"metric":"percent"},{"benchmark":"mathvision","model":"gemma-4-12b-it","score":79.7,"metric":"percent"},{"benchmark":"mathvision","model":"gemma-4-e4b-it","score":59.5,"metric":"percent"},{"benchmark":"mathvision","model":"gemma-4-e2b-it","score":52.4,"metric":"percent"},{"benchmark":"mathvision","model":"gemma-3-27b-it","score":46,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemma-4-31b-it","score":61.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemma-4-26b-a4b-it","score":58.1,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemma-4-12b-it","score":48.7,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemma-4-e4b-it","score":28.7,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemma-4-e2b-it","score":23.5,"metric":"percent"},{"benchmark":"covost","model":"gemma-4-e4b-it","score":35.54,"metric":"bleu"},{"benchmark":"covost","model":"gemma-4-e2b-it","score":33.47,"metric":"bleu"},{"benchmark":"fleurs","model":"gemma-4-e4b-it","score":0.08,"metric":"wer"},{"benchmark":"fleurs","model":"gemma-4-e2b-it","score":0.09,"metric":"wer"},{"benchmark":"mrcr-128k-8n","model":"gemma-4-31b-it","score":66.4,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemma-4-26b-a4b-it","score":44.1,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemma-4-12b-it","score":43.4,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemma-4-e4b-it","score":25.4,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemma-4-e2b-it","score":19.1,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"gemma-3-27b-it","score":13.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"diffusiongemma-26b-a4b","score":77.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"diffusiongemma-26b-a4b","score":69.1,"metric":"percent"},{"benchmark":"livecodebench","model":"diffusiongemma-26b-a4b","score":69.1,"metric":"percent"},{"benchmark":"codeforces","model":"diffusiongemma-26b-a4b","score":1429,"metric":"ELO"},{"benchmark":"gpqa-diamond","model":"diffusiongemma-26b-a4b","score":73.2,"metric":"percent"},{"benchmark":"hle","model":"diffusiongemma-26b-a4b","score":11,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"diffusiongemma-26b-a4b","score":11.9,"metric":"avg@3"},{"benchmark":"big-bench-extra-hard","model":"diffusiongemma-26b-a4b","score":47.6,"metric":"percent"},{"benchmark":"mmmlu","model":"diffusiongemma-26b-a4b","score":81.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"diffusiongemma-26b-a4b","score":54.3,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"diffusiongemma-26b-a4b","score":0.319,"metric":"edit_distance"},{"benchmark":"mathvision","model":"diffusiongemma-26b-a4b","score":70.5,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"diffusiongemma-26b-a4b","score":49,"metric":"percent"},{"benchmark":"mrcr-128k-8n","model":"diffusiongemma-26b-a4b","score":32,"metric":"percent"},{"benchmark":"charxiv-rq","model":"muse-spark","score":86.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.6","score":65.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.1-pro","score":80.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.4","score":82.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"grok-4.2","score":60.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"muse-spark","score":80.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.6","score":77.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-pro","score":83.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"grok-4.2","score":75.2,"metric":"percent"},{"benchmark":"erqa","model":"muse-spark","score":64.7,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-4.6","score":51.6,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3.1-pro","score":69.4,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.4","score":65.4,"metric":"percent"},{"benchmark":"erqa","model":"grok-4.2","score":54.1,"metric":"percent"},{"benchmark":"simplevqa","model":"muse-spark","score":71.3,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-opus-4.6","score":62.2,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3.1-pro","score":72.4,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5.4","score":61.1,"metric":"percent"},{"benchmark":"simplevqa","model":"grok-4.2","score":57.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"muse-spark","score":84.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-opus-4.6","score":83.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gemini-3.1-pro","score":84.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5.4","score":85.4,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"muse-spark","score":33,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"gemini-3.1-pro","score":29,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"gpt-5.4","score":41,"metric":"percent"},{"benchmark":"hle","model":"muse-spark","score":42.8,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-3.1-pro","score":45.4,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4","score":43.9,"metric":"avg@3"},{"benchmark":"hle","model":"grok-4.2","score":31.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"muse-spark","score":50.4,"metric":"avg@3"},{"benchmark":"arc-agi-2","model":"muse-spark","score":42.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.6","score":63.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.1-pro","score":76.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4","score":76.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.2","score":53.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"muse-spark","score":89.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.6","score":92.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"grok-4.2","score":88.5,"metric":"percent"},{"benchmark":"healthbench-hard","model":"muse-spark","score":42.8,"metric":"percent"},{"benchmark":"healthbench-hard","model":"claude-opus-4.6","score":14.8,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gemini-3.1-pro","score":20.6,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gpt-5.4","score":40.1,"metric":"percent"},{"benchmark":"healthbench-hard","model":"grok-4.2","score":20.3,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"muse-spark","score":52.6,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"claude-opus-4.6","score":52.1,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"gemini-3.1-pro","score":71.5,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"gpt-5.4","score":59.6,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"grok-4.2","score":50.2,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"muse-spark","score":78.4,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"claude-opus-4.6","score":64.8,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemini-3.1-pro","score":81.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gpt-5.4","score":77.1,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"grok-4.2","score":65.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"muse-spark","score":74.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-4.6","score":73.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gemini-3.1-pro","score":69.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-5.4","score":73.6,"metric":"percent"},{"benchmark":"deepsearchqa","model":"grok-4.2","score":62.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"muse-spark","score":77.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"grok-4.2","score":76.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"muse-spark","score":52.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"grok-4.2","score":51.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"muse-spark","score":59,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"grok-4.2","score":47.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"muse-spark","score":91.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.6","score":92.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-3.1-pro","score":95.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.4","score":91.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"grok-4.2","score":96.5,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"muse-spark","score":1444,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gemini-3.1-pro","score":1320,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gpt-5.4","score":1672,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"grok-4.2","score":1055,"metric":"elo"},{"benchmark":"hle","model":"muse-spark-contemplating","score":50.2,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-3.1-deep-think","score":48.4,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4-pro","score":43.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"muse-spark-contemplating","score":58.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemini-3.1-deep-think","score":53.4,"metric":"avg@3"},{"benchmark":"ipho-2025-theory","model":"muse-spark-contemplating","score":82.6,"metric":"percent"},{"benchmark":"ipho-2025-theory","model":"gemini-3.1-deep-think","score":87.7,"metric":"percent"},{"benchmark":"ipho-2025-theory","model":"gpt-5.4-pro","score":93.5,"metric":"percent"},{"benchmark":"frontierscience-research","model":"muse-spark-contemplating","score":38.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gemini-3.1-deep-think","score":23.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"muse-spark-1.1","score":88.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"muse-spark","score":82.2,"metric":"percent"},{"benchmark":"jobbench","model":"muse-spark-1.1","score":54.7,"metric":"percent"},{"benchmark":"jobbench","model":"muse-spark","score":17,"metric":"percent"},{"benchmark":"jobbench","model":"gemini-3.1-pro","score":15.9,"metric":"percent"},{"benchmark":"jobbench","model":"claude-opus-4.8","score":48.4,"metric":"percent"},{"benchmark":"jobbench","model":"gpt-5.5","score":38.3,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"muse-spark-1.1","score":75.6,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"muse-spark","score":49.4,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gemini-3.1-pro","score":61.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gpt-5.5","score":73.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"muse-spark-1.1","score":80.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"muse-spark","score":53.3,"metric":"percent"},{"benchmark":"hle-with-tools","model":"muse-spark-1.1","score":62.1,"metric":"avg@3"},{"benchmark":"financeagent-v2","model":"muse-spark-1.1","score":57.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"muse-spark-1.1","score":80,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"muse-spark","score":67.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"muse-spark-1.1","score":61.5,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"muse-spark","score":55,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-1.1","score":53.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark","score":10,"metric":"percent"},{"benchmark":"charxiv-rq","model":"muse-spark-1.1","score":88.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"muse-spark","score":88.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.1-pro","score":81.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.5","score":84.8,"metric":"percent"},{"benchmark":"babyvision","model":"muse-spark-1.1","score":76.3,"metric":"percent"},{"benchmark":"babyvision","model":"muse-spark","score":39.9,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3.1-pro","score":51.5,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.5","score":83.6,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-5.5","score":87.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"muse-spark-1.1","score":84.9,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-4.8","score":84.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"muse-spark","score":76.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gemini-3.1-pro","score":71.3,"metric":"percent"},{"benchmark":"vibe-code-bench-v1.1","model":"muse-spark-1.1","score":72.2,"metric":"percent"},{"benchmark":"vibe-code-bench-v1.1","model":"muse-spark","score":19.7,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"muse-spark-1.1","score":42,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"muse-spark","score":24.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-5","score":86.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-terra","score":81.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"grok-4.5","score":81.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemini-3.6-flash","score":78.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"muse-spark-1.1","score":76.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-5","score":65,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-terra","score":64.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-1.2","score":59.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.5","score":56.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-1.1","score":53,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.6-flash","score":40,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-5","score":1852,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"muse-spark-1.2","score":1631,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-terra","score":1577,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"grok-4.5","score":1526,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.6-flash","score":1423,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"muse-spark-1.1","score":1371,"metric":"elo"},{"benchmark":"mcp-atlas","model":"muse-spark-1.2","score":90.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k3","score":82.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.6-sol","score":81.8,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"gpt-5.6-sol","score":54.6,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"muse-spark-1.2","score":54,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"claude-opus-5","score":47.5,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"muse-spark-1.1","score":46,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"gemini-3.7-flash","score":30,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"gemini-3.7-flash","score":77.8,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"muse-spark-1.2","score":75,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"muse-spark-1.1","score":73.3,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"claude-opus-5","score":70.3,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"gpt-5.6-sol","score":64.7,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-opus-5","score":89.3,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"muse-spark-1.1","score":88.4,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"muse-spark-1.2","score":87.6,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-5.6-sol","score":84,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"muse-spark-1.3","score":1754,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"muse-spark-1.2","score":1615,"metric":"elo"},{"benchmark":"jobbench","model":"muse-spark-1.3","score":64.9,"metric":"percent"},{"benchmark":"jobbench","model":"muse-spark-1.2","score":61.6,"metric":"percent"},{"benchmark":"jobbench","model":"gpt-5.6-sol","score":45.4,"metric":"percent"},{"benchmark":"jobbench","model":"claude-opus-5","score":65.7,"metric":"percent"},{"benchmark":"osworld-2.0","model":"muse-spark-1.3","score":66.9,"metric":"percent"},{"benchmark":"osworld-2.0","model":"muse-spark-1.2","score":47.6,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-5.6-sol","score":62.7,"metric":"percent"},{"benchmark":"osworld-2.0","model":"claude-opus-5","score":68.3,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"muse-spark-1.3","score":32,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"muse-spark-1.2","score":17.9,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"gpt-5.6-sol","score":27.3,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"claude-opus-5","score":31.4,"metric":"percent"},{"benchmark":"deepsearchqa","model":"muse-spark-1.3","score":90.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"muse-spark-1.2","score":85.9,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-5.6-sol","score":93.1,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-5","score":90.4,"metric":"percent"},{"benchmark":"automationbench","model":"muse-spark-1.3","score":49.6,"metric":"percent"},{"benchmark":"automationbench","model":"muse-spark-1.2","score":38.2,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-sol","score":46.7,"metric":"percent"},{"benchmark":"mrcr-512k-8n","model":"muse-spark-1.3","score":98.5,"metric":"percent"},{"benchmark":"mrcr-512k-8n","model":"muse-spark-1.2","score":66.3,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"muse-spark-1.3","score":98.1,"metric":"percent"},{"benchmark":"mrcr-1m-8n","model":"muse-spark-1.2","score":55.5,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-1.3","score":75.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-1.2","score":55,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"muse-spark-1.3","score":59.4,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"muse-spark-1.2","score":46.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"gpt-5.6-sol","score":53.5,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-opus-5","score":52.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"muse-spark-1.3","score":88.8,"metric":"percent"},{"benchmark":"legal-agent-benchmark-aa","model":"muse-wonder-full","score":13.1,"metric":"percent"},{"benchmark":"legal-agent-benchmark-aa","model":"muse-wonder","score":10,"metric":"percent"},{"benchmark":"legal-agent-benchmark-aa","model":"claude-fable-5.1","score":6.4,"metric":"percent"},{"benchmark":"legal-agent-benchmark-aa","model":"gpt-6-astra","score":8.6,"metric":"percent"},{"benchmark":"legal-agent-benchmark-aa","model":"claude-opus-5.5","score":4.2,"metric":"percent"},{"benchmark":"financeagent-v2","model":"muse-wonder-full","score":59.1,"metric":"percent"},{"benchmark":"financeagent-v2","model":"muse-wonder","score":56.6,"metric":"percent"},{"benchmark":"healthbench-professional","model":"muse-wonder-full","score":62.3,"metric":"percent"},{"benchmark":"healthbench-professional","model":"muse-wonder","score":60.5,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gpt-6-astra","score":65.3,"metric":"percent"},{"benchmark":"automationbench-aa","model":"muse-wonder-full","score":45.4,"metric":"percent"},{"benchmark":"automationbench-aa","model":"muse-wonder","score":39.1,"metric":"percent"},{"benchmark":"automationbench-aa","model":"claude-fable-5.1","score":32.1,"metric":"percent"},{"benchmark":"automationbench-aa","model":"gpt-6-astra","score":41.6,"metric":"percent"},{"benchmark":"automationbench-aa","model":"claude-opus-5.5","score":41.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"muse-wonder-full","score":33.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"muse-wonder","score":30.8,"metric":"percent"},{"benchmark":"gdp-pdf","model":"claude-fable-5.1","score":27.6,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gpt-6-astra","score":34.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"claude-opus-5.5","score":30.6,"metric":"percent"},{"benchmark":"jobbench","model":"muse-wonder-full","score":75.3,"metric":"percent"},{"benchmark":"jobbench","model":"muse-wonder","score":70.5,"metric":"percent"},{"benchmark":"jobbench","model":"claude-fable-5.1","score":73.1,"metric":"percent"},{"benchmark":"jobbench","model":"gpt-6-astra","score":66.1,"metric":"percent"},{"benchmark":"jobbench","model":"claude-opus-5.5","score":75.4,"metric":"percent"},{"benchmark":"osworld-2.1","model":"muse-wonder-full","score":78.4,"metric":"percent"},{"benchmark":"osworld-2.1","model":"muse-wonder","score":72.6,"metric":"percent"},{"benchmark":"osworld-2.1","model":"gpt-6-astra","score":75.8,"metric":"percent"},{"benchmark":"osworld-2.1-strict","model":"muse-wonder-full","score":39.4,"metric":"percent"},{"benchmark":"osworld-2.1-strict","model":"muse-wonder","score":34.3,"metric":"percent"},{"benchmark":"osworld-2.1-strict","model":"claude-fable-5.1","score":43.1,"metric":"percent"},{"benchmark":"osworld-2.1-strict","model":"gpt-6-astra","score":34.3,"metric":"percent"},{"benchmark":"memorybench","model":"muse-wonder-full","score":85.5,"metric":"percent"},{"benchmark":"memorybench","model":"muse-wonder","score":85.6,"metric":"percent"},{"benchmark":"memorybench","model":"claude-fable-5.1","score":79,"metric":"percent"},{"benchmark":"memorybench","model":"gpt-6-astra","score":81.4,"metric":"percent"},{"benchmark":"memorybench","model":"claude-opus-5.5","score":81.5,"metric":"percent"},{"benchmark":"terminal-bench-4.0-aa","model":"muse-wonder-full","score":57.1,"metric":"percent"},{"benchmark":"terminal-bench-4.0-aa","model":"muse-wonder","score":52,"metric":"percent"},{"benchmark":"terminal-bench-4.0-aa","model":"claude-fable-5.1","score":52,"metric":"percent"},{"benchmark":"terminal-bench-4.0-aa","model":"gpt-6-astra","score":59.1,"metric":"percent"},{"benchmark":"terminal-bench-4.0-aa","model":"claude-opus-5.5","score":59.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-wonder-full","score":79,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-wonder","score":78.8,"metric":"percent"},{"benchmark":"swe-marathon","model":"muse-wonder-full","score":57.5,"metric":"percent"},{"benchmark":"swe-marathon","model":"muse-wonder","score":53.1,"metric":"percent"},{"benchmark":"swe-marathon","model":"claude-fable-5.1","score":45.6,"metric":"percent"},{"benchmark":"swe-marathon","model":"gpt-6-astra","score":42.5,"metric":"percent"},{"benchmark":"swe-marathon","model":"claude-opus-5.5","score":46.3,"metric":"percent"},{"benchmark":"programbench","model":"muse-wonder-full","score":59,"metric":"percent"},{"benchmark":"programbench","model":"muse-wonder","score":50,"metric":"percent"},{"benchmark":"programbench","model":"claude-fable-5.1","score":55.5,"metric":"percent"},{"benchmark":"programbench","model":"gpt-6-astra","score":52.5,"metric":"percent"},{"benchmark":"programbench","model":"claude-opus-5.5","score":70.5,"metric":"percent"},{"benchmark":"jobbench","model":"muse-spark-open","score":61.8,"metric":"percent"},{"benchmark":"jobbench","model":"inkling","score":31.1,"metric":"percent"},{"benchmark":"jobbench","model":"nemotron-3-ultra","score":27.2,"metric":"percent"},{"benchmark":"jobbench","model":"qwen3.8-max","score":52.7,"metric":"percent"},{"benchmark":"jobbench","model":"glm-5.3","score":61.4,"metric":"percent"},{"benchmark":"jobbench","model":"kimi-k3","score":54.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"muse-spark-open","score":89.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"inkling","score":76,"metric":"percent"},{"benchmark":"mcp-atlas","model":"nemotron-3-ultra","score":63.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"beam","score":78.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.8-max","score":84.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5.3","score":84.2,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"muse-spark-open","score":1401,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"inkling","score":1079,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-3-ultra","score":1016,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"mistral-large-4","score":1424,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.8-max","score":1613,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.3","score":1653,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"kimi-k3","score":1537,"metric":"elo"},{"benchmark":"osworld-verified","model":"muse-spark-open","score":80.4,"metric":"percent"},{"benchmark":"osworld-verified","model":"inkling","score":40.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"kimi-k3","score":84.8,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"muse-spark-open","score":72.8,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"inkling","score":45.5,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"nemotron-3-ultra","score":34.3,"metric":"percent"},{"benchmark":"hle-diamond","model":"muse-spark-open","score":26.1,"metric":"percent"},{"benchmark":"hle-diamond","model":"inkling","score":11.2,"metric":"percent"},{"benchmark":"hle-diamond","model":"nemotron-3-ultra","score":8.9,"metric":"percent"},{"benchmark":"hle-diamond","model":"qwen3.8-max","score":17.3,"metric":"percent"},{"benchmark":"hle-diamond","model":"glm-5.3","score":16.4,"metric":"percent"},{"benchmark":"hle-diamond","model":"kimi-k3","score":22.2,"metric":"percent"},{"benchmark":"aa-omniscience","model":"muse-spark-open","score":25,"metric":"index"},{"benchmark":"aa-omniscience","model":"inkling","score":2,"metric":"index"},{"benchmark":"aa-omniscience","model":"nemotron-3-ultra","score":0,"metric":"index"},{"benchmark":"aa-omniscience","model":"beam","score":13,"metric":"index"},{"benchmark":"aa-omniscience","model":"mistral-large-4","score":-5,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3.8-max","score":4,"metric":"index"},{"benchmark":"aa-omniscience","model":"glm-5.3","score":14,"metric":"index"},{"benchmark":"aa-omniscience","model":"kimi-k3","score":20,"metric":"index"},{"benchmark":"scicode","model":"muse-spark-open","score":58.5,"metric":"percent"},{"benchmark":"scicode","model":"inkling","score":47,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-ultra","score":40.3,"metric":"percent"},{"benchmark":"scicode","model":"beam","score":49.7,"metric":"percent"},{"benchmark":"scicode","model":"mistral-large-4","score":54.2,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-max","score":54.1,"metric":"percent"},{"benchmark":"scicode","model":"glm-5.3","score":59,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k3","score":59.5,"metric":"percent"},{"benchmark":"hle-with-tools","model":"muse-spark-open","score":61,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"inkling","score":46,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"nemotron-3-ultra","score":37.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"beam","score":51.2,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"muse-spark-open","score":89,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"inkling","score":87.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-ultra","score":86.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"beam","score":90.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.8-max","score":93.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5.3","score":91.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k3","score":93.5,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-open","score":60,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"beam","score":44,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"mistral-large-4","score":62,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-max","score":57,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.3","score":67,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k3","score":68,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"muse-spark-open","score":58,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"beam","score":35,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"mistral-large-4","score":59,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"qwen3.8-max","score":62,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"glm-5.3","score":59,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"kimi-k3","score":66,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"muse-spark-open","score":76.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"inkling","score":55.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-ultra","score":53.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"beam","score":80.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-max","score":82,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.3","score":83.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k3","score":85,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"muse-spark-open","score":50,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"inkling","score":14,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"muse-spark-open","score":80.2,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"inkling","score":34.2,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"muse-spark-open","score":73.6,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"inkling","score":52.3,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"kimi-k3","score":71.9,"metric":"percent"},{"benchmark":"worldvqa-with-tools","model":"muse-spark-open","score":49.4,"metric":"percent"},{"benchmark":"worldvqa-with-tools","model":"inkling","score":18,"metric":"percent"},{"benchmark":"worldvqa-with-tools","model":"kimi-k3","score":51,"metric":"percent"},{"benchmark":"intphys-2","model":"muse-spark-open","score":68.3,"metric":"percent"},{"benchmark":"intphys-2","model":"inkling","score":55.2,"metric":"percent"},{"benchmark":"intphys-2","model":"kimi-k3","score":60.3,"metric":"percent"},{"benchmark":"videomme-v2","model":"muse-spark-open","score":61.5,"metric":"percent"},{"benchmark":"videomme-v2","model":"inkling","score":36.9,"metric":"percent"},{"benchmark":"videomme-v2","model":"kimi-k3","score":65.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"muse-glimmer-30b","score":75.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemma-4-31b-it","score":54.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.6-27b","score":62.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"muse-glimmer-30b","score":74.6,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gemma-4-31b-it","score":61.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"qwen3.6-27b","score":71.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"muse-glimmer-30b","score":23.5,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-31b-it","score":15.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.6-27b","score":16.7,"metric":"percent"},{"benchmark":"wildclawbench","model":"muse-glimmer-30b","score":47.6,"metric":"percent"},{"benchmark":"wildclawbench","model":"gemma-4-31b-it","score":37.6,"metric":"percent"},{"benchmark":"wildclawbench","model":"qwen3.6-27b","score":43.2,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"muse-glimmer-30b","score":953,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemma-4-31b-it","score":811,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.6-27b","score":1141,"metric":"elo"},{"benchmark":"gaia2","model":"muse-glimmer-30b","score":43.3,"metric":"percent"},{"benchmark":"gaia2","model":"gemma-4-31b-it","score":36.4,"metric":"percent"},{"benchmark":"gaia2","model":"qwen3.6-27b","score":40,"metric":"percent"},{"benchmark":"skillsbench","model":"muse-glimmer-30b","score":44.3,"metric":"percent"},{"benchmark":"skillsbench","model":"gemma-4-31b-it","score":32.4,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.6-27b","score":46.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"muse-glimmer-30b","score":65.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"gemma-4-31b-it","score":58.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.6-27b","score":75.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"muse-glimmer-30b","score":51.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemma-4-31b-it","score":36.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.6-27b","score":50.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"muse-glimmer-30b","score":76,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-31b-it","score":66.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"muse-glimmer-30b","score":51.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-31b-it","score":43.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-27b","score":60.7,"metric":"percent"},{"benchmark":"scicode","model":"muse-glimmer-30b","score":43.6,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-31b-it","score":43.4,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-27b","score":39.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"muse-glimmer-30b","score":78.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemma-4-31b-it","score":77.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"muse-glimmer-30b","score":75.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gemma-4-31b-it","score":75.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.6-27b","score":76.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"muse-glimmer-30b","score":74,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-31b-it","score":73,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.6-27b","score":75,"metric":"percent"},{"benchmark":"ifbench","model":"muse-glimmer-30b","score":77,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-31b-it","score":76,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-27b","score":70.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"muse-glimmer-30b","score":94.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"muse-glimmer-30b","score":83.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-31b-it","score":85.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-27b","score":84.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"muse-glimmer-30b","score":22,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemma-4-31b-it","score":23.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.6-27b","score":23.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"muse-glimmer-30b","score":80,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-31b-it","score":68.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.6-27b","score":73.3,"metric":"percent"},{"benchmark":"beam-128k","model":"muse-glimmer-30b","score":65.1,"metric":"percent"},{"benchmark":"beam-128k","model":"gemma-4-31b-it","score":58.2,"metric":"percent"},{"benchmark":"beam-128k","model":"qwen3.6-27b","score":63,"metric":"percent"},{"benchmark":"math500","model":"smollm2-135m-instruct","score":3,"metric":"percent"},{"benchmark":"math500","model":"mobilellm-r1-140m","score":6.2,"metric":"percent"},{"benchmark":"math500","model":"mobilellm-r1.5-140m","score":16,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-270m-it","score":6.8,"metric":"percent"},{"benchmark":"math500","model":"smollm2-360m-instruct","score":3.4,"metric":"percent"},{"benchmark":"math500","model":"mobilellm-r1-360m","score":28.4,"metric":"percent"},{"benchmark":"math500","model":"mobilellm-r1.5-360m","score":63.4,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-0.5b-instruct","score":31.2,"metric":"percent"},{"benchmark":"math500","model":"qwen3-0.6b","score":73,"metric":"percent"},{"benchmark":"math500","model":"mobilellm-r1-950m","score":74,"metric":"percent"},{"benchmark":"math500","model":"mobilellm-r1.5-950m","score":86.6,"metric":"percent"},{"benchmark":"math500","model":"llama-3.2-1b-instruct","score":24.8,"metric":"percent"},{"benchmark":"math500","model":"olmo-2-0425-1b-instruct","score":19.2,"metric":"percent"},{"benchmark":"math500","model":"openreasoning-nemotron-1.5b","score":83.4,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1-distill-qwen-1.5b","score":83.2,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-1.5b-instruct","score":54,"metric":"percent"},{"benchmark":"math500","model":"smollm2-1.7b-instruct","score":19.2,"metric":"percent"},{"benchmark":"math500","model":"qwen3-1.7b","score":89.4,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-135m-instruct","score":2.4,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1-140m","score":4.1,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1.5-140m","score":8.3,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-270m-it","score":8.4,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-360m-instruct","score":8.1,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1-360m","score":24.5,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1.5-360m","score":52.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-0.5b-instruct","score":48.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-0.6b","score":79.2,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1-950m","score":67.5,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-r1.5-950m","score":82.6,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-1b-it","score":62.9,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-1b-instruct","score":38.8,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-2-0425-1b-instruct","score":69.7,"metric":"percent"},{"benchmark":"gsm8k","model":"openreasoning-nemotron-1.5b","score":76.7,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-r1-distill-qwen-1.5b","score":77.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-1.5b-instruct","score":70,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-1.7b-instruct","score":41.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-1.7b","score":90.3,"metric":"percent"},{"benchmark":"aime-2024","model":"mobilellm-r1.5-360m","score":4.1,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-0.5b-instruct","score":0.1,"metric":"percent"},{"benchmark":"aime-2024","model":"mobilellm-r1.5-950m","score":39.9,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.2-1b-instruct","score":1.1,"metric":"percent"},{"benchmark":"aime-2024","model":"openreasoning-nemotron-1.5b","score":49.7,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-1.5b-instruct","score":2.5,"metric":"percent"},{"benchmark":"aime-2024","model":"smollm2-1.7b-instruct","score":0.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-1.7b","score":47,"metric":"percent"},{"benchmark":"aime-2025","model":"mobilellm-r1.5-360m","score":10.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-0.5b-instruct","score":0.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-0.6b","score":17,"metric":"percent"},{"benchmark":"aime-2025","model":"mobilellm-r1-950m","score":16.3,"metric":"percent"},{"benchmark":"aime-2025","model":"mobilellm-r1.5-950m","score":31.1,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-1b-it","score":0,"metric":"percent"},{"benchmark":"aime-2025","model":"llama-3.2-1b-instruct","score":0.2,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-2-0425-1b-instruct","score":0.1,"metric":"percent"},{"benchmark":"aime-2025","model":"openreasoning-nemotron-1.5b","score":40.4,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-distill-qwen-1.5b","score":23.4,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-1.5b-instruct","score":0.9,"metric":"percent"},{"benchmark":"aime-2025","model":"smollm2-1.7b-instruct","score":0.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-1.7b","score":37,"metric":"percent"},{"benchmark":"livecodebench","model":"smollm2-135m-instruct","score":0,"metric":"percent"},{"benchmark":"livecodebench","model":"mobilellm-r1-140m","score":1.7,"metric":"percent"},{"benchmark":"livecodebench","model":"mobilellm-r1.5-140m","score":1.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-270m-it","score":0,"metric":"percent"},{"benchmark":"livecodebench","model":"mobilellm-r1-360m","score":5.1,"metric":"percent"},{"benchmark":"livecodebench","model":"mobilellm-r1.5-360m","score":8.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-0.5b-instruct","score":3.6,"metric":"percent"},{"benchmark":"livecodebench","model":"mobilellm-r1.5-950m","score":29.1,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.2-1b-instruct","score":4.1,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-2-0425-1b-instruct","score":0,"metric":"percent"},{"benchmark":"livecodebench","model":"openreasoning-nemotron-1.5b","score":28.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-1.5b-instruct","score":7.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-1.7b","score":29.8,"metric":"percent"},{"benchmark":"hellaswag","model":"mobilellm-p1","score":52.2,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-2-0425-1b-instruct","score":67.3,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm2-1.7b-instruct","score":71.7,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3.5-2b","score":62.2,"metric":"percent"},{"benchmark":"hellaswag","model":"olmoe-1b-7b","score":78.8,"metric":"percent"},{"benchmark":"hellaswag","model":"mobilemoe-l","score":72.9,"metric":"percent"},{"benchmark":"piqa","model":"mobilellm-p1","score":73.2,"metric":"percent"},{"benchmark":"piqa","model":"olmo-2-0425-1b-instruct","score":75.2,"metric":"percent"},{"benchmark":"piqa","model":"smollm2-1.7b-instruct","score":76.2,"metric":"percent"},{"benchmark":"piqa","model":"qwen3.5-2b","score":72.8,"metric":"percent"},{"benchmark":"piqa","model":"olmoe-1b-7b","score":79.7,"metric":"percent"},{"benchmark":"piqa","model":"mobilemoe-l","score":79.4,"metric":"percent"},{"benchmark":"siqa","model":"mobilellm-p1","score":42.7,"metric":"percent"},{"benchmark":"siqa","model":"olmo-2-0425-1b-instruct","score":46.1,"metric":"percent"},{"benchmark":"siqa","model":"smollm2-1.7b-instruct","score":44.6,"metric":"percent"},{"benchmark":"siqa","model":"qwen3.5-2b","score":41,"metric":"percent"},{"benchmark":"siqa","model":"olmoe-1b-7b","score":50.8,"metric":"percent"},{"benchmark":"siqa","model":"mobilemoe-l","score":53.6,"metric":"percent"},{"benchmark":"winogrande","model":"mobilellm-p1","score":51.7,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-2-0425-1b-instruct","score":63.5,"metric":"percent"},{"benchmark":"winogrande","model":"smollm2-1.7b-instruct","score":68.4,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3.5-2b","score":63,"metric":"percent"},{"benchmark":"winogrande","model":"olmoe-1b-7b","score":68.7,"metric":"percent"},{"benchmark":"winogrande","model":"mobilemoe-l","score":67,"metric":"percent"},{"benchmark":"mmlu","model":"mobilellm-p1","score":38.7,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-2-0425-1b-instruct","score":42.9,"metric":"percent"},{"benchmark":"mmlu","model":"smollm2-1.7b-instruct","score":49.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-2b","score":57.4,"metric":"percent"},{"benchmark":"mmlu","model":"olmoe-1b-7b","score":52.7,"metric":"percent"},{"benchmark":"mmlu","model":"mobilemoe-l","score":60.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"mobilellm-p1","score":8.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"olmo-2-0425-1b-instruct","score":12.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"smollm2-1.7b-instruct","score":14.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen3.5-2b","score":8.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"olmoe-1b-7b","score":17.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"mobilemoe-l","score":22.1,"metric":"percent"},{"benchmark":"triviaqa","model":"mobilellm-p1","score":19.9,"metric":"percent"},{"benchmark":"triviaqa","model":"olmo-2-0425-1b-instruct","score":37.6,"metric":"percent"},{"benchmark":"triviaqa","model":"smollm2-1.7b-instruct","score":46,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3.5-2b","score":28.1,"metric":"percent"},{"benchmark":"triviaqa","model":"olmoe-1b-7b","score":54.1,"metric":"percent"},{"benchmark":"triviaqa","model":"mobilemoe-l","score":55.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"mobilellm-p1","score":35.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-2-0425-1b-instruct","score":45.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"smollm2-1.7b-instruct","score":53.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-2b","score":53.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmoe-1b-7b","score":57.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"mobilemoe-l","score":57.8,"metric":"percent"},{"benchmark":"arc-easy","model":"mobilellm-p1","score":52.7,"metric":"percent"},{"benchmark":"arc-easy","model":"olmo-2-0425-1b-instruct","score":69.8,"metric":"percent"},{"benchmark":"arc-easy","model":"smollm2-1.7b-instruct","score":62.9,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen3.5-2b","score":66,"metric":"percent"},{"benchmark":"arc-easy","model":"olmoe-1b-7b","score":75.9,"metric":"percent"},{"benchmark":"arc-easy","model":"mobilemoe-l","score":82.3,"metric":"percent"},{"benchmark":"openbookqa","model":"mobilellm-p1","score":29.6,"metric":"percent"},{"benchmark":"openbookqa","model":"olmo-2-0425-1b-instruct","score":42.2,"metric":"percent"},{"benchmark":"openbookqa","model":"smollm2-1.7b-instruct","score":45.8,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen3.5-2b","score":35.2,"metric":"percent"},{"benchmark":"openbookqa","model":"olmoe-1b-7b","score":46.8,"metric":"percent"},{"benchmark":"openbookqa","model":"mobilemoe-l","score":43,"metric":"percent"},{"benchmark":"boolq","model":"mobilellm-p1","score":68.8,"metric":"percent"},{"benchmark":"boolq","model":"olmo-2-0425-1b-instruct","score":71,"metric":"percent"},{"benchmark":"boolq","model":"smollm2-1.7b-instruct","score":68.5,"metric":"percent"},{"benchmark":"boolq","model":"qwen3.5-2b","score":71.7,"metric":"percent"},{"benchmark":"boolq","model":"olmoe-1b-7b","score":81.1,"metric":"percent"},{"benchmark":"boolq","model":"mobilemoe-l","score":81.7,"metric":"percent"},{"benchmark":"drop","model":"mobilellm-p1","score":25.5,"metric":"percent"},{"benchmark":"drop","model":"olmo-2-0425-1b-instruct","score":31.2,"metric":"percent"},{"benchmark":"drop","model":"smollm2-1.7b-instruct","score":24.8,"metric":"percent"},{"benchmark":"drop","model":"qwen3.5-2b","score":44.7,"metric":"percent"},{"benchmark":"drop","model":"olmoe-1b-7b","score":29.3,"metric":"percent"},{"benchmark":"drop","model":"mobilemoe-l","score":51.3,"metric":"percent"},{"benchmark":"bbh","model":"mobilellm-p1","score":29.1,"metric":"percent"},{"benchmark":"bbh","model":"olmo-2-0425-1b-instruct","score":35,"metric":"percent"},{"benchmark":"bbh","model":"smollm2-1.7b-instruct","score":35.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-2b","score":45.2,"metric":"percent"},{"benchmark":"bbh","model":"olmoe-1b-7b","score":37.1,"metric":"percent"},{"benchmark":"bbh","model":"mobilemoe-l","score":40.4,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilellm-p1","score":31.8,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-2-0425-1b-instruct","score":46.9,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-1.7b-instruct","score":46.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-2b","score":61.3,"metric":"percent"},{"benchmark":"gsm8k","model":"olmoe-1b-7b","score":49.1,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilemoe-l","score":76.8,"metric":"percent"},{"benchmark":"math500","model":"mobilellm-p1","score":8.8,"metric":"percent"},{"benchmark":"math500","model":"olmo-2-0425-1b-instruct","score":10.2,"metric":"percent"},{"benchmark":"math500","model":"smollm2-1.7b-instruct","score":15.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-2b","score":31,"metric":"percent"},{"benchmark":"math500","model":"olmoe-1b-7b","score":8.4,"metric":"percent"},{"benchmark":"math500","model":"mobilemoe-l","score":39.4,"metric":"percent"},{"benchmark":"gsm-plus","model":"mobilellm-p1","score":17,"metric":"percent"},{"benchmark":"gsm-plus","model":"olmo-2-0425-1b-instruct","score":25.1,"metric":"percent"},{"benchmark":"gsm-plus","model":"smollm2-1.7b-instruct","score":26.6,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3.5-2b","score":42.4,"metric":"percent"},{"benchmark":"gsm-plus","model":"olmoe-1b-7b","score":28.1,"metric":"percent"},{"benchmark":"gsm-plus","model":"mobilemoe-l","score":49.7,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-2-0425-1b-instruct","score":29.3,"metric":"percent"},{"benchmark":"humaneval","model":"smollm2-1.7b-instruct","score":1.2,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3.5-2b","score":50,"metric":"percent"},{"benchmark":"humaneval","model":"olmoe-1b-7b","score":36,"metric":"percent"},{"benchmark":"humaneval","model":"mobilemoe-l","score":65.2,"metric":"percent"},{"benchmark":"mbpp","model":"mobilellm-p1","score":44.2,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-2-0425-1b-instruct","score":14.8,"metric":"percent"},{"benchmark":"mbpp","model":"smollm2-1.7b-instruct","score":34.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3.5-2b","score":41.2,"metric":"percent"},{"benchmark":"mbpp","model":"olmoe-1b-7b","score":30.2,"metric":"percent"},{"benchmark":"mbpp","model":"mobilemoe-l","score":54.8,"metric":"percent"},{"benchmark":"ifeval","model":"mobilellm-p1","score":63.1,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-2-0425-1b-instruct","score":53.5,"metric":"percent"},{"benchmark":"ifeval","model":"smollm2-1.7b-instruct","score":54.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-2b","score":73.3,"metric":"percent"},{"benchmark":"ifeval","model":"olmoe-1b-7b","score":48.1,"metric":"percent"},{"benchmark":"ifeval","model":"mobilemoe-l","score":69.7,"metric":"percent"},{"benchmark":"ifbench","model":"mobilellm-p1","score":17,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-2-0425-1b-instruct","score":14.5,"metric":"percent"},{"benchmark":"ifbench","model":"smollm2-1.7b-instruct","score":16.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-2b","score":30.3,"metric":"percent"},{"benchmark":"ifbench","model":"olmoe-1b-7b","score":16.6,"metric":"percent"},{"benchmark":"ifbench","model":"mobilemoe-l","score":18.4,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-270m-it","score":39.4,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm2-360m-instruct","score":56.9,"metric":"percent"},{"benchmark":"hellaswag","model":"mobilemoe-s","score":56.1,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3.5-0.8b","score":49.7,"metric":"percent"},{"benchmark":"hellaswag","model":"mobilemoe-m","score":66.7,"metric":"percent"},{"benchmark":"piqa","model":"gemma-3-270m-it","score":67.1,"metric":"percent"},{"benchmark":"piqa","model":"smollm2-360m-instruct","score":71.6,"metric":"percent"},{"benchmark":"piqa","model":"mobilemoe-s","score":74.8,"metric":"percent"},{"benchmark":"piqa","model":"qwen3.5-0.8b","score":69.4,"metric":"percent"},{"benchmark":"piqa","model":"mobilemoe-m","score":77.7,"metric":"percent"},{"benchmark":"siqa","model":"gemma-3-270m-it","score":39.6,"metric":"percent"},{"benchmark":"siqa","model":"smollm2-360m-instruct","score":40.6,"metric":"percent"},{"benchmark":"siqa","model":"mobilemoe-s","score":43.1,"metric":"percent"},{"benchmark":"siqa","model":"qwen3.5-0.8b","score":38.8,"metric":"percent"},{"benchmark":"siqa","model":"mobilemoe-m","score":49.4,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-270m-it","score":53,"metric":"percent"},{"benchmark":"winogrande","model":"smollm2-360m-instruct","score":57.4,"metric":"percent"},{"benchmark":"winogrande","model":"mobilemoe-s","score":59.6,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3.5-0.8b","score":57.6,"metric":"percent"},{"benchmark":"winogrande","model":"mobilemoe-m","score":62.7,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-270m-it","score":26.5,"metric":"percent"},{"benchmark":"mmlu","model":"smollm2-360m-instruct","score":25.9,"metric":"percent"},{"benchmark":"mmlu","model":"mobilemoe-s","score":42.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-0.8b","score":50.2,"metric":"percent"},{"benchmark":"mmlu","model":"mobilemoe-m","score":54.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"gemma-3-270m-it","score":2.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"smollm2-360m-instruct","score":6.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"mobilemoe-s","score":10.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen3.5-0.8b","score":3.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"mobilemoe-m","score":17.7,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-270m-it","score":9.1,"metric":"percent"},{"benchmark":"triviaqa","model":"smollm2-360m-instruct","score":20.4,"metric":"percent"},{"benchmark":"triviaqa","model":"mobilemoe-s","score":30.5,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3.5-0.8b","score":16.1,"metric":"percent"},{"benchmark":"triviaqa","model":"mobilemoe-m","score":46.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-270m-it","score":27.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"smollm2-360m-instruct","score":38.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"mobilemoe-s","score":46.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-0.8b","score":41.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"mobilemoe-m","score":52.5,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-3-270m-it","score":50.5,"metric":"percent"},{"benchmark":"arc-easy","model":"smollm2-360m-instruct","score":49.1,"metric":"percent"},{"benchmark":"arc-easy","model":"mobilemoe-s","score":73.6,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen3.5-0.8b","score":61.4,"metric":"percent"},{"benchmark":"arc-easy","model":"mobilemoe-m","score":80.1,"metric":"percent"},{"benchmark":"openbookqa","model":"gemma-3-270m-it","score":35,"metric":"percent"},{"benchmark":"openbookqa","model":"smollm2-360m-instruct","score":36.2,"metric":"percent"},{"benchmark":"openbookqa","model":"mobilemoe-s","score":32.6,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen3.5-0.8b","score":30.8,"metric":"percent"},{"benchmark":"openbookqa","model":"mobilemoe-m","score":39.8,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3-270m-it","score":56.1,"metric":"percent"},{"benchmark":"boolq","model":"smollm2-360m-instruct","score":42.5,"metric":"percent"},{"benchmark":"boolq","model":"mobilemoe-s","score":72.7,"metric":"percent"},{"benchmark":"boolq","model":"qwen3.5-0.8b","score":62.5,"metric":"percent"},{"benchmark":"boolq","model":"mobilemoe-m","score":77.7,"metric":"percent"},{"benchmark":"drop","model":"gemma-3-270m-it","score":11,"metric":"percent"},{"benchmark":"drop","model":"smollm2-360m-instruct","score":15.2,"metric":"percent"},{"benchmark":"drop","model":"mobilemoe-s","score":33.1,"metric":"percent"},{"benchmark":"drop","model":"qwen3.5-0.8b","score":33.3,"metric":"percent"},{"benchmark":"drop","model":"mobilemoe-m","score":49.9,"metric":"percent"},{"benchmark":"bbh","model":"gemma-3-270m-it","score":31.8,"metric":"percent"},{"benchmark":"bbh","model":"smollm2-360m-instruct","score":30.5,"metric":"percent"},{"benchmark":"bbh","model":"mobilemoe-s","score":32.5,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-0.8b","score":37.8,"metric":"percent"},{"benchmark":"bbh","model":"mobilemoe-m","score":38.8,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-270m-it","score":5.8,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm2-360m-instruct","score":10,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilemoe-s","score":52.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-0.8b","score":45.7,"metric":"percent"},{"benchmark":"gsm8k","model":"mobilemoe-m","score":67.6,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-270m-it","score":7.2,"metric":"percent"},{"benchmark":"math500","model":"smollm2-360m-instruct","score":3.8,"metric":"percent"},{"benchmark":"math500","model":"mobilemoe-s","score":18.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-0.8b","score":19.6,"metric":"percent"},{"benchmark":"math500","model":"mobilemoe-m","score":26.8,"metric":"percent"},{"benchmark":"gsm-plus","model":"gemma-3-270m-it","score":4.3,"metric":"percent"},{"benchmark":"gsm-plus","model":"smollm2-360m-instruct","score":4.6,"metric":"percent"},{"benchmark":"gsm-plus","model":"mobilemoe-s","score":28.9,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3.5-0.8b","score":26.5,"metric":"percent"},{"benchmark":"gsm-plus","model":"mobilemoe-m","score":42.6,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-270m-it","score":12.8,"metric":"percent"},{"benchmark":"humaneval","model":"smollm2-360m-instruct","score":0,"metric":"percent"},{"benchmark":"humaneval","model":"mobilemoe-s","score":46.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3.5-0.8b","score":31.1,"metric":"percent"},{"benchmark":"humaneval","model":"mobilemoe-m","score":59.8,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-270m-it","score":9.8,"metric":"percent"},{"benchmark":"mbpp","model":"smollm2-360m-instruct","score":22.8,"metric":"percent"},{"benchmark":"mbpp","model":"mobilemoe-s","score":27.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3.5-0.8b","score":25.4,"metric":"percent"},{"benchmark":"mbpp","model":"mobilemoe-m","score":44.4,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-3-270m-it","score":31.2,"metric":"percent"},{"benchmark":"ifeval","model":"smollm2-360m-instruct","score":40.2,"metric":"percent"},{"benchmark":"ifeval","model":"mobilemoe-s","score":59.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-0.8b","score":59.9,"metric":"percent"},{"benchmark":"ifeval","model":"mobilemoe-m","score":61.6,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-3-270m-it","score":11.2,"metric":"percent"},{"benchmark":"ifbench","model":"smollm2-360m-instruct","score":19.1,"metric":"percent"},{"benchmark":"ifbench","model":"mobilemoe-s","score":14.2,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-0.8b","score":19.8,"metric":"percent"},{"benchmark":"ifbench","model":"mobilemoe-m","score":20.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m3","score":80.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m2.7","score":79.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.5","score":82.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minimax-m3","score":66,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minimax-m2.7","score":51.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro-thinking-max","score":59.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.1","score":48.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k2.6-thinking","score":53.9,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"minimax-m3","score":37.9,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"minimax-m2.7","score":11.3,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-opus-4.7","score":45.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"gpt-5.5","score":45.4,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"gemini-3.1-pro","score":13.5,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-sonnet-4.6","score":31.2,"metric":"percent"},{"benchmark":"nl2repo","model":"minimax-m2.7","score":35,"metric":"percent"},{"benchmark":"nl2repo","model":"claude-opus-4.7","score":56.3,"metric":"percent"},{"benchmark":"nl2repo","model":"gpt-5.5","score":52.9,"metric":"percent"},{"benchmark":"nl2repo","model":"gemini-3.1-pro","score":21.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"minimax-m3","score":30.8,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"minimax-m2.7","score":18.9,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"claude-opus-4.7","score":38.21,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"gpt-5.5","score":42.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"gemini-3.1-pro","score":29.8,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"claude-sonnet-4.6","score":31.8,"metric":"percent"},{"benchmark":"swe-fficiency","model":"minimax-m3","score":34.8,"metric":"percent"},{"benchmark":"swe-fficiency","model":"minimax-m2.7","score":14,"metric":"percent"},{"benchmark":"swe-fficiency","model":"claude-opus-4.7","score":42.2,"metric":"percent"},{"benchmark":"swe-fficiency","model":"gpt-5.5","score":46.6,"metric":"percent"},{"benchmark":"swe-fficiency","model":"gemini-3.1-pro","score":19.7,"metric":"percent"},{"benchmark":"livesqlbench","model":"minimax-m3","score":40.2,"metric":"percent"},{"benchmark":"livesqlbench","model":"minimax-m2.7","score":33.2,"metric":"percent"},{"benchmark":"livesqlbench","model":"claude-opus-4.7","score":41,"metric":"percent"},{"benchmark":"livesqlbench","model":"gpt-5.5","score":40.2,"metric":"percent"},{"benchmark":"livesqlbench","model":"gemini-3.1-pro","score":39.8,"metric":"percent"},{"benchmark":"cl-bench","model":"minimax-m3","score":20.5,"metric":"percent"},{"benchmark":"cl-bench","model":"minimax-m2.7","score":15.4,"metric":"percent"},{"benchmark":"cl-bench","model":"claude-opus-4.7","score":22.9,"metric":"percent"},{"benchmark":"cl-bench","model":"gpt-5.5","score":25.4,"metric":"percent"},{"benchmark":"cl-bench","model":"gemini-3.1-pro","score":21.1,"metric":"percent"},{"benchmark":"svg-bench","model":"minimax-m3","score":63.7,"metric":"percent"},{"benchmark":"svg-bench","model":"minimax-m2.7","score":48,"metric":"percent"},{"benchmark":"svg-bench","model":"claude-opus-4.7","score":62.3,"metric":"percent"},{"benchmark":"svg-bench","model":"gpt-5.5","score":58.2,"metric":"percent"},{"benchmark":"svg-bench","model":"gemini-3.1-pro","score":59.2,"metric":"percent"},{"benchmark":"svg-bench","model":"claude-sonnet-4.6","score":64.1,"metric":"percent"},{"benchmark":"svg-bench","model":"deepseek-v4-pro-thinking-max","score":61.7,"metric":"percent"},{"benchmark":"svg-bench","model":"glm-5.1","score":56.9,"metric":"percent"},{"benchmark":"svg-bench","model":"kimi-k2.6-thinking","score":60,"metric":"percent"},{"benchmark":"posttrainbench","model":"minimax-m3","score":37.1,"metric":"percent"},{"benchmark":"posttrainbench","model":"minimax-m2.7","score":13.1,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-4.7","score":42.4,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.5","score":39.3,"metric":"percent"},{"benchmark":"posttrainbench","model":"gemini-3.1-pro","score":15.2,"metric":"percent"},{"benchmark":"kernelbench-hard","model":"minimax-m3","score":28.8,"metric":"percent"},{"benchmark":"kernelbench-hard","model":"minimax-m2.7","score":10.5,"metric":"percent"},{"benchmark":"kernelbench-hard","model":"claude-opus-4.7","score":30.7,"metric":"percent"},{"benchmark":"kernelbench-hard","model":"gpt-5.5","score":20.9,"metric":"percent"},{"benchmark":"kernelbench-hard","model":"gemini-3.1-pro","score":18.6,"metric":"percent"},{"benchmark":"paperbench","model":"minimax-m3","score":52.6,"metric":"percent"},{"benchmark":"paperbench","model":"minimax-m2.7","score":30.6,"metric":"percent"},{"benchmark":"paperbench","model":"claude-opus-4.7","score":58.5,"metric":"percent"},{"benchmark":"paperbench","model":"gpt-5.5","score":57.5,"metric":"percent"},{"benchmark":"paperbench","model":"gemini-3.1-pro","score":46.7,"metric":"percent"},{"benchmark":"browsecomp","model":"minimax-m3","score":83.5,"metric":"percent"},{"benchmark":"browsecomp","model":"minimax-m2.7","score":76.3,"metric":"percent"},{"benchmark":"draco","model":"minimax-m3","score":73.2,"metric":"percent"},{"benchmark":"draco","model":"minimax-m2.7","score":66.8,"metric":"percent"},{"benchmark":"draco","model":"claude-opus-4.7","score":77.7,"metric":"percent"},{"benchmark":"draco","model":"claude-sonnet-4.6","score":75.8,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"minimax-m3","score":74.8,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"minimax-m2.7","score":66.4,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"claude-opus-4.7","score":79.8,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"gpt-5.5","score":80.7,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"gemini-3.1-pro","score":57.8,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"claude-sonnet-4.6","score":75.7,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"deepseek-v4-pro-thinking-max","score":70.3,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"glm-5.1","score":68.3,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"kimi-k2.6-thinking","score":65.1,"metric":"percent"},{"benchmark":"bankertoolbench","model":"minimax-m3","score":76.1,"metric":"percent"},{"benchmark":"bankertoolbench","model":"minimax-m2.7","score":63.9,"metric":"percent"},{"benchmark":"bankertoolbench","model":"claude-opus-4.7","score":81.3,"metric":"percent"},{"benchmark":"bankertoolbench","model":"gpt-5.5","score":70,"metric":"percent"},{"benchmark":"bankertoolbench","model":"gemini-3.1-pro","score":67,"metric":"percent"},{"benchmark":"officeqa-pro","model":"minimax-m3","score":45.1,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"minimax-m3","score":89.4,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"minimax-m2.7","score":84.9,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"claude-opus-4.7","score":88.5,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"gpt-5.5","score":88.1,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"gemini-3.1-pro","score":56.1,"metric":"percent"},{"benchmark":"yc-bench","model":"minimax-m3","score":2.1,"metric":"usd_millions"},{"benchmark":"yc-bench","model":"minimax-m2.7","score":0,"metric":"usd_millions"},{"benchmark":"yc-bench","model":"claude-opus-4.7","score":2.2,"metric":"usd_millions"},{"benchmark":"yc-bench","model":"gpt-5.5","score":1.3,"metric":"usd_millions"},{"benchmark":"yc-bench","model":"gemini-3.1-pro","score":1.1,"metric":"usd_millions"},{"benchmark":"yc-bench","model":"claude-sonnet-4.6","score":0.1,"metric":"usd_millions"},{"benchmark":"yc-bench","model":"deepseek-v4-pro-thinking-max","score":0.5,"metric":"usd_millions"},{"benchmark":"loca-bench","model":"minimax-m3","score":49.3,"metric":"percent"},{"benchmark":"loca-bench","model":"claude-opus-4.7","score":57,"metric":"percent"},{"benchmark":"mcp-atlas","model":"minimax-m2.7","score":49.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.7","score":77,"metric":"percent"},{"benchmark":"apex-agents","model":"minimax-m3","score":27.7,"metric":"percent"},{"benchmark":"apex-agents","model":"minimax-m2.7","score":5.6,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-4.7","score":37.2,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.5","score":41.7,"metric":"percent"},{"benchmark":"apex-agents","model":"gemini-3.1-pro","score":33.4,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-sonnet-4.6","score":26.2,"metric":"percent"},{"benchmark":"claweval-pass3","model":"minimax-m3","score":74.5,"metric":"percent"},{"benchmark":"claweval-pass3","model":"minimax-m2.7","score":49.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"claude-opus-4.7","score":71.6,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gemini-3.1-pro","score":57.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"claude-sonnet-4.6","score":68.3,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v4-pro-thinking-max","score":58.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"glm-5.1","score":62.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"kimi-k2.6-thinking","score":61.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"minimax-m3","score":75.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"kimi-k2.6-thinking","score":73.1,"metric":"percent"},{"benchmark":"omnidocbench","model":"minimax-m3","score":91.6,"metric":"percent"},{"benchmark":"omnidocbench","model":"claude-opus-4.7","score":89.3,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-5.5","score":87.5,"metric":"percent"},{"benchmark":"omnidocbench","model":"gemini-3.1-pro","score":88.1,"metric":"percent"},{"benchmark":"omnidocbench","model":"claude-sonnet-4.6","score":86.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"minimax-m3","score":78.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.7","score":77,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k2.6-thinking","score":79.4,"metric":"percent"},{"benchmark":"videommmu","model":"minimax-m3","score":84.6,"metric":"percent"},{"benchmark":"videommmu","model":"claude-opus-4.7","score":83,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5.5","score":86.4,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-3.1-pro","score":87.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"minimax-m3","score":85.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5.5","score":89.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-3.1-pro","score":87.9,"metric":"percent"},{"benchmark":"imo-2025","model":"claude-opus-4.7","score":17.4,"metric":"percent"},{"benchmark":"imo-2025","model":"gpt-5.5","score":76.1,"metric":"percent"},{"benchmark":"imo-2025","model":"gemini-3.1-pro","score":42.4,"metric":"percent"},{"benchmark":"usamo-2026","model":"claude-opus-4.7","score":52.8,"metric":"percent"},{"benchmark":"usamo-2026","model":"gpt-5.5","score":98.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"minimax-m2.5","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-sonnet-4.6","score":57.2,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"minimax-m2.7","score":52.7,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"claude-sonnet-4.6","score":51,"metric":"percent"},{"benchmark":"multi-swe-bench","model":"gpt-5.4","score":49,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"minimax-m2.7","score":66.6,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"minimax-m2.5","score":51.5,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"gemini-3.1-pro","score":66.6,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"claude-sonnet-4.6","score":72.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"claude-opus-4.6","score":75.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"gpt-5.4","score":71.2,"metric":"percent"},{"benchmark":"toolathlon","model":"minimax-m2.5","score":38.3,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-sonnet-4.6","score":44.8,"metric":"percent"},{"benchmark":"mm-clawbench","model":"minimax-m2.7","score":62.7,"metric":"percent"},{"benchmark":"mm-clawbench","model":"minimax-m2.5","score":57.6,"metric":"percent"},{"benchmark":"mm-clawbench","model":"gemini-3.1-pro","score":61.8,"metric":"percent"},{"benchmark":"mm-clawbench","model":"claude-sonnet-4.6","score":64.2,"metric":"percent"},{"benchmark":"mm-clawbench","model":"claude-opus-4.6","score":75.4,"metric":"percent"},{"benchmark":"mm-clawbench","model":"gpt-5.4","score":73.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"minimax-m2.7","score":56.22,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"minimax-m2.7","score":76.5,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"minimax-m2.7","score":1495,"metric":"elo"},{"benchmark":"browsecomp-agent-swarm","model":"kimi-k2.6-thinking","score":86.3,"metric":"percent"},{"benchmark":"browsecomp-agent-swarm","model":"kimi-k2.5-thinking","score":78.4,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"kimi-k2.6-thinking","score":92.5,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"gpt-5.4","score":78.6,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"claude-opus-4.6","score":91.3,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"gemini-3.1-pro","score":81.9,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"kimi-k2.5-thinking","score":89,"metric":"percent"},{"benchmark":"deepsearchqa","model":"kimi-k2.6-thinking","score":83,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-5.4","score":63.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-4.6","score":80.6,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gemini-3.1-pro","score":60.2,"metric":"percent"},{"benchmark":"wide-search","model":"kimi-k2.6-thinking","score":80.8,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5.4","score":62.5,"metric":"percent"},{"benchmark":"mcpmark","model":"gemini-3.1-pro","score":55.9,"metric":"percent"},{"benchmark":"mcpmark","model":"kimi-k2.5-thinking","score":29.5,"metric":"percent"},{"benchmark":"claweval-pass3","model":"kimi-k2.6-thinking","score":62.3,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gpt-5.4","score":60.3,"metric":"percent"},{"benchmark":"claweval-pass3","model":"claude-opus-4.6","score":70.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"kimi-k2.5-thinking","score":52.3,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"kimi-k2.6-thinking","score":80.9,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"gpt-5.4","score":78.4,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"claude-opus-4.6","score":82.4,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"gemini-3.1-pro","score":82.9,"metric":"percent"},{"benchmark":"claweval-pass-at-3","model":"kimi-k2.5-thinking","score":75.4,"metric":"percent"},{"benchmark":"apex-agents","model":"kimi-k2.6-thinking","score":27.9,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.4","score":33.3,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-4.6","score":33,"metric":"percent"},{"benchmark":"apex-agents","model":"gemini-3.1-pro","score":32,"metric":"percent"},{"benchmark":"apex-agents","model":"kimi-k2.5-thinking","score":11.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"kimi-k2.5-thinking","score":63.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.4","score":65.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"kimi-k2.5-thinking","score":50.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemini-3.1-pro","score":76.9,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.4","score":56.6,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3.1-pro","score":58.9,"metric":"percent"},{"benchmark":"ojbench","model":"kimi-k2.6-thinking","score":60.6,"metric":"percent"},{"benchmark":"ojbench","model":"claude-opus-4.6","score":60.3,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-3.1-pro","score":70.7,"metric":"percent"},{"benchmark":"ojbench","model":"kimi-k2.5-thinking","score":54.7,"metric":"percent"},{"benchmark":"hle","model":"kimi-k2.6-thinking","score":34.7,"metric":"avg@3"},{"benchmark":"aime-2026-i","model":"kimi-k2.6-thinking","score":96.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.4","score":99.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.6","score":96.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3.1-pro","score":98.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.5-thinking","score":95.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"kimi-k2.5-thinking","score":87.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3.1-pro","score":91,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-pro","score":83,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"kimi-k2.6-thinking","score":80.1,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"gemini-3.1-pro","score":85.3,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"kimi-k2.5-thinking","score":77.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"kimi-k2.6-thinking","score":80.4,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"kimi-k2.6-thinking","score":86.7,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-5.4","score":90,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gemini-3.1-pro","score":89.9,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"kimi-k2.5-thinking","score":78.7,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-k2.6-thinking","score":87.4,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.4","score":92,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.6","score":71.2,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.1-pro","score":89.8,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"kimi-k2.6-thinking","score":93.2,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"gpt-5.4","score":96.1,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"claude-opus-4.6","score":84.6,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"gemini-3.1-pro","score":95.7,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"kimi-k2.5-thinking","score":85,"metric":"percent"},{"benchmark":"babyvision","model":"kimi-k2.6-thinking","score":39.8,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.4","score":49.7,"metric":"percent"},{"benchmark":"babyvision","model":"claude-opus-4.6","score":14.8,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3.1-pro","score":51.6,"metric":"percent"},{"benchmark":"babyvision","model":"kimi-k2.5-thinking","score":36.5,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"kimi-k2.6-thinking","score":68.5,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"gpt-5.4","score":80.2,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"claude-opus-4.6","score":38.4,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"gemini-3.1-pro","score":68.3,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"kimi-k2.5-thinking","score":40.5,"metric":"percent"},{"benchmark":"v-star-with-tools","model":"kimi-k2.6-thinking","score":96.9,"metric":"percent"},{"benchmark":"v-star-with-tools","model":"gpt-5.4","score":98.4,"metric":"percent"},{"benchmark":"v-star-with-tools","model":"claude-opus-4.6","score":86.4,"metric":"percent"},{"benchmark":"v-star-with-tools","model":"gemini-3.1-pro","score":96.9,"metric":"percent"},{"benchmark":"v-star-with-tools","model":"kimi-k2.5-thinking","score":86.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2.6-thinking","score":36.4,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"kimi-k2.6-thinking","score":50.9,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"kimi-k2.7-code","score":62,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"gpt-5.5","score":69,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"claude-opus-4.8","score":67.4,"metric":"percent"},{"benchmark":"programbench","model":"kimi-k2.6-thinking","score":48.3,"metric":"percent"},{"benchmark":"programbench","model":"kimi-k2.7-code","score":53.6,"metric":"percent"},{"benchmark":"programbench","model":"gpt-5.5","score":69.1,"metric":"percent"},{"benchmark":"programbench","model":"claude-opus-4.8","score":63.8,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"kimi-k2.6-thinking","score":26.7,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"kimi-k2.7-code","score":35.1,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"gpt-5.5","score":35.5,"metric":"percent"},{"benchmark":"kimi-claw-24-7-bench","model":"kimi-k2.6-thinking","score":42.9,"metric":"percent"},{"benchmark":"kimi-claw-24-7-bench","model":"kimi-k2.7-code","score":46.9,"metric":"percent"},{"benchmark":"kimi-claw-24-7-bench","model":"gpt-5.5","score":52.8,"metric":"percent"},{"benchmark":"kimi-claw-24-7-bench","model":"claude-opus-4.8","score":50.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k2.6-thinking","score":69.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k2.7-code","score":76,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.5","score":79.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.8","score":81.3,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"kimi-k2.6-thinking","score":72.8,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"kimi-k2.7-code","score":81.1,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"gpt-5.5","score":92.9,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"claude-opus-4.8","score":76.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.8","score":91,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.5","score":93.5,"metric":"percent"},{"benchmark":"critpt","model":"kimi-k3","score":23.4,"metric":"percent"},{"benchmark":"critpt","model":"claude-fable-5","score":28.6,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5.6-sol","score":32.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k3","score":74.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-fable-5","score":70,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.6-sol","score":73.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-opus-4.8","score":67.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.5","score":74.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.2","score":71.3,"metric":"percent"},{"benchmark":"programbench","model":"kimi-k3","score":77.8,"metric":"percent"},{"benchmark":"programbench","model":"claude-fable-5","score":76.8,"metric":"percent"},{"benchmark":"programbench","model":"gpt-5.6-sol","score":77.6,"metric":"percent"},{"benchmark":"frontierswe","model":"kimi-k3","score":81.2,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-fable-5","score":86.6,"metric":"percent"},{"benchmark":"frontierswe","model":"gpt-5.6-sol","score":71.3,"metric":"percent"},{"benchmark":"frontierswe","model":"claude-opus-4.8","score":66.7,"metric":"percent"},{"benchmark":"frontierswe","model":"gpt-5.5","score":64.9,"metric":"percent"},{"benchmark":"frontierswe","model":"glm-5.2","score":67.3,"metric":"percent"},{"benchmark":"swe-marathon","model":"kimi-k3","score":42,"metric":"percent"},{"benchmark":"swe-marathon","model":"claude-fable-5","score":35,"metric":"percent"},{"benchmark":"swe-marathon","model":"gpt-5.6-sol","score":39,"metric":"percent"},{"benchmark":"swe-marathon","model":"claude-opus-4.8","score":40,"metric":"percent"},{"benchmark":"swe-marathon","model":"gpt-5.5","score":14,"metric":"percent"},{"benchmark":"posttrainbench","model":"kimi-k3","score":36.6,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-fable-5","score":41.4,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.6-sol","score":34.6,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-4.8","score":34.1,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"kimi-k3","score":48.3,"metric":"percent"},{"benchmark":"mls-bench-lite","model":"glm-5.2","score":40.4,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k3","score":58.7,"metric":"percent"},{"benchmark":"scicode","model":"claude-fable-5","score":60.2,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.6-sol","score":56.1,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.8","score":53.5,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.5","score":56.1,"metric":"percent"},{"benchmark":"scicode","model":"glm-5.2","score":50.5,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"kimi-k3","score":72.9,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"claude-fable-5","score":76.9,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"gpt-5.6-sol","score":64.8,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"claude-opus-4.8","score":71.7,"metric":"percent"},{"benchmark":"kimi-code-bench-v2","model":"glm-5.2","score":64.2,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k3","score":91.2,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-fable-5","score":88,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"kimi-k3","score":95,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"claude-fable-5","score":94.2,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"claude-opus-4.8","score":93.1,"metric":"percent"},{"benchmark":"researchrubrics","model":"kimi-k3","score":76.2,"metric":"percent"},{"benchmark":"researchrubrics","model":"gpt-5.6-sol","score":73.8,"metric":"percent"},{"benchmark":"researchrubrics","model":"claude-opus-4.8","score":73.5,"metric":"percent"},{"benchmark":"researchrubrics","model":"gpt-5.5","score":64,"metric":"percent"},{"benchmark":"researchrubrics","model":"glm-5.2","score":71.1,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"kimi-k3","score":1686,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.5","score":1491,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.2","score":1510,"metric":"elo"},{"benchmark":"mcpmark-verified","model":"kimi-k3","score":94.5,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"claude-fable-5","score":87.4,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"gpt-5.6-sol","score":92.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k3","score":84.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-fable-5","score":84.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.6-sol","score":83.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-4.8","score":83.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.5","score":82.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5.2","score":82.6,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.5","score":22.7,"metric":"percent"},{"benchmark":"jobbench","model":"claude-fable-5","score":57.4,"metric":"percent"},{"benchmark":"jobbench","model":"glm-5.2","score":43.4,"metric":"percent"},{"benchmark":"aa-briefcase","model":"kimi-k3","score":1548,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-fable-5","score":1583,"metric":"elo"},{"benchmark":"aa-briefcase","model":"gpt-5.6-sol","score":1495,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-opus-4.8","score":1354,"metric":"elo"},{"benchmark":"aa-briefcase","model":"gpt-5.5","score":1158,"metric":"elo"},{"benchmark":"aa-briefcase","model":"glm-5.2","score":1260,"metric":"elo"},{"benchmark":"agents-last-exam","model":"kimi-k3","score":28.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-fable-5","score":25.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol","score":29.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.5","score":26.6,"metric":"percent"},{"benchmark":"apex-agents","model":"kimi-k3","score":41,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-fable-5","score":43.3,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.6-sol","score":39.9,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-4.8","score":39.4,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.5","score":38.5,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-5.2","score":35.6,"metric":"percent"},{"benchmark":"officeqa-pro","model":"kimi-k3","score":63.3,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-fable-5","score":69.9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.6-sol","score":63.2,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-opus-4.8","score":63.9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.5","score":60.9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"glm-5.2","score":41.4,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"kimi-k3","score":34.8,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"claude-fable-5","score":34.7,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"gpt-5.6-sol","score":32.4,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"claude-opus-4.8","score":31.6,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"gpt-5.5","score":29.1,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"glm-5.2","score":28.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.6-sol","score":83,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.5","score":79,"metric":"percent"},{"benchmark":"osworld-2.0","model":"kimi-k3","score":58.3,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-5.5","score":49.5,"metric":"percent"},{"benchmark":"saas-bench","model":"kimi-k3","score":60.1,"metric":"percent"},{"benchmark":"saas-bench","model":"gpt-5.6-sol","score":61.4,"metric":"percent"},{"benchmark":"saas-bench","model":"claude-opus-4.8","score":56.1,"metric":"percent"},{"benchmark":"saas-bench","model":"gpt-5.5","score":43.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"kimi-k3","score":33.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-fable-5","score":26.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.6-sol","score":33,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-opus-4.8","score":27.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.5","score":31.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.2","score":26.8,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"kimi-k3","score":94.6,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"claude-fable-5","score":93.6,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"gpt-5.6-sol","score":87.2,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"claude-opus-4.8","score":91.1,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"gpt-5.5","score":86.3,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"glm-5.2","score":91,"metric":"percent"},{"benchmark":"corpfin","model":"kimi-k3","score":71.6,"metric":"percent"},{"benchmark":"corpfin","model":"claude-fable-5","score":71.8,"metric":"percent"},{"benchmark":"corpfin","model":"gpt-5.6-sol","score":64.4,"metric":"percent"},{"benchmark":"corpfin","model":"claude-opus-4.8","score":66.7,"metric":"percent"},{"benchmark":"corpfin","model":"gpt-5.5","score":68.4,"metric":"percent"},{"benchmark":"corpfin","model":"glm-5.2","score":66.1,"metric":"percent"},{"benchmark":"financeagent-v2","model":"kimi-k3","score":54.4,"metric":"percent"},{"benchmark":"financeagent-v2","model":"claude-fable-5","score":56.3,"metric":"percent"},{"benchmark":"financeagent-v2","model":"glm-5.2","score":49.7,"metric":"percent"},{"benchmark":"legal-research-bench","model":"kimi-k3","score":44.2,"metric":"percent"},{"benchmark":"legal-research-bench","model":"claude-fable-5","score":49.5,"metric":"percent"},{"benchmark":"legal-research-bench","model":"gpt-5.6-sol","score":48.1,"metric":"percent"},{"benchmark":"legal-research-bench","model":"claude-opus-4.8","score":43.8,"metric":"percent"},{"benchmark":"legal-research-bench","model":"gpt-5.5","score":40.4,"metric":"percent"},{"benchmark":"legal-research-bench","model":"glm-5.2","score":31.3,"metric":"percent"},{"benchmark":"worldvqa","model":"kimi-k3","score":51,"metric":"percent"},{"benchmark":"worldvqa","model":"claude-fable-5","score":56.7,"metric":"percent"},{"benchmark":"worldvqa","model":"gpt-5.6-sol","score":41.8,"metric":"percent"},{"benchmark":"worldvqa","model":"claude-opus-4.8","score":39.1,"metric":"percent"},{"benchmark":"worldvqa","model":"gpt-5.5","score":38.5,"metric":"percent"},{"benchmark":"omnidocbench","model":"kimi-k3","score":91.1,"metric":"percent"},{"benchmark":"omnidocbench","model":"claude-fable-5","score":89.8,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-5.6-sol","score":85.8,"metric":"percent"},{"benchmark":"omnidocbench","model":"claude-opus-4.8","score":87.9,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-5.5","score":89.4,"metric":"percent"},{"benchmark":"perceptionbench","model":"kimi-k3","score":58.5,"metric":"percent"},{"benchmark":"perceptionbench","model":"claude-fable-5","score":57.2,"metric":"percent"},{"benchmark":"perceptionbench","model":"gpt-5.6-sol","score":59.7,"metric":"percent"},{"benchmark":"perceptionbench","model":"claude-opus-4.8","score":47.2,"metric":"percent"},{"benchmark":"perceptionbench","model":"gpt-5.5","score":55.8,"metric":"percent"},{"benchmark":"videomme-sub","model":"kimi-k3","score":90,"metric":"percent"},{"benchmark":"videomme-sub","model":"claude-opus-4.8","score":86,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5.5","score":89.3,"metric":"percent"},{"benchmark":"mmvu","model":"kimi-k3","score":82.1,"metric":"percent"},{"benchmark":"mmvu","model":"claude-opus-4.8","score":79.2,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5.5","score":81.7,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"claude-fable-5","score":90.5,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"claude-opus-4.8","score":81.2,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"gpt-5.5","score":83.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k3","score":81.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.8","score":78.9,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"kimi-k3","score":83.4,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"claude-fable-5","score":86.5,"metric":"percent"},{"benchmark":"mmmu-pro-with-tools","model":"claude-opus-4.8","score":82.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"kimi-k3","score":84.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-fable-5","score":88.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.6-sol","score":84.6,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"kimi-k3","score":91.3,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-fable-5","score":93.5,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-5.6-sol","score":89.1,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-5.5","score":89,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-k3","score":94.3,"metric":"percent"},{"benchmark":"mathvision","model":"claude-fable-5","score":94.8,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.6-sol","score":95.8,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.8","score":86.7,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.5","score":92.2,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"kimi-k3","score":97.8,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"claude-fable-5","score":98.6,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"gpt-5.6-sol","score":97.8,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"claude-opus-4.8","score":97.1,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"gpt-5.5","score":96.8,"metric":"percent"},{"benchmark":"zerobench","model":"kimi-k3","score":23,"metric":"percent"},{"benchmark":"zerobench","model":"claude-fable-5","score":23,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5.6-sol","score":17,"metric":"percent"},{"benchmark":"zerobench","model":"claude-opus-4.8","score":17,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5.5","score":22,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"gpt-5.5","score":41,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-fable-5","score":66.1,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"gpt-5.5","score":64.31,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"grok-4.5","score":62,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-opus-4.8","score":55.75,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-opus-4.7","score":40.12,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.5","score":53,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.2","score":44,"metric":"percent"},{"benchmark":"swe-marathon","model":"grok-4.5","score":29,"metric":"percent"},{"benchmark":"swe-marathon","model":"claude-fable-5","score":24,"metric":"percent"},{"benchmark":"swe-marathon","model":"claude-opus-4.7","score":16,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.7","score":78.9,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-fable-5","score":80.4,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"grok-4.6","score":1753,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1728,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5","score":1741,"metric":"elo"},{"benchmark":"cursorbench-3.2","model":"grok-4.6","score":69.9,"metric":"percent"},{"benchmark":"cursorbench-3.2","model":"grok-4.5","score":66.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.6","score":65.9,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"grok-4.6","score":61.3,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"grok-4.5","score":56.6,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-fable-5","score":63.6,"metric":"percent"},{"benchmark":"apex-agents","model":"grok-4.6","score":57.5,"metric":"percent"},{"benchmark":"apex-agents","model":"grok-4.5","score":47.1,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.6-sol","score":56.7,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-fable-5","score":59.2,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"grok-4.6","score":26,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"grok-4.5","score":15.7,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-fable-5","score":34.1,"metric":"percent"},{"benchmark":"apex-swe","model":"grok-4.6","score":56.4,"metric":"percent"},{"benchmark":"apex-swe","model":"grok-4.5","score":53.6,"metric":"percent"},{"benchmark":"apex-swe","model":"claude-fable-5","score":58.8,"metric":"percent"},{"benchmark":"aa-briefcase","model":"grok-4.6","score":1577,"metric":"elo"},{"benchmark":"aa-briefcase","model":"grok-4.5","score":1313,"metric":"elo"},{"benchmark":"legal-agent-benchmark-held-out","model":"grok-4.6","score":15.8,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"grok-4.5","score":12.9,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"claude-fable-5","score":11.3,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"grok-4.7","score":46.3,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"grok-4.6","score":40.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.7","score":71,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.6","score":65.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-fable-5.1","score":70,"metric":"percent"},{"benchmark":"eebench","model":"grok-4.7","score":64,"metric":"percent"},{"benchmark":"eebench","model":"grok-4.6","score":53,"metric":"percent"},{"benchmark":"eebench","model":"gpt-5.6-sol","score":39.4,"metric":"percent"},{"benchmark":"eebench","model":"claude-fable-5.1","score":56.4,"metric":"percent"},{"benchmark":"aa-briefcase","model":"grok-4.7","score":1657,"metric":"elo"},{"benchmark":"aa-briefcase","model":"grok-4.6","score":1546,"metric":"elo"},{"benchmark":"aa-briefcase","model":"gpt-5.6-sol","score":1487,"metric":"elo"},{"benchmark":"terminal-bench-4.0","model":"grok-4.7","score":37.6,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"grok-4.6","score":20.3,"metric":"percent"},{"benchmark":"legal-agent-benchmark-held-out","model":"grok-4.7","score":19.6,"metric":"percent"},{"benchmark":"healthbench-professional","model":"grok-4.7","score":56.7,"metric":"percent"},{"benchmark":"healthbench-professional","model":"grok-4.6","score":48.5,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"grok-4.7","score":1695,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"grok-4.6","score":1605,"metric":"elo"},{"benchmark":"aime-2025","model":"ministral-3-14b-reasoning","score":85,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-14b-thinking","score":73.7,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-3-r-8b","score":78.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-8b-thinking","score":79.8,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-3-3b-reasoning","score":72.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-4b-thinking","score":69.7,"metric":"percent"},{"benchmark":"aime-2024","model":"ministral-3-14b-reasoning","score":89.8,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-14b-thinking","score":83.7,"metric":"percent"},{"benchmark":"aime-2024","model":"ministral-3-r-8b","score":86,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-vl-8b-thinking","score":86,"metric":"percent"},{"benchmark":"aime-2024","model":"ministral-3-3b-reasoning","score":77.5,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-vl-4b-thinking","score":72.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-14b-reasoning","score":71.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-14b-thinking","score":66.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-r-8b","score":66.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-vl-8b-thinking","score":67.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-3b-reasoning","score":53.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-vl-4b-thinking","score":60.1,"metric":"percent"},{"benchmark":"livecodebench","model":"ministral-3-14b-reasoning","score":64.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-14b-thinking","score":59.3,"metric":"percent"},{"benchmark":"livecodebench","model":"ministral-3-r-8b","score":61.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-8b-thinking","score":58,"metric":"percent"},{"benchmark":"livecodebench","model":"ministral-3-3b-reasoning","score":54.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-4b-thinking","score":51.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"ministral-3-14b-instruct","score":55.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-14b","score":42.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemma-3-12b-it","score":43.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"ministral-3-8b-instruct","score":50.9,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-vl-8b-instruct","score":52.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"ministral-3-3b-instruct","score":30.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-vl-4b-instruct","score":43.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-vl-2b-instruct","score":16.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemma-3-4b-it","score":31.8,"metric":"percent"},{"benchmark":"wildbench-v2","model":"ministral-3-14b-instruct","score":68.5,"metric":"percent"},{"benchmark":"wildbench-v2","model":"qwen3-14b","score":65.1,"metric":"percent"},{"benchmark":"wildbench-v2","model":"gemma-3-12b-it","score":63.2,"metric":"percent"},{"benchmark":"wildbench-v2","model":"ministral-3-8b-instruct","score":66.8,"metric":"percent"},{"benchmark":"wildbench-v2","model":"qwen3-vl-8b-instruct","score":66.3,"metric":"percent"},{"benchmark":"wildbench-v2","model":"ministral-3-3b-instruct","score":56.8,"metric":"percent"},{"benchmark":"wildbench-v2","model":"qwen3-vl-4b-instruct","score":56.8,"metric":"percent"},{"benchmark":"wildbench-v2","model":"qwen3-vl-2b-instruct","score":42.2,"metric":"percent"},{"benchmark":"wildbench-v2","model":"gemma-3-4b-it","score":49.1,"metric":"percent"},{"benchmark":"math","model":"ministral-3-14b-instruct","score":90.4,"metric":"percent"},{"benchmark":"math","model":"qwen3-14b","score":87,"metric":"percent"},{"benchmark":"math","model":"gemma-3-12b-it","score":85.4,"metric":"percent"},{"benchmark":"math","model":"ministral-3-8b-instruct","score":87.6,"metric":"percent"},{"benchmark":"math","model":"qwen3-vl-8b-instruct","score":94.6,"metric":"percent"},{"benchmark":"math","model":"ministral-3-3b-instruct","score":83,"metric":"percent"},{"benchmark":"math","model":"qwen3-vl-4b-instruct","score":90,"metric":"percent"},{"benchmark":"math","model":"qwen3-vl-2b-instruct","score":78.6,"metric":"percent"},{"benchmark":"math","model":"gemma-3-4b-it","score":75.9,"metric":"percent"},{"benchmark":"mm-mt-bench","model":"ministral-3-14b-instruct","score":8.49,"metric":"score"},{"benchmark":"mm-mt-bench","model":"gemma-3-12b-it","score":6.7,"metric":"score"},{"benchmark":"mm-mt-bench","model":"ministral-3-8b-instruct","score":8.08,"metric":"score"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-8b-instruct","score":8,"metric":"score"},{"benchmark":"mm-mt-bench","model":"ministral-3-3b-instruct","score":7.83,"metric":"score"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-4b-instruct","score":8.01,"metric":"score"},{"benchmark":"mm-mt-bench","model":"qwen3-vl-2b-instruct","score":6.36,"metric":"score"},{"benchmark":"mm-mt-bench","model":"gemma-3-4b-it","score":5.23,"metric":"score"},{"benchmark":"agieval","model":"ministral-3-14b-base","score":64.8,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-14b-base","score":66.1,"metric":"percent"},{"benchmark":"agieval","model":"gemma-3-12b-base","score":58.7,"metric":"percent"},{"benchmark":"agieval","model":"ministral-3-8b-base","score":59.1,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-8b-base","score":59.6,"metric":"percent"},{"benchmark":"agieval","model":"ministral-3-3b-base","score":51.1,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-4b-base","score":57,"metric":"percent"},{"benchmark":"agieval","model":"gemma-3-4b-base","score":43,"metric":"percent"},{"benchmark":"mmlu-redux","model":"ministral-3-14b-base","score":82,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-14b-base","score":83.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-3-12b-base","score":76.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"ministral-3-8b-base","score":79.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-8b-base","score":79.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"ministral-3-3b-base","score":73.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-4b-base","score":75.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-3-4b-base","score":62.6,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-3-14b-base","score":79.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-14b-base","score":80.4,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-12b-base","score":74.5,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-3-8b-base","score":76.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b-base","score":76,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-3-3b-base","score":70.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-4b-base","score":71.3,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-4b-base","score":58.9,"metric":"percent"},{"benchmark":"triviaqa","model":"ministral-3-14b-base","score":74.9,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3-14b-base","score":70.3,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-12b-base","score":78.8,"metric":"percent"},{"benchmark":"triviaqa","model":"ministral-3-8b-base","score":68.1,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3-8b-base","score":63.9,"metric":"percent"},{"benchmark":"triviaqa","model":"ministral-3-3b-base","score":59.2,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3-4b-base","score":53,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-3-4b-base","score":64,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"devstral-2","score":72.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"devstral-small-2","score":68,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-plus","score":69.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.1-codex","score":73.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"devstral-2","score":61.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"devstral-small-2","score":55.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3-coder-plus","score":54.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"devstral-2","score":32.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"devstral-small-2","score":22.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-4.6","score":24.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-coder-plus","score":25.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1-codex","score":52.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1-codex-max","score":60.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-120b","score":62.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"grok-code-fast-1","score":70.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-small-4","score":59.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-small-4-thinking","score":71.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-small-3.2-24b-instruct","score":50,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-medium-3.1","score":65.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-large-3","score":64.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-4","score":73.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-4-thinking","score":78,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-3.2-24b-instruct","score":69,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-medium-3.1","score":76.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-large-3","score":80.9,"metric":"percent"},{"benchmark":"ifbench","model":"mistral-small-4","score":35.7,"metric":"percent"},{"benchmark":"ifbench","model":"mistral-small-4-thinking","score":48,"metric":"percent"},{"benchmark":"ifbench","model":"mistral-small-3.2-24b-instruct","score":34,"metric":"percent"},{"benchmark":"ifbench","model":"mistral-medium-3.1","score":40.8,"metric":"percent"},{"benchmark":"ifbench","model":"mistral-large-3","score":37.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"mistral-small-4","score":55.8,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"mistral-small-4-thinking","score":58.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"mistral-medium-3.1","score":67.3,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"mistral-large-3","score":66.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mistral-small-4","score":46.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mistral-small-4-thinking","score":60,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mistral-small-3.2-24b-instruct","score":49.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mistral-medium-3.1","score":43.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mistral-large-3","score":54,"metric":"percent"},{"benchmark":"aa-lcr","model":"mistral-small-4-thinking","score":71.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"magistral-medium-1.2","score":73,"metric":"percent"},{"benchmark":"aa-lcr","model":"magistral-small-1.2","score":27,"metric":"percent"},{"benchmark":"aime-2025","model":"mistral-small-4-thinking","score":83.8,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-medium-1.2","score":84.4,"metric":"percent"},{"benchmark":"aime-2025","model":"magistral-small-1.2","score":80.2,"metric":"percent"},{"benchmark":"collie","model":"mistral-small-4-thinking","score":62.9,"metric":"percent"},{"benchmark":"collie","model":"magistral-medium-1.2","score":61.3,"metric":"percent"},{"benchmark":"collie","model":"magistral-small-1.2","score":60.3,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-small-4-thinking","score":63.6,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-medium-1.2","score":66.1,"metric":"percent"},{"benchmark":"livecodebench","model":"magistral-small-1.2","score":60.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"mistral-small-4","score":44,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-120b","score":51,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-4.5-haiku","score":80,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-next-80b-a3b-instruct","score":62,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-next-80b-a3b-thinking","score":75,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-small-4","score":32,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":63,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-4.5-haiku","score":49,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b-instruct","score":40,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b-thinking","score":66,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-122b-a10b","score":74,"metric":"percent"},{"benchmark":"aime-2025","model":"mistral-small-4","score":36,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":89,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-4.5-haiku","score":83,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-next-80b-a3b-instruct","score":65,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-next-80b-a3b-thinking","score":88,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-122b-a10b","score":93,"metric":"percent"},{"benchmark":"aime-2025","model":"mistral-medium-3.5","score":86.3,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4.5","score":86.7,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4.6","score":86.9,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2.5-thinking","score":84.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-397b-a17b","score":83.1,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-5","score":87.1,"metric":"percent"},{"benchmark":"ifbench","model":"mistral-medium-3.5","score":69,"metric":"percent"},{"benchmark":"ifbench","model":"claude-sonnet-4.5","score":55.4,"metric":"percent"},{"benchmark":"ifbench","model":"claude-sonnet-4.6","score":57.1,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.5-thinking","score":70.1,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5","score":67,"metric":"percent"},{"benchmark":"collie","model":"mistral-medium-3.5","score":95.8,"metric":"percent"},{"benchmark":"collie","model":"claude-sonnet-4.5","score":90.5,"metric":"percent"},{"benchmark":"collie","model":"claude-sonnet-4.6","score":67.7,"metric":"percent"},{"benchmark":"collie","model":"kimi-k2.5-thinking","score":87.8,"metric":"percent"},{"benchmark":"collie","model":"qwen3.5-397b-a17b","score":88.9,"metric":"percent"},{"benchmark":"collie","model":"glm-5","score":86.4,"metric":"percent"},{"benchmark":"beyondaime","model":"mistral-medium-3.5","score":66.9,"metric":"percent"},{"benchmark":"beyondaime","model":"claude-sonnet-4.5","score":59.8,"metric":"percent"},{"benchmark":"beyondaime","model":"claude-sonnet-4.6","score":47.3,"metric":"percent"},{"benchmark":"beyondaime","model":"kimi-k2.5-thinking","score":60.3,"metric":"percent"},{"benchmark":"beyondaime","model":"qwen3.5-397b-a17b","score":72.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mistral-medium-3.5","score":77.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5.1","score":80.2,"metric":"percent"},{"benchmark":"tau3-telecom","model":"mistral-medium-3.5","score":91.4,"metric":"percent"},{"benchmark":"tau3-telecom","model":"claude-sonnet-4.5","score":84.9,"metric":"percent"},{"benchmark":"tau3-telecom","model":"claude-sonnet-4.6","score":70.4,"metric":"percent"},{"benchmark":"tau3-telecom","model":"kimi-k2.5-thinking","score":86.8,"metric":"percent"},{"benchmark":"tau3-telecom","model":"glm-5.1","score":98.7,"metric":"percent"},{"benchmark":"tau3-telecom","model":"qwen3.5-397b-a17b","score":97.8,"metric":"percent"},{"benchmark":"tau3-airline","model":"mistral-medium-3.5","score":72,"metric":"percent"},{"benchmark":"tau3-airline","model":"claude-sonnet-4.5","score":72,"metric":"percent"},{"benchmark":"tau3-airline","model":"claude-sonnet-4.6","score":83,"metric":"percent"},{"benchmark":"tau3-airline","model":"kimi-k2.5-thinking","score":76.5,"metric":"percent"},{"benchmark":"tau3-airline","model":"glm-5.1","score":79.5,"metric":"percent"},{"benchmark":"tau3-airline","model":"qwen3.5-397b-a17b","score":81.5,"metric":"percent"},{"benchmark":"tau3-retail","model":"mistral-medium-3.5","score":76.1,"metric":"percent"},{"benchmark":"tau3-retail","model":"claude-sonnet-4.5","score":72.4,"metric":"percent"},{"benchmark":"tau3-retail","model":"claude-sonnet-4.6","score":75.9,"metric":"percent"},{"benchmark":"tau3-retail","model":"kimi-k2.5-thinking","score":72.8,"metric":"percent"},{"benchmark":"tau3-retail","model":"glm-5.1","score":76.3,"metric":"percent"},{"benchmark":"tau3-retail","model":"qwen3.5-397b-a17b","score":84.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"mistral-medium-3.5","score":13.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-sonnet-4.5","score":22.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-sonnet-4.6","score":28.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"kimi-k2.5-thinking","score":14.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.1","score":16.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-397b-a17b","score":9.8,"metric":"percent"},{"benchmark":"browsecomp","model":"mistral-medium-3.5","score":48.6,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2.5-thinking","score":74.9,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-397b-a17b","score":78.6,"metric":"percent"},{"benchmark":"tau3-telecom","model":"magistral-medium-1.2","score":60.5,"metric":"percent"},{"benchmark":"tau3-telecom","model":"mistral-small-4","score":47.1,"metric":"percent"},{"benchmark":"tau3-telecom","model":"mistral-medium-3.1","score":46.9,"metric":"percent"},{"benchmark":"tau3-airline","model":"magistral-medium-1.2","score":53.5,"metric":"percent"},{"benchmark":"tau3-airline","model":"mistral-small-4","score":38.5,"metric":"percent"},{"benchmark":"tau3-airline","model":"mistral-medium-3.1","score":41.5,"metric":"percent"},{"benchmark":"tau3-retail","model":"magistral-medium-1.2","score":70.2,"metric":"percent"},{"benchmark":"tau3-retail","model":"mistral-small-4","score":67.8,"metric":"percent"},{"benchmark":"tau3-retail","model":"mistral-medium-3.1","score":64.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"magistral-medium-1.2","score":7.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"mistral-small-4","score":7,"metric":"percent"},{"benchmark":"tau3-banking","model":"mistral-medium-3.1","score":5.7,"metric":"percent"},{"benchmark":"browsecomp","model":"magistral-medium-1.2","score":10,"metric":"percent"},{"benchmark":"browsecomp","model":"mistral-small-4","score":21.3,"metric":"percent"},{"benchmark":"browsecomp","model":"mistral-medium-3.1","score":7.8,"metric":"percent"},{"benchmark":"flteval","model":"leanstral","score":21.9,"metric":"percent"},{"benchmark":"flteval","model":"claude-4.5-haiku","score":23,"metric":"percent"},{"benchmark":"flteval","model":"claude-sonnet-4.6","score":23.7,"metric":"percent"},{"benchmark":"flteval","model":"claude-opus-4.6","score":39.6,"metric":"percent"},{"benchmark":"flteval","model":"leanstral-1.5","score":28.9,"metric":"percent"},{"benchmark":"minif2f-test","model":"leanstral-1.5","score":100,"metric":"percent"},{"benchmark":"putnambench","model":"leanstral-1.5","score":87.35,"metric":"percent"},{"benchmark":"fate-h","model":"leanstral-1.5","score":87,"metric":"percent"},{"benchmark":"fate-x","model":"leanstral-1.5","score":34,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mistral-ocr-4","score":85.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"chandra-ocr-2","score":83,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mineru2.5-pro","score":82,"metric":"percent"},{"benchmark":"olmocr-bench","model":"glm-ocr","score":79,"metric":"percent"},{"benchmark":"olmocr-bench","model":"deepseek-ocr-2","score":77,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gemini-3.1-pro","score":72,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gpt-5.5","score":71,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b","score":83.73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b","score":81,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-super-120b-a12b","score":90.21,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-122b-a10b","score":90.36,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":92.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"nemotron-3-super-120b-a12b","score":93.67,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-3-super-120b-a12b","score":79.23,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-122b-a10b","score":86.6,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-oss-120b","score":80.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nemotron-3-super-120b-a12b","score":81.19,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3.5-122b-a10b","score":78.93,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-oss-120b","score":88,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-super-120b-a12b","score":42.05,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-122b-a10b","score":42,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-120b","score":39,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-super-120b-a12b","score":18.26,"metric":"percent"},{"benchmark":"hle-with-tools","model":"nemotron-3-super-120b-a12b","score":22.82,"metric":"avg@3"},{"benchmark":"terminal-bench-hard","model":"nemotron-3-super-120b-a12b","score":25.78,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"qwen3.5-122b-a10b","score":26.8,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-oss-120b","score":24,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"nemotron-3-super-120b-a12b","score":31,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-122b-a10b","score":37.5,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"nemotron-3-super-120b-a12b","score":60.47,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"qwen3.5-122b-a10b","score":66.4,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"gpt-oss-120b","score":41.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3-super-120b-a12b","score":45.78,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-oss-120b","score":30.8,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3-super-120b-a12b","score":56.25,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3.5-122b-a10b","score":66,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-oss-120b","score":49.2,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3-super-120b-a12b","score":62.83,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.5-122b-a10b","score":62.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-oss-120b","score":67.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-super-120b-a12b","score":64.36,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-122b-a10b","score":95,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-super-120b-a12b","score":31.28,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-oss-120b","score":33.89,"metric":"percent"},{"benchmark":"bird-sql","model":"nemotron-3-super-120b-a12b","score":41.8,"metric":"percent"},{"benchmark":"bird-sql","model":"gpt-oss-120b","score":38.25,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-super-120b-a12b","score":72.56,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-122b-a10b","score":73.77,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-120b","score":68.32,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"nemotron-3-super-120b-a12b","score":55.23,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"qwen3.5-122b-a10b","score":61.5,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"gpt-oss-120b","score":58.29,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"nemotron-3-super-120b-a12b","score":73.88,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3.5-122b-a10b","score":75.15,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-oss-120b","score":90.26,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-super-120b-a12b","score":58.31,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-3-super-120b-a12b","score":96.3,"metric":"percent"},{"benchmark":"ruler-256k","model":"qwen3.5-122b-a10b","score":96.74,"metric":"percent"},{"benchmark":"ruler-256k","model":"gpt-oss-120b","score":52.3,"metric":"percent"},{"benchmark":"ruler-512k","model":"nemotron-3-super-120b-a12b","score":95.67,"metric":"percent"},{"benchmark":"ruler-512k","model":"qwen3.5-122b-a10b","score":95.95,"metric":"percent"},{"benchmark":"ruler-512k","model":"gpt-oss-120b","score":46.7,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3-super-120b-a12b","score":91.75,"metric":"percent"},{"benchmark":"ruler-1m","model":"qwen3.5-122b-a10b","score":91.33,"metric":"percent"},{"benchmark":"ruler-1m","model":"gpt-oss-120b","score":22.3,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nemotron-3-super-120b-a12b","score":79.36,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-122b-a10b","score":85.06,"metric":"percent"},{"benchmark":"mmlu-prox","model":"gpt-oss-120b","score":76.59,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nemotron-3-super-120b-a12b","score":86.67,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-122b-a10b","score":87.84,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gpt-oss-120b","score":88.89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-labs-3-puzzle-75b-a9b","score":82.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b","score":83.8,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-labs-3-puzzle-75b-a9b","score":89.7,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-super-120b-a12b","score":92.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"nemotron-labs-3-puzzle-75b-a9b","score":93.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"nemotron-3-super-120b-a12b","score":94.2,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-labs-3-puzzle-75b-a9b","score":78.6,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-3-super-120b-a12b","score":80.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nemotron-labs-3-puzzle-75b-a9b","score":81.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nemotron-3-super-120b-a12b","score":82.1,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-labs-3-puzzle-75b-a9b","score":40.6,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-super-120b-a12b","score":42.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-labs-3-puzzle-75b-a9b","score":16.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-super-120b-a12b","score":18.5,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"nemotron-labs-3-puzzle-75b-a9b","score":24,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"nemotron-3-super-120b-a12b","score":25.5,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"nemotron-labs-3-puzzle-75b-a9b","score":56.9,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"nemotron-3-super-120b-a12b","score":59.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-labs-3-puzzle-75b-a9b","score":55.8,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3-super-120b-a12b","score":56.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-labs-3-puzzle-75b-a9b","score":63.2,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3-super-120b-a12b","score":64.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-labs-3-puzzle-75b-a9b","score":61.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-super-120b-a12b","score":61.1,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-labs-3-puzzle-75b-a9b","score":71.9,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-super-120b-a12b","score":73.4,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"nemotron-labs-3-puzzle-75b-a9b","score":56.6,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"nemotron-3-super-120b-a12b","score":56.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"nemotron-labs-3-puzzle-75b-a9b","score":68.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"nemotron-3-super-120b-a12b","score":72.8,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-labs-3-puzzle-75b-a9b","score":56.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-super-120b-a12b","score":56.8,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-labs-3-puzzle-75b-a9b","score":95.1,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-3-super-120b-a12b","score":96.7,"metric":"percent"},{"benchmark":"ruler-512k","model":"nemotron-labs-3-puzzle-75b-a9b","score":94.2,"metric":"percent"},{"benchmark":"ruler-512k","model":"nemotron-3-super-120b-a12b","score":95.7,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-labs-3-puzzle-75b-a9b","score":92.2,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3-super-120b-a12b","score":93.9,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nemotron-labs-3-puzzle-75b-a9b","score":77.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nemotron-3-super-120b-a12b","score":79.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nemotron-labs-3-puzzle-75b-a9b","score":85.2,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nemotron-3-super-120b-a12b","score":86.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-ultra","score":56.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minimax-m2.7","score":55.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.1","score":59.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k2.6-thinking","score":67.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-397b-a17b","score":49.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro","score":49.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash","score":54.2,"metric":"percent"},{"benchmark":"gdpval","model":"nemotron-3-ultra","score":46.7,"metric":"percent"},{"benchmark":"gdpval","model":"minimax-m2.7","score":47.6,"metric":"percent"},{"benchmark":"gdpval","model":"glm-5.1","score":54.7,"metric":"percent"},{"benchmark":"gdpval","model":"kimi-k2.6-thinking","score":50.4,"metric":"percent"},{"benchmark":"gdpval","model":"qwen3.5-397b-a17b","score":34.6,"metric":"percent"},{"benchmark":"gdpval","model":"deepseek-v4-pro","score":54.6,"metric":"percent"},{"benchmark":"gdpval","model":"deepseek-v4-flash","score":50.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-ultra","score":70.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m2.7","score":75.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5.1","score":76.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.6-thinking","score":75.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-397b-a17b","score":73.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-pro","score":74.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-flash","score":73.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3-ultra","score":67.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"minimax-m2.7","score":71.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.1","score":74.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2.6-thinking","score":77.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-397b-a17b","score":70.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-pro","score":76.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-flash","score":75,"metric":"percent"},{"benchmark":"pinchbench","model":"nemotron-3-ultra","score":90,"metric":"percent"},{"benchmark":"pinchbench","model":"minimax-m2.7","score":77.6,"metric":"percent"},{"benchmark":"pinchbench","model":"glm-5.1","score":81.2,"metric":"percent"},{"benchmark":"pinchbench","model":"kimi-k2.6-thinking","score":90.2,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-397b-a17b","score":86.6,"metric":"percent"},{"benchmark":"pinchbench","model":"deepseek-v4-pro","score":88.6,"metric":"percent"},{"benchmark":"pinchbench","model":"deepseek-v4-flash","score":91.3,"metric":"percent"},{"benchmark":"tau3-airline","model":"nemotron-3-ultra","score":81.5,"metric":"percent"},{"benchmark":"tau3-airline","model":"minimax-m2.7","score":75.3,"metric":"percent"},{"benchmark":"tau3-airline","model":"glm-5.1","score":85,"metric":"percent"},{"benchmark":"tau3-airline","model":"kimi-k2.6-thinking","score":85.8,"metric":"percent"},{"benchmark":"tau3-airline","model":"qwen3.5-397b-a17b","score":76.5,"metric":"percent"},{"benchmark":"tau3-airline","model":"deepseek-v4-pro","score":80.8,"metric":"percent"},{"benchmark":"tau3-airline","model":"deepseek-v4-flash","score":80.8,"metric":"percent"},{"benchmark":"tau3-retail","model":"nemotron-3-ultra","score":86.4,"metric":"percent"},{"benchmark":"tau3-retail","model":"minimax-m2.7","score":84.9,"metric":"percent"},{"benchmark":"tau3-retail","model":"glm-5.1","score":84.1,"metric":"percent"},{"benchmark":"tau3-retail","model":"kimi-k2.6-thinking","score":82.9,"metric":"percent"},{"benchmark":"tau3-retail","model":"qwen3.5-397b-a17b","score":88.5,"metric":"percent"},{"benchmark":"tau3-retail","model":"deepseek-v4-pro","score":88.9,"metric":"percent"},{"benchmark":"tau3-retail","model":"deepseek-v4-flash","score":89.1,"metric":"percent"},{"benchmark":"tau3-telecom","model":"nemotron-3-ultra","score":92.9,"metric":"percent"},{"benchmark":"tau3-telecom","model":"minimax-m2.7","score":89.6,"metric":"percent"},{"benchmark":"tau3-telecom","model":"glm-5.1","score":96.9,"metric":"percent"},{"benchmark":"tau3-telecom","model":"kimi-k2.6-thinking","score":97.8,"metric":"percent"},{"benchmark":"tau3-telecom","model":"qwen3.5-397b-a17b","score":98,"metric":"percent"},{"benchmark":"tau3-telecom","model":"deepseek-v4-pro","score":96.3,"metric":"percent"},{"benchmark":"tau3-telecom","model":"deepseek-v4-flash","score":98.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-ultra","score":22.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"minimax-m2.7","score":14.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.1","score":12.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"kimi-k2.6-thinking","score":23.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-397b-a17b","score":20.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-pro","score":25.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-flash","score":26.7,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-ultra","score":44.4,"metric":"percent"},{"benchmark":"browsecomp","model":"minimax-m2.7","score":54.1,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5.1","score":59.4,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2.6-thinking","score":61.3,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-397b-a17b","score":40.5,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-pro","score":59.4,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-flash","score":46.9,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"nemotron-3-ultra","score":53.7,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"minimax-m2.7","score":50.5,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"glm-5.1","score":60.7,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"kimi-k2.6-thinking","score":58.8,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"qwen3.5-397b-a17b","score":59,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"deepseek-v4-pro","score":62.3,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"deepseek-v4-flash","score":60.1,"metric":"percent"},{"benchmark":"ioi-2025","model":"nemotron-3-ultra","score":570,"metric":"points"},{"benchmark":"ioi-2025","model":"glm-5.1","score":456.5,"metric":"points"},{"benchmark":"ioi-2025","model":"kimi-k2.6-thinking","score":585,"metric":"points"},{"benchmark":"ioi-2025","model":"qwen3.5-397b-a17b","score":441.3,"metric":"points"},{"benchmark":"ioi-2025","model":"deepseek-v4-pro","score":580.1,"metric":"points"},{"benchmark":"livecodebench","model":"nemotron-3-ultra","score":89,"metric":"percent"},{"benchmark":"livecodebench","model":"minimax-m2.7","score":77.2,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-5.1","score":85.7,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2.6-thinking","score":90.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-397b-a17b","score":79.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-pro","score":92.5,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash","score":90.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nemotron-3-ultra","score":88.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"minimax-m2.7","score":68.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"glm-5.1","score":86.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2.6-thinking","score":91.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-397b-a17b","score":83.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-pro","score":93,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-flash","score":91.1,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"nemotron-3-ultra","score":74.9,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"minimax-m2.7","score":28.9,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"glm-5.1","score":71.1,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"kimi-k2.6-thinking","score":77.4,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"qwen3.5-397b-a17b","score":61.4,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-pro","score":85.8,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-flash","score":82.4,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-3-ultra","score":87,"metric":"percent"},{"benchmark":"gpqa","model":"minimax-m2.7","score":86.6,"metric":"percent"},{"benchmark":"gpqa","model":"glm-5.1","score":86.1,"metric":"percent"},{"benchmark":"gpqa","model":"kimi-k2.6-thinking","score":91,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-397b-a17b","score":87.1,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v4-pro","score":87.8,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v4-flash","score":88.5,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-ultra","score":44.6,"metric":"percent"},{"benchmark":"scicode","model":"minimax-m2.7","score":38.3,"metric":"percent"},{"benchmark":"scicode","model":"glm-5.1","score":47.7,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k2.6-thinking","score":52,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-397b-a17b","score":48,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-pro","score":50.5,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-flash","score":48.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-ultra","score":26.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"minimax-m2.7","score":23.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.1","score":27.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2.6-thinking","score":34.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-397b-a17b","score":28.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-pro","score":37.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-flash","score":32.2,"metric":"percent"},{"benchmark":"hle-with-tools","model":"deepseek-v4-flash","score":45.1,"metric":"avg@3"},{"benchmark":"critpt","model":"nemotron-3-ultra","score":3.1,"metric":"percent"},{"benchmark":"critpt","model":"minimax-m2.7","score":0.6,"metric":"percent"},{"benchmark":"critpt","model":"glm-5.1","score":3.7,"metric":"percent"},{"benchmark":"critpt","model":"kimi-k2.6-thinking","score":9.1,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.5-397b-a17b","score":2.4,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v4-pro","score":14,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v4-flash","score":10.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-ultra","score":86.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-m2.7","score":81.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-5.1","score":85.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2.6-thinking","score":88.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-397b-a17b","score":88.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-pro","score":87.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-flash","score":86.4,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-3-ultra","score":24.1,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"minimax-m2.7","score":20.5,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"glm-5.1","score":31.3,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"kimi-k2.6-thinking","score":35.5,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.5-397b-a17b","score":35.9,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"deepseek-v4-pro","score":46.8,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"deepseek-v4-flash","score":39.9,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"nemotron-3-ultra","score":78.7,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"minimax-m2.7","score":74.4,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"glm-5.1","score":66.8,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"kimi-k2.6-thinking","score":67.1,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"qwen3.5-397b-a17b","score":7.4,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"deepseek-v4-pro","score":5.7,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"deepseek-v4-flash","score":2.8,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-ultra","score":81.7,"metric":"percent"},{"benchmark":"ifbench","model":"minimax-m2.7","score":74.6,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5.1","score":76.6,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.6-thinking","score":73.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-397b-a17b","score":78.2,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-pro","score":79.1,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-flash","score":82,"metric":"percent"},{"benchmark":"multichallenge","model":"nemotron-3-ultra","score":63.8,"metric":"percent"},{"benchmark":"multichallenge","model":"minimax-m2.7","score":42.5,"metric":"percent"},{"benchmark":"multichallenge","model":"glm-5.1","score":63,"metric":"percent"},{"benchmark":"multichallenge","model":"kimi-k2.6-thinking","score":63.1,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-397b-a17b","score":63.9,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v4-pro","score":64.1,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v4-flash","score":63.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-ultra","score":65.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"minimax-m2.7","score":69.8,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.1","score":66.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2.6-thinking","score":70.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-397b-a17b","score":68.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-pro","score":67.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-flash","score":62.7,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3-ultra","score":94.7,"metric":"percent"},{"benchmark":"ruler-1m","model":"qwen3.5-397b-a17b","score":90.1,"metric":"percent"},{"benchmark":"ruler-1m","model":"deepseek-v4-pro","score":94.2,"metric":"percent"},{"benchmark":"ruler-1m","model":"deepseek-v4-flash","score":87.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"nemotron-3-ultra","score":61.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-397b-a17b","score":68.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v4-pro","score":62.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v4-flash","score":57,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nemotron-3-ultra","score":83,"metric":"percent"},{"benchmark":"mmlu-prox","model":"minimax-m2.7","score":78.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"glm-5.1","score":85.8,"metric":"percent"},{"benchmark":"mmlu-prox","model":"kimi-k2.6-thinking","score":85,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-397b-a17b","score":86.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"deepseek-v4-pro","score":85.6,"metric":"percent"},{"benchmark":"mmlu-prox","model":"deepseek-v4-flash","score":84.3,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nemotron-3-ultra","score":83.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"minimax-m2.7","score":82.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"glm-5.1","score":84.4,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"kimi-k2.6-thinking","score":84.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-397b-a17b","score":86.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"deepseek-v4-pro","score":85.9,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"deepseek-v4-flash","score":85.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3.5-lightning-30b-a3b","score":81.94,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-35b-a3b","score":85.63,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-26b-a4b-it","score":85.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":78.46,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b","score":83.89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b","score":76.4,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-3.5-lightning-30b-a3b","score":17.5,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.6-35b-a3b","score":19.47,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gemma-4-26b-a4b-it","score":22.17,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":20.15,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-3-super-120b-a12b","score":26.68,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gpt-oss-20b","score":16.62,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3.5-lightning-30b-a3b","score":75.44,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-35b-a3b","score":83.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-26b-a4b-it","score":79.61,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":74.05,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-super-120b-a12b","score":78.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b","score":71.46,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3.5-lightning-30b-a3b","score":11.72,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.6-35b-a3b","score":19.56,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemma-4-26b-a4b-it","score":17.42,"metric":"percent"},{"benchmark":"hle-text-only","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":10.89,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-super-120b-a12b","score":20.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-oss-20b","score":13.76,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3.5-lightning-30b-a3b","score":32.6,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-35b-a3b","score":35.33,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-26b-a4b-it","score":40.28,"metric":"percent"},{"benchmark":"scicode","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":30.08,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-super-120b-a12b","score":35.11,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-20b","score":38.63,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3.5-lightning-30b-a3b","score":51.56,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-35b-a3b","score":70.12,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-26b-a4b-it","score":57.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":34.08,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-super-120b-a12b","score":63.08,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-20b","score":52.44,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3.5-lightning-30b-a3b","score":39.33,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.6-35b-a3b","score":63.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemma-4-26b-a4b-it","score":43.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":14.07,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3-super-120b-a12b","score":49.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-oss-20b","score":41.93,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3.5-lightning-30b-a3b","score":24.58,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":44.38,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-26b-a4b-it","score":37.22,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":8.29,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-super-120b-a12b","score":39.61,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-oss-20b","score":15.17,"metric":"percent"},{"benchmark":"pinchbench","model":"nemotron-3.5-lightning-30b-a3b","score":85.37,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.6-35b-a3b","score":88.07,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-26b-a4b-it","score":74.7,"metric":"percent"},{"benchmark":"pinchbench","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":66.11,"metric":"percent"},{"benchmark":"pinchbench","model":"nemotron-3-super-120b-a12b","score":80.36,"metric":"percent"},{"benchmark":"pinchbench","model":"gpt-oss-20b","score":57.2,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3.5-lightning-30b-a3b","score":36.97,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.6-35b-a3b","score":48.74,"metric":"percent"},{"benchmark":"browsecomp","model":"gemma-4-26b-a4b-it","score":26.3,"metric":"percent"},{"benchmark":"browsecomp","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":13.74,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-super-120b-a12b","score":22.77,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3.5-lightning-30b-a3b","score":9.28,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.6-35b-a3b","score":10.52,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-26b-a4b-it","score":14.02,"metric":"percent"},{"benchmark":"tau3-banking","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":7.01,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-super-120b-a12b","score":12.37,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-3.5-lightning-30b-a3b","score":832,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.6-35b-a3b","score":1015,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemma-4-26b-a4b-it","score":807,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":473,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-3-super-120b-a12b","score":746,"metric":"elo"},{"benchmark":"ifbench","model":"nemotron-3.5-lightning-30b-a3b","score":71.88,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":63.71,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-26b-a4b-it","score":77.25,"metric":"percent"},{"benchmark":"ifbench","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":72.17,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-super-120b-a12b","score":71.92,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b","score":68.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3.5-lightning-30b-a3b","score":52,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.6-35b-a3b","score":61.06,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-26b-a4b-it","score":57.56,"metric":"percent"},{"benchmark":"aa-lcr","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":32.75,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-super-120b-a12b","score":58.44,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-20b","score":32.88,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3.5-lightning-30b-a3b","score":23.46,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3.5-bolt-74b-a9b","score":53.93,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3.5-lightning-30b-a3b","score":9.48,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3.5-bolt-74b-a9b","score":17.01,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3.5-lightning-30b-a3b","score":10.47,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3.5-bolt-74b-a9b","score":28.73,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-3.5-lightning-30b-a3b","score":16.63,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-3.5-bolt-74b-a9b","score":21.8,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3.5-lightning-30b-a3b","score":31.38,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3.5-bolt-74b-a9b","score":44.49,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3.5-lightning-30b-a3b","score":75.57,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3.5-bolt-74b-a9b","score":88.83,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3.5-lightning-30b-a3b","score":49.19,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3.5-bolt-74b-a9b","score":67.38,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"qwen3.6-35b-a3b","score":65.85,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"gemma-4-26b-a4b-it","score":14.22,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"nemotron-3.5-lightning-30b-a3b","score":68.81,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"nemotron-3.5-bolt-74b-a9b","score":56.14,"metric":"percent"},{"benchmark":"pinchbench","model":"nemotron-3.5-lightning-30b-a3b","score":83.43,"metric":"percent"},{"benchmark":"pinchbench","model":"nemotron-3.5-bolt-74b-a9b","score":90.35,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.6-35b-a3b","score":51.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"nemotron-3.5-lightning-30b-a3b","score":46.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"nemotron-3.5-bolt-74b-a9b","score":55.6,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3.5-lightning-30b-a3b","score":36.81,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3.5-bolt-74b-a9b","score":70,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3.5-super-vl-120b-a12b","score":89.52,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-122b-a10b","score":86.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.8-flash-next","score":92.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash-0731","score":89.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-ultra","score":87,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"inkling-small","score":88.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5.3-flash","score":91.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3.5-super-vl-120b-a12b","score":31.79,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-122b-a10b","score":24.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.8-flash-next","score":39.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-flash-0731","score":35.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-ultra","score":29.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"inkling-small","score":33.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.3-flash","score":36.47,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nemotron-3.5-super-vl-120b-a12b","score":76.91,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.5-122b-a10b","score":83.2,"metric":"percent"},{"benchmark":"mmlu-prox","model":"qwen3.8-flash-next","score":83,"metric":"percent"},{"benchmark":"mmlu-prox","model":"deepseek-v4-flash-0731","score":85.5,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nemotron-3-ultra","score":83.1,"metric":"percent"},{"benchmark":"mmlu-prox","model":"inkling-small","score":84,"metric":"percent"},{"benchmark":"mmlu-prox","model":"glm-5.3-flash","score":83,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-3.5-super-vl-120b-a12b","score":26.2,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.5-122b-a10b","score":26.2,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.8-flash-next","score":27.9,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"deepseek-v4-flash-0731","score":45,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-3-ultra","score":25.3,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"inkling-small","score":35.4,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"glm-5.3-flash","score":34.2,"metric":"percent"},{"benchmark":"aa-omniscience","model":"nemotron-3.5-super-vl-120b-a12b","score":4.03,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3.5-122b-a10b","score":-36.1,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3.8-flash-next","score":-1.9,"metric":"index"},{"benchmark":"aa-omniscience","model":"deepseek-v4-flash-0731","score":-7.8,"metric":"index"},{"benchmark":"aa-omniscience","model":"nemotron-3-ultra","score":8.8,"metric":"index"},{"benchmark":"aa-omniscience","model":"inkling-small","score":-3.1,"metric":"index"},{"benchmark":"aa-omniscience","model":"glm-5.3-flash","score":14.3,"metric":"index"},{"benchmark":"critpt","model":"nemotron-3.5-super-vl-120b-a12b","score":10.86,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.5-122b-a10b","score":1.1,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v4-flash-0731","score":12.6,"metric":"percent"},{"benchmark":"critpt","model":"inkling-small","score":9.1,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"nemotron-3.5-super-vl-120b-a12b","score":88.36,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"qwen3.5-122b-a10b","score":54.7,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"qwen3.8-flash-next","score":91.8,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-flash-0731","score":88.7,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"nemotron-3-ultra","score":75,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"inkling-small","score":71.5,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"glm-5.3-flash","score":77.1,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3.5-super-vl-120b-a12b","score":88.22,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-122b-a10b","score":76.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.8-flash-next","score":94.1,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-0731","score":94.6,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-ultra","score":89.2,"metric":"percent"},{"benchmark":"livecodebench","model":"inkling-small","score":88.3,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-5.3-flash","score":80.6,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3.5-super-vl-120b-a12b","score":47.13,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-122b-a10b","score":39.8,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-flash-next","score":46.6,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-flash-0731","score":49.3,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-ultra","score":42,"metric":"percent"},{"benchmark":"scicode","model":"inkling-small","score":48.3,"metric":"percent"},{"benchmark":"scicode","model":"glm-5.3-flash","score":50.05,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3.5-super-vl-120b-a12b","score":68.62,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-122b-a10b","score":75.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.8-flash-next","score":78.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-flash-0731","score":79.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-ultra","score":75.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"inkling-small","score":77.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.3-flash","score":79.5,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3.5-super-vl-120b-a12b","score":70.86,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-122b-a10b","score":67.6,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-flash-next","score":75.6,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-flash-0731","score":76.2,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-ultra","score":82.9,"metric":"percent"},{"benchmark":"ifbench","model":"inkling-small","score":79.3,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5.3-flash","score":57.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nemotron-3.5-super-vl-120b-a12b","score":84.8,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-122b-a10b","score":86.3,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.8-flash-next","score":86.2,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"deepseek-v4-flash-0731","score":85.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nemotron-3-ultra","score":82.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"inkling-small","score":84.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"glm-5.3-flash","score":86.1,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3.5-super-vl-120b-a12b","score":69.24,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.5-122b-a10b","score":55.4,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.8-flash-next","score":71.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"deepseek-v4-flash-0731","score":73.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3-ultra","score":73.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"inkling-small","score":71.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"glm-5.3-flash","score":78.2,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3.5-super-vl-120b-a12b","score":76.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3.5-122b-a10b","score":63.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3.8-flash-next","score":80.8,"metric":"percent"},{"benchmark":"tau2-airline","model":"deepseek-v4-flash-0731","score":83.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3-ultra","score":79.8,"metric":"percent"},{"benchmark":"tau2-airline","model":"inkling-small","score":62.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"glm-5.3-flash","score":81.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3.5-super-vl-120b-a12b","score":73.19,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-122b-a10b","score":87.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.8-flash-next","score":90.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v4-flash-0731","score":98.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-ultra","score":83,"metric":"percent"},{"benchmark":"tau2-telecom","model":"inkling-small","score":90.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-5.3-flash","score":98.5,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3.5-super-vl-120b-a12b","score":18.88,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-122b-a10b","score":14.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.8-flash-next","score":44.5,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-flash-0731","score":38.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-ultra","score":18.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.3-flash","score":34.8,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-3.5-super-vl-120b-a12b","score":1211,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.5-122b-a10b","score":861,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.8-flash-next","score":1561,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4-flash-0731","score":1382,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-3-ultra","score":1148,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"inkling-small","score":1313,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.3-flash","score":1563,"metric":"elo"},{"benchmark":"browsecomp","model":"nemotron-3.5-super-vl-120b-a12b","score":78,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-122b-a10b","score":58.1,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.8-flash-next","score":89,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-flash-0731","score":84.2,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-ultra","score":67.85,"metric":"percent"},{"benchmark":"browsecomp","model":"inkling-small","score":74.1,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5.3-flash","score":86.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3.5-super-vl-120b-a12b","score":71.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-122b-a10b","score":71.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.8-flash-next","score":78.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-flash-0731","score":75.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-ultra","score":73.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"inkling-small","score":75.27,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5.3-flash","score":79.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3.5-super-vl-120b-a12b","score":67.72,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-122b-a10b","score":62,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.8-flash-next","score":77.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-flash-0731","score":72,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3-ultra","score":68.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"inkling-small","score":71.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.3-flash","score":78.3,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"nemotron-3.5-super-vl-120b-a12b","score":51.78,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.5-122b-a10b","score":44.9,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.8-flash-next","score":60.37,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"deepseek-v4-flash-0731","score":56.91,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"nemotron-3-ultra","score":49.66,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"inkling-small","score":56.54,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"glm-5.3-flash","score":59.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3.5-super-vl-120b-a12b","score":60.67,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-122b-a10b","score":48.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-flash-next","score":85.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash-0731","score":76.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-ultra","score":54.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"inkling-small","score":53.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.3-flash","score":82.7,"metric":"percent"},{"benchmark":"babyvision","model":"nemotron-3.5-super-vl-120b-a12b","score":29.6,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.5-122b-a10b","score":35.7,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.8-flash-next","score":46.8,"metric":"percent"},{"benchmark":"babyvision","model":"inkling-small","score":24.7,"metric":"percent"},{"benchmark":"babyvision","model":"glm-5.3-flash","score":39.1,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"nemotron-3.5-super-vl-120b-a12b","score":62.82,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.5-122b-a10b","score":63.7,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"qwen3.8-flash-next","score":67.9,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"inkling-small","score":49.06,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"glm-5.3-flash","score":65.8,"metric":"percent"},{"benchmark":"v-star","model":"nemotron-3.5-super-vl-120b-a12b","score":85.6,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.5-122b-a10b","score":91.1,"metric":"percent"},{"benchmark":"v-star","model":"qwen3.8-flash-next","score":93,"metric":"percent"},{"benchmark":"v-star","model":"inkling-small","score":70.5,"metric":"percent"},{"benchmark":"v-star","model":"glm-5.3-flash","score":88.1,"metric":"percent"},{"benchmark":"ocrreasoning","model":"nemotron-3.5-super-vl-120b-a12b","score":65.08,"metric":"percent"},{"benchmark":"ocrreasoning","model":"qwen3.5-122b-a10b","score":64.3,"metric":"percent"},{"benchmark":"ocrreasoning","model":"qwen3.8-flash-next","score":67.1,"metric":"percent"},{"benchmark":"ocrreasoning","model":"inkling-small","score":54.7,"metric":"percent"},{"benchmark":"ocrreasoning","model":"glm-5.3-flash","score":64.6,"metric":"percent"},{"benchmark":"mathvision","model":"nemotron-3.5-super-vl-120b-a12b","score":78.16,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-122b-a10b","score":83.3,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.8-flash-next","score":87.5,"metric":"percent"},{"benchmark":"mathvision","model":"inkling-small","score":78.8,"metric":"percent"},{"benchmark":"mathvision","model":"glm-5.3-flash","score":82.5,"metric":"percent"},{"benchmark":"hle","model":"nemotron-3.5-super-vl-120b-a12b","score":29.2,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-122b-a10b","score":24.4,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.8-flash-next","score":38.8,"metric":"avg@3"},{"benchmark":"hle","model":"inkling-small","score":31.6,"metric":"avg@3"},{"benchmark":"hle","model":"glm-5.3-flash","score":35.1,"metric":"avg@3"},{"benchmark":"ocrbenchv2-en","model":"nemotron-3.5-super-vl-120b-a12b","score":68.12,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-122b-a10b","score":68.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.8-flash-next","score":67.9,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"inkling-small","score":54.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"glm-5.3-flash","score":61.8,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"nemotron-3.5-super-vl-120b-a12b","score":59.15,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.5-122b-a10b","score":67.3,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.8-flash-next","score":68.3,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"inkling-small","score":52.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"glm-5.3-flash","score":56.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"nemotron-3.5-super-vl-120b-a12b","score":80.82,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-122b-a10b","score":83.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.8-flash-next","score":85.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"inkling-small","score":77.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"glm-5.3-flash","score":81.9,"metric":"percent"},{"benchmark":"videomme-v2","model":"nemotron-3.5-super-vl-120b-a12b","score":32.85,"metric":"percent"},{"benchmark":"videomme-v2","model":"qwen3.5-122b-a10b","score":32,"metric":"percent"},{"benchmark":"videomme-v2","model":"qwen3.8-flash-next","score":45.1,"metric":"percent"},{"benchmark":"videomme-v2","model":"glm-5.3-flash","score":14.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"nemotron-3.5-super-vl-120b-a12b","score":51.14,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-122b-a10b","score":51.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.8-flash-next","score":55.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"glm-5.3-flash","score":14.78,"metric":"percent"},{"benchmark":"webvoyager","model":"nemotron-3.5-super-vl-120b-a12b","score":77.72,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen3.5-122b-a10b","score":54.89,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen3.8-flash-next","score":90.39,"metric":"percent"},{"benchmark":"webvoyager","model":"inkling-small","score":5.25,"metric":"percent"},{"benchmark":"webvoyager","model":"glm-5.3-flash","score":72.64,"metric":"percent"},{"benchmark":"automationbench-aa","model":"nemotron-3.5-super-vl-120b-a12b","score":32.44,"metric":"percent"},{"benchmark":"automationbench-aa","model":"qwen3.5-122b-a10b","score":27.25,"metric":"percent"},{"benchmark":"automationbench-aa","model":"qwen3.8-flash-next","score":72.06,"metric":"percent"},{"benchmark":"automationbench-aa","model":"deepseek-v4-flash-0731","score":63.86,"metric":"percent"},{"benchmark":"automationbench-aa","model":"nemotron-3-ultra","score":23.28,"metric":"percent"},{"benchmark":"automationbench-aa","model":"inkling-small","score":32.83,"metric":"percent"},{"benchmark":"automationbench-aa","model":"glm-5.3-flash","score":70.17,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"nemotron-3.5-super-vl-120b-a12b","score":1,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"qwen3.5-122b-a10b","score":0,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"qwen3.8-flash-next","score":20.71,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"deepseek-v4-flash-0731","score":3.54,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"nemotron-3-ultra","score":0,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"inkling-small","score":0.5,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"glm-5.3-flash","score":15.15,"metric":"percent"},{"benchmark":"deepswe","model":"nemotron-3.5-super-vl-120b-a12b","score":24.65,"metric":"percent"},{"benchmark":"deepswe","model":"qwen3.5-122b-a10b","score":0.4,"metric":"percent"},{"benchmark":"deepswe","model":"qwen3.8-flash-next","score":55.57,"metric":"percent"},{"benchmark":"deepswe","model":"deepseek-v4-flash-0731","score":42.3,"metric":"percent"},{"benchmark":"deepswe","model":"nemotron-3-ultra","score":3,"metric":"percent"},{"benchmark":"deepswe","model":"inkling-small","score":18,"metric":"percent"},{"benchmark":"bfcl-v3","model":"nemotron-3-nano-4b","score":61.1,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-nano-4b","score":43.2,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-3-nano-4b","score":82.8,"metric":"percent"},{"benchmark":"ruler-128k","model":"nemotron-3-nano-4b","score":91.1,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3-nano-4b","score":28,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3-nano-4b","score":34.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-nano-4b","score":24.9,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-nano-4b-thinking","score":78.5,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3-nano-4b-thinking","score":95.4,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-3-nano-4b-thinking","score":53.2,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-nano-4b-thinking","score":51.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"nemotron-3-nano-4b-thinking","score":61.1,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-3-nano-4b-thinking","score":87.9,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3-nano-4b-thinking","score":33.3,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3-nano-4b-thinking","score":39.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-nano-4b-thinking","score":33,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-labs-3-elastic-30b-a3b","score":88.54,"metric":"percent"},{"benchmark":"aime-2025","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":87.92,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b","score":80,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-labs-3-elastic-30b-a3b","score":72.1,"metric":"percent"},{"benchmark":"gpqa","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":73.11,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-30b-a3b","score":70.83,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nemotron-labs-3-elastic-30b-a3b","score":72.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":71.75,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-30b-a3b","score":68.25,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-labs-3-elastic-30b-a3b","score":78.63,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":78.86,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b","score":81.11,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-labs-3-elastic-30b-a3b","score":70.58,"metric":"percent"},{"benchmark":"ifbench","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":70.82,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b","score":43.28,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-labs-3-elastic-30b-a3b","score":43.33,"metric":"percent"},{"benchmark":"tau2-airline","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":44.67,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-30b-a3b","score":52.67,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-labs-3-elastic-30b-a3b","score":59.36,"metric":"percent"},{"benchmark":"tau2-retail","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":53.51,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-30b-a3b","score":56.43,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-labs-3-elastic-30b-a3b","score":33.33,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":30.99,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-30b-a3b","score":28.36,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":70.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nemotron-3-super-120b-a12b","score":77.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-35b-a3b","score":74.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nemotron-cascade-2-30b-a3b","score":79.3,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-super-120b-a12b","score":90.2,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-35b-a3b","score":91.9,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-cascade-2-30b-a3b","score":92.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":89.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-3-super-120b-a12b","score":89.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-35b-a3b","score":91.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-cascade-2-30b-a3b","score":90.9,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":84.6,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"nemotron-3-super-120b-a12b","score":93.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"nemotron-cascade-2-30b-a3b","score":94.6,"metric":"percent"},{"benchmark":"ioi-2025","model":"qwen3.5-35b-a3b","score":348.6,"metric":"points"},{"benchmark":"ioi-2025","model":"nemotron-cascade-2-30b-a3b","score":439.3,"metric":"points"},{"benchmark":"livecodebench","model":"nemotron-3-super-120b-a12b","score":78.7,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-cascade-2-30b-a3b","score":87.2,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":54.5,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nemotron-3-super-120b-a12b","score":81.7,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3.5-35b-a3b","score":81.1,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nemotron-cascade-2-30b-a3b","score":87,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":3.5,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nemotron-3-super-120b-a12b","score":23.2,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3.5-35b-a3b","score":17.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nemotron-cascade-2-30b-a3b","score":27.6,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-super-120b-a12b","score":42.1,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-35b-a3b","score":38,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-cascade-2-30b-a3b","score":36.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"nemotron-cascade-2-30b-a3b","score":86.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b","score":83.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-cascade-2-30b-a3b","score":79.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":73,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-super-120b-a12b","score":79.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-cascade-2-30b-a3b","score":76.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":10.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-super-120b-a12b","score":18.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-cascade-2-30b-a3b","score":17.7,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3.5-35b-a3b","score":65.4,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"nemotron-cascade-2-30b-a3b","score":83.5,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"nemotron-3-super-120b-a12b","score":73.9,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"qwen3.5-35b-a3b","score":64.5,"metric":"percent"},{"benchmark":"arena-hard-v2-hard-prompt","model":"nemotron-cascade-2-30b-a3b","score":88.2,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"qwen3.5-35b-a3b","score":66.3,"metric":"percent"},{"benchmark":"arena-hard-v2-creative-writing","model":"nemotron-cascade-2-30b-a3b","score":78.7,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-super-120b-a12b","score":72.6,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-cascade-2-30b-a3b","score":82.9,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"nemotron-3-super-120b-a12b","score":55.2,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"qwen3.5-35b-a3b","score":60,"metric":"percent"},{"benchmark":"scale-ai-multi-challenge","model":"nemotron-cascade-2-30b-a3b","score":45.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-super-120b-a12b","score":58.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-cascade-2-30b-a3b","score":39.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":39.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"nemotron-cascade-2-30b-a3b","score":40.3,"metric":"percent"},{"benchmark":"cl-bench","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":12,"metric":"percent"},{"benchmark":"cl-bench","model":"qwen3.5-35b-a3b","score":15.5,"metric":"percent"},{"benchmark":"cl-bench","model":"nemotron-cascade-2-30b-a3b","score":12.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nemotron-cascade-2-30b-a3b","score":52.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":8.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"nemotron-cascade-2-30b-a3b","score":21.1,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"nemotron-3-super-120b-a12b","score":60.5,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"qwen3.5-35b-a3b","score":69.2,"metric":"percent"},{"benchmark":"swe-bench-openhands","model":"nemotron-cascade-2-30b-a3b","score":50.2,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nemotron-3-super-120b-a12b","score":79.4,"metric":"percent"},{"benchmark":"mmlu-prox","model":"nemotron-cascade-2-30b-a3b","score":72.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nemotron-3-super-120b-a12b","score":86.7,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"qwen3.5-35b-a3b","score":87.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"nemotron-cascade-2-30b-a3b","score":84.1,"metric":"percent"},{"benchmark":"cv-bench","model":"cosmos-reason2-32b","score":88.01,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-32b-instruct","score":86.74,"metric":"percent"},{"benchmark":"cv-bench","model":"cosmos-reason2-8b","score":85.6,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-8b-instruct","score":85.17,"metric":"percent"},{"benchmark":"cv-bench","model":"cosmos-reason2-2b","score":78.74,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-2b-instruct","score":78.67,"metric":"percent"},{"benchmark":"erqa","model":"cosmos-reason2-32b","score":45.25,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-32b-instruct","score":46.5,"metric":"percent"},{"benchmark":"erqa","model":"cosmos-reason2-8b","score":44,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-8b-instruct","score":44,"metric":"percent"},{"benchmark":"erqa","model":"cosmos-reason2-2b","score":37.75,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-2b-instruct","score":37.75,"metric":"percent"},{"benchmark":"lingoqa","model":"cosmos-reason2-32b","score":69,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3-vl-32b-instruct","score":67.8,"metric":"percent"},{"benchmark":"lingoqa","model":"cosmos-reason2-8b","score":72.4,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3-vl-8b-instruct","score":68.4,"metric":"percent"},{"benchmark":"lingoqa","model":"cosmos-reason2-2b","score":59,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3-vl-2b-instruct","score":59.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"nemotron-3-nano-omni-30b-a3b-reasoning","score":67.04,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"nemotron-nano-12b-v2-vl","score":54.8,"metric":"percent"},{"benchmark":"osworld","model":"nemotron-3-nano-omni-30b-a3b-reasoning","score":47.4,"metric":"percent"},{"benchmark":"osworld","model":"nemotron-nano-12b-v2-vl","score":11.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"nemotron-3-nano-omni-30b-a3b-reasoning","score":63.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"nemotron-nano-12b-v2-vl","score":41.3,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"nemotron-3-nano-omni-30b-a3b-reasoning","score":57.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"nemotron-nano-12b-v2-vl","score":38,"metric":"percent"},{"benchmark":"mathvista-mini","model":"nemotron-3-nano-omni-30b-a3b-reasoning","score":82.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"nemotron-nano-12b-v2-vl","score":75.5,"metric":"percent"},{"benchmark":"ocrreasoning","model":"nemotron-3-nano-omni-30b-a3b-reasoning","score":54.14,"metric":"percent"},{"benchmark":"ocrreasoning","model":"nemotron-nano-12b-v2-vl","score":33.9,"metric":"percent"},{"benchmark":"videomme","model":"nemotron-3-nano-omni-30b-a3b-reasoning","score":72.2,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"nemotron-nano-9b-v2-japanese","score":64.9,"metric":"percent"},{"benchmark":"bfcl-v3-ja","model":"qwen3-8b","score":60.8,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"nemotron-nano-9b-v2-japanese","score":63.2,"metric":"percent"},{"benchmark":"m-ifeval-ja","model":"qwen3-8b","score":61.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-8b","score":2.47,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"nemotron-terminal-8b","score":13,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-14b","score":4.04,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"nemotron-terminal-14b","score":20.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-32b","score":3.37,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"nemotron-terminal-32b","score":27.4,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-4b-instruct-2507","score":64.79,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-instruct-2507","score":48.75,"metric":"percent"},{"benchmark":"amc-23","model":"qwen3-4b-instruct-2507","score":85.17,"metric":"percent"},{"benchmark":"math500","model":"qwen3-4b-instruct-2507","score":94.66,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen3-4b-instruct-2507","score":50.09,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen3-4b-instruct-2507","score":65.83,"metric":"percent"},{"benchmark":"aime-2024","model":"nemotron-research-goosereason-4b-instruct","score":70,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-research-goosereason-4b-instruct","score":63.96,"metric":"percent"},{"benchmark":"amc-23","model":"nemotron-research-goosereason-4b-instruct","score":89.16,"metric":"percent"},{"benchmark":"math500","model":"nemotron-research-goosereason-4b-instruct","score":96.7,"metric":"percent"},{"benchmark":"minerva-math","model":"nemotron-research-goosereason-4b-instruct","score":54.37,"metric":"percent"},{"benchmark":"olympiadbench","model":"nemotron-research-goosereason-4b-instruct","score":68.79,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b-instruct-2507","score":76.66,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-instruct-2507","score":63.74,"metric":"percent"},{"benchmark":"amc-23","model":"qwen3-30b-a3b-instruct-2507","score":91.64,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b-instruct-2507","score":97.1,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen3-30b-a3b-instruct-2507","score":51.99,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen3-30b-a3b-instruct-2507","score":70.05,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-4b-instruct-2507","score":77.56,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-instruct-2507","score":31.74,"metric":"percent"},{"benchmark":"humaneval-plus","model":"nemotron-research-goosereason-4b-instruct","score":86.46,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-research-goosereason-4b-instruct","score":41.64,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-30b-a3b-instruct-2507","score":80.56,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-instruct-2507","score":43.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b-instruct-2507","score":60.26,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b-instruct-2507","score":72.36,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-research-goosereason-4b-instruct","score":66.79,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-research-goosereason-4b-instruct","score":76.39,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-instruct-2507","score":70.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-instruct-2507","score":82.73,"metric":"percent"},{"benchmark":"ioi-2025","model":"nemotron-labs-3-competitive-coding-550b-a55b","score":502,"metric":"points"},{"benchmark":"mmlu","model":"nemotron-3-super-120b-a12b-base","score":86.01,"metric":"percent"},{"benchmark":"mmlu","model":"ling-flash-base-2.0","score":81,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.5-air-base","score":81,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b-base","score":75.65,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-flash-base-2.0","score":62.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-air-base","score":58.2,"metric":"percent"},{"benchmark":"agieval","model":"nemotron-3-super-120b-a12b-base","score":77.92,"metric":"percent"},{"benchmark":"agieval","model":"ling-flash-base-2.0","score":61.7,"metric":"percent"},{"benchmark":"agieval","model":"glm-4.5-air-base","score":62.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-super-120b-a12b-base","score":60,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ling-flash-base-2.0","score":36,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.5-air-base","score":23.2,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3-super-120b-a12b-base","score":90.67,"metric":"percent"},{"benchmark":"gsm8k","model":"ling-flash-base-2.0","score":90.75,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4.5-air-base","score":82.6,"metric":"percent"},{"benchmark":"math","model":"nemotron-3-super-120b-a12b-base","score":84.84,"metric":"percent"},{"benchmark":"math","model":"ling-flash-base-2.0","score":63.8,"metric":"percent"},{"benchmark":"math","model":"glm-4.5-air-base","score":50.36,"metric":"percent"},{"benchmark":"math-lvl5","model":"nemotron-3-super-120b-a12b-base","score":70,"metric":"percent"},{"benchmark":"math-lvl5","model":"ling-flash-base-2.0","score":39.8,"metric":"percent"},{"benchmark":"math-lvl5","model":"glm-4.5-air-base","score":26.3,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-super-120b-a12b-base","score":79.4,"metric":"percent"},{"benchmark":"humaneval","model":"ling-flash-base-2.0","score":70.1,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4.5-air-base","score":76.3,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-super-120b-a12b-base","score":78.38,"metric":"percent"},{"benchmark":"mbpp","model":"ling-flash-base-2.0","score":77.3,"metric":"percent"},{"benchmark":"mbpp","model":"glm-4.5-air-base","score":77.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3-super-120b-a12b-base","score":96.08,"metric":"percent"},{"benchmark":"arc-challenge","model":"ling-flash-base-2.0","score":94.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"glm-4.5-air-base","score":93.9,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3-super-120b-a12b-base","score":88.97,"metric":"percent"},{"benchmark":"hellaswag","model":"ling-flash-base-2.0","score":84.69,"metric":"percent"},{"benchmark":"hellaswag","model":"glm-4.5-air-base","score":87.7,"metric":"percent"},{"benchmark":"openbookqa","model":"nemotron-3-super-120b-a12b-base","score":50.2,"metric":"percent"},{"benchmark":"openbookqa","model":"ling-flash-base-2.0","score":47,"metric":"percent"},{"benchmark":"openbookqa","model":"glm-4.5-air-base","score":48.6,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-3-super-120b-a12b-base","score":85.47,"metric":"percent"},{"benchmark":"piqa","model":"ling-flash-base-2.0","score":84,"metric":"percent"},{"benchmark":"piqa","model":"glm-4.5-air-base","score":84.22,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-3-super-120b-a12b-base","score":78.93,"metric":"percent"},{"benchmark":"winogrande","model":"ling-flash-base-2.0","score":78.37,"metric":"percent"},{"benchmark":"winogrande","model":"glm-4.5-air-base","score":83.82,"metric":"percent"},{"benchmark":"race","model":"nemotron-3-super-120b-a12b-base","score":91,"metric":"percent"},{"benchmark":"race","model":"ling-flash-base-2.0","score":90.1,"metric":"percent"},{"benchmark":"race","model":"glm-4.5-air-base","score":89.5,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"nemotron-3-super-120b-a12b-base","score":85.72,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"ling-flash-base-2.0","score":74.94,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"glm-4.5-air-base","score":79.25,"metric":"percent"},{"benchmark":"mgsm","model":"nemotron-3-super-120b-a12b-base","score":87.47,"metric":"percent"},{"benchmark":"mgsm","model":"ling-flash-base-2.0","score":82.73,"metric":"percent"},{"benchmark":"mgsm","model":"glm-4.5-air-base","score":80.33,"metric":"percent"},{"benchmark":"ruler-64k","model":"nemotron-3-super-120b-a12b-base","score":93.17,"metric":"percent"},{"benchmark":"ruler-64k","model":"glm-4.5-air-base","score":81.58,"metric":"percent"},{"benchmark":"ruler-128k","model":"nemotron-3-super-120b-a12b-base","score":89,"metric":"percent"},{"benchmark":"ruler-128k","model":"ling-flash-base-2.0","score":57.56,"metric":"percent"},{"benchmark":"ruler-128k","model":"glm-4.5-air-base","score":63.62,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-3-super-120b-a12b-base","score":86.18,"metric":"percent"},{"benchmark":"ruler-512k","model":"nemotron-3-super-120b-a12b-base","score":82.16,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3-super-120b-a12b-base","score":74.39,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3-ultra-base","score":89.08,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3.2-exp-base","score":87.82,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-large-3-base","score":87.35,"metric":"percent"},{"benchmark":"mmlu","model":"kimi-k2-base","score":87.6,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.5-base","score":86.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-ultra-base","score":79.07,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.2-exp-base","score":63.26,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-large-3-base","score":67.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2-base","score":69.15,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-base","score":65.78,"metric":"percent"},{"benchmark":"agieval","model":"nemotron-3-ultra-base","score":78.73,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v3.2-exp-base","score":70.13,"metric":"percent"},{"benchmark":"agieval","model":"mistral-large-3-base","score":69.3,"metric":"percent"},{"benchmark":"agieval","model":"kimi-k2-base","score":72.55,"metric":"percent"},{"benchmark":"agieval","model":"glm-4.5-base","score":70.06,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-3-ultra-base","score":50,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v3.2-exp-base","score":31.82,"metric":"percent"},{"benchmark":"gpqa","model":"mistral-large-3-base","score":34.85,"metric":"percent"},{"benchmark":"gpqa","model":"kimi-k2-base","score":43.43,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4.5-base","score":34.85,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3-ultra-base","score":88.1,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3.2-exp-base","score":84.38,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-large-3-base","score":91.21,"metric":"percent"},{"benchmark":"gsm8k","model":"kimi-k2-base","score":91.05,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4.5-base","score":85.37,"metric":"percent"},{"benchmark":"math","model":"nemotron-3-ultra-base","score":82,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3.2-exp-base","score":60.12,"metric":"percent"},{"benchmark":"math","model":"mistral-large-3-base","score":62.88,"metric":"percent"},{"benchmark":"math","model":"kimi-k2-base","score":68.4,"metric":"percent"},{"benchmark":"math","model":"glm-4.5-base","score":57.58,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-ultra-base","score":83.84,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v3.2-exp-base","score":61.85,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-large-3-base","score":66.71,"metric":"percent"},{"benchmark":"humaneval","model":"kimi-k2-base","score":78.2,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4.5-base","score":78.16,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-ultra-base","score":85.97,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v3.2-exp-base","score":58.66,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-large-3-base","score":84.08,"metric":"percent"},{"benchmark":"mbpp","model":"kimi-k2-base","score":72.14,"metric":"percent"},{"benchmark":"mbpp","model":"glm-4.5-base","score":76.69,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3-ultra-base","score":97.35,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v3.2-exp-base","score":95.22,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-large-3-base","score":97.27,"metric":"percent"},{"benchmark":"arc-challenge","model":"kimi-k2-base","score":95.82,"metric":"percent"},{"benchmark":"arc-challenge","model":"glm-4.5-base","score":96.59,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3-ultra-base","score":90.51,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v3.2-exp-base","score":89.44,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-large-3-base","score":88.88,"metric":"percent"},{"benchmark":"hellaswag","model":"kimi-k2-base","score":90.92,"metric":"percent"},{"benchmark":"hellaswag","model":"glm-4.5-base","score":90.17,"metric":"percent"},{"benchmark":"openbookqa","model":"nemotron-3-ultra-base","score":48.6,"metric":"percent"},{"benchmark":"openbookqa","model":"deepseek-v3.2-exp-base","score":48.2,"metric":"percent"},{"benchmark":"openbookqa","model":"mistral-large-3-base","score":51.4,"metric":"percent"},{"benchmark":"openbookqa","model":"kimi-k2-base","score":50.8,"metric":"percent"},{"benchmark":"openbookqa","model":"glm-4.5-base","score":49.6,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-3-ultra-base","score":83.79,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-v3.2-exp-base","score":85.09,"metric":"percent"},{"benchmark":"piqa","model":"mistral-large-3-base","score":84.82,"metric":"percent"},{"benchmark":"piqa","model":"kimi-k2-base","score":85.47,"metric":"percent"},{"benchmark":"piqa","model":"glm-4.5-base","score":85.09,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-3-ultra-base","score":79.32,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v3.2-exp-base","score":83.43,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-large-3-base","score":82.08,"metric":"percent"},{"benchmark":"winogrande","model":"kimi-k2-base","score":84.21,"metric":"percent"},{"benchmark":"winogrande","model":"glm-4.5-base","score":85.24,"metric":"percent"},{"benchmark":"race","model":"nemotron-3-ultra-base","score":92.15,"metric":"percent"},{"benchmark":"race","model":"deepseek-v3.2-exp-base","score":93.21,"metric":"percent"},{"benchmark":"race","model":"mistral-large-3-base","score":93.3,"metric":"percent"},{"benchmark":"race","model":"kimi-k2-base","score":91.96,"metric":"percent"},{"benchmark":"race","model":"glm-4.5-base","score":92.15,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"nemotron-3-ultra-base","score":90.13,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"deepseek-v3.2-exp-base","score":85.59,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"mistral-large-3-base","score":87.34,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"kimi-k2-base","score":85.63,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"glm-4.5-base","score":85.81,"metric":"percent"},{"benchmark":"mgsm","model":"nemotron-3-ultra-base","score":87.73,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v3.2-exp-base","score":82.33,"metric":"percent"},{"benchmark":"mgsm","model":"mistral-large-3-base","score":82.93,"metric":"percent"},{"benchmark":"mgsm","model":"kimi-k2-base","score":85.2,"metric":"percent"},{"benchmark":"mgsm","model":"glm-4.5-base","score":81.27,"metric":"percent"},{"benchmark":"ruler-64k","model":"nemotron-3-ultra-base","score":95.3,"metric":"percent"},{"benchmark":"ruler-64k","model":"deepseek-v3.2-exp-base","score":93.3,"metric":"percent"},{"benchmark":"ruler-64k","model":"mistral-large-3-base","score":90.11,"metric":"percent"},{"benchmark":"ruler-64k","model":"kimi-k2-base","score":93.79,"metric":"percent"},{"benchmark":"ruler-64k","model":"glm-4.5-base","score":16.12,"metric":"percent"},{"benchmark":"ruler-128k","model":"nemotron-3-ultra-base","score":92.49,"metric":"percent"},{"benchmark":"ruler-128k","model":"deepseek-v3.2-exp-base","score":91.88,"metric":"percent"},{"benchmark":"ruler-128k","model":"mistral-large-3-base","score":55.77,"metric":"percent"},{"benchmark":"ruler-128k","model":"kimi-k2-base","score":88.61,"metric":"percent"},{"benchmark":"ruler-128k","model":"glm-4.5-base","score":0,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-3-ultra-base","score":86.22,"metric":"percent"},{"benchmark":"ruler-256k","model":"mistral-large-3-base","score":35.5,"metric":"percent"},{"benchmark":"ruler-512k","model":"nemotron-3-ultra-base","score":84.54,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3-ultra-base","score":76.83,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-35b-a3b-base","score":81.07,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-26b-a4b","score":77.81,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3-nano-30b-a3b-base","score":78.48,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3.5-lightning-30b-a3b-base","score":78.59,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-35b-a3b-base","score":64.49,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-26b-a4b","score":50.02,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-30b-a3b-base","score":64.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3.5-lightning-30b-a3b-base","score":67.94,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b-base","score":74.43,"metric":"percent"},{"benchmark":"agieval","model":"qwen3.5-35b-a3b-base","score":70.51,"metric":"percent"},{"benchmark":"agieval","model":"gemma-4-26b-a4b","score":55.28,"metric":"percent"},{"benchmark":"agieval","model":"nemotron-3-nano-30b-a3b-base","score":68.45,"metric":"percent"},{"benchmark":"agieval","model":"nemotron-3.5-lightning-30b-a3b-base","score":70.02,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-35b-a3b-base","score":90.07,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-4-26b-a4b","score":77.03,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3-nano-30b-a3b-base","score":91.43,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3.5-lightning-30b-a3b-base","score":91.28,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen3.5-35b-a3b-base","score":59.66,"metric":"percent"},{"benchmark":"minerva-math","model":"gemma-4-26b-a4b","score":43.74,"metric":"percent"},{"benchmark":"minerva-math","model":"nemotron-3-nano-30b-a3b-base","score":82.64,"metric":"percent"},{"benchmark":"minerva-math","model":"nemotron-3.5-lightning-30b-a3b-base","score":82.78,"metric":"percent"},{"benchmark":"minerva-math","model":"nemotron-3-super-120b-a12b-base","score":84.84,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3.5-35b-a3b-base","score":70.76,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-4-26b-a4b","score":68.39,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-nano-30b-a3b-base","score":73.82,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3.5-lightning-30b-a3b-base","score":78.59,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-super-120b-a12b-base","score":81.71,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3.5-35b-a3b-base","score":66.46,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-4-26b-a4b","score":50,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-nano-30b-a3b-base","score":75,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3.5-lightning-30b-a3b-base","score":77.44,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-super-120b-a12b-base","score":80.49,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-35b-a3b-base","score":95.39,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-4-26b-a4b","score":92.83,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3-nano-30b-a3b-base","score":91.98,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3.5-lightning-30b-a3b-base","score":92.66,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3.5-35b-a3b-base","score":85.61,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-4-26b-a4b","score":85.26,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3-nano-30b-a3b-base","score":85.55,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3.5-lightning-30b-a3b-base","score":85.55,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen3.5-35b-a3b-base","score":44.2,"metric":"percent"},{"benchmark":"openbookqa","model":"gemma-4-26b-a4b","score":48.8,"metric":"percent"},{"benchmark":"openbookqa","model":"nemotron-3-nano-30b-a3b-base","score":46.8,"metric":"percent"},{"benchmark":"openbookqa","model":"nemotron-3.5-lightning-30b-a3b-base","score":47.6,"metric":"percent"},{"benchmark":"openbookqa","model":"nemotron-3-super-120b-a12b-base","score":48.6,"metric":"percent"},{"benchmark":"piqa","model":"qwen3.5-35b-a3b-base","score":82.54,"metric":"percent"},{"benchmark":"piqa","model":"gemma-4-26b-a4b","score":83.84,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-3.5-lightning-30b-a3b-base","score":85.2,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3.5-35b-a3b-base","score":79.24,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-4-26b-a4b","score":79.08,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-3-nano-30b-a3b-base","score":79.16,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-3.5-lightning-30b-a3b-base","score":79.95,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"qwen3.5-35b-a3b-base","score":80.94,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemma-4-26b-a4b","score":74.78,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"nemotron-3-nano-30b-a3b-base","score":74.62,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"nemotron-3.5-lightning-30b-a3b-base","score":75.53,"metric":"percent"},{"benchmark":"ruler-256k","model":"qwen3.5-35b-a3b-base","score":82.36,"metric":"percent"},{"benchmark":"ruler-256k","model":"gemma-4-26b-a4b","score":85.73,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-3-nano-30b-a3b-base","score":71.71,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-3.5-lightning-30b-a3b-base","score":76.88,"metric":"percent"},{"benchmark":"ruler-256k","model":"nemotron-3-super-120b-a12b-base","score":83.03,"metric":"percent"},{"benchmark":"ruler-1m","model":"qwen3.5-35b-a3b-base","score":56.43,"metric":"percent"},{"benchmark":"ruler-1m","model":"gemma-4-26b-a4b","score":72.93,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3-nano-30b-a3b-base","score":51.23,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3.5-lightning-30b-a3b-base","score":69.62,"metric":"percent"},{"benchmark":"ruler-1m","model":"nemotron-3-super-120b-a12b-base","score":66.98,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3.5-super-vl-120b-a12b-base","score":84.14,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3.5-super-vl-120b-a12b-base","score":76.25,"metric":"percent"},{"benchmark":"agieval","model":"nemotron-3.5-super-vl-120b-a12b-base","score":75.65,"metric":"percent"},{"benchmark":"supergpqa","model":"nemotron-3.5-super-vl-120b-a12b-base","score":47.65,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3.5-super-vl-120b-a12b-base","score":66.16,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3.5-super-vl-120b-a12b-base","score":91.74,"metric":"percent"},{"benchmark":"minerva-math","model":"nemotron-3.5-super-vl-120b-a12b-base","score":87.66,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3.5-super-vl-120b-a12b-base","score":81.56,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3.5-super-vl-120b-a12b-base","score":81.31,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3.5-super-vl-120b-a12b-base","score":79.06,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3.5-super-vl-120b-a12b-base","score":47.61,"metric":"percent"},{"benchmark":"commonsenseqa","model":"nemotron-3.5-super-vl-120b-a12b-base","score":85.26,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3.5-super-vl-120b-a12b-base","score":95.99,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3.5-super-vl-120b-a12b-base","score":88.96,"metric":"percent"},{"benchmark":"openbookqa","model":"nemotron-3.5-super-vl-120b-a12b-base","score":48.8,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-3.5-super-vl-120b-a12b-base","score":85.09,"metric":"percent"},{"benchmark":"truthfulqa","model":"nemotron-3.5-super-vl-120b-a12b-base","score":71.18,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-3.5-super-vl-120b-a12b-base","score":79.08,"metric":"percent"},{"benchmark":"socialiqa","model":"nemotron-3.5-super-vl-120b-a12b-base","score":49.03,"metric":"percent"},{"benchmark":"race","model":"nemotron-3.5-super-vl-120b-a12b-base","score":91.39,"metric":"percent"},{"benchmark":"global-mmlu","model":"nemotron-3.5-super-vl-120b-a12b-base","score":86.56,"metric":"percent"},{"benchmark":"mgsm","model":"nemotron-3.5-super-vl-120b-a12b-base","score":87.53,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.4-none","score":0.109,"metric":"edit_distance"},{"benchmark":"tau2-telecom","model":"gpt-5.4-none","score":64.3,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.2-none","score":0.14,"metric":"edit_distance"},{"benchmark":"tau2-telecom","model":"gpt-5.2-none","score":57.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.1-none","score":45.2,"metric":"percent"},{"benchmark":"math","model":"olmo-3.1-instruct-32b-sft","score":74.4,"metric":"percent"},{"benchmark":"math","model":"olmo-3.1-instruct-32b-dpo","score":86.6,"metric":"percent"},{"benchmark":"math","model":"olmo-3.1-instruct-32b","score":93.4,"metric":"percent"},{"benchmark":"math","model":"apertus-70b-instruct","score":36.2,"metric":"percent"},{"benchmark":"math","model":"qwen3-32b","score":84.3,"metric":"percent"},{"benchmark":"math","model":"qwen3-vl-32b-instruct","score":95.1,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3.1-instruct-32b-sft","score":12.7,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3.1-instruct-32b-dpo","score":35.2,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3.1-instruct-32b","score":67.8,"metric":"percent"},{"benchmark":"aime-2024","model":"apertus-70b-instruct","score":0.31,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-32b","score":27.9,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-vl-32b-instruct","score":75.4,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3.1-instruct-32b-sft","score":8.2,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3.1-instruct-32b-dpo","score":23.3,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3.1-instruct-32b","score":57.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b","score":21.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-32b-instruct","score":64.2,"metric":"percent"},{"benchmark":"omega","model":"olmo-3.1-instruct-32b-sft","score":15.5,"metric":"percent"},{"benchmark":"omega","model":"olmo-3.1-instruct-32b-dpo","score":33.3,"metric":"percent"},{"benchmark":"omega","model":"olmo-3.1-instruct-32b","score":42.2,"metric":"percent"},{"benchmark":"omega","model":"apertus-70b-instruct","score":5.6,"metric":"percent"},{"benchmark":"omega","model":"qwen3-32b","score":23.4,"metric":"percent"},{"benchmark":"omega","model":"qwen3-vl-32b-instruct","score":44,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3.1-instruct-32b-sft","score":69,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3.1-instruct-32b-dpo","score":82.1,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3.1-instruct-32b","score":84,"metric":"percent"},{"benchmark":"bbh","model":"apertus-70b-instruct","score":57,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-32b","score":80.4,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-vl-32b-instruct","score":89,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3.1-instruct-32b-sft","score":30.6,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3.1-instruct-32b-dpo","score":51.1,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3.1-instruct-32b","score":61.7,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-32b","score":28.4,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-vl-32b-instruct","score":86.7,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3.1-instruct-32b-sft","score":71.7,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3.1-instruct-32b-dpo","score":79.4,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3.1-instruct-32b","score":79.5,"metric":"percent"},{"benchmark":"agieval","model":"apertus-70b-instruct","score":61.6,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-32b","score":82.4,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-vl-32b-instruct","score":89.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3.1-instruct-32b-sft","score":80.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3.1-instruct-32b-dpo","score":85.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3.1-instruct-32b","score":86.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-32b","score":83.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-vl-32b-instruct","score":89.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3.1-instruct-32b-sft","score":61.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3.1-instruct-32b-dpo","score":63.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3.1-instruct-32b","score":65.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"apertus-70b-instruct","score":45.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-32b","score":67.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-vl-32b-instruct","score":69,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3.1-instruct-32b-sft","score":35.4,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3.1-instruct-32b-dpo","score":49.6,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3.1-instruct-32b","score":54.7,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"apertus-70b-instruct","score":9.7,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-32b","score":57.5,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-vl-32b-instruct","score":70.2,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3.1-instruct-32b-sft","score":87.7,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3.1-instruct-32b-dpo","score":87.3,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3.1-instruct-32b","score":88.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-32b","score":87.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-32b-instruct","score":88.1,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3.1-instruct-32b-sft","score":29.7,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3.1-instruct-32b-dpo","score":36.3,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3.1-instruct-32b","score":39.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-32b","score":31.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-vl-32b-instruct","score":37.2,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3.1-instruct-32b-sft","score":79,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3.1-instruct-32b-dpo","score":81.9,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3.1-instruct-32b","score":80.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-32b","score":85.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-32b-instruct","score":88.7,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3.1-instruct-32b-sft","score":23.7,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3.1-instruct-32b-dpo","score":28.5,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3.1-instruct-32b","score":25,"metric":"percent"},{"benchmark":"popqa","model":"apertus-70b-instruct","score":33.5,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-32b","score":25.9,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-vl-32b-instruct","score":25.7,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3.1-instruct-32b-sft","score":41.3,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3.1-instruct-32b-dpo","score":47.9,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3.1-instruct-32b","score":48.6,"metric":"percent"},{"benchmark":"gpqa","model":"apertus-70b-instruct","score":27.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b","score":54.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-vl-32b-instruct","score":61.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3.1-instruct-32b-sft","score":42.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3.1-instruct-32b-dpo","score":69.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3.1-instruct-32b","score":59.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"apertus-70b-instruct","score":19.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-32b","score":67.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-vl-32b-instruct","score":84.3,"metric":"percent"},{"benchmark":"math","model":"olmo-3.1-think-32b","score":96.2,"metric":"percent"},{"benchmark":"math","model":"qwen3-32b-thinking","score":95.4,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3.1-think-32b","score":80.6,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-32b-thinking","score":80.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b-thinking","score":70.9,"metric":"percent"},{"benchmark":"omega","model":"olmo-3.1-think-32b","score":53.4,"metric":"percent"},{"benchmark":"omega","model":"qwen3-32b-thinking","score":47.7,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3.1-think-32b","score":88.6,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-32b-thinking","score":90.6,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-32b-thinking","score":88.3,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3.1-think-32b","score":89.2,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-32b-thinking","score":90,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-32b-thinking","score":91.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3.1-think-32b","score":68.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-32b-thinking","score":70.6,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3.1-think-32b","score":83.3,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-32b-thinking","score":90.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-32b-thinking","score":86.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-32b-thinking","score":37.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-32b-thinking","score":88.8,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3.1-think-32b","score":30.9,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-32b-thinking","score":30.7,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3.1-think-32b","score":57.5,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b-thinking","score":67.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3.1-think-32b","score":69.1,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-32b-thinking","score":75.6,"metric":"percent"},{"benchmark":"math","model":"olmo-hybrid-instruct-7b-sft","score":66.7,"metric":"percent"},{"benchmark":"math","model":"olmo-hybrid-instruct-7b-dpo","score":72.9,"metric":"percent"},{"benchmark":"math","model":"olmo-3-7b-sft","score":65.1,"metric":"percent"},{"benchmark":"math","model":"olmo-3-instruct-7b-dpo","score":79.6,"metric":"percent"},{"benchmark":"math","model":"olmo-3-instruct-7b","score":87.3,"metric":"percent"},{"benchmark":"math","model":"qwen3-8b","score":82.3,"metric":"percent"},{"benchmark":"math","model":"qwen3-vl-8b-instruct","score":91.6,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-7b-instruct","score":71,"metric":"percent"},{"benchmark":"math","model":"olmo-2-1124-7b-instruct","score":30.1,"metric":"percent"},{"benchmark":"math","model":"granite-3.3-8b-instruct","score":67.3,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-hybrid-instruct-7b-sft","score":6.7,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-hybrid-instruct-7b-dpo","score":10.1,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-7b-sft","score":6.7,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-instruct-7b-dpo","score":23.5,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-instruct-7b","score":44.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-8b","score":26.2,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-vl-8b-instruct","score":55.1,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-7b-instruct","score":11.3,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-2-1124-7b-instruct","score":1.3,"metric":"percent"},{"benchmark":"aime-2024","model":"granite-3.3-8b-instruct","score":7.3,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-hybrid-instruct-7b-sft","score":8.8,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-hybrid-instruct-7b-dpo","score":10.2,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-instruct-7b-dpo","score":20.4,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-instruct-7b","score":32.5,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b","score":21.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-8b-instruct","score":43.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen2.5-7b-instruct","score":6.3,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-2-1124-7b-instruct","score":0.4,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-3.3-8b-instruct","score":6.3,"metric":"percent"},{"benchmark":"omega","model":"olmo-hybrid-instruct-7b-sft","score":16,"metric":"percent"},{"benchmark":"omega","model":"olmo-hybrid-instruct-7b-dpo","score":19.5,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-7b-sft","score":14.4,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-instruct-7b-dpo","score":22.8,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-instruct-7b","score":28.9,"metric":"percent"},{"benchmark":"omega","model":"qwen3-8b","score":20.5,"metric":"percent"},{"benchmark":"omega","model":"qwen3-vl-8b-instruct","score":32.3,"metric":"percent"},{"benchmark":"omega","model":"qwen2.5-7b-instruct","score":13.7,"metric":"percent"},{"benchmark":"omega","model":"olmo-2-1124-7b-instruct","score":5.2,"metric":"percent"},{"benchmark":"omega","model":"granite-3.3-8b-instruct","score":10.7,"metric":"percent"},{"benchmark":"bbh","model":"olmo-hybrid-instruct-7b-sft","score":47.3,"metric":"percent"},{"benchmark":"bbh","model":"olmo-hybrid-instruct-7b-dpo","score":57.3,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-7b-sft","score":51,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-instruct-7b-dpo","score":69.3,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-instruct-7b","score":71.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-8b","score":73.7,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-vl-8b-instruct","score":85.6,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-7b-instruct","score":68.8,"metric":"percent"},{"benchmark":"bbh","model":"olmo-2-1124-7b-instruct","score":43.8,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.3-8b-instruct","score":61.2,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-hybrid-instruct-7b-sft","score":17,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-hybrid-instruct-7b-dpo","score":29.1,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-7b-sft","score":18,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-instruct-7b-dpo","score":28.4,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-instruct-7b","score":32.9,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-8b","score":25.4,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-vl-8b-instruct","score":64.3,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen2.5-7b-instruct","score":10.7,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-2-1124-7b-instruct","score":5.3,"metric":"percent"},{"benchmark":"zebralogic","model":"granite-3.3-8b-instruct","score":17.6,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-7b-sft","score":59.2,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-instruct-7b-dpo","score":64,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-instruct-7b","score":64.4,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-8b","score":76,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-vl-8b-instruct","score":84.5,"metric":"percent"},{"benchmark":"agieval","model":"qwen2.5-7b-instruct","score":69.8,"metric":"percent"},{"benchmark":"agieval","model":"olmo-2-1124-7b-instruct","score":56.1,"metric":"percent"},{"benchmark":"agieval","model":"granite-3.3-8b-instruct","score":64,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-hybrid-instruct-7b-sft","score":69.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-hybrid-instruct-7b-dpo","score":75.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-instruct-7b-dpo","score":72.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-instruct-7b","score":77.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-8b","score":79.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-vl-8b-instruct","score":82.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-7b-instruct","score":74.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-2-1124-7b-instruct","score":25.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-3.3-8b-instruct","score":64,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-hybrid-instruct-7b-sft","score":55.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-hybrid-instruct-7b-dpo","score":56.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-instruct-7b-dpo","score":55.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-instruct-7b","score":60.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-8b","score":64.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-vl-8b-instruct","score":66.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-7b-instruct","score":62.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-2-1124-7b-instruct","score":40.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"granite-3.3-8b-instruct","score":54,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-hybrid-instruct-7b-sft","score":21.3,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-hybrid-instruct-7b-dpo","score":22,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-7b-sft","score":20,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-instruct-7b-dpo","score":18.8,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-instruct-7b","score":29.5,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-8b","score":53.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-vl-8b-instruct","score":55.9,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen2.5-7b-instruct","score":34.5,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-2-1124-7b-instruct","score":7.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"granite-3.3-8b-instruct","score":11.5,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-hybrid-instruct-7b-sft","score":81.5,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-hybrid-instruct-7b-dpo","score":80.5,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-7b-sft","score":81.7,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-instruct-7b-dpo","score":82,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-instruct-7b","score":85.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-8b","score":86.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-8b-instruct","score":87.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-7b-instruct","score":73.4,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-2-1124-7b-instruct","score":72.2,"metric":"percent"},{"benchmark":"ifeval","model":"granite-3.3-8b-instruct","score":77.5,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-hybrid-instruct-7b-sft","score":29,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-hybrid-instruct-7b-dpo","score":33.3,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-7b-sft","score":27.4,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-instruct-7b-dpo","score":29.3,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-instruct-7b","score":32.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-8b","score":29.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-vl-8b-instruct","score":34,"metric":"percent"},{"benchmark":"ifbench","model":"qwen2.5-7b-instruct","score":28.4,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-2-1124-7b-instruct","score":26.7,"metric":"percent"},{"benchmark":"ifbench","model":"granite-3.3-8b-instruct","score":22.3,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-hybrid-instruct-7b-sft","score":71.9,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-hybrid-instruct-7b-dpo","score":73.6,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-7b-sft","score":67.1,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-instruct-7b-dpo","score":69.1,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-instruct-7b","score":69.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b","score":80.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-8b-instruct","score":83.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-7b-instruct","score":77.2,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-2-1124-7b-instruct","score":61.6,"metric":"percent"},{"benchmark":"mmlu","model":"granite-3.3-8b-instruct","score":63.5,"metric":"percent"},{"benchmark":"popqa","model":"olmo-hybrid-instruct-7b-sft","score":16.8,"metric":"percent"},{"benchmark":"popqa","model":"olmo-hybrid-instruct-7b-dpo","score":21,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-7b-sft","score":16.5,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-instruct-7b-dpo","score":20.7,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-instruct-7b","score":14.1,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-8b","score":20.4,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-vl-8b-instruct","score":26.5,"metric":"percent"},{"benchmark":"popqa","model":"qwen2.5-7b-instruct","score":21.5,"metric":"percent"},{"benchmark":"popqa","model":"olmo-2-1124-7b-instruct","score":25.5,"metric":"percent"},{"benchmark":"popqa","model":"granite-3.3-8b-instruct","score":28.9,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-hybrid-instruct-7b-sft","score":36.8,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-hybrid-instruct-7b-dpo","score":38,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-7b-sft","score":30,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-instruct-7b-dpo","score":37.9,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-instruct-7b","score":40.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-8b","score":44.6,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-vl-8b-instruct","score":51.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-7b-instruct","score":35.6,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-2-1124-7b-instruct","score":31.3,"metric":"percent"},{"benchmark":"gpqa","model":"granite-3.3-8b-instruct","score":33,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-hybrid-instruct-7b-sft","score":25.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-hybrid-instruct-7b-dpo","score":56.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-7b-sft","score":21.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-instruct-7b-dpo","score":43.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-instruct-7b","score":40.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-8b","score":49.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-vl-8b-instruct","score":73.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen2.5-7b-instruct","score":23,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-2-1124-7b-instruct","score":18.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-3.3-8b-instruct","score":28.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"olmo-3-instruct-7b-dpo","score":49.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"olmo-3-instruct-7b","score":49.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-vl-8b-instruct","score":66.2,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen2.5-7b-instruct","score":55.8,"metric":"percent"},{"benchmark":"math","model":"olmo-hybrid-think-7b-sft","score":93.8,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-7b-sft","score":94.4,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-7b-dpo","score":92.4,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-7b","score":95.1,"metric":"percent"},{"benchmark":"math","model":"nvidia-nemotron-nano-9b-v2","score":94.4,"metric":"percent"},{"benchmark":"math","model":"deepseek-r1-distill-qwen-7b","score":87.9,"metric":"percent"},{"benchmark":"math","model":"qwen3-8b-thinking","score":95.1,"metric":"percent"},{"benchmark":"math","model":"qwen3-vl-8b-thinking","score":95.2,"metric":"percent"},{"benchmark":"math","model":"openreasoning-nemotron-7b","score":94.6,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-hybrid-think-7b-sft","score":66.2,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-7b-sft","score":69.6,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-7b-dpo","score":74.6,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-7b","score":71.6,"metric":"percent"},{"benchmark":"aime-2024","model":"nvidia-nemotron-nano-9b-v2","score":72.1,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-distill-qwen-7b","score":54.9,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-8b-thinking","score":74,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-vl-8b-thinking","score":70.9,"metric":"percent"},{"benchmark":"aime-2024","model":"openreasoning-nemotron-7b","score":77,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-hybrid-think-7b-sft","score":55.2,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-7b-sft","score":57.6,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-7b-dpo","score":62.7,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-7b","score":64.6,"metric":"percent"},{"benchmark":"aime-2025","model":"nvidia-nemotron-nano-9b-v2","score":58.9,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-distill-qwen-7b","score":40.2,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b-thinking","score":67.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-8b-thinking","score":61.5,"metric":"percent"},{"benchmark":"aime-2025","model":"openreasoning-nemotron-7b","score":73.1,"metric":"percent"},{"benchmark":"omega","model":"olmo-hybrid-think-7b-sft","score":35.1,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-think-7b-sft","score":45,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-think-7b-dpo","score":40.5,"metric":"percent"},{"benchmark":"omega","model":"olmo-3-think-7b","score":37.8,"metric":"percent"},{"benchmark":"omega","model":"nvidia-nemotron-nano-9b-v2","score":42.4,"metric":"percent"},{"benchmark":"omega","model":"deepseek-r1-distill-qwen-7b","score":28.5,"metric":"percent"},{"benchmark":"omega","model":"qwen3-8b-thinking","score":43.4,"metric":"percent"},{"benchmark":"omega","model":"qwen3-vl-8b-thinking","score":38.1,"metric":"percent"},{"benchmark":"omega","model":"openreasoning-nemotron-7b","score":43.2,"metric":"percent"},{"benchmark":"bbh","model":"olmo-hybrid-think-7b-sft","score":84.6,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-7b-sft","score":84.1,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-7b-dpo","score":83.7,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-7b","score":86.6,"metric":"percent"},{"benchmark":"bbh","model":"nvidia-nemotron-nano-9b-v2","score":86.2,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-r1-distill-qwen-7b","score":73.5,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-8b-thinking","score":84.4,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-vl-8b-thinking","score":86.8,"metric":"percent"},{"benchmark":"bbh","model":"openreasoning-nemotron-7b","score":81.3,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-hybrid-think-7b-sft","score":55.1,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-think-7b-sft","score":57.9,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-think-7b-dpo","score":60.6,"metric":"percent"},{"benchmark":"zebralogic","model":"olmo-3-think-7b","score":66.5,"metric":"percent"},{"benchmark":"zebralogic","model":"nvidia-nemotron-nano-9b-v2","score":60.8,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-r1-distill-qwen-7b","score":26.1,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-8b-thinking","score":85.2,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen3-vl-8b-thinking","score":91.2,"metric":"percent"},{"benchmark":"zebralogic","model":"openreasoning-nemotron-7b","score":22.4,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-think-7b-sft","score":77.2,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-think-7b-dpo","score":79.1,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-think-7b","score":81.5,"metric":"percent"},{"benchmark":"agieval","model":"nvidia-nemotron-nano-9b-v2","score":83.1,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-r1-distill-qwen-7b","score":69.5,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-8b-thinking","score":87,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-vl-8b-thinking","score":90.1,"metric":"percent"},{"benchmark":"agieval","model":"openreasoning-nemotron-7b","score":81.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-hybrid-think-7b-sft","score":86.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-7b-sft","score":88.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-7b-dpo","score":91.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-7b","score":89.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"nvidia-nemotron-nano-9b-v2","score":89.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-r1-distill-qwen-7b","score":83,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-8b-thinking","score":80.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-vl-8b-thinking","score":83.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"openreasoning-nemotron-7b","score":89.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-hybrid-think-7b-sft","score":63.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-7b-sft","score":63.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-7b-dpo","score":63,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-7b","score":64.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"nvidia-nemotron-nano-9b-v2","score":66.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-r1-distill-qwen-7b","score":63.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-8b-thinking","score":69.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-vl-8b-thinking","score":63,"metric":"percent"},{"benchmark":"mbpp-plus","model":"openreasoning-nemotron-7b","score":61.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-hybrid-think-7b-sft","score":65.5,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-think-7b-sft","score":67.8,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-think-7b-dpo","score":75.1,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"olmo-3-think-7b","score":75.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"nvidia-nemotron-nano-9b-v2","score":83.4,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"deepseek-r1-distill-qwen-7b","score":58.8,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-8b-thinking","score":86.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen3-vl-8b-thinking","score":85.5,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"openreasoning-nemotron-7b","score":82.3,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-hybrid-think-7b-sft","score":80.4,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-7b-sft","score":77.9,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-7b-dpo","score":75.9,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-7b","score":88.2,"metric":"percent"},{"benchmark":"ifeval","model":"nvidia-nemotron-nano-9b-v2","score":86,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-r1-distill-qwen-7b","score":59.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-8b-thinking","score":87.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-8b-thinking","score":85.5,"metric":"percent"},{"benchmark":"ifeval","model":"openreasoning-nemotron-7b","score":42.5,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-hybrid-think-7b-sft","score":31.6,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-think-7b-sft","score":30,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-think-7b-dpo","score":28.3,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-think-7b","score":41.6,"metric":"percent"},{"benchmark":"ifbench","model":"nvidia-nemotron-nano-9b-v2","score":34.6,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-r1-distill-qwen-7b","score":16.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-8b-thinking","score":37.1,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-vl-8b-thinking","score":40.4,"metric":"percent"},{"benchmark":"ifbench","model":"openreasoning-nemotron-7b","score":23.4,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-hybrid-think-7b-sft","score":80.5,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-7b-sft","score":74.9,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-7b-dpo","score":74.8,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-7b","score":77.8,"metric":"percent"},{"benchmark":"mmlu","model":"nvidia-nemotron-nano-9b-v2","score":84.3,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-r1-distill-qwen-7b","score":67.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b-thinking","score":85.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-8b-thinking","score":86.5,"metric":"percent"},{"benchmark":"mmlu","model":"openreasoning-nemotron-7b","score":80.7,"metric":"percent"},{"benchmark":"popqa","model":"olmo-hybrid-think-7b-sft","score":25.1,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-think-7b-sft","score":20.8,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-think-7b-dpo","score":24.7,"metric":"percent"},{"benchmark":"popqa","model":"olmo-3-think-7b","score":23.7,"metric":"percent"},{"benchmark":"popqa","model":"nvidia-nemotron-nano-9b-v2","score":17.9,"metric":"percent"},{"benchmark":"popqa","model":"deepseek-r1-distill-qwen-7b","score":12.8,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-8b-thinking","score":24.3,"metric":"percent"},{"benchmark":"popqa","model":"qwen3-vl-8b-thinking","score":29.3,"metric":"percent"},{"benchmark":"popqa","model":"openreasoning-nemotron-7b","score":14.5,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-hybrid-think-7b-sft","score":47,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-7b-sft","score":45.8,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-7b-dpo","score":48.6,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-7b","score":46.2,"metric":"percent"},{"benchmark":"gpqa","model":"nvidia-nemotron-nano-9b-v2","score":56.2,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-r1-distill-qwen-7b","score":54.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-8b-thinking","score":57.7,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-vl-8b-thinking","score":61.5,"metric":"percent"},{"benchmark":"gpqa","model":"openreasoning-nemotron-7b","score":56.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-hybrid-think-7b-sft","score":49,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-think-7b-sft","score":43.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-think-7b-dpo","score":50.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-think-7b","score":52.1,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"nvidia-nemotron-nano-9b-v2","score":58,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-r1-distill-qwen-7b","score":7.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-8b-thinking","score":60.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3-vl-8b-thinking","score":73.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"openreasoning-nemotron-7b","score":8.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"olmo-2-1124-7b","score":8.8,"metric":"pass@1"},{"benchmark":"humaneval","model":"olmo-2-1124-7b","score":16.3,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-2-1124-7b","score":21.2,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"olmo-2-1124-7b","score":4.2,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"olmo-2-1124-7b","score":12.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"olmo-2-1124-7b","score":53.2,"metric":"percent"},{"benchmark":"medqa","model":"olmo-2-1124-7b","score":43.8,"metric":"percent"},{"benchmark":"sciq","model":"olmo-2-1124-7b","score":90.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-2-1124-7b","score":72,"metric":"percent"},{"benchmark":"piqa","model":"olmo-2-1124-7b","score":80.1,"metric":"percent"},{"benchmark":"socialiqa","model":"olmo-2-1124-7b","score":77.5,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-2-1124-7b","score":82.2,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-2-1124-7b","score":87.4,"metric":"percent"},{"benchmark":"lambada","model":"olmo-2-1124-7b","score":70.5,"metric":"percent"},{"benchmark":"drop","model":"olmo-2-1124-7b","score":61.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"olmo-2-1124-7b","score":37.4,"metric":"percent"},{"benchmark":"squad-v1.1","model":"olmo-2-1124-7b","score":91.5,"metric":"percent"},{"benchmark":"bbh","model":"olmo-2-1124-7b","score":49.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-2-1124-7b","score":33.1,"metric":"percent"},{"benchmark":"deepmind-math","model":"olmo-2-1124-7b","score":16.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-8b-base","score":42.5,"metric":"pass@1"},{"benchmark":"humaneval","model":"qwen3-8b-base","score":71.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-8b-base","score":66.2,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"qwen3-8b-base","score":52.3,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"qwen3-8b-base","score":48.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen3-8b-base","score":76.7,"metric":"percent"},{"benchmark":"medqa","model":"qwen3-8b-base","score":62.1,"metric":"percent"},{"benchmark":"sciq","model":"qwen3-8b-base","score":96.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen3-8b-base","score":84.1,"metric":"percent"},{"benchmark":"piqa","model":"qwen3-8b-base","score":89.9,"metric":"percent"},{"benchmark":"socialiqa","model":"qwen3-8b-base","score":83.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-8b-base","score":80.5,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3-8b-base","score":86.4,"metric":"percent"},{"benchmark":"lambada","model":"qwen3-8b-base","score":73,"metric":"percent"},{"benchmark":"drop","model":"qwen3-8b-base","score":57.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen3-8b-base","score":33.8,"metric":"percent"},{"benchmark":"squad-v1.1","model":"qwen3-8b-base","score":89.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-8b-base","score":76.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b-base","score":50.3,"metric":"percent"},{"benchmark":"deepmind-math","model":"qwen3-8b-base","score":47.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"gemma-2-9b","score":30.9,"metric":"pass@1"},{"benchmark":"humaneval","model":"gemma-2-9b","score":40,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-9b","score":49.1,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"gemma-2-9b","score":27.9,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"gemma-2-9b","score":38.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-2-9b","score":62.8,"metric":"percent"},{"benchmark":"medqa","model":"gemma-2-9b","score":55.4,"metric":"percent"},{"benchmark":"sciq","model":"gemma-2-9b","score":94.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"gemma-2-9b","score":75.3,"metric":"percent"},{"benchmark":"piqa","model":"gemma-2-9b","score":85.7,"metric":"percent"},{"benchmark":"socialiqa","model":"gemma-2-9b","score":80.3,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2-9b","score":81.8,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-2-9b","score":88.8,"metric":"percent"},{"benchmark":"lambada","model":"gemma-2-9b","score":76.3,"metric":"percent"},{"benchmark":"drop","model":"gemma-2-9b","score":68.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"gemma-2-9b","score":40.4,"metric":"percent"},{"benchmark":"squad-v1.1","model":"gemma-2-9b","score":88.8,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-9b","score":68.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-9b","score":44.7,"metric":"percent"},{"benchmark":"deepmind-math","model":"gemma-2-9b","score":23,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-7b","score":39.7,"metric":"pass@1"},{"benchmark":"humaneval","model":"qwen2.5-7b","score":66.1,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-7b","score":55.4,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"qwen2.5-7b","score":40.3,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"qwen2.5-7b","score":45.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-7b","score":67.6,"metric":"percent"},{"benchmark":"medqa","model":"qwen2.5-7b","score":56.6,"metric":"percent"},{"benchmark":"sciq","model":"qwen2.5-7b","score":95.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen2.5-7b","score":85,"metric":"percent"},{"benchmark":"piqa","model":"qwen2.5-7b","score":88.5,"metric":"percent"},{"benchmark":"socialiqa","model":"qwen2.5-7b","score":82.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-7b","score":81,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-7b","score":86,"metric":"percent"},{"benchmark":"lambada","model":"qwen2.5-7b","score":70.3,"metric":"percent"},{"benchmark":"drop","model":"qwen2.5-7b","score":56.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen2.5-7b","score":31.2,"metric":"percent"},{"benchmark":"squad-v1.1","model":"qwen2.5-7b","score":87,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-7b","score":54.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-7b","score":48.1,"metric":"percent"},{"benchmark":"deepmind-math","model":"qwen2.5-7b","score":32.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"llama-3.1-8b-base","score":30.7,"metric":"pass@1"},{"benchmark":"humaneval","model":"llama-3.1-8b-base","score":40.4,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-8b-base","score":12.1,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"llama-3.1-8b-base","score":14.5,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"llama-3.1-8b-base","score":28.3,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.1-8b-base","score":55.7,"metric":"percent"},{"benchmark":"medqa","model":"llama-3.1-8b-base","score":53.7,"metric":"percent"},{"benchmark":"sciq","model":"llama-3.1-8b-base","score":92.7,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-3.1-8b-base","score":72.9,"metric":"percent"},{"benchmark":"piqa","model":"llama-3.1-8b-base","score":78.3,"metric":"percent"},{"benchmark":"socialiqa","model":"llama-3.1-8b-base","score":77,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-8b-base","score":81.5,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.1-8b-base","score":87.3,"metric":"percent"},{"benchmark":"lambada","model":"llama-3.1-8b-base","score":75.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-3.1-8b-base","score":36.7,"metric":"percent"},{"benchmark":"squad-v1.1","model":"llama-3.1-8b-base","score":89.2,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-8b-base","score":63,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b-base","score":37.4,"metric":"percent"},{"benchmark":"deepmind-math","model":"llama-3.1-8b-base","score":24.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"granite-3.3-8b-base","score":0.4,"metric":"pass@1"},{"benchmark":"humaneval","model":"granite-3.3-8b-base","score":0,"metric":"percent"},{"benchmark":"mbpp","model":"granite-3.3-8b-base","score":48.5,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"granite-3.3-8b-base","score":22.3,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"granite-3.3-8b-base","score":32.3,"metric":"percent"},{"benchmark":"mmlu-stem","model":"granite-3.3-8b-base","score":55.6,"metric":"percent"},{"benchmark":"medqa","model":"granite-3.3-8b-base","score":43,"metric":"percent"},{"benchmark":"sciq","model":"granite-3.3-8b-base","score":90.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"granite-3.3-8b-base","score":82.3,"metric":"percent"},{"benchmark":"piqa","model":"granite-3.3-8b-base","score":81.5,"metric":"percent"},{"benchmark":"socialiqa","model":"granite-3.3-8b-base","score":83.1,"metric":"percent"},{"benchmark":"hellaswag","model":"granite-3.3-8b-base","score":83.7,"metric":"percent"},{"benchmark":"winogrande","model":"granite-3.3-8b-base","score":89.4,"metric":"percent"},{"benchmark":"lambada","model":"granite-3.3-8b-base","score":76,"metric":"percent"},{"benchmark":"drop","model":"granite-3.3-8b-base","score":38.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"granite-3.3-8b-base","score":37,"metric":"percent"},{"benchmark":"squad-v1.1","model":"granite-3.3-8b-base","score":89.6,"metric":"percent"},{"benchmark":"bbh","model":"granite-3.3-8b-base","score":61.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.3-8b-base","score":33.9,"metric":"percent"},{"benchmark":"deepmind-math","model":"granite-3.3-8b-base","score":32.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"olmo-3-7b","score":34.1,"metric":"pass@1"},{"benchmark":"humaneval","model":"olmo-3-7b","score":49.1,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3-7b","score":43.6,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"olmo-3-7b","score":28.7,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"olmo-3-7b","score":38.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"olmo-3-7b","score":59.7,"metric":"percent"},{"benchmark":"medqa","model":"olmo-3-7b","score":41.8,"metric":"percent"},{"benchmark":"sciq","model":"olmo-3-7b","score":92.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-3-7b","score":75.3,"metric":"percent"},{"benchmark":"piqa","model":"olmo-3-7b","score":80.2,"metric":"percent"},{"benchmark":"socialiqa","model":"olmo-3-7b","score":80.3,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-7b","score":77.7,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-3-7b","score":85.7,"metric":"percent"},{"benchmark":"lambada","model":"olmo-3-7b","score":68.9,"metric":"percent"},{"benchmark":"drop","model":"olmo-3-7b","score":71.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"olmo-3-7b","score":32.6,"metric":"percent"},{"benchmark":"squad-v1.1","model":"olmo-3-7b","score":93.5,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-7b","score":63.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3-7b","score":37.3,"metric":"percent"},{"benchmark":"deepmind-math","model":"olmo-3-7b","score":23.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"olmo-hybrid-7b","score":35.1,"metric":"pass@1"},{"benchmark":"humaneval","model":"olmo-hybrid-7b","score":49,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-hybrid-7b","score":50.3,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"olmo-hybrid-7b","score":29.4,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"olmo-hybrid-7b","score":39.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"olmo-hybrid-7b","score":64.6,"metric":"percent"},{"benchmark":"medqa","model":"olmo-hybrid-7b","score":48.7,"metric":"percent"},{"benchmark":"sciq","model":"olmo-hybrid-7b","score":93.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-hybrid-7b","score":78.4,"metric":"percent"},{"benchmark":"piqa","model":"olmo-hybrid-7b","score":82.7,"metric":"percent"},{"benchmark":"socialiqa","model":"olmo-hybrid-7b","score":81.1,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-hybrid-7b","score":79,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-hybrid-7b","score":86.2,"metric":"percent"},{"benchmark":"lambada","model":"olmo-hybrid-7b","score":70.2,"metric":"percent"},{"benchmark":"drop","model":"olmo-hybrid-7b","score":72.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"olmo-hybrid-7b","score":34.8,"metric":"percent"},{"benchmark":"squad-v1.1","model":"olmo-hybrid-7b","score":92.1,"metric":"percent"},{"benchmark":"bbh","model":"olmo-hybrid-7b","score":65.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-hybrid-7b","score":41.7,"metric":"percent"},{"benchmark":"deepmind-math","model":"olmo-hybrid-7b","score":23.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"sera-8b-ga","score":31.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"sera-8b","score":31.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-32b","score":24.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"frogboss-32b-2510","score":35,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.7-flash","score":37.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-30b-a3b-instruct","score":45,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-dev-72b","score":48.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"devstral-small-2","score":50,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.5-air","score":50.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.6","score":60.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"sera-32b-ga","score":46.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"sera-32b","score":49.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"swe-smith-lm-32b","score":32.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"sera-14b","score":41.7,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"qwen3.5-2b","score":5.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-2b","score":1.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-2b","score":2.3,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"tmax-2b","score":11.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"tmax-2b","score":4.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"tmax-2b","score":2.9,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"qwen3.5-4b","score":31.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-4b","score":14.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-4b","score":16.6,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"tmax-4b","score":42.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"tmax-4b","score":19.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"tmax-4b","score":18.9,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"qwen3.5-9b","score":41.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-9b","score":16.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-9b","score":21.1,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"tmax-9b","score":57.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"tmax-9b","score":28.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"tmax-9b","score":27.2,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"qwen3.6-27b","score":70.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-27b","score":40.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.6-27b","score":39.6,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"tmax-27b","score":68.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"tmax-27b","score":44.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"tmax-27b","score":42.7,"metric":"percent"},{"benchmark":"webvoyager","model":"ui-tars-1.5-7b","score":66.4,"metric":"percent"},{"benchmark":"online-mind2web","model":"ui-tars-1.5-7b","score":31.3,"metric":"percent"},{"benchmark":"deepshop","model":"ui-tars-1.5-7b","score":11.6,"metric":"percent"},{"benchmark":"webtailbench","model":"ui-tars-1.5-7b","score":19.5,"metric":"percent"},{"benchmark":"webvoyager","model":"glm-4.1v-9b-thinking","score":66.8,"metric":"percent"},{"benchmark":"online-mind2web","model":"glm-4.1v-9b-thinking","score":33.9,"metric":"percent"},{"benchmark":"deepshop","model":"glm-4.1v-9b-thinking","score":32,"metric":"percent"},{"benchmark":"webtailbench","model":"glm-4.1v-9b-thinking","score":22.4,"metric":"percent"},{"benchmark":"webvoyager","model":"fara-7b","score":73.5,"metric":"percent"},{"benchmark":"online-mind2web","model":"fara-7b","score":34.1,"metric":"percent"},{"benchmark":"deepshop","model":"fara-7b","score":26.2,"metric":"percent"},{"benchmark":"webtailbench","model":"fara-7b","score":38.4,"metric":"percent"},{"benchmark":"webvoyager","model":"holo1-7b","score":55.4,"metric":"percent"},{"benchmark":"webvoyager","model":"molmoweb-4b","score":75.2,"metric":"percent"},{"benchmark":"online-mind2web","model":"molmoweb-4b","score":31.3,"metric":"percent"},{"benchmark":"deepshop","model":"molmoweb-4b","score":35.6,"metric":"percent"},{"benchmark":"webtailbench","model":"molmoweb-4b","score":43.8,"metric":"percent"},{"benchmark":"webvoyager","model":"molmoweb-8b","score":78.2,"metric":"percent"},{"benchmark":"online-mind2web","model":"molmoweb-8b","score":35.3,"metric":"percent"},{"benchmark":"deepshop","model":"molmoweb-8b","score":42.3,"metric":"percent"},{"benchmark":"webtailbench","model":"molmoweb-8b","score":49.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"claude-3.7-sonnet","score":87.6,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gemini-3-pro","score":93.7,"metric":"percent"},{"benchmark":"screenspot","model":"qwen2.5-vl-7b","score":85.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen2.5-vl-7b","score":89.3,"metric":"percent"},{"benchmark":"screenspot","model":"holo1-7b","score":87.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo1-7b","score":89.9,"metric":"percent"},{"benchmark":"screenspot","model":"fara-7b","score":86.7,"metric":"percent"},{"benchmark":"screenspot-v2","model":"fara-7b","score":89.3,"metric":"percent"},{"benchmark":"screenspot","model":"molmoweb-4b","score":87.2,"metric":"percent"},{"benchmark":"screenspot-v2","model":"molmoweb-4b","score":89.5,"metric":"percent"},{"benchmark":"point-bench","model":"gemini-robotics-er-1.5-thinking","score":71.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-robotics-er-1.5-thinking","score":48.5,"metric":"percent"},{"benchmark":"where2place","model":"gemini-robotics-er-1.5-thinking","score":59,"metric":"percent"},{"benchmark":"blink","model":"gemini-robotics-er-1.5-thinking","score":57.8,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-robotics-er-1.5-thinking","score":84.3,"metric":"percent"},{"benchmark":"erqa","model":"gemini-robotics-er-1.5-thinking","score":54.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-robotics-er-1.5-thinking","score":78.4,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-robotics-er-1.5-thinking","score":54.7,"metric":"percent"},{"benchmark":"sat","model":"gemini-robotics-er-1.5-thinking","score":76.7,"metric":"percent"},{"benchmark":"openeqa","model":"gemini-robotics-er-1.5-thinking","score":55,"metric":"percent"},{"benchmark":"vsi-bench","model":"gemini-robotics-er-1.5-thinking","score":45.8,"metric":"percent"},{"benchmark":"point-bench","model":"gemini-robotics-er-1.5","score":73.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-robotics-er-1.5","score":41.8,"metric":"percent"},{"benchmark":"where2place","model":"gemini-robotics-er-1.5","score":48,"metric":"percent"},{"benchmark":"blink","model":"gemini-robotics-er-1.5","score":65.2,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-robotics-er-1.5","score":83.6,"metric":"percent"},{"benchmark":"erqa","model":"gemini-robotics-er-1.5","score":47,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-robotics-er-1.5","score":73.4,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-robotics-er-1.5","score":47.7,"metric":"percent"},{"benchmark":"sat","model":"gemini-robotics-er-1.5","score":62,"metric":"percent"},{"benchmark":"openeqa","model":"gemini-robotics-er-1.5","score":50.5,"metric":"percent"},{"benchmark":"vsi-bench","model":"gemini-robotics-er-1.5","score":39.9,"metric":"percent"},{"benchmark":"point-bench","model":"gemini-2.5-pro","score":62.7,"metric":"percent"},{"benchmark":"where2place","model":"gemini-2.5-pro","score":37,"metric":"percent"},{"benchmark":"blink","model":"gemini-2.5-pro","score":69.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-2.5-pro","score":78,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-2.5-pro","score":59.2,"metric":"percent"},{"benchmark":"sat","model":"gemini-2.5-pro","score":74.7,"metric":"percent"},{"benchmark":"openeqa","model":"gemini-2.5-pro","score":55,"metric":"percent"},{"benchmark":"vsi-bench","model":"gemini-2.5-pro","score":51.1,"metric":"percent"},{"benchmark":"point-bench","model":"gpt-5","score":43.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5","score":23.5,"metric":"percent"},{"benchmark":"where2place","model":"gpt-5","score":37,"metric":"percent"},{"benchmark":"blink","model":"gpt-5","score":71.3,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-5","score":86.1,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5","score":59,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5","score":81.5,"metric":"percent"},{"benchmark":"mindcube","model":"gpt-5","score":58,"metric":"percent"},{"benchmark":"sat","model":"gpt-5","score":86.7,"metric":"percent"},{"benchmark":"openeqa","model":"gpt-5","score":64.4,"metric":"percent"},{"benchmark":"vsi-bench","model":"gpt-5","score":52.9,"metric":"percent"},{"benchmark":"point-bench","model":"gpt-5-mini","score":39.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5-mini","score":23,"metric":"percent"},{"benchmark":"where2place","model":"gpt-5-mini","score":33.5,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-mini","score":56.4,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-5-mini","score":85.9,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5-mini","score":57.3,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5-mini","score":78.8,"metric":"percent"},{"benchmark":"mindcube","model":"gpt-5-mini","score":55.6,"metric":"percent"},{"benchmark":"sat","model":"gpt-5-mini","score":81.3,"metric":"percent"},{"benchmark":"openeqa","model":"gpt-5-mini","score":59.2,"metric":"percent"},{"benchmark":"vsi-bench","model":"gpt-5-mini","score":46.2,"metric":"percent"},{"benchmark":"point-bench","model":"qwen3-vl-4b-instruct","score":63.8,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-4b-instruct","score":49.5,"metric":"percent"},{"benchmark":"where2place","model":"qwen3-vl-4b-instruct","score":63,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-4b-instruct","score":65.2,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-4b-instruct","score":85.8,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-4b-instruct","score":39.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-4b-instruct","score":78.1,"metric":"percent"},{"benchmark":"mindcube","model":"qwen3-vl-4b-instruct","score":27.4,"metric":"percent"},{"benchmark":"sat","model":"qwen3-vl-4b-instruct","score":60.7,"metric":"percent"},{"benchmark":"openeqa","model":"qwen3-vl-4b-instruct","score":47.6,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-4b-instruct","score":61.4,"metric":"percent"},{"benchmark":"point-bench","model":"qwen3-vl-8b-instruct","score":64.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-8b-instruct","score":47.5,"metric":"percent"},{"benchmark":"where2place","model":"qwen3-vl-8b-instruct","score":63,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-8b-instruct","score":66.6,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-8b-instruct","score":85.6,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-8b-instruct","score":41.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-8b-instruct","score":78.2,"metric":"percent"},{"benchmark":"mindcube","model":"qwen3-vl-8b-instruct","score":33.4,"metric":"percent"},{"benchmark":"sat","model":"qwen3-vl-8b-instruct","score":70,"metric":"percent"},{"benchmark":"openeqa","model":"qwen3-vl-8b-instruct","score":49.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-8b-instruct","score":63.3,"metric":"percent"},{"benchmark":"point-bench","model":"llava-onevision-7b","score":9.4,"metric":"percent"},{"benchmark":"refspatialbench","model":"llava-onevision-7b","score":3,"metric":"percent"},{"benchmark":"where2place","model":"llava-onevision-7b","score":19,"metric":"percent"},{"benchmark":"blink","model":"llava-onevision-7b","score":44.2,"metric":"percent"},{"benchmark":"cv-bench","model":"llava-onevision-7b","score":70.3,"metric":"percent"},{"benchmark":"erqa","model":"llava-onevision-7b","score":39.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"llava-onevision-7b","score":69.7,"metric":"percent"},{"benchmark":"mindcube","model":"llava-onevision-7b","score":45.6,"metric":"percent"},{"benchmark":"sat","model":"llava-onevision-7b","score":58,"metric":"percent"},{"benchmark":"openeqa","model":"llava-onevision-7b","score":36.2,"metric":"percent"},{"benchmark":"vsi-bench","model":"llava-onevision-7b","score":31.2,"metric":"percent"},{"benchmark":"point-bench","model":"internvl3.5-4b","score":43,"metric":"percent"},{"benchmark":"refspatialbench","model":"internvl3.5-4b","score":21.5,"metric":"percent"},{"benchmark":"where2place","model":"internvl3.5-4b","score":53,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-4b","score":58.7,"metric":"percent"},{"benchmark":"cv-bench","model":"internvl3.5-4b","score":80.5,"metric":"percent"},{"benchmark":"erqa","model":"internvl3.5-4b","score":37,"metric":"percent"},{"benchmark":"embspatialbench","model":"internvl3.5-4b","score":72,"metric":"percent"},{"benchmark":"mindcube","model":"internvl3.5-4b","score":42.6,"metric":"percent"},{"benchmark":"sat","model":"internvl3.5-4b","score":49.3,"metric":"percent"},{"benchmark":"openeqa","model":"internvl3.5-4b","score":44.6,"metric":"percent"},{"benchmark":"vsi-bench","model":"internvl3.5-4b","score":56.5,"metric":"percent"},{"benchmark":"point-bench","model":"internvl3.5-8b","score":45.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"internvl3.5-8b","score":35,"metric":"percent"},{"benchmark":"where2place","model":"internvl3.5-8b","score":57,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-8b","score":59.1,"metric":"percent"},{"benchmark":"cv-bench","model":"internvl3.5-8b","score":80.9,"metric":"percent"},{"benchmark":"erqa","model":"internvl3.5-8b","score":41,"metric":"percent"},{"benchmark":"embspatialbench","model":"internvl3.5-8b","score":74.7,"metric":"percent"},{"benchmark":"mindcube","model":"internvl3.5-8b","score":39.7,"metric":"percent"},{"benchmark":"sat","model":"internvl3.5-8b","score":58.7,"metric":"percent"},{"benchmark":"openeqa","model":"internvl3.5-8b","score":43.5,"metric":"percent"},{"benchmark":"vsi-bench","model":"internvl3.5-8b","score":56.4,"metric":"percent"},{"benchmark":"point-bench","model":"molmo2-4b","score":76.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"molmo2-4b","score":52.5,"metric":"percent"},{"benchmark":"where2place","model":"molmo2-4b","score":18,"metric":"percent"},{"benchmark":"blink","model":"molmo2-4b","score":50.8,"metric":"percent"},{"benchmark":"cv-bench","model":"molmo2-4b","score":64.4,"metric":"percent"},{"benchmark":"erqa","model":"molmo2-4b","score":46.3,"metric":"percent"},{"benchmark":"embspatialbench","model":"molmo2-4b","score":67,"metric":"percent"},{"benchmark":"mindcube","model":"molmo2-4b","score":37.6,"metric":"percent"},{"benchmark":"sat","model":"molmo2-4b","score":50,"metric":"percent"},{"benchmark":"openeqa","model":"molmo2-4b","score":46.9,"metric":"percent"},{"benchmark":"vsi-bench","model":"molmo2-4b","score":26.1,"metric":"percent"},{"benchmark":"point-bench","model":"molmo2-er","score":77.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"molmo2-er","score":52.5,"metric":"percent"},{"benchmark":"where2place","model":"molmo2-er","score":54,"metric":"percent"},{"benchmark":"blink","model":"molmo2-er","score":72.5,"metric":"percent"},{"benchmark":"cv-bench","model":"molmo2-er","score":87.8,"metric":"percent"},{"benchmark":"erqa","model":"molmo2-er","score":46.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"molmo2-er","score":78.8,"metric":"percent"},{"benchmark":"mindcube","model":"molmo2-er","score":57,"metric":"percent"},{"benchmark":"sat","model":"molmo2-er","score":78,"metric":"percent"},{"benchmark":"openeqa","model":"molmo2-er","score":44.7,"metric":"percent"},{"benchmark":"vsi-bench","model":"molmo2-er","score":74.5,"metric":"percent"},{"benchmark":"point-bench","model":"gemini-robotics-er-1.5","score":67.1,"metric":"percent"},{"benchmark":"point-bench","model":"gemini-2.5-pro","score":62.8,"metric":"percent"},{"benchmark":"point-bench","model":"qwen2.5-vl-32b-instruct","score":59,"metric":"percent"},{"benchmark":"point-bench","model":"qwen2.5-vl-72b-instruct","score":59,"metric":"percent"},{"benchmark":"point-bench","model":"qwen3-vl-235b-a22b-instruct","score":58.3,"metric":"percent"},{"benchmark":"point-bench","model":"molmo-7b-d","score":61.6,"metric":"percent"},{"benchmark":"point-bench","model":"molmo-72b","score":63.8,"metric":"percent"},{"benchmark":"point-bench","model":"molmo-7b-o","score":63.3,"metric":"percent"},{"benchmark":"point-bench","model":"molmo2-4b","score":67.7,"metric":"percent"},{"benchmark":"point-bench","model":"molmo2-8b","score":68.7,"metric":"percent"},{"benchmark":"point-bench","model":"molmo2-o-7b","score":66.5,"metric":"percent"},{"benchmark":"point-bench","model":"molmopoint-8b","score":70.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-3.7-sonnet","score":27.7,"metric":"percent"},{"benchmark":"osworld-g","model":"gemini-3-pro","score":35.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-tars-1.5-7b","score":94.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-tars-1.5-7b","score":61.6,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-tars-1.5-7b","score":64.2,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-8b-instruct","score":92.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-8b-instruct","score":52.7,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-8b-instruct","score":57.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"molmo2-8b","score":89.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"molmo2-8b","score":30.4,"metric":"percent"},{"benchmark":"osworld-g","model":"molmo2-8b","score":54.1,"metric":"percent"},{"benchmark":"screenspot-v2","model":"molmopoint-8b","score":89.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"molmopoint-8b","score":36.4,"metric":"percent"},{"benchmark":"osworld-g","model":"molmopoint-8b","score":54.9,"metric":"percent"},{"benchmark":"screenspot-v2","model":"molmopoint-gui-8b","score":93.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"molmopoint-gui-8b","score":60.2,"metric":"percent"},{"benchmark":"osworld-g","model":"molmopoint-gui-8b","score":70,"metric":"percent"},{"benchmark":"nextqa","model":"gpt-5","score":86.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"gpt-5","score":79.4,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-5","score":74.1,"metric":"percent"},{"benchmark":"tomato","model":"gpt-5","score":53,"metric":"percent"},{"benchmark":"motionbench","model":"gpt-5","score":65.4,"metric":"percent"},{"benchmark":"tempcompass","model":"gpt-5","score":80.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-5","score":83.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5","score":86.9,"metric":"percent"},{"benchmark":"longvideobench","model":"gpt-5","score":72.6,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5","score":77.7,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-5","score":65.2,"metric":"percent"},{"benchmark":"videoevalpro","model":"gpt-5","score":68.8,"metric":"percent"},{"benchmark":"egoschema","model":"gpt-5","score":75.6,"metric":"percent"},{"benchmark":"nextqa","model":"gpt-5-mini","score":83.2,"metric":"percent"},{"benchmark":"perceptiontest","model":"gpt-5-mini","score":72,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-5-mini","score":66.5,"metric":"percent"},{"benchmark":"tomato","model":"gpt-5-mini","score":44.1,"metric":"percent"},{"benchmark":"motionbench","model":"gpt-5-mini","score":59.9,"metric":"percent"},{"benchmark":"tempcompass","model":"gpt-5-mini","score":74.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-5-mini","score":77.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5-mini","score":82.3,"metric":"percent"},{"benchmark":"longvideobench","model":"gpt-5-mini","score":69.7,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-5-mini","score":69.1,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-5-mini","score":54.7,"metric":"percent"},{"benchmark":"videoevalpro","model":"gpt-5-mini","score":60.1,"metric":"percent"},{"benchmark":"egoschema","model":"gpt-5-mini","score":70.9,"metric":"percent"},{"benchmark":"nextqa","model":"gemini-3-pro","score":84.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"gemini-3-pro","score":77.6,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-3-pro","score":70.4,"metric":"percent"},{"benchmark":"tomato","model":"gemini-3-pro","score":48.3,"metric":"percent"},{"benchmark":"motionbench","model":"gemini-3-pro","score":62.6,"metric":"percent"},{"benchmark":"tempcompass","model":"gemini-3-pro","score":82.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-3-pro","score":88.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-3-pro","score":87.5,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-3-pro","score":75.9,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-3-pro","score":75.7,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3-pro","score":77,"metric":"percent"},{"benchmark":"videoevalpro","model":"gemini-3-pro","score":78,"metric":"percent"},{"benchmark":"egoschema","model":"gemini-3-pro","score":68.9,"metric":"percent"},{"benchmark":"nextqa","model":"gemini-2.5-pro","score":85.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"gemini-2.5-pro","score":78.4,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-2.5-pro","score":70.6,"metric":"percent"},{"benchmark":"tomato","model":"gemini-2.5-pro","score":48.6,"metric":"percent"},{"benchmark":"motionbench","model":"gemini-2.5-pro","score":62,"metric":"percent"},{"benchmark":"tempcompass","model":"gemini-2.5-pro","score":81.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-2.5-pro","score":87.8,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-2.5-pro","score":87.8,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-2.5-pro","score":76.8,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-2.5-pro","score":81.5,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-2.5-pro","score":75.7,"metric":"percent"},{"benchmark":"videoevalpro","model":"gemini-2.5-pro","score":78.4,"metric":"percent"},{"benchmark":"egoschema","model":"gemini-2.5-pro","score":72.2,"metric":"percent"},{"benchmark":"nextqa","model":"gemini-2.5-flash","score":81.8,"metric":"percent"},{"benchmark":"perceptiontest","model":"gemini-2.5-flash","score":74.7,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-2.5-flash","score":67,"metric":"percent"},{"benchmark":"tomato","model":"gemini-2.5-flash","score":39.1,"metric":"percent"},{"benchmark":"motionbench","model":"gemini-2.5-flash","score":59.3,"metric":"percent"},{"benchmark":"tempcompass","model":"gemini-2.5-flash","score":80.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-2.5-flash","score":84.2,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-2.5-flash","score":84.2,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-2.5-flash","score":73.1,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-2.5-flash","score":75.1,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-2.5-flash","score":64.9,"metric":"percent"},{"benchmark":"videoevalpro","model":"gemini-2.5-flash","score":69.6,"metric":"percent"},{"benchmark":"egoschema","model":"gemini-2.5-flash","score":70.2,"metric":"percent"},{"benchmark":"nextqa","model":"claude-sonnet-4.5","score":79.2,"metric":"percent"},{"benchmark":"perceptiontest","model":"claude-sonnet-4.5","score":64.3,"metric":"percent"},{"benchmark":"mvbench","model":"claude-sonnet-4.5","score":62.1,"metric":"percent"},{"benchmark":"tomato","model":"claude-sonnet-4.5","score":39.6,"metric":"percent"},{"benchmark":"motionbench","model":"claude-sonnet-4.5","score":58.5,"metric":"percent"},{"benchmark":"tempcompass","model":"claude-sonnet-4.5","score":72.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"claude-sonnet-4.5","score":74.2,"metric":"percent"},{"benchmark":"videomme-sub","model":"claude-sonnet-4.5","score":80.5,"metric":"percent"},{"benchmark":"longvideobench","model":"claude-sonnet-4.5","score":65.1,"metric":"percent"},{"benchmark":"mlvu","model":"claude-sonnet-4.5","score":64,"metric":"percent"},{"benchmark":"lvbench","model":"claude-sonnet-4.5","score":50.5,"metric":"percent"},{"benchmark":"videoevalpro","model":"claude-sonnet-4.5","score":50.5,"metric":"percent"},{"benchmark":"egoschema","model":"claude-sonnet-4.5","score":73.1,"metric":"percent"},{"benchmark":"nextqa","model":"internvl3.5-4b","score":80.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"internvl3.5-4b","score":68.1,"metric":"percent"},{"benchmark":"mvbench","model":"internvl3.5-4b","score":71.2,"metric":"percent"},{"benchmark":"tomato","model":"internvl3.5-4b","score":26.8,"metric":"percent"},{"benchmark":"motionbench","model":"internvl3.5-4b","score":56.5,"metric":"percent"},{"benchmark":"tempcompass","model":"internvl3.5-4b","score":68.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl3.5-4b","score":65.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl3.5-4b","score":68.6,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl3.5-4b","score":60.8,"metric":"percent"},{"benchmark":"mlvu","model":"internvl3.5-4b","score":52,"metric":"percent"},{"benchmark":"lvbench","model":"internvl3.5-4b","score":43.2,"metric":"percent"},{"benchmark":"videoevalpro","model":"internvl3.5-4b","score":46.5,"metric":"percent"},{"benchmark":"egoschema","model":"internvl3.5-4b","score":58.9,"metric":"percent"},{"benchmark":"nextqa","model":"internvl3.5-8b","score":81.7,"metric":"percent"},{"benchmark":"perceptiontest","model":"internvl3.5-8b","score":72.7,"metric":"percent"},{"benchmark":"mvbench","model":"internvl3.5-8b","score":72.1,"metric":"percent"},{"benchmark":"tomato","model":"internvl3.5-8b","score":24.6,"metric":"percent"},{"benchmark":"motionbench","model":"internvl3.5-8b","score":56.6,"metric":"percent"},{"benchmark":"tempcompass","model":"internvl3.5-8b","score":70.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl3.5-8b","score":66,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl3.5-8b","score":68.6,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl3.5-8b","score":62.1,"metric":"percent"},{"benchmark":"mlvu","model":"internvl3.5-8b","score":53.2,"metric":"percent"},{"benchmark":"lvbench","model":"internvl3.5-8b","score":43.4,"metric":"percent"},{"benchmark":"videoevalpro","model":"internvl3.5-8b","score":48.1,"metric":"percent"},{"benchmark":"egoschema","model":"internvl3.5-8b","score":58.6,"metric":"percent"},{"benchmark":"nextqa","model":"qwen3-vl-4b-instruct","score":81.4,"metric":"percent"},{"benchmark":"perceptiontest","model":"qwen3-vl-4b-instruct","score":70.7,"metric":"percent"},{"benchmark":"tomato","model":"qwen3-vl-4b-instruct","score":31.8,"metric":"percent"},{"benchmark":"motionbench","model":"qwen3-vl-4b-instruct","score":58.6,"metric":"percent"},{"benchmark":"tempcompass","model":"qwen3-vl-4b-instruct","score":70.8,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3-vl-4b-instruct","score":74,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-vl-4b-instruct","score":62.8,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-4b-instruct","score":58.4,"metric":"percent"},{"benchmark":"videoevalpro","model":"qwen3-vl-4b-instruct","score":49.8,"metric":"percent"},{"benchmark":"egoschema","model":"qwen3-vl-4b-instruct","score":68.4,"metric":"percent"},{"benchmark":"nextqa","model":"qwen3-vl-8b-instruct","score":83.4,"metric":"percent"},{"benchmark":"perceptiontest","model":"qwen3-vl-8b-instruct","score":72.7,"metric":"percent"},{"benchmark":"tomato","model":"qwen3-vl-8b-instruct","score":35.7,"metric":"percent"},{"benchmark":"motionbench","model":"qwen3-vl-8b-instruct","score":56.9,"metric":"percent"},{"benchmark":"tempcompass","model":"qwen3-vl-8b-instruct","score":74.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3-vl-8b-instruct","score":75.2,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-vl-8b-instruct","score":62.4,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-8b-instruct","score":57.6,"metric":"percent"},{"benchmark":"videoevalpro","model":"qwen3-vl-8b-instruct","score":50.3,"metric":"percent"},{"benchmark":"egoschema","model":"qwen3-vl-8b-instruct","score":69.8,"metric":"percent"},{"benchmark":"nextqa","model":"keye-vl-1.5-8b","score":75.8,"metric":"percent"},{"benchmark":"perceptiontest","model":"keye-vl-1.5-8b","score":64.2,"metric":"percent"},{"benchmark":"mvbench","model":"keye-vl-1.5-8b","score":56.9,"metric":"percent"},{"benchmark":"tomato","model":"keye-vl-1.5-8b","score":33,"metric":"percent"},{"benchmark":"motionbench","model":"keye-vl-1.5-8b","score":55.1,"metric":"percent"},{"benchmark":"tempcompass","model":"keye-vl-1.5-8b","score":75.5,"metric":"percent"},{"benchmark":"videomme-nosub","model":"keye-vl-1.5-8b","score":73,"metric":"percent"},{"benchmark":"videomme-sub","model":"keye-vl-1.5-8b","score":76.2,"metric":"percent"},{"benchmark":"longvideobench","model":"keye-vl-1.5-8b","score":66,"metric":"percent"},{"benchmark":"mlvu","model":"keye-vl-1.5-8b","score":53.8,"metric":"percent"},{"benchmark":"lvbench","model":"keye-vl-1.5-8b","score":42.8,"metric":"percent"},{"benchmark":"videoevalpro","model":"keye-vl-1.5-8b","score":54.9,"metric":"percent"},{"benchmark":"egoschema","model":"keye-vl-1.5-8b","score":56.3,"metric":"percent"},{"benchmark":"nextqa","model":"glm-4.1v-9b-thinking","score":81.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"glm-4.1v-9b-thinking","score":74.2,"metric":"percent"},{"benchmark":"mvbench","model":"glm-4.1v-9b-thinking","score":68.4,"metric":"percent"},{"benchmark":"tomato","model":"glm-4.1v-9b-thinking","score":30,"metric":"percent"},{"benchmark":"motionbench","model":"glm-4.1v-9b-thinking","score":59,"metric":"percent"},{"benchmark":"tempcompass","model":"glm-4.1v-9b-thinking","score":72.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"glm-4.1v-9b-thinking","score":68.2,"metric":"percent"},{"benchmark":"videomme-sub","model":"glm-4.1v-9b-thinking","score":75.6,"metric":"percent"},{"benchmark":"longvideobench","model":"glm-4.1v-9b-thinking","score":65.7,"metric":"percent"},{"benchmark":"mlvu","model":"glm-4.1v-9b-thinking","score":56.6,"metric":"percent"},{"benchmark":"lvbench","model":"glm-4.1v-9b-thinking","score":44,"metric":"percent"},{"benchmark":"videoevalpro","model":"glm-4.1v-9b-thinking","score":51.1,"metric":"percent"},{"benchmark":"egoschema","model":"glm-4.1v-9b-thinking","score":62.6,"metric":"percent"},{"benchmark":"nextqa","model":"minicpm-v-4.5-8b","score":78.8,"metric":"percent"},{"benchmark":"perceptiontest","model":"minicpm-v-4.5-8b","score":70.9,"metric":"percent"},{"benchmark":"mvbench","model":"minicpm-v-4.5-8b","score":60.5,"metric":"percent"},{"benchmark":"tomato","model":"minicpm-v-4.5-8b","score":29.8,"metric":"percent"},{"benchmark":"motionbench","model":"minicpm-v-4.5-8b","score":59.7,"metric":"percent"},{"benchmark":"tempcompass","model":"minicpm-v-4.5-8b","score":72.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"minicpm-v-4.5-8b","score":67.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"minicpm-v-4.5-8b","score":73.5,"metric":"percent"},{"benchmark":"longvideobench","model":"minicpm-v-4.5-8b","score":63.9,"metric":"percent"},{"benchmark":"mlvu","model":"minicpm-v-4.5-8b","score":60.6,"metric":"percent"},{"benchmark":"lvbench","model":"minicpm-v-4.5-8b","score":50.4,"metric":"percent"},{"benchmark":"videoevalpro","model":"minicpm-v-4.5-8b","score":54.9,"metric":"percent"},{"benchmark":"egoschema","model":"minicpm-v-4.5-8b","score":49.6,"metric":"percent"},{"benchmark":"nextqa","model":"eagle2.5-8b","score":85,"metric":"percent"},{"benchmark":"perceptiontest","model":"eagle2.5-8b","score":81,"metric":"percent"},{"benchmark":"mvbench","model":"eagle2.5-8b","score":74.8,"metric":"percent"},{"benchmark":"tomato","model":"eagle2.5-8b","score":31,"metric":"percent"},{"benchmark":"motionbench","model":"eagle2.5-8b","score":55.7,"metric":"percent"},{"benchmark":"tempcompass","model":"eagle2.5-8b","score":74.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"eagle2.5-8b","score":72.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"eagle2.5-8b","score":75.7,"metric":"percent"},{"benchmark":"longvideobench","model":"eagle2.5-8b","score":66.4,"metric":"percent"},{"benchmark":"mlvu","model":"eagle2.5-8b","score":60.4,"metric":"percent"},{"benchmark":"lvbench","model":"eagle2.5-8b","score":50.9,"metric":"percent"},{"benchmark":"videoevalpro","model":"eagle2.5-8b","score":58.6,"metric":"percent"},{"benchmark":"egoschema","model":"eagle2.5-8b","score":72.2,"metric":"percent"},{"benchmark":"nextqa","model":"plm-3b","score":83.4,"metric":"percent"},{"benchmark":"perceptiontest","model":"plm-3b","score":79.3,"metric":"percent"},{"benchmark":"mvbench","model":"plm-3b","score":74.7,"metric":"percent"},{"benchmark":"tomato","model":"plm-3b","score":30.9,"metric":"percent"},{"benchmark":"motionbench","model":"plm-3b","score":60.4,"metric":"percent"},{"benchmark":"tempcompass","model":"plm-3b","score":69.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"plm-3b","score":54.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"plm-3b","score":59.4,"metric":"percent"},{"benchmark":"longvideobench","model":"plm-3b","score":57.9,"metric":"percent"},{"benchmark":"mlvu","model":"plm-3b","score":48.4,"metric":"percent"},{"benchmark":"lvbench","model":"plm-3b","score":40.4,"metric":"percent"},{"benchmark":"videoevalpro","model":"plm-3b","score":46.2,"metric":"percent"},{"benchmark":"egoschema","model":"plm-3b","score":66.9,"metric":"percent"},{"benchmark":"nextqa","model":"plm-8b","score":84.1,"metric":"percent"},{"benchmark":"perceptiontest","model":"plm-8b","score":82.7,"metric":"percent"},{"benchmark":"mvbench","model":"plm-8b","score":77.1,"metric":"percent"},{"benchmark":"tomato","model":"plm-8b","score":33.2,"metric":"percent"},{"benchmark":"motionbench","model":"plm-8b","score":61.4,"metric":"percent"},{"benchmark":"tempcompass","model":"plm-8b","score":72.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"plm-8b","score":58.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"plm-8b","score":65.4,"metric":"percent"},{"benchmark":"longvideobench","model":"plm-8b","score":56.9,"metric":"percent"},{"benchmark":"mlvu","model":"plm-8b","score":52.6,"metric":"percent"},{"benchmark":"lvbench","model":"plm-8b","score":44.5,"metric":"percent"},{"benchmark":"videoevalpro","model":"plm-8b","score":47.2,"metric":"percent"},{"benchmark":"egoschema","model":"plm-8b","score":68.8,"metric":"percent"},{"benchmark":"nextqa","model":"molmo2-4b","score":85.5,"metric":"percent"},{"benchmark":"perceptiontest","model":"molmo2-4b","score":81.3,"metric":"percent"},{"benchmark":"mvbench","model":"molmo2-4b","score":75.1,"metric":"percent"},{"benchmark":"tomato","model":"molmo2-4b","score":39.8,"metric":"percent"},{"benchmark":"motionbench","model":"molmo2-4b","score":61.6,"metric":"percent"},{"benchmark":"tempcompass","model":"molmo2-4b","score":72.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"molmo2-4b","score":69.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"molmo2-4b","score":75.7,"metric":"percent"},{"benchmark":"longvideobench","model":"molmo2-4b","score":68,"metric":"percent"},{"benchmark":"mlvu","model":"molmo2-4b","score":63,"metric":"percent"},{"benchmark":"lvbench","model":"molmo2-4b","score":53.9,"metric":"percent"},{"benchmark":"videoevalpro","model":"molmo2-4b","score":59.9,"metric":"percent"},{"benchmark":"egoschema","model":"molmo2-4b","score":61.2,"metric":"percent"},{"benchmark":"nextqa","model":"molmo2-8b","score":86.2,"metric":"percent"},{"benchmark":"perceptiontest","model":"molmo2-8b","score":82.1,"metric":"percent"},{"benchmark":"mvbench","model":"molmo2-8b","score":75.9,"metric":"percent"},{"benchmark":"tomato","model":"molmo2-8b","score":39.6,"metric":"percent"},{"benchmark":"motionbench","model":"molmo2-8b","score":62.2,"metric":"percent"},{"benchmark":"tempcompass","model":"molmo2-8b","score":73.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"molmo2-8b","score":69.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"molmo2-8b","score":75.8,"metric":"percent"},{"benchmark":"longvideobench","model":"molmo2-8b","score":67.5,"metric":"percent"},{"benchmark":"mlvu","model":"molmo2-8b","score":60.2,"metric":"percent"},{"benchmark":"lvbench","model":"molmo2-8b","score":52.8,"metric":"percent"},{"benchmark":"videoevalpro","model":"molmo2-8b","score":60.4,"metric":"percent"},{"benchmark":"egoschema","model":"molmo2-8b","score":62,"metric":"percent"},{"benchmark":"nextqa","model":"molmo2-o-7b","score":84.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"molmo2-o-7b","score":79.6,"metric":"percent"},{"benchmark":"mvbench","model":"molmo2-o-7b","score":74.8,"metric":"percent"},{"benchmark":"tomato","model":"molmo2-o-7b","score":36.2,"metric":"percent"},{"benchmark":"motionbench","model":"molmo2-o-7b","score":60.6,"metric":"percent"},{"benchmark":"tempcompass","model":"molmo2-o-7b","score":73,"metric":"percent"},{"benchmark":"videomme-nosub","model":"molmo2-o-7b","score":64.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"molmo2-o-7b","score":69.2,"metric":"percent"},{"benchmark":"longvideobench","model":"molmo2-o-7b","score":63.7,"metric":"percent"},{"benchmark":"mlvu","model":"molmo2-o-7b","score":55.2,"metric":"percent"},{"benchmark":"lvbench","model":"molmo2-o-7b","score":49.6,"metric":"percent"},{"benchmark":"videoevalpro","model":"molmo2-o-7b","score":55.1,"metric":"percent"},{"benchmark":"egoschema","model":"molmo2-o-7b","score":56.8,"metric":"percent"},{"benchmark":"nextqa","model":"molmopoint-8b","score":86.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"molmopoint-8b","score":82.3,"metric":"percent"},{"benchmark":"mvbench","model":"molmopoint-8b","score":75.2,"metric":"percent"},{"benchmark":"tomato","model":"molmopoint-8b","score":37.3,"metric":"percent"},{"benchmark":"motionbench","model":"molmopoint-8b","score":61.4,"metric":"percent"},{"benchmark":"tempcompass","model":"molmopoint-8b","score":74.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"molmopoint-8b","score":69.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"molmopoint-8b","score":76.9,"metric":"percent"},{"benchmark":"longvideobench","model":"molmopoint-8b","score":67.3,"metric":"percent"},{"benchmark":"mlvu","model":"molmopoint-8b","score":62.4,"metric":"percent"},{"benchmark":"lvbench","model":"molmopoint-8b","score":52.5,"metric":"percent"},{"benchmark":"videoevalpro","model":"molmopoint-8b","score":58,"metric":"percent"},{"benchmark":"egoschema","model":"molmopoint-8b","score":63,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5","score":89.5,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5","score":83.8,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5-mini","score":82.1,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-pro","score":77.8,"metric":"percent"},{"benchmark":"ai2d","model":"claude-sonnet-4.5","score":91.5,"metric":"percent"},{"benchmark":"chartqa","model":"claude-sonnet-4.5","score":80.2,"metric":"percent"},{"benchmark":"docvqa","model":"claude-sonnet-4.5","score":91.7,"metric":"percent"},{"benchmark":"infoqa","model":"claude-sonnet-4.5","score":65.9,"metric":"percent"},{"benchmark":"textvqa","model":"claude-sonnet-4.5","score":67.2,"metric":"percent"},{"benchmark":"vqav2","model":"claude-sonnet-4.5","score":77,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-sonnet-4.5","score":61.1,"metric":"percent"},{"benchmark":"mmmu","model":"claude-sonnet-4.5","score":77.8,"metric":"percent"},{"benchmark":"mathvista","model":"claude-sonnet-4.5","score":73.1,"metric":"percent"},{"benchmark":"countbench","model":"claude-sonnet-4.5","score":87.3,"metric":"percent"},{"benchmark":"pixmocount","model":"claude-sonnet-4.5","score":58.3,"metric":"percent"},{"benchmark":"muirbench","model":"claude-sonnet-4.5","score":59.6,"metric":"percent"},{"benchmark":"mmiu","model":"claude-sonnet-4.5","score":54.1,"metric":"percent"},{"benchmark":"blink","model":"claude-sonnet-4.5","score":64.8,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-4b-instruct","score":85,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-8b-instruct","score":85.2,"metric":"percent"},{"benchmark":"chartqa","model":"keye-vl-1.5-8b","score":85,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4.1v-9b-thinking","score":87.9,"metric":"percent"},{"benchmark":"chartqa","model":"glm-4.1v-9b-thinking","score":70,"metric":"percent"},{"benchmark":"docvqa","model":"glm-4.1v-9b-thinking","score":93.3,"metric":"percent"},{"benchmark":"infoqa","model":"glm-4.1v-9b-thinking","score":80.3,"metric":"percent"},{"benchmark":"textvqa","model":"glm-4.1v-9b-thinking","score":79.6,"metric":"percent"},{"benchmark":"vqav2","model":"glm-4.1v-9b-thinking","score":68.3,"metric":"percent"},{"benchmark":"realworldqa","model":"glm-4.1v-9b-thinking","score":70.7,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.1v-9b-thinking","score":68,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.1v-9b-thinking","score":80.7,"metric":"percent"},{"benchmark":"countbench","model":"glm-4.1v-9b-thinking","score":88,"metric":"percent"},{"benchmark":"pixmocount","model":"glm-4.1v-9b-thinking","score":60.7,"metric":"percent"},{"benchmark":"muirbench","model":"glm-4.1v-9b-thinking","score":74.7,"metric":"percent"},{"benchmark":"mmiu","model":"glm-4.1v-9b-thinking","score":62.4,"metric":"percent"},{"benchmark":"blink","model":"glm-4.1v-9b-thinking","score":65.1,"metric":"percent"},{"benchmark":"pixmocount","model":"eagle2.5-8b","score":66.9,"metric":"percent"},{"benchmark":"ai2d","model":"molmopoint-8b","score":96.4,"metric":"percent"},{"benchmark":"chartqa","model":"molmopoint-8b","score":86.8,"metric":"percent"},{"benchmark":"docvqa","model":"molmopoint-8b","score":93.8,"metric":"percent"},{"benchmark":"infoqa","model":"molmopoint-8b","score":83,"metric":"percent"},{"benchmark":"textvqa","model":"molmopoint-8b","score":86,"metric":"percent"},{"benchmark":"vqav2","model":"molmopoint-8b","score":87.2,"metric":"percent"},{"benchmark":"realworldqa","model":"molmopoint-8b","score":77.4,"metric":"percent"},{"benchmark":"mmmu","model":"molmopoint-8b","score":53.7,"metric":"percent"},{"benchmark":"mathvista","model":"molmopoint-8b","score":59.4,"metric":"percent"},{"benchmark":"countbench","model":"molmopoint-8b","score":92.9,"metric":"percent"},{"benchmark":"pixmocount","model":"molmopoint-8b","score":87.6,"metric":"percent"},{"benchmark":"muirbench","model":"molmopoint-8b","score":62.5,"metric":"percent"},{"benchmark":"mmiu","model":"molmopoint-8b","score":54.6,"metric":"percent"},{"benchmark":"blink","model":"molmopoint-8b","score":50.8,"metric":"percent"},{"benchmark":"ifbench","model":"trinity-large-thinking","score":52.3,"metric":"percent"},{"benchmark":"ifbench","model":"claude-opus-4.6","score":53.1,"metric":"percent"},{"benchmark":"ifbench","model":"minimax-m2.7","score":75.7,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.5-thinking","score":70.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"trinity-large-thinking","score":76.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.6","score":89.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5","score":81.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m2.7","score":86.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.5-thinking","score":86.9,"metric":"percent"},{"benchmark":"tau2-airline","model":"trinity-large-thinking","score":88,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-opus-4.6","score":82,"metric":"percent"},{"benchmark":"tau2-airline","model":"glm-5","score":80.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"minimax-m2.7","score":80,"metric":"percent"},{"benchmark":"tau2-airline","model":"kimi-k2.5-thinking","score":80,"metric":"percent"},{"benchmark":"tau2-telecom","model":"trinity-large-thinking","score":94.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-5","score":98.2,"metric":"percent"},{"benchmark":"tau2-telecom","model":"minimax-m2.7","score":84.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2.5-thinking","score":95.9,"metric":"percent"},{"benchmark":"pinchbench-best","model":"trinity-large-thinking","score":91.9,"metric":"percent"},{"benchmark":"pinchbench-best","model":"glm-5","score":86.4,"metric":"percent"},{"benchmark":"pinchbench-best","model":"minimax-m2.7","score":89.8,"metric":"percent"},{"benchmark":"aime-2025","model":"trinity-large-thinking","score":96.3,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.6","score":99.8,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-5","score":93.3,"metric":"percent"},{"benchmark":"aime-2025","model":"minimax-m2.7","score":80,"metric":"percent"},{"benchmark":"aime-2025","model":"kimi-k2.5-thinking","score":96.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"trinity-large-thinking","score":70.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"claude-opus-4.6","score":77,"metric":"percent"},{"benchmark":"bfcl-v4","model":"glm-5","score":70.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"minimax-m2.7","score":70.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"kimi-k2.5-thinking","score":68.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trinity-large-thinking","score":83.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-5","score":85.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-m2.7","score":80.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"trinity-large-thinking","score":63.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.6","score":75.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5","score":72.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m2.7","score":75.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.5-thinking","score":70.8,"metric":"percent"},{"benchmark":"gsm8k","model":"trinity-nano-base","score":58.4,"metric":"percent"},{"benchmark":"math500","model":"trinity-nano-base","score":36,"metric":"percent"},{"benchmark":"drop","model":"trinity-nano-base","score":63.6,"metric":"percent"},{"benchmark":"drop","model":"trinity-nano-base","score":4.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"trinity-nano-base","score":31.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"trinity-nano-base","score":44.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"trinity-nano-base","score":84,"metric":"percent"},{"benchmark":"arc-challenge","model":"trinity-nano-base","score":78.2,"metric":"percent"},{"benchmark":"arc-easy","model":"trinity-nano-base","score":94.8,"metric":"percent"},{"benchmark":"arc-easy","model":"trinity-nano-base","score":91.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"trinity-nano-base","score":74.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"trinity-nano-base","score":62.7,"metric":"percent"},{"benchmark":"openbookqa","model":"trinity-nano-base","score":82.2,"metric":"percent"},{"benchmark":"openbookqa","model":"trinity-nano-base","score":75.2,"metric":"percent"},{"benchmark":"winogrande","model":"trinity-nano-base","score":72.8,"metric":"percent"},{"benchmark":"winogrande","model":"trinity-nano-base","score":68,"metric":"percent"},{"benchmark":"mmlu","model":"trinity-nano-base","score":67.7,"metric":"percent"},{"benchmark":"mmlu","model":"trinity-nano-base","score":64.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trinity-nano-base","score":35.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trinity-nano-base","score":27.7,"metric":"percent"},{"benchmark":"agieval","model":"trinity-nano-base","score":51.8,"metric":"percent"},{"benchmark":"bbh","model":"trinity-nano-base","score":50.4,"metric":"percent"},{"benchmark":"bbh","model":"trinity-nano-base","score":7.6,"metric":"percent"},{"benchmark":"boolq","model":"trinity-nano-base","score":84.3,"metric":"percent"},{"benchmark":"hellaswag","model":"trinity-nano-base","score":77.4,"metric":"percent"},{"benchmark":"piqa","model":"trinity-nano-base","score":82.2,"metric":"percent"},{"benchmark":"sciq","model":"trinity-nano-base","score":93.2,"metric":"percent"},{"benchmark":"siqa","model":"trinity-nano-base","score":73,"metric":"percent"},{"benchmark":"arc-challenge","model":"trinity-mini-base","score":90,"metric":"percent"},{"benchmark":"commonsenseqa","model":"trinity-mini-base","score":79.6,"metric":"percent"},{"benchmark":"openbookqa","model":"trinity-mini-base","score":89,"metric":"percent"},{"benchmark":"winogrande","model":"trinity-mini-base","score":75.9,"metric":"percent"},{"benchmark":"mmlu","model":"trinity-mini-base","score":74.7,"metric":"percent"},{"benchmark":"agieval","model":"trinity-mini-base","score":61.8,"metric":"percent"},{"benchmark":"bbh","model":"trinity-mini-base","score":54.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trinity-mini-base","score":45.6,"metric":"percent"},{"benchmark":"gsm8k","model":"trinity-mini-base","score":56.6,"metric":"percent"},{"benchmark":"math500","model":"trinity-mini-base","score":51.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"trinity-mini-base","score":57.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"trinity-mini-base","score":55.3,"metric":"percent"},{"benchmark":"putnam-2025","model":"nomos-1","score":87,"metric":"points"},{"benchmark":"putnam-2025","model":"qwen3-30b-a3b-thinking-2507","score":24,"metric":"points"},{"benchmark":"simpleqa","model":"trinity-large-preview","score":23.92,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"beam","score":44.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.3","score":61,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-max","score":51,"metric":"percent"},{"benchmark":"swe-bench-pro-v2-hard","model":"beam","score":77.2,"metric":"percent"},{"benchmark":"swe-bench-pro-v2-hard","model":"inkling","score":56.9,"metric":"percent"},{"benchmark":"swe-bench-pro-v2-hard","model":"glm-5.3","score":84.3,"metric":"percent"},{"benchmark":"swe-bench-pro-v2-hard","model":"kimi-k3","score":88.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"beam","score":65.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"inkling","score":54.3,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"nemotron-3-ultra","score":46.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"inkling","score":63.8,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"beam","score":34.6,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"glm-5.3","score":61,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"kimi-k3","score":68,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"beam","score":78,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"beam","score":80.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"inkling","score":77.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"beam","score":97.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"inkling","score":97.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"beam","score":36.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"inkling","score":29.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.2","score":40.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.3","score":42.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k3","score":46.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.8-max","score":43.6,"metric":"percent"},{"benchmark":"scicode","model":"inkling","score":46.1,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-max","score":52.1,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4.1-flash","score":52,"metric":"percent"},{"benchmark":"critpt","model":"beam","score":16.3,"metric":"percent"},{"benchmark":"critpt","model":"inkling","score":5.4,"metric":"percent"},{"benchmark":"critpt","model":"glm-5.3","score":19.1,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.8-max","score":20,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v4.1-flash","score":14.3,"metric":"percent"},{"benchmark":"automationbench","model":"beam","score":37,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5.2","score":77.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"beam","score":38,"metric":"percent"},{"benchmark":"tau3-banking","model":"inkling","score":25,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.2","score":37.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"kimi-k3","score":37.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.8-max","score":55.2,"metric":"percent"},{"benchmark":"browsecomp","model":"beam","score":77.4,"metric":"percent"},{"benchmark":"browsecomp","model":"inkling","score":77.1,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"beam","score":80.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"beam","score":79.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"inkling","score":77.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-ultra","score":79.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.2","score":78.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.3","score":79.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k3","score":88.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.8-max","score":80.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4.1-flash","score":84,"metric":"percent"},{"benchmark":"longbench-v2","model":"beam","score":65.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"glm-5.2","score":64,"metric":"percent"},{"benchmark":"ifbench","model":"beam","score":79.7,"metric":"percent"},{"benchmark":"ifbench","model":"inkling","score":79.8,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5.2","score":73.3,"metric":"percent"},{"benchmark":"aa-omniscience-public","model":"beam","score":13,"metric":"index"},{"benchmark":"aa-omniscience-public","model":"inkling","score":14.2,"metric":"index"},{"benchmark":"aa-omniscience-public","model":"nemotron-3-ultra","score":8.6,"metric":"index"},{"benchmark":"aa-omniscience-public","model":"glm-5.3","score":22.6,"metric":"index"},{"benchmark":"aa-omniscience-public","model":"deepseek-v4.1-flash","score":6.6,"metric":"index"},{"benchmark":"deepswe-v1.1","model":"beam","score":43.3,"metric":"percent"},{"benchmark":"swe-bench-pro-v2-hard","model":"beam","score":76.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"beam","score":66.1,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"beam","score":31.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"beam","score":78.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"beam","score":81.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"beam","score":97.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"beam","score":36,"metric":"percent"},{"benchmark":"hle-with-tools","model":"beam","score":51.1,"metric":"avg@3"},{"benchmark":"scicode","model":"beam","score":49.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"beam","score":90.6,"metric":"percent"},{"benchmark":"livecodebench","model":"beam","score":88.3,"metric":"percent"},{"benchmark":"automationbench","model":"beam","score":39.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"beam","score":80.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"beam","score":36.1,"metric":"percent"},{"benchmark":"browsecomp","model":"beam","score":76.8,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"beam","score":80.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"beam","score":78.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"beam","score":67.5,"metric":"percent"},{"benchmark":"ifbench","model":"beam","score":79.6,"metric":"percent"},{"benchmark":"aa-omniscience-public","model":"beam","score":10.8,"metric":"index"},{"benchmark":"hle-text-only","model":"nemotron-3-ultra","score":26.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2.5-thinking","score":29.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2.6-thinking","score":35.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.2","score":40.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-pro-thinking-max","score":35.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3.1-pro","score":44.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-fable-5","score":53.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.6-sol","score":47.2,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gpt-5.6-sol","score":55,"metric":"avg@3"},{"benchmark":"aime-2026-i","model":"nemotron-3-ultra","score":94.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-pro-thinking-max","score":96.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.6-sol","score":99.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.5-thinking","score":87.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.6-thinking","score":91.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5.2","score":89.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-pro-thinking-max","score":88.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3.1-pro","score":94.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k2.5-thinking","score":51.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k2.6-thinking","score":71.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro-thinking-max","score":64,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-sol","score":89.5,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"inkling","score":1233,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-3-ultra","score":1164,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"kimi-k2.5-thinking","score":1009,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"kimi-k2.6-thinking","score":1190,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.2","score":1514,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4-pro-thinking-max","score":1307,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.1-pro","score":962,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5","score":1760,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1748,"metric":"elo"},{"benchmark":"mcp-atlas","model":"inkling","score":74.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"nemotron-3-ultra","score":44.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k2.5-thinking","score":64,"metric":"percent"},{"benchmark":"mcp-atlas","model":"kimi-k2.6-thinking","score":68.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-pro-thinking-max","score":73.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"inkling","score":23.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-ultra","score":13.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"kimi-k2.5-thinking","score":13.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"kimi-k2.6-thinking","score":20.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-pro-thinking-max","score":25.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemini-3.1-pro","score":16.5,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.6-sol","score":89.4,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"inkling","score":43.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"nemotron-3-ultra","score":32.4,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"kimi-k2.5-thinking","score":36.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"kimi-k2.6-thinking","score":38.7,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"glm-5.2","score":38.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-pro-thinking-max","score":57,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-3.1-pro","score":77.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-fable-5","score":68.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.6-sol","score":71.6,"metric":"percent"},{"benchmark":"aa-omniscience","model":"inkling","score":1,"metric":"index"},{"benchmark":"aa-omniscience","model":"nemotron-3-ultra","score":-1,"metric":"index"},{"benchmark":"aa-omniscience","model":"kimi-k2.5-thinking","score":-8,"metric":"index"},{"benchmark":"aa-omniscience","model":"kimi-k2.6-thinking","score":6,"metric":"index"},{"benchmark":"aa-omniscience","model":"glm-5.2","score":4,"metric":"index"},{"benchmark":"aa-omniscience","model":"deepseek-v4-pro-thinking-max","score":-10,"metric":"index"},{"benchmark":"aa-omniscience","model":"gemini-3.1-pro","score":33,"metric":"index"},{"benchmark":"aa-omniscience","model":"claude-fable-5","score":40,"metric":"index"},{"benchmark":"aa-omniscience","model":"gpt-5.6-sol","score":22,"metric":"index"},{"benchmark":"ifbench","model":"nemotron-3-ultra","score":81.4,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-pro-thinking-max","score":76.5,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-3.1-pro","score":77.1,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"inkling","score":88.7,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"nemotron-3-ultra","score":85.6,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"kimi-k2.5-thinking","score":84,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"kimi-k2.6-thinking","score":88.4,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"glm-5.2","score":89.2,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"deepseek-v4-pro-thinking-max","score":89.3,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemini-3.1-pro","score":92.7,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"claude-fable-5","score":93.3,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gpt-5.6-sol","score":91.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"inkling","score":73.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k2.5-thinking","score":75,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k2.6-thinking","score":79,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-pro","score":82,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-fable-5","score":84.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"inkling","score":78.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-fable-5","score":86.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.6-sol","score":84.7,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"inkling","score":82,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-fable-5","score":89.4,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-5.6-sol","score":87.8,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"inkling","score":77.2,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"gemini-3.1-pro","score":82.5,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"inkling","score":78,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"nemotron-3-ultra","score":77.6,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"kimi-k2.5-thinking","score":54.1,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"kimi-k2.6-thinking","score":65.6,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"glm-5.2","score":71.3,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"deepseek-v4-pro-thinking-max","score":36,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"gemini-3.1-pro","score":65.2,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"claude-fable-5","score":96,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"gpt-5.6-sol","score":82.4,"metric":"percent"},{"benchmark":"fortress-benign","model":"inkling","score":95.9,"metric":"percent"},{"benchmark":"fortress-benign","model":"nemotron-3-ultra","score":90.5,"metric":"percent"},{"benchmark":"fortress-benign","model":"kimi-k2.5-thinking","score":98.3,"metric":"percent"},{"benchmark":"fortress-benign","model":"kimi-k2.6-thinking","score":97.2,"metric":"percent"},{"benchmark":"fortress-benign","model":"glm-5.2","score":90,"metric":"percent"},{"benchmark":"fortress-benign","model":"deepseek-v4-pro-thinking-max","score":98.5,"metric":"percent"},{"benchmark":"fortress-benign","model":"gemini-3.1-pro","score":98,"metric":"percent"},{"benchmark":"fortress-benign","model":"claude-fable-5","score":55.1,"metric":"percent"},{"benchmark":"fortress-benign","model":"gpt-5.6-sol","score":98.1,"metric":"percent"},{"benchmark":"strongreject","model":"inkling","score":98.6,"metric":"percent"},{"benchmark":"strongreject","model":"nemotron-3-ultra","score":98.7,"metric":"percent"},{"benchmark":"strongreject","model":"kimi-k2.5-thinking","score":99.5,"metric":"percent"},{"benchmark":"strongreject","model":"kimi-k2.6-thinking","score":99.8,"metric":"percent"},{"benchmark":"strongreject","model":"glm-5.2","score":98.5,"metric":"percent"},{"benchmark":"strongreject","model":"deepseek-v4-pro-thinking-max","score":98.6,"metric":"percent"},{"benchmark":"strongreject","model":"gemini-3.1-pro","score":98,"metric":"percent"},{"benchmark":"strongreject","model":"claude-fable-5","score":98.7,"metric":"percent"},{"benchmark":"strongreject","model":"gpt-5.6-sol","score":98.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"inkling-small","score":80.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mimo-v2.5","score":71,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3.5-flash-lite","score":75,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.6-luna","score":93,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"inkling-small","score":55.9,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"mimo-v2.5","score":56.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"inkling-small","score":64.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-397b-a17b","score":51.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mimo-v2.5","score":63.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minimax-m2.7","score":55.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-luna","score":82.5,"metric":"percent"},{"benchmark":"scicode","model":"inkling-small","score":48.7,"metric":"percent"},{"benchmark":"scicode","model":"mimo-v2.5","score":43.1,"metric":"percent"},{"benchmark":"scicode","model":"minimax-m2.7","score":47,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-flash-thinking-max","score":44.9,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-ultra","score":39.9,"metric":"percent"},{"benchmark":"scicode","model":"claude-4.5-haiku","score":43.3,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3.5-flash-lite","score":40.9,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.6-luna","score":50,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"inkling-small","score":1269,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.5-397b-a17b","score":962,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"mimo-v2.5","score":1145,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"minimax-m2.7","score":1159,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4-flash-thinking-max","score":1189,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"inkling","score":1238,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-4.5-haiku","score":911,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemini-3.5-flash-lite","score":1139,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-luna","score":1530,"metric":"elo"},{"benchmark":"mcp-atlas","model":"inkling-small","score":79.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-4.5-haiku","score":40.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3.5-flash-lite","score":76.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.6-luna","score":75,"metric":"percent"},{"benchmark":"tau3-banking","model":"inkling-small","score":15.5,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-397b-a17b","score":13.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"mimo-v2.5","score":6.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"minimax-m2.7","score":8.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-flash-thinking-max","score":22.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-4.5-haiku","score":9.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemini-3.5-flash-lite","score":16.5,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.6-luna","score":24.3,"metric":"percent"},{"benchmark":"browsecomp","model":"inkling-small","score":77.4,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-ultra","score":63,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.6-luna","score":84,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"inkling-small","score":54.4,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.5-397b-a17b","score":40.7,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"mimo-v2.5","score":49.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"minimax-m2.7","score":47.5,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-flash-thinking-max","score":50.9,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"claude-4.5-haiku","score":26.9,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gemini-3.5-flash-lite","score":57.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gpt-5.6-luna","score":67.9,"metric":"percent"},{"benchmark":"aa-briefcase","model":"inkling-small","score":917,"metric":"elo"},{"benchmark":"aa-briefcase","model":"deepseek-v4-flash-thinking-max","score":833,"metric":"elo"},{"benchmark":"aa-briefcase","model":"nemotron-3-ultra","score":870,"metric":"elo"},{"benchmark":"aa-briefcase","model":"inkling","score":839,"metric":"elo"},{"benchmark":"aa-briefcase","model":"claude-4.5-haiku","score":612,"metric":"elo"},{"benchmark":"gpqa-diamond","model":"inkling-small","score":89.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-397b-a17b","score":89.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-v2.5","score":84.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m2.7","score":87.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash-thinking-max","score":89.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-4.5-haiku","score":67.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3.5-flash-lite","score":83.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.6-luna","score":89.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"inkling-small","score":31.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-397b-a17b","score":27.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"mimo-v2.5","score":25.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"minimax-m2.7","score":28.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-flash-thinking-max","score":32.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-4.5-haiku","score":9.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3.5-flash-lite","score":17.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.6-luna","score":35.6,"metric":"percent"},{"benchmark":"hle-with-tools","model":"inkling-small","score":47.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"mimo-v2.5","score":40,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"minimax-m2.7","score":40.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-4.5-haiku","score":17.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemini-3.5-flash-lite","score":42.5,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.6-luna","score":48.9,"metric":"avg@3"},{"benchmark":"aime-2026-i","model":"inkling-small","score":95.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"mimo-v2.5","score":93.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minimax-m2.7","score":87.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-flash-thinking-max","score":95.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-4.5-haiku","score":85.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3.5-flash-lite","score":82.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.6-luna","score":97.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"inkling-small","score":90.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"mimo-v2.5","score":82.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"minimax-m2.7","score":71.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-flash-thinking-max","score":93.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"nemotron-3-ultra","score":78.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"inkling","score":86.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-4.5-haiku","score":66.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemini-3.5-flash-lite","score":63.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.6-luna","score":98.5,"metric":"percent"},{"benchmark":"critpt","model":"inkling-small","score":8.3,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.5-397b-a17b","score":1.7,"metric":"percent"},{"benchmark":"critpt","model":"mimo-v2.5","score":3.7,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v4-flash-thinking-max","score":7.1,"metric":"percent"},{"benchmark":"critpt","model":"claude-4.5-haiku","score":0,"metric":"percent"},{"benchmark":"critpt","model":"gemini-3.5-flash-lite","score":0,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5.6-luna","score":20.6,"metric":"percent"},{"benchmark":"arc-agi-1","model":"inkling-small","score":84,"metric":"percent"},{"benchmark":"arc-agi-1","model":"inkling","score":79.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-haiku","score":47.7,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna","score":87.7,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling-small","score":40.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling","score":36.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna","score":47.6,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"inkling-small","score":20.6,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"qwen3.5-397b-a17b","score":26,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"mimo-v2.5","score":16.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"minimax-m2.7","score":13.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-4.5-haiku","score":5.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-3.5-flash-lite","score":44.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.6-luna","score":41.7,"metric":"percent"},{"benchmark":"aa-omniscience","model":"inkling-small","score":-9,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3.5-397b-a17b","score":-29.8,"metric":"index"},{"benchmark":"aa-omniscience","model":"mimo-v2.5","score":-9.3,"metric":"index"},{"benchmark":"aa-omniscience","model":"minimax-m2.7","score":0.7,"metric":"index"},{"benchmark":"aa-omniscience","model":"deepseek-v4-flash-thinking-max","score":-22.9,"metric":"index"},{"benchmark":"aa-omniscience","model":"inkling","score":2.1,"metric":"index"},{"benchmark":"aa-omniscience","model":"claude-4.5-haiku","score":-4.2,"metric":"index"},{"benchmark":"aa-omniscience","model":"gemini-3.5-flash-lite","score":6.9,"metric":"index"},{"benchmark":"aa-omniscience","model":"gpt-5.6-luna","score":-11.6,"metric":"index"},{"benchmark":"ifbench","model":"inkling-small","score":82.2,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-397b-a17b","score":78.8,"metric":"percent"},{"benchmark":"ifbench","model":"mimo-v2.5","score":67.1,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-flash-thinking-max","score":79.2,"metric":"percent"},{"benchmark":"ifbench","model":"claude-4.5-haiku","score":54.3,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-3.5-flash-lite","score":78.6,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.6-luna","score":67.3,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"inkling-small","score":86.7,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"qwen3.5-397b-a17b","score":90,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"mimo-v2.5","score":83.5,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"minimax-m2.7","score":83.9,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"deepseek-v4-flash-thinking-max","score":88.4,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"claude-4.5-haiku","score":83.4,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gemini-3.5-flash-lite","score":89.4,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"gpt-5.6-luna","score":88.7,"metric":"percent"},{"benchmark":"strongreject","model":"inkling-small","score":98.4,"metric":"percent"},{"benchmark":"strongreject","model":"qwen3.5-397b-a17b","score":99.4,"metric":"percent"},{"benchmark":"strongreject","model":"mimo-v2.5","score":99.3,"metric":"percent"},{"benchmark":"strongreject","model":"minimax-m2.7","score":99.4,"metric":"percent"},{"benchmark":"strongreject","model":"deepseek-v4-flash-thinking-max","score":97.4,"metric":"percent"},{"benchmark":"strongreject","model":"claude-4.5-haiku","score":98.6,"metric":"percent"},{"benchmark":"strongreject","model":"gemini-3.5-flash-lite","score":97.6,"metric":"percent"},{"benchmark":"strongreject","model":"gpt-5.6-luna","score":98.7,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"inkling-small","score":71.6,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"qwen3.5-397b-a17b","score":77.3,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"mimo-v2.5","score":64.8,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"minimax-m2.7","score":86.3,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"deepseek-v4-flash-thinking-max","score":32,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"claude-4.5-haiku","score":91.3,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"gemini-3.5-flash-lite","score":70.7,"metric":"percent"},{"benchmark":"fortress-adversarial","model":"gpt-5.6-luna","score":83.8,"metric":"percent"},{"benchmark":"fortress-benign","model":"inkling-small","score":96.9,"metric":"percent"},{"benchmark":"fortress-benign","model":"qwen3.5-397b-a17b","score":95.4,"metric":"percent"},{"benchmark":"fortress-benign","model":"mimo-v2.5","score":94.6,"metric":"percent"},{"benchmark":"fortress-benign","model":"minimax-m2.7","score":90.1,"metric":"percent"},{"benchmark":"fortress-benign","model":"deepseek-v4-flash-thinking-max","score":99.2,"metric":"percent"},{"benchmark":"fortress-benign","model":"nemotron-3-ultra","score":90.6,"metric":"percent"},{"benchmark":"fortress-benign","model":"claude-4.5-haiku","score":94.1,"metric":"percent"},{"benchmark":"fortress-benign","model":"gemini-3.5-flash-lite","score":95.5,"metric":"percent"},{"benchmark":"fortress-benign","model":"gpt-5.6-luna","score":97.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"inkling-small","score":74,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-397b-a17b","score":77.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mimo-v2.5","score":75.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-4.5-haiku","score":58.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.5-flash-lite","score":79,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.6-luna","score":78.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"inkling-small","score":77.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"mimo-v2.5","score":81,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-4.5-haiku","score":57.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.5-flash-lite","score":70,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.6-luna","score":81.4,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"inkling-small","score":81.3,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"inkling-small","score":77,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"mimo-v2.5","score":73.6,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"gemini-3.5-flash-lite","score":75.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"rnj-1.5","score":72.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-3-12b-it","score":74.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-oss-20b","score":75.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"rnj-1.5","score":88.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-3-12b-it","score":78,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-oss-20b","score":81.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"rnj-1.5","score":56.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemma-3-12b-it","score":48.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gpt-oss-20b","score":55.7,"metric":"pass@1"},{"benchmark":"aime-2025","model":"rnj-1.5","score":40,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-12b-it","score":18.8,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b","score":46.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"rnj-1.5","score":80,"metric":"percent"},{"benchmark":"mmlu-stem","model":"rnj-1","score":82,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen3-8b","score":92.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-3-12b-it","score":82.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gpt-oss-20b","score":92.2,"metric":"percent"},{"benchmark":"supergpqa","model":"rnj-1.5","score":26.8,"metric":"percent"},{"benchmark":"supergpqa","model":"rnj-1","score":28.2,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-8b","score":39.8,"metric":"percent"},{"benchmark":"supergpqa","model":"gemma-3-12b-it","score":29.3,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-oss-20b","score":42.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"rnj-1.5","score":40,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-3-12b-it","score":2.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-20b","score":1.1,"metric":"percent"},{"benchmark":"enamel","model":"rnj-1.5","score":50.7,"metric":"percent"},{"benchmark":"enamel","model":"gemma-3-12b-it","score":11.5,"metric":"percent"},{"benchmark":"enamel","model":"gpt-oss-20b","score":38.3,"metric":"percent"},{"benchmark":"bfcl-v3","model":"rnj-1.5","score":61.7,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemma-3-12b-it","score":50.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gpt-oss-20b","score":45.9,"metric":"percent"},{"benchmark":"ruler-128k","model":"rnj-1.5","score":76.9,"metric":"percent"},{"benchmark":"ruler-128k","model":"rnj-1","score":28,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen3-8b","score":77.4,"metric":"percent"},{"benchmark":"ruler-128k","model":"gemma-3-12b-it","score":57.1,"metric":"percent"},{"benchmark":"ruler-128k","model":"gpt-oss-20b","score":68.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mercury-2","score":74,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-nano-minimal","score":43,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-4.5-haiku","score":65,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash-lite-thinking","score":71,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3-flash","score":90,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash-thinking","score":79,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-mini-medium","score":80,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-4.5-haiku-thinking","score":67,"metric":"percent"},{"benchmark":"livecodebench","model":"mercury-2","score":67,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-nano-minimal","score":47,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-4.5-haiku","score":51,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-lite-thinking","score":59,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-flash","score":91,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-thinking","score":69,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini-medium","score":69,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-4.5-haiku-thinking","score":62,"metric":"percent"},{"benchmark":"scicode","model":"mercury-2","score":38,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5-nano-minimal","score":29,"metric":"percent"},{"benchmark":"scicode","model":"claude-4.5-haiku","score":34,"metric":"percent"},{"benchmark":"scicode","model":"gemini-2.5-flash-lite-thinking","score":29,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3-flash","score":51,"metric":"percent"},{"benchmark":"scicode","model":"gemini-2.5-flash-thinking","score":39,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5-mini-medium","score":41,"metric":"percent"},{"benchmark":"scicode","model":"claude-4.5-haiku-thinking","score":43,"metric":"percent"},{"benchmark":"ifbench","model":"mercury-2","score":71,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5-nano-minimal","score":33,"metric":"percent"},{"benchmark":"ifbench","model":"claude-4.5-haiku","score":42,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-2.5-flash-lite-thinking","score":53,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-3-flash","score":78,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-2.5-flash-thinking","score":50,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5-mini-medium","score":71,"metric":"percent"},{"benchmark":"ifbench","model":"claude-4.5-haiku-thinking","score":54,"metric":"percent"},{"benchmark":"aime-2025","model":"mercury-2","score":91,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-nano-minimal","score":27,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-4.5-haiku","score":39,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash-lite-thinking","score":69,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3-flash","score":78,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash-thinking","score":57,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-mini-medium","score":48,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-4.5-haiku-thinking","score":84,"metric":"percent"},{"benchmark":"tau2-telecom","model":"mercury-2","score":53,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-nano-minimal","score":26,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-4.5-haiku","score":33,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash-lite-thinking","score":31,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-3-flash","score":80,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash-thinking","score":32,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-mini-medium","score":71,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-4.5-haiku-thinking","score":55,"metric":"percent"},{"benchmark":"tau3-telecom","model":"mercury-2.5","score":96,"metric":"percent"},{"benchmark":"tau3-telecom","model":"mercury-2","score":65,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mercury-2.5","score":79,"metric":"percent"},{"benchmark":"ifbench","model":"mercury-2.5","score":77,"metric":"percent"},{"benchmark":"ifbench","model":"mercury-2","score":69,"metric":"percent"},{"benchmark":"aa-lcr","model":"mercury-2.5","score":68,"metric":"percent"},{"benchmark":"aa-lcr","model":"mercury-2","score":41,"metric":"percent"},{"benchmark":"scicode","model":"mercury-2.5","score":38,"metric":"percent"},{"benchmark":"scicode","model":"mercury-2","score":37,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"mercury-2.5","score":37,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"mercury-2","score":25,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"mercury-2.5","score":33,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"mercury-2","score":18,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"mercury-2.5","score":22,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"mercury-2","score":24,"metric":"percent"},{"benchmark":"tau3-telecom","model":"mercury-voice","score":77.2,"metric":"percent"},{"benchmark":"tau3-telecom","model":"gemma-4-31b-it","score":50,"metric":"percent"},{"benchmark":"tau3-telecom","model":"gpt-4.1","score":48.2,"metric":"percent"},{"benchmark":"tau3-airline","model":"mercury-voice","score":78,"metric":"percent"},{"benchmark":"tau3-airline","model":"gemma-4-31b-it","score":66,"metric":"percent"},{"benchmark":"tau3-airline","model":"gpt-4.1","score":54,"metric":"percent"},{"benchmark":"tau3-retail","model":"mercury-voice","score":69.3,"metric":"percent"},{"benchmark":"tau3-retail","model":"gemma-4-31b-it","score":69.3,"metric":"percent"},{"benchmark":"tau3-retail","model":"gpt-4.1","score":64,"metric":"percent"},{"benchmark":"ifbench","model":"mercury-voice","score":67.4,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-31b-it","score":54.1,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-4.1","score":45.1,"metric":"percent"},{"benchmark":"bfcl-v4-multi-turn","model":"mercury-voice","score":60.5,"metric":"percent"},{"benchmark":"bfcl-v4-multi-turn","model":"gemma-4-31b-it","score":55.6,"metric":"percent"},{"benchmark":"bfcl-v4-multi-turn","model":"gpt-4.1","score":45.5,"metric":"percent"},{"benchmark":"aider-polyglot","model":"jan-code-4b","score":19,"metric":"percent"},{"benchmark":"aider-polyglot","model":"jan-v3","score":18,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-4b-instruct-2507","score":12.9,"metric":"percent"},{"benchmark":"livecodebench","model":"jan-code-4b","score":51,"metric":"percent"},{"benchmark":"livecodebench","model":"jan-v3","score":45.8,"metric":"percent"},{"benchmark":"aime-2025","model":"jan-code-4b","score":53,"metric":"percent"},{"benchmark":"aime-2025","model":"jan-v3","score":47,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-instruct-2507","score":47,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-4b-thinking-2507","score":12.1,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"composer-2","score":61.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"composer-2","score":73.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"composer-2","score":61.7,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"composer-1.5","score":44.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"composer-1.5","score":65.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"composer-1.5","score":47.9,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"composer-1","score":38,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"composer-1","score":56.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"composer-1","score":40,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"claude-opus-4.6","score":58.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.6","score":75.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.6","score":58,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"claude-opus-4.5","score":48.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.5","score":73.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.5","score":76.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.5","score":52.1,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"gpt-5.4","score":63.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.4","score":76.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.4","score":66.5,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"gpt-5.3-codex","score":59.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.3-codex","score":74.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.3-codex","score":64.8,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"gpt-5.2","score":56.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.2","score":68.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2","score":60.5,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"glm-5","score":42.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5","score":66.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-5","score":59.6,"metric":"percent"},{"benchmark":"cursorbench-3.0","model":"kimi-k2.5-thinking","score":36,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2.5-thinking","score":65.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2.5-thinking","score":47.3,"metric":"percent"},{"benchmark":"cursorbench-4.0","model":"composer-2.5","score":27.7,"metric":"percent"},{"benchmark":"frontiercode-main","model":"swe-1.7","score":42.3,"metric":"percent"},{"benchmark":"frontiercode-main","model":"kimi-k2.7-code","score":30.1,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-5.5","score":43,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-opus-4.7","score":38.5,"metric":"percent"},{"benchmark":"frontiercode-main","model":"glm-5.2","score":24.5,"metric":"percent"},{"benchmark":"frontiercode-main","model":"composer-2.5","score":25.6,"metric":"percent"},{"benchmark":"frontiercode-main","model":"swe-1.6","score":9.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"swe-1.7","score":81.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k2.7-code","score":72.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.5","score":84.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.8","score":86.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.7","score":83,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"composer-2.5","score":76,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"swe-1.6","score":39.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"swe-1.7","score":77.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2.7-code","score":73.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.5","score":76.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.2","score":74.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"composer-2.5","score":71.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"swe-1.6","score":58.3,"metric":"percent"},{"benchmark":"frontiercode-main","model":"swe-2","score":50,"metric":"percent"},{"benchmark":"frontiercode-main","model":"kimi-k3","score":44.2,"metric":"percent"},{"benchmark":"frontiercode-main","model":"grok-4.6","score":48,"metric":"percent"},{"benchmark":"frontiercode-main","model":"swe-1.7","score":42,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"swe-2","score":73,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k3","score":68.5,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.6","score":67.5,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-fable-5.1","score":67.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"swe-1.7","score":37.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"swe-2","score":92.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"grok-4.6","score":88.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-fable-5.1","score":91.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-6-astra","score":89.9,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"swe-2","score":27.3,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"kimi-k3","score":21.5,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"swe-1.7","score":7.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"laguna-m.1","score":74.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"laguna-m.1","score":63.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"laguna-m.1","score":49.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"laguna-m.1","score":45.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"laguna-xs.2","score":69.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"laguna-xs.2","score":57.7,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"laguna-xs.2","score":46.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"laguna-xs.2","score":35.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"laguna-m.1","score":72.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"laguna-xs.2","score":68.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"laguna-m.1","score":67.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"laguna-xs.2","score":62.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"laguna-m.1","score":46.9,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"laguna-xs.2","score":44.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"laguna-m.1","score":40.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"laguna-xs.2","score":30.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"laguna-xs-2.1","score":70.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"laguna-xs-2.1","score":63.1,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"laguna-xs-2.1","score":47.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gpt-oss-120b","score":16.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"laguna-xs-2.1","score":37.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"laguna-s-2.1","score":70.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"laguna-s-2.1","score":78.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"laguna-s-2.1","score":59.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"muse-spark-1.1","score":61.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-fable-5","score":80.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"laguna-s-2.1","score":40.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro-thinking-max","score":9,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k3","score":69,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"laguna-s-2.1","score":46.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"deepseek-v4-pro-thinking-max","score":27.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"muse-spark-1.1","score":42.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"laguna-s-2.1","score":49.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"inkling-small","score":52.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-27b","score":51.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":44.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-super-120b-a12b","score":38.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"laguna-xs-2.1","score":33.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mistral-small-4","score":21.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-terra","score":70,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.4","score":52,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k2.7-code","score":31,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-sonnet-4.6","score":30,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"laguna-xs-2.1","score":0.3,"metric":"percent"},{"benchmark":"bbh","model":"mimo-v2.5-pro-base","score":88.4,"metric":"percent"},{"benchmark":"bbh","model":"mimo-v2.5-base","score":87.2,"metric":"percent"},{"benchmark":"mmlu","model":"mimo-v2.5-pro-base","score":89.4,"metric":"percent"},{"benchmark":"mmlu","model":"mimo-v2.5-base","score":86.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mimo-v2.5-pro-base","score":92.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mimo-v2.5-base","score":89.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-v2.5-pro-base","score":68.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-v2.5-base","score":65.8,"metric":"percent"},{"benchmark":"drop","model":"mimo-v2.5-pro-base","score":86.3,"metric":"percent"},{"benchmark":"drop","model":"mimo-v2.5-base","score":83.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"mimo-v2.5-pro-base","score":97.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"mimo-v2.5-base","score":96.5,"metric":"percent"},{"benchmark":"hellaswag","model":"mimo-v2.5-pro-base","score":89.8,"metric":"percent"},{"benchmark":"hellaswag","model":"mimo-v2.5-base","score":88.6,"metric":"percent"},{"benchmark":"winogrande","model":"mimo-v2.5-pro-base","score":85.6,"metric":"percent"},{"benchmark":"winogrande","model":"mimo-v2.5-base","score":84.7,"metric":"percent"},{"benchmark":"triviaqa","model":"mimo-v2.5-pro-base","score":81.3,"metric":"percent"},{"benchmark":"triviaqa","model":"mimo-v2.5-base","score":80.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-v2.5-pro-base","score":66.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-v2.5-base","score":58.1,"metric":"percent"},{"benchmark":"gsm8k","model":"mimo-v2.5-pro-base","score":99.6,"metric":"percent"},{"benchmark":"gsm8k","model":"mimo-v2.5-base","score":83.3,"metric":"percent"},{"benchmark":"math","model":"mimo-v2.5-pro-base","score":86.2,"metric":"percent"},{"benchmark":"math","model":"mimo-v2.5-base","score":67.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mimo-v2.5-pro-base","score":75.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mimo-v2.5-base","score":71.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mimo-v2.5-pro-base","score":74.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mimo-v2.5-base","score":70.9,"metric":"percent"},{"benchmark":"livecodebench","model":"mimo-v2.5-pro-base","score":39.6,"metric":"percent"},{"benchmark":"livecodebench","model":"mimo-v2.5-base","score":35.5,"metric":"percent"},{"benchmark":"swe-bench","model":"mimo-v2.5-pro-base","score":35.7,"metric":"percent"},{"benchmark":"swe-bench","model":"mimo-v2.5-base","score":30.8,"metric":"percent"},{"benchmark":"c-eval","model":"mimo-v2.5-pro-base","score":91.5,"metric":"percent"},{"benchmark":"c-eval","model":"mimo-v2.5-base","score":88.6,"metric":"percent"},{"benchmark":"cmmlu","model":"mimo-v2.5-pro-base","score":90.2,"metric":"percent"},{"benchmark":"cmmlu","model":"mimo-v2.5-base","score":88.2,"metric":"percent"},{"benchmark":"global-mmlu","model":"mimo-v2.5-pro-base","score":83.6,"metric":"percent"},{"benchmark":"global-mmlu","model":"mimo-v2.5-base","score":77.4,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"mimo-v2.5-pro","score":77,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"mimo-v2-pro","score":44,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"mimo-v2.5-pro","score":37,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"mimo-v2-pro","score":0,"metric":"percent"},{"benchmark":"graphwalks-parents-256k","model":"mimo-v2.5-pro","score":97,"metric":"percent"},{"benchmark":"graphwalks-parents-256k","model":"mimo-v2-pro","score":35,"metric":"percent"},{"benchmark":"graphwalks-parents-1m","model":"mimo-v2.5-pro","score":62,"metric":"percent"},{"benchmark":"graphwalks-parents-1m","model":"mimo-v2-pro","score":0,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"mimo-v2.5-pro","score":1581,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"mimo-v2-pro","score":1426,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"kimi-k2.6-thinking","score":1480,"metric":"elo"},{"benchmark":"claweval-pass3","model":"mimo-v2.5-pro","score":63.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"mimo-v2-pro","score":57.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v4-pro-thinking-max","score":59.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"mimo-v2.5","score":62.3,"metric":"percent"},{"benchmark":"hle-with-tools","model":"mimo-v2.5-pro","score":48,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"mimo-v2-pro","score":40,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.4","score":58.7,"metric":"avg@3"},{"benchmark":"hle","model":"mimo-v2.5-pro","score":34,"metric":"avg@3"},{"benchmark":"hle","model":"mimo-v2-pro","score":28,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4","score":42.7,"metric":"avg@3"},{"benchmark":"swe-bench-pro","model":"mimo-v2.5-pro","score":57.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"mimo-v2-pro","score":55,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.6","score":57.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k2.6-thinking","score":58.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"glm-5.1","score":58.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-pro-thinking-max","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"mimo-v2.5","score":56.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mimo-v2.5-pro","score":78.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mimo-v2-pro","score":78,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3.1-pro","score":76.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"mimo-v2.5-pro","score":68.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"mimo-v2-pro","score":57.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"mimo-v2.5","score":65.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"mimo-v2-omni","score":80.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.6","score":77.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mimo-v2.5","score":77.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mimo-v2-omni","score":76.8,"metric":"percent"},{"benchmark":"hrbench4k","model":"mimo-v2.5","score":88.5,"metric":"percent"},{"benchmark":"hrbench4k","model":"mimo-v2-omni","score":83.3,"metric":"percent"},{"benchmark":"hrbench4k","model":"gemini-3-pro","score":86.4,"metric":"percent"},{"benchmark":"omnidocbench","model":"mimo-v2.5","score":87.2,"metric":"percent"},{"benchmark":"omnidocbench","model":"mimo-v2-omni","score":86.7,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-5.4","score":89,"metric":"percent"},{"benchmark":"claw-eval-multimodal","model":"mimo-v2.5","score":23.8,"metric":"percent"},{"benchmark":"claw-eval-multimodal","model":"mimo-v2-omni","score":15.8,"metric":"percent"},{"benchmark":"claw-eval-multimodal","model":"claude-opus-4.6","score":24.8,"metric":"percent"},{"benchmark":"claw-eval-multimodal","model":"claude-sonnet-4.6","score":23.8,"metric":"percent"},{"benchmark":"claw-eval-multimodal","model":"gpt-5.4","score":25.7,"metric":"percent"},{"benchmark":"claw-eval-multimodal","model":"kimi-k2.6-thinking","score":18.8,"metric":"percent"},{"benchmark":"video-mme","model":"mimo-v2.5","score":87.7,"metric":"percent"},{"benchmark":"video-mme","model":"mimo-v2-omni","score":85.3,"metric":"percent"},{"benchmark":"video-mme","model":"gemini-3-pro","score":88.4,"metric":"percent"},{"benchmark":"daily-omni","model":"mimo-v2.5","score":83.5,"metric":"percent"},{"benchmark":"daily-omni","model":"mimo-v2-omni","score":80.5,"metric":"percent"},{"benchmark":"daily-omni","model":"gemini-3-pro","score":84.2,"metric":"percent"},{"benchmark":"videoholmes","model":"mimo-v2.5","score":64,"metric":"percent"},{"benchmark":"videoholmes","model":"mimo-v2-omni","score":59.5,"metric":"percent"},{"benchmark":"claweval-pass3","model":"claude-opus-4.6","score":70.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v4-flash-thinking-max","score":57.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-flash-thinking-max","score":52.6,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"mimo-v2-pro","score":81,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"mimo-v2-flash","score":62.1,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"claude-opus-4.6","score":81.5,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"claude-sonnet-4.6","score":79.2,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gemini-3-pro","score":67.7,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gpt-5.2-thinking-xhigh","score":77,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"mimo-v2-omni","score":81.2,"metric":"percent"},{"benchmark":"claw-eval","model":"mimo-v2-pro","score":61.5,"metric":"percent"},{"benchmark":"claw-eval","model":"mimo-v2-flash","score":48.1,"metric":"percent"},{"benchmark":"claw-eval","model":"claude-opus-4.6","score":66.3,"metric":"percent"},{"benchmark":"claw-eval","model":"claude-sonnet-4.6","score":66.3,"metric":"percent"},{"benchmark":"claw-eval","model":"gemini-3-pro","score":51.9,"metric":"percent"},{"benchmark":"claw-eval","model":"gpt-5.2-thinking-xhigh","score":50,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"mimo-v2-flash","score":1040,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gpt-5.2-thinking-xhigh","score":1462,"metric":"elo"},{"benchmark":"swe-bench-verified","model":"mimo-v2-flash","score":78.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"mimo-v2-pro","score":71.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-sonnet-4.6","score":75.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-pro","score":56.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"mimo-v2-pro","score":96.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"mimo-v2-flash","score":93.5,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"mimo-v2-pro","score":86.7,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"mimo-v2-flash","score":69,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"claude-sonnet-4.6","score":89.2,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"gemini-3-pro","score":76.9,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"gpt-5.2-thinking-xhigh","score":79,"metric":"percent"},{"benchmark":"mmau-pro","model":"mimo-v2-omni","score":69.4,"metric":"percent"},{"benchmark":"mmau-pro","model":"gemini-3-pro","score":65,"metric":"percent"},{"benchmark":"mmau-pro","model":"gemini-3-flash","score":67,"metric":"percent"},{"benchmark":"big-bench-audio","model":"mimo-v2-omni","score":94,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gemini-3-pro","score":91.2,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gemini-3-flash","score":99.2,"metric":"percent"},{"benchmark":"video-mme","model":"gemini-3-flash","score":76.7,"metric":"percent"},{"benchmark":"futureomni","model":"mimo-v2-omni","score":66.7,"metric":"percent"},{"benchmark":"futureomni","model":"gemini-3-pro","score":60.3,"metric":"percent"},{"benchmark":"futureomni","model":"gemini-3-flash","score":62.9,"metric":"percent"},{"benchmark":"mm-browsecomp","model":"mimo-v2-omni","score":52,"metric":"percent"},{"benchmark":"mm-browsecomp","model":"claude-opus-4.6","score":59.3,"metric":"percent"},{"benchmark":"mm-browsecomp","model":"gemini-3-pro","score":37.2,"metric":"percent"},{"benchmark":"mm-browsecomp","model":"gemini-3-flash","score":41.9,"metric":"percent"},{"benchmark":"mm-browsecomp","model":"gpt-5.2-thinking-xhigh","score":47.4,"metric":"percent"},{"benchmark":"omnigaia","model":"mimo-v2-omni","score":49.8,"metric":"percent"},{"benchmark":"omnigaia","model":"claude-opus-4.6","score":59.7,"metric":"percent"},{"benchmark":"omnigaia","model":"gemini-3-pro","score":62.5,"metric":"percent"},{"benchmark":"omnigaia","model":"gemini-3-flash","score":51.7,"metric":"percent"},{"benchmark":"omnigaia","model":"gpt-5.2-thinking-xhigh","score":58.3,"metric":"percent"},{"benchmark":"claw-eval","model":"mimo-v2-omni","score":54.8,"metric":"percent"},{"benchmark":"claw-eval","model":"gemini-3-flash","score":47.1,"metric":"percent"},{"benchmark":"claw-eval","model":"gpt-5.2-thinking-xhigh","score":59.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mimo-v2-omni","score":74.8,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"mimo-v2-omni","score":1410,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gemini-3-flash","score":1191,"metric":"elo"},{"benchmark":"pinchbench-avg","model":"gemini-3-flash","score":72.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"mimo-v2.6-pro-rl","score":71.9,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"mimo-v2.6-flash-rl","score":67.9,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"mimo-v2.5-pro","score":19,"metric":"percent"},{"benchmark":"programbench","model":"mimo-v2.6-pro-rl","score":26.5,"metric":"percent"},{"benchmark":"programbench","model":"mimo-v2.6-flash-rl","score":26,"metric":"percent"},{"benchmark":"programbench","model":"mimo-v2.5-pro","score":12.5,"metric":"percent"},{"benchmark":"programbench","model":"gpt-5.6-sol","score":25,"metric":"percent"},{"benchmark":"programbench","model":"claude-fable-5","score":33,"metric":"percent"},{"benchmark":"automationbench","model":"mimo-v2.6-pro-rl","score":53.1,"metric":"percent"},{"benchmark":"automationbench","model":"mimo-v2.6-flash-rl","score":52.3,"metric":"percent"},{"benchmark":"automationbench","model":"mimo-v2.5-pro","score":16,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"mimo-v2.6-pro-rl","score":76.9,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"mimo-v2.6-flash-rl","score":73.6,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"mimo-v2.5-pro","score":49.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"claude-opus-5","score":80.6,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"mimo-v2.6-pro-rl","score":1673,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"mimo-v2.5-pro","score":1107,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-fable-5","score":1595,"metric":"elo"},{"benchmark":"agents-last-exam","model":"mimo-v2.6-pro-rl","score":31.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"mimo-v2.6-flash-rl","score":27.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"mimo-v2.5-pro","score":13.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5","score":31.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol","score":30.8,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"mimo-v2.6-pro-rl","score":34.9,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"mimo-v2.6-flash-rl","score":28.8,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"mimo-v2.5-pro","score":1.5,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-opus-5","score":49,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-fable-5","score":42.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mimo-v2.6-pro-rl","score":89.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mimo-v2.6-flash-rl","score":87.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mimo-v2.5-pro","score":65.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"mimo-v2.6-pro-rl","score":82,"metric":"percent"},{"benchmark":"osworld-verified","model":"mimo-v2.6-flash-rl","score":80.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-opus-5","score":83.4,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-fable-5","score":86,"metric":"percent"},{"benchmark":"jobbench","model":"mimo-v2.6-pro-rl","score":62,"metric":"percent"},{"benchmark":"jobbench","model":"mimo-v2.6-flash-rl","score":61.2,"metric":"percent"},{"benchmark":"jobbench","model":"mimo-v2.5-pro","score":25,"metric":"percent"},{"benchmark":"cybergym","model":"mimo-v2.6-pro-rl","score":94,"metric":"percent"},{"benchmark":"cybergym","model":"mimo-v2.6-flash-rl","score":95.1,"metric":"percent"},{"benchmark":"cybergym","model":"mimo-v2.5-pro","score":40,"metric":"percent"},{"benchmark":"exploitgym","model":"mimo-v2.6-pro-rl","score":17.8,"metric":"percent"},{"benchmark":"exploitgym","model":"mimo-v2.6-flash-rl","score":6,"metric":"percent"},{"benchmark":"exploitgym","model":"mimo-v2.5-pro","score":0.2,"metric":"percent"},{"benchmark":"exploitbench","model":"mimo-v2.6-pro-rl","score":47.9,"metric":"percent"},{"benchmark":"exploitbench","model":"mimo-v2.6-flash-rl","score":25.3,"metric":"percent"},{"benchmark":"exploitbench","model":"mimo-v2.5-pro","score":16.6,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"mimo-v2.6-pro-rl","score":66.3,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"mimo-v2.6-flash-rl","score":47.5,"metric":"percent"},{"benchmark":"sec-bench-pro","model":"mimo-v2.5-pro","score":17.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-9b","score":60,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mimo-v2.6-distill-qwen-9b","score":61.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-9b","score":32,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"mimo-v2.6-distill-qwen-9b","score":44.6,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.5-9b","score":5,"metric":"percent"},{"benchmark":"automationbench","model":"mimo-v2.6-distill-qwen-9b","score":30.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-9b","score":27,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mimo-v2.6-distill-qwen-9b","score":37.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.5-9b","score":25.9,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"mimo-v2.6-distill-qwen-9b","score":35.2,"metric":"percent"},{"benchmark":"officeqa-pro","model":"qwen3.5-9b","score":9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"mimo-v2.6-distill-qwen-9b","score":19.5,"metric":"percent"},{"benchmark":"jobbench","model":"qwen3.5-9b","score":2.6,"metric":"percent"},{"benchmark":"jobbench","model":"mimo-v2.6-distill-qwen-9b","score":18.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"step-5-preview","score":67.7,"metric":"percent"},{"benchmark":"programbench","model":"step-5-preview","score":80.5,"metric":"percent"},{"benchmark":"programbench","model":"glm-5.3","score":72,"metric":"percent"},{"benchmark":"programbench","model":"gpt-6-astra","score":85.4,"metric":"percent"},{"benchmark":"programbench","model":"claude-opus-5","score":82.3,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"glm-5.3","score":41.9,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"step-5-preview","score":33.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"step-5-preview","score":29.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"glm-5.3","score":28.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra","score":33.3,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.3","score":1645,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"step-5-preview","score":1566,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"kimi-k3","score":1524,"metric":"elo"},{"benchmark":"frontierfinance","model":"step-5-preview","score":66.4,"metric":"percent"},{"benchmark":"frontierfinance","model":"glm-5.3","score":64.1,"metric":"percent"},{"benchmark":"frontierfinance","model":"kimi-k3","score":62.6,"metric":"percent"},{"benchmark":"frontierfinance","model":"claude-opus-5","score":69.7,"metric":"percent"},{"benchmark":"frontierfinance","model":"gpt-6-astra","score":55,"metric":"percent"},{"benchmark":"draco","model":"step-5-preview","score":83.3,"metric":"percent"},{"benchmark":"draco","model":"glm-5.3","score":82.3,"metric":"percent"},{"benchmark":"draco","model":"kimi-k3","score":78.5,"metric":"percent"},{"benchmark":"draco","model":"claude-opus-5","score":87.6,"metric":"percent"},{"benchmark":"draco","model":"gpt-6-astra","score":76.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"step-3.7-flash","score":47.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"step-3.5-flash-20260204","score":35.7,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemini-3.5-flash","score":40.2,"metric":"avg@3"},{"benchmark":"browsecomp","model":"step-3.7-flash","score":75.8,"metric":"percent"},{"benchmark":"browsecomp","model":"step-3.5-flash-20260204","score":69,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.5","score":90.1,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"step-3.7-flash","score":92.8,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"step-3.5-flash-20260204","score":85.5,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"deepseek-v4-flash-thinking-max","score":90.6,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"gpt-5.5","score":94,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"claude-opus-4.7","score":91.7,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"glm-5.1","score":91.2,"metric":"percent"},{"benchmark":"deepsearchqa","model":"step-3.7-flash","score":81.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"step-3.5-flash-20260204","score":73.4,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v4-flash-thinking-max","score":79.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-5.5","score":85.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-4.7","score":82.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"glm-5.1","score":81.3,"metric":"percent"},{"benchmark":"researchrubrics","model":"step-3.7-flash","score":71.7,"metric":"percent"},{"benchmark":"researchrubrics","model":"deepseek-v4-flash-thinking-max","score":66.2,"metric":"percent"},{"benchmark":"researchrubrics","model":"gemini-3.5-flash","score":63.6,"metric":"percent"},{"benchmark":"researchrubrics","model":"deepseek-v4-pro-thinking-max","score":68.3,"metric":"percent"},{"benchmark":"researchrubrics","model":"gpt-5.5","score":61.5,"metric":"percent"},{"benchmark":"researchrubrics","model":"claude-opus-4.7","score":73.9,"metric":"percent"},{"benchmark":"researchrubrics","model":"kimi-k2.6-thinking","score":63,"metric":"percent"},{"benchmark":"researchrubrics","model":"glm-5.1","score":67.9,"metric":"percent"},{"benchmark":"toolathlon","model":"step-3.7-flash","score":49.5,"metric":"percent"},{"benchmark":"toolathlon","model":"step-3.5-flash-20260204","score":33.3,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v4-flash-thinking-max","score":52.8,"metric":"percent"},{"benchmark":"toolathlon","model":"deepseek-v4-pro-thinking-max","score":56.6,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.5","score":60.2,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-opus-4.7","score":65.4,"metric":"percent"},{"benchmark":"toolathlon","model":"kimi-k2.6-thinking","score":54.6,"metric":"percent"},{"benchmark":"toolathlon","model":"glm-5.1","score":48.1,"metric":"percent"},{"benchmark":"claweval-pass3","model":"step-3.7-flash","score":67.1,"metric":"percent"},{"benchmark":"claweval-pass3","model":"step-3.5-flash-20260204","score":43.6,"metric":"percent"},{"benchmark":"claweval-pass3","model":"glm-5.1","score":62.3,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"deepseek-v4-flash-thinking-max","score":1414,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"kimi-k2.6-thinking","score":1481,"metric":"elo"},{"benchmark":"swe-bench-multilingual","model":"step-3.7-flash","score":72.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"step-3.5-flash-20260204","score":67.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"step-3.7-flash","score":56.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"step-3.5-flash-20260204","score":51.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-flash-thinking-max","score":55.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"step-3.7-flash","score":76.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"step-3.7-flash","score":59.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"step-3.5-flash-20260204","score":53.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash-thinking-max","score":62,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro-thinking-max","score":72,"metric":"percent"},{"benchmark":"aa-lcr","model":"step-3.7-flash","score":63.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"step-3.5-flash-20260204","score":45.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-flash-thinking-max","score":63.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-3.5-flash","score":71,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-pro-thinking-max","score":66.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-opus-4.7","score":70.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2.6-thinking","score":69.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.1","score":64.9,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"step-3.7-flash","score":79.16,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"kimi-k2.6-thinking","score":78.24,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"glm-5v-turbo","score":78.2,"metric":"percent"},{"benchmark":"simplevqa-with-tools","model":"gpt-5.5","score":79.11,"metric":"percent"},{"benchmark":"worldvqa-with-tools","model":"step-3.7-flash","score":58.1,"metric":"percent"},{"benchmark":"worldvqa-with-tools","model":"kimi-k2.6-thinking","score":55.98,"metric":"percent"},{"benchmark":"worldvqa-with-tools","model":"glm-5v-turbo","score":47.81,"metric":"percent"},{"benchmark":"worldvqa-with-tools","model":"gpt-5.5","score":54.58,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"step-3.7-flash","score":58.96,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"kimi-k2.6-thinking","score":57.12,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"gpt-5.5","score":65.68,"metric":"percent"},{"benchmark":"v-star-with-tools","model":"step-3.7-flash","score":95.29,"metric":"percent"},{"benchmark":"v-star-with-tools","model":"glm-5v-turbo","score":89,"metric":"percent"},{"benchmark":"v-star-with-tools","model":"gemini-3-flash","score":96.3,"metric":"percent"},{"benchmark":"bbh","model":"step-3.5-flash-base-midtrain","score":87.3,"metric":"percent"},{"benchmark":"bbh","model":"step-3.5-flash-base","score":88.2,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3.1-base","score":88.2,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3.2-exp-base","score":88.7,"metric":"percent"},{"benchmark":"mmlu","model":"step-3.5-flash-base-midtrain","score":83.4,"metric":"percent"},{"benchmark":"mmlu","model":"step-3.5-flash-base","score":85.8,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3.1-base","score":87.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3.2-exp-base","score":87.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"step-3.5-flash-base-midtrain","score":87.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"step-3.5-flash-base","score":89.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3.1-base","score":90,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3.2-exp-base","score":90.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"step-3.5-flash-base-midtrain","score":63.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"step-3.5-flash-base","score":62.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.1-base","score":58.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.2-exp-base","score":62.1,"metric":"percent"},{"benchmark":"hellaswag","model":"step-3.5-flash-base-midtrain","score":91,"metric":"percent"},{"benchmark":"hellaswag","model":"step-3.5-flash-base","score":90.2,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v3.1-base","score":89.2,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v3.2-exp-base","score":89.4,"metric":"percent"},{"benchmark":"winogrande","model":"step-3.5-flash-base-midtrain","score":75.8,"metric":"percent"},{"benchmark":"winogrande","model":"step-3.5-flash-base","score":79.1,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v3.1-base","score":85.9,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v3.2-exp-base","score":85.6,"metric":"percent"},{"benchmark":"gpqa","model":"step-3.5-flash-base-midtrain","score":43.8,"metric":"percent"},{"benchmark":"gpqa","model":"step-3.5-flash-base","score":41.7,"metric":"percent"},{"benchmark":"gpqa","model":"mimo-v2-flash-base","score":43.5,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4.5-base","score":33.5,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v3.1-base","score":43.1,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v3.2-exp-base","score":37.3,"metric":"percent"},{"benchmark":"gpqa","model":"kimi-k2-base","score":43.1,"metric":"percent"},{"benchmark":"supergpqa","model":"step-3.5-flash-base-midtrain","score":41.2,"metric":"percent"},{"benchmark":"supergpqa","model":"step-3.5-flash-base","score":41,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3.1-base","score":42.3,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3.2-exp-base","score":43.6,"metric":"percent"},{"benchmark":"simpleqa","model":"step-3.5-flash-base-midtrain","score":28.4,"metric":"percent"},{"benchmark":"simpleqa","model":"step-3.5-flash-base","score":31.6,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3.1-base","score":26.3,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3.2-exp-base","score":27,"metric":"percent"},{"benchmark":"gsm8k","model":"step-3.5-flash-base-midtrain","score":88.9,"metric":"percent"},{"benchmark":"gsm8k","model":"step-3.5-flash-base","score":88.2,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4.5-base","score":87.6,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3.1-base","score":91.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3.2-exp-base","score":91.1,"metric":"percent"},{"benchmark":"math","model":"step-3.5-flash-base-midtrain","score":65.7,"metric":"percent"},{"benchmark":"math","model":"step-3.5-flash-base","score":66.8,"metric":"percent"},{"benchmark":"math","model":"glm-4.5-base","score":62.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3.1-base","score":62.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3.2-exp-base","score":62.5,"metric":"percent"},{"benchmark":"humaneval","model":"step-3.5-flash-base-midtrain","score":67,"metric":"percent"},{"benchmark":"humaneval","model":"step-3.5-flash-base","score":81.1,"metric":"percent"},{"benchmark":"humaneval","model":"mimo-v2-flash-base","score":77.4,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4.5-base","score":79.8,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v3.1-base","score":72.5,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v3.2-exp-base","score":67.7,"metric":"percent"},{"benchmark":"humaneval","model":"kimi-k2-base","score":84.8,"metric":"percent"},{"benchmark":"mbpp","model":"step-3.5-flash-base-midtrain","score":79,"metric":"percent"},{"benchmark":"mbpp","model":"step-3.5-flash-base","score":79.4,"metric":"percent"},{"benchmark":"mbpp","model":"mimo-v2-flash-base","score":81,"metric":"percent"},{"benchmark":"mbpp","model":"glm-4.5-base","score":81.6,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v3.1-base","score":74.6,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v3.2-exp-base","score":75.6,"metric":"percent"},{"benchmark":"mbpp","model":"kimi-k2-base","score":89,"metric":"percent"},{"benchmark":"humaneval-plus","model":"step-3.5-flash-base-midtrain","score":75,"metric":"percent"},{"benchmark":"humaneval-plus","model":"step-3.5-flash-base","score":72,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3.1-base","score":64.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3.2-exp-base","score":67.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"step-3.5-flash-base-midtrain","score":62.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"step-3.5-flash-base","score":70.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3.1-base","score":72.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3.2-exp-base","score":69.8,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"step-3.5-flash-base-midtrain","score":63,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"step-3.5-flash-base","score":67.7,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"deepseek-v3.1-base","score":45.9,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"deepseek-v3.2-exp-base","score":45.7,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"step-3.5-flash-base-midtrain","score":47.9,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"step-3.5-flash-base","score":58,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"deepseek-v3.1-base","score":52.5,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"deepseek-v3.2-exp-base","score":50.6,"metric":"percent"},{"benchmark":"c-eval","model":"step-3.5-flash-base-midtrain","score":87.2,"metric":"percent"},{"benchmark":"c-eval","model":"step-3.5-flash-base","score":89.6,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3.1-base","score":90,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3.2-exp-base","score":91,"metric":"percent"},{"benchmark":"cmmlu","model":"step-3.5-flash-base-midtrain","score":86.9,"metric":"percent"},{"benchmark":"cmmlu","model":"step-3.5-flash-base","score":88.9,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v3.1-base","score":88.8,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v3.2-exp-base","score":88.9,"metric":"percent"},{"benchmark":"csimpleqa","model":"step-3.5-flash-base-midtrain","score":58.1,"metric":"percent"},{"benchmark":"csimpleqa","model":"step-3.5-flash-base","score":63.2,"metric":"percent"},{"benchmark":"csimpleqa","model":"glm-4.5-base","score":70.1,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v3.1-base","score":70.9,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v3.2-exp-base","score":68,"metric":"percent"},{"benchmark":"big-bench-audio","model":"step-audio-r1.1","score":96.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-5","score":93.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5","score":83.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5","score":26,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5","score":71.1,"metric":"percent"},{"benchmark":"hmmt-2025","model":"qwen3-235b-a22b-thinking-2507","score":82.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b-thinking-2507","score":74.5,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-235b-a22b-thinking-2507","score":60.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"glm-4.6","score":88.7,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.6","score":79.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-4.6","score":17.2,"metric":"percent"},{"benchmark":"multichallenge","model":"glm-4.6","score":54.9,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.1-terminus-thinking","score":74.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v3.1-terminus-thinking","score":19.3,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v3.1-terminus-thinking","score":54.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"kimi-k2-thinking","score":86.5,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-thinking","score":79.2,"metric":"percent"},{"benchmark":"multichallenge","model":"kimi-k2-thinking","score":66.4,"metric":"percent"},{"benchmark":"hmmt-2025","model":"rlvr-8b-0926","score":75.4,"metric":"percent"},{"benchmark":"livecodebench","model":"rlvr-8b-0926","score":70.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"rlvr-8b-0926","score":9.3,"metric":"percent"},{"benchmark":"multichallenge","model":"rlvr-8b-0926","score":33.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"pacore-8b","score":94.5,"metric":"percent"},{"benchmark":"livecodebench","model":"pacore-8b","score":78.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"pacore-8b","score":16.2,"metric":"percent"},{"benchmark":"multichallenge","model":"pacore-8b","score":47,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"longcat-2.0","score":70.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.5","score":73.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.7","score":71.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"longcat-2.0","score":59.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"longcat-2.0","score":77.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.8","score":84.8,"metric":"percent"},{"benchmark":"forte","model":"longcat-2.0","score":73.2,"metric":"percent"},{"benchmark":"forte","model":"gemini-3.1-pro","score":70.3,"metric":"percent"},{"benchmark":"forte","model":"gpt-5.5","score":77.8,"metric":"percent"},{"benchmark":"forte","model":"claude-opus-4.6","score":73.2,"metric":"percent"},{"benchmark":"forte","model":"claude-opus-4.7","score":77.6,"metric":"percent"},{"benchmark":"forte","model":"claude-opus-4.8","score":77.2,"metric":"percent"},{"benchmark":"browsecomp","model":"longcat-2.0","score":79.9,"metric":"percent"},{"benchmark":"rw-search","model":"longcat-2.0","score":78.8,"metric":"percent"},{"benchmark":"rw-search","model":"gemini-3.1-pro","score":76.3,"metric":"percent"},{"benchmark":"rw-search","model":"gpt-5.5","score":85.3,"metric":"percent"},{"benchmark":"rw-search","model":"claude-opus-4.6","score":81.3,"metric":"percent"},{"benchmark":"rw-search","model":"claude-opus-4.7","score":79.3,"metric":"percent"},{"benchmark":"rw-search","model":"claude-opus-4.8","score":77.3,"metric":"percent"},{"benchmark":"ifeval","model":"longcat-2.0","score":90,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-3.1-pro","score":96.1,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-5.5","score":95,"metric":"percent"},{"benchmark":"ifeval","model":"claude-opus-4.6","score":92.2,"metric":"percent"},{"benchmark":"ifeval","model":"claude-opus-4.7","score":88.7,"metric":"percent"},{"benchmark":"ifeval","model":"claude-opus-4.8","score":86,"metric":"percent"},{"benchmark":"writingbench","model":"longcat-2.0","score":83.8,"metric":"percent"},{"benchmark":"writingbench","model":"gemini-3.1-pro","score":83.7,"metric":"percent"},{"benchmark":"writingbench","model":"gpt-5.5","score":84.7,"metric":"percent"},{"benchmark":"writingbench","model":"claude-opus-4.7","score":85.3,"metric":"percent"},{"benchmark":"writingbench","model":"claude-opus-4.8","score":85.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"longcat-2.0","score":81.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3.1-pro","score":90,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.5","score":79.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.7","score":81.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.8","score":75.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"longcat-2.0","score":88.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.8","score":92.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"longcat-flash-lite-sparse","score":68.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"longcat-flash-lite-sparse","score":40.63,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"longcat-flash-lite-sparse","score":59.33,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"longcat-flash-lite-sparse","score":33.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"longcat-flash-lite-sparse","score":95.18,"metric":"percent"},{"benchmark":"vitabench","model":"longcat-flash-lite-sparse","score":21.67,"metric":"percent"},{"benchmark":"mcp-atlas","model":"longcat-flash-lite-sparse","score":45.6,"metric":"percent"},{"benchmark":"browsecomp","model":"longcat-flash-lite-sparse","score":48.62,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"longcat-flash-lite-sparse","score":61.94,"metric":"percent"},{"benchmark":"rw-search","model":"longcat-flash-lite-sparse","score":68.5,"metric":"percent"},{"benchmark":"mmlu","model":"longcat-flash-lite-sparse","score":85.31,"metric":"percent"},{"benchmark":"mmlu-pro","model":"longcat-flash-lite-sparse","score":79.24,"metric":"percent"},{"benchmark":"cmmlu","model":"longcat-flash-lite-sparse","score":84.25,"metric":"percent"},{"benchmark":"c-eval","model":"longcat-flash-lite-sparse","score":85.76,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"longcat-flash-lite-sparse","score":69.49,"metric":"percent"},{"benchmark":"math500","model":"longcat-flash-lite-sparse","score":95.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"longcat-flash-lite-sparse","score":65.73,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"longcat-flash-lite-sparse","score":40.53,"metric":"percent"},{"benchmark":"beyondaime","model":"longcat-flash-lite-sparse","score":44.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"longcat-flash-lite-sparse","score":49.38,"metric":"percent"},{"benchmark":"longbench-v2","model":"longcat-flash-lite-sparse","score":52.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"longcat-flash-lite-sparse","score":48,"metric":"percent"},{"benchmark":"mmmu-pro","model":"longcat-next","score":60.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-omni-30b-a3b-instruct","score":57,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-minimal","score":62.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-flash-lite","score":64.1,"metric":"percent"},{"benchmark":"mmmu","model":"longcat-next","score":70.6,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-omni-30b-a3b-instruct","score":69.1,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-minimal","score":74.4,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-flash-lite","score":74.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"longcat-next","score":83.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-omni-30b-a3b-instruct","score":75.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-5-minimal","score":50.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-2.5-flash-lite","score":78.2,"metric":"percent"},{"benchmark":"mathvision","model":"longcat-next","score":64.7,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-omni-30b-a3b-instruct","score":56.3,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-minimal","score":45.8,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.5-flash-lite","score":61.9,"metric":"percent"},{"benchmark":"visulogic","model":"longcat-next","score":29.4,"metric":"percent"},{"benchmark":"visulogic","model":"qwen3-omni-30b-a3b-instruct","score":20,"metric":"percent"},{"benchmark":"visulogic","model":"gemini-2.5-flash-lite","score":26.1,"metric":"percent"},{"benchmark":"visulogic","model":"qwen3-vl-30b-a3b-instruct","score":23,"metric":"percent"},{"benchmark":"babyvision","model":"longcat-next","score":14.4,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-omni-30b-a3b-instruct","score":11.9,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-2.5-flash-lite","score":19.6,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-vl-30b-a3b-instruct","score":16,"metric":"percent"},{"benchmark":"charxiv-dq","model":"longcat-next","score":89.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-omni-30b-a3b-instruct","score":78.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5-minimal","score":79.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-2.5-flash-lite","score":91.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"longcat-next","score":60.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-omni-30b-a3b-instruct","score":42.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5-minimal","score":57.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-flash-lite","score":60,"metric":"percent"},{"benchmark":"chartqa","model":"longcat-next","score":88,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-omni-30b-a3b-instruct","score":86.8,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5-minimal","score":59.1,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-flash-lite","score":79,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-30b-a3b-instruct","score":86.8,"metric":"percent"},{"benchmark":"infovqa","model":"longcat-next","score":83.3,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-omni-30b-a3b-instruct","score":84.4,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-5-minimal","score":69.9,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-2.5-flash-lite","score":82.2,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-30b-a3b-instruct","score":81.8,"metric":"percent"},{"benchmark":"docvqa","model":"longcat-next","score":94.2,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-omni-30b-a3b-instruct","score":94.1,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5-minimal","score":89.6,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-flash-lite","score":91.8,"metric":"percent"},{"benchmark":"ocrbench","model":"longcat-next","score":86.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-omni-30b-a3b-instruct","score":85.4,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5-minimal","score":78.7,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-flash-lite","score":84.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"longcat-next","score":58.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-omni-30b-a3b-instruct","score":62,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gpt-5-minimal","score":48.2,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemini-2.5-flash-lite","score":51.5,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"longcat-next","score":59.3,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-omni-30b-a3b-instruct","score":60.5,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gpt-5-minimal","score":37.7,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gemini-2.5-flash-lite","score":39.5,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-30b-a3b-instruct","score":57.8,"metric":"percent"},{"benchmark":"osworld-g","model":"longcat-next","score":58.3,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-omni-30b-a3b-instruct","score":60.3,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-30b-a3b-instruct","score":60.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"longcat-next","score":88.3,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-omni-30b-a3b-instruct","score":91.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-30b-a3b-instruct","score":87.7,"metric":"percent"},{"benchmark":"mmstar","model":"longcat-next","score":69.3,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-omni-30b-a3b-instruct","score":68.5,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-minimal","score":65.2,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-flash-lite","score":74.93,"metric":"percent"},{"benchmark":"realworldqa","model":"longcat-next","score":72,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-omni-30b-a3b-instruct","score":72.9,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5-minimal","score":77.3,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-2.5-flash-lite","score":70.5,"metric":"percent"},{"benchmark":"countbench","model":"longcat-next","score":82.1,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-omni-30b-a3b-instruct","score":83.8,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5-minimal","score":87.8,"metric":"percent"},{"benchmark":"countbench","model":"gemini-2.5-flash-lite","score":90,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-30b-a3b-instruct","score":90.6,"metric":"percent"},{"benchmark":"asr-librispeech-clean","model":"longcat-next","score":1.63,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"qwen3-omni-30b-a3b-instruct","score":1.22,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"longcat-next","score":3.42,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"qwen3-omni-30b-a3b-instruct","score":2.48,"metric":"wer"},{"benchmark":"tau2-airline","model":"longcat-next","score":56.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-omni-30b-a3b-instruct","score":27,"metric":"percent"},{"benchmark":"tau2-retail","model":"longcat-next","score":73.68,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-omni-30b-a3b-instruct","score":40.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"longcat-next","score":62.06,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-omni-30b-a3b-instruct","score":4.39,"metric":"percent"},{"benchmark":"vitabench","model":"longcat-next","score":5.8,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3-next-80b-a3b-instruct","score":5.8,"metric":"percent"},{"benchmark":"swe-bench","model":"longcat-next","score":43,"metric":"percent"},{"benchmark":"terminal-bench","model":"longcat-next","score":18.75,"metric":"percent"},{"benchmark":"mmlu","model":"longcat-next","score":83.95,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-omni-30b-a3b-instruct","score":87.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"longcat-next","score":77.02,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-omni-30b-a3b-instruct","score":79.89,"metric":"percent"},{"benchmark":"c-eval","model":"longcat-next","score":86.8,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-omni-30b-a3b-instruct","score":88.5,"metric":"percent"},{"benchmark":"cmmlu","model":"longcat-next","score":82.13,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-omni-30b-a3b-instruct","score":85.76,"metric":"percent"},{"benchmark":"matholympiadbench","model":"deepseek-v3.2-thinking","score":14.7,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"deepseek-v3.2-thinking","score":77.9,"metric":"percent"},{"benchmark":"proofnet-test","model":"deepseek-v3.2-thinking","score":20.4,"metric":"percent"},{"benchmark":"proverbench","model":"deepseek-v3.2-thinking","score":42.8,"metric":"percent"},{"benchmark":"putnambench","model":"deepseek-v3.2-thinking","score":5.8,"metric":"percent"},{"benchmark":"matholympiadbench","model":"kimi-k2.5-thinking","score":7.5,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"kimi-k2.5-thinking","score":76.6,"metric":"percent"},{"benchmark":"proofnet-test","model":"kimi-k2.5-thinking","score":19.9,"metric":"percent"},{"benchmark":"proverbench","model":"kimi-k2.5-thinking","score":44.3,"metric":"percent"},{"benchmark":"putnambench","model":"kimi-k2.5-thinking","score":1.2,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"claude-opus-4.5-thinking","score":65.6,"metric":"percent"},{"benchmark":"proofnet-test","model":"claude-opus-4.5-thinking","score":35,"metric":"percent"},{"benchmark":"matholympiadbench","model":"gemini-3-pro","score":3.9,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"gemini-3-pro","score":56.2,"metric":"percent"},{"benchmark":"proofnet-test","model":"gemini-3-pro","score":22,"metric":"percent"},{"benchmark":"proverbench","model":"gemini-3-pro","score":33.5,"metric":"percent"},{"benchmark":"putnambench","model":"gemini-3-pro","score":1.2,"metric":"percent"},{"benchmark":"matholympiadbench","model":"longcat-flash-prover","score":35.8,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"longcat-flash-prover","score":93.9,"metric":"percent"},{"benchmark":"proofnet-test","model":"longcat-flash-prover","score":47.3,"metric":"percent"},{"benchmark":"proverbench","model":"longcat-flash-prover","score":66.5,"metric":"percent"},{"benchmark":"putnambench","model":"longcat-flash-prover","score":28.9,"metric":"percent"},{"benchmark":"aime-2025","model":"longcat-flash-prover","score":97.7,"metric":"percent"},{"benchmark":"hmmt-2025","model":"longcat-flash-prover","score":90.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"longcat-flash-prover","score":77.3,"metric":"percent"},{"benchmark":"amobench","model":"longcat-flash-prover","score":62.2,"metric":"percent"},{"benchmark":"amobench-zh","model":"longcat-flash-prover","score":57.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"longcat-flash-prover","score":79.2,"metric":"percent"},{"benchmark":"livecodebench","model":"longcat-flash-prover","score":81.8,"metric":"percent"},{"benchmark":"ojbench","model":"longcat-flash-prover","score":41.8,"metric":"percent"},{"benchmark":"aime-2025","model":"longcat-flash-thinking-zigzag","score":99.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"longcat-flash-thinking-zigzag","score":93.5,"metric":"percent"},{"benchmark":"amobench","model":"longcat-flash-thinking-zigzag","score":60.4,"metric":"percent"},{"benchmark":"amobench-zh","model":"longcat-flash-thinking-zigzag","score":58.3,"metric":"percent"},{"benchmark":"browsecomp","model":"longcat-flash-thinking-zigzag","score":55.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"longcat-flash-thinking-zigzag","score":71.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"longcat-flash-thinking-zigzag","score":86.8,"metric":"percent"},{"benchmark":"tau2-airline","model":"longcat-flash-thinking-zigzag","score":76.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"longcat-flash-thinking-zigzag","score":97.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"longcat-flash-thinking-zigzag","score":25.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"longcat-flash-thinking-zigzag","score":80.6,"metric":"percent"},{"benchmark":"livecodebench","model":"longcat-flash-thinking-zigzag","score":81.7,"metric":"percent"},{"benchmark":"ojbench","model":"longcat-flash-thinking-zigzag","score":41.2,"metric":"percent"},{"benchmark":"visualprobe","model":"step-3.7-flash","score":65.05,"metric":"percent"},{"benchmark":"visualprobe","model":"kimi-k2.6-thinking","score":64.47,"metric":"percent"},{"benchmark":"visualprobe","model":"glm-5v-turbo","score":53.01,"metric":"percent"},{"benchmark":"visualprobe","model":"gemini-3-flash","score":69.9,"metric":"percent"},{"benchmark":"android-daily","model":"gemini-3-flash","score":63.21,"metric":"percent"},{"benchmark":"android-daily","model":"step-3.7-flash","score":61.87,"metric":"percent"},{"benchmark":"android-daily","model":"kimi-k2.6-thinking","score":53.36,"metric":"percent"},{"benchmark":"android-daily","model":"glm-5v-turbo","score":51.68,"metric":"percent"},{"benchmark":"arc-challenge","model":"ling-3.0-flash-base","score":96.27,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3-super-120b-a12b-base","score":96.27,"metric":"percent"},{"benchmark":"arc-challenge","model":"hy3-preview-base","score":94.58,"metric":"percent"},{"benchmark":"arc-challenge","model":"mimo-v2.5-base","score":95.59,"metric":"percent"},{"benchmark":"agieval","model":"ling-3.0-flash-base","score":77.5,"metric":"percent"},{"benchmark":"agieval","model":"nemotron-3-super-120b-a12b-base","score":67.08,"metric":"percent"},{"benchmark":"agieval","model":"hy3-preview-base","score":77.61,"metric":"percent"},{"benchmark":"agieval","model":"mimo-v2.5-base","score":71.84,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"ling-3.0-flash-base","score":26.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"nemotron-3-super-120b-a12b-base","score":21.2,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"hy3-preview-base","score":24.2,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"mimo-v2.5-base","score":19.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-3.0-flash-base","score":67.74,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b-base","score":63.89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"hy3-preview-base","score":66.44,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-v2.5-base","score":64.9,"metric":"percent"},{"benchmark":"c-eval","model":"ling-3.0-flash-base","score":89.76,"metric":"percent"},{"benchmark":"c-eval","model":"nemotron-3-super-120b-a12b-base","score":78.12,"metric":"percent"},{"benchmark":"c-eval","model":"hy3-preview-base","score":90.74,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-3.0-flash-base","score":81.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"nemotron-3-super-120b-a12b-base","score":78.05,"metric":"percent"},{"benchmark":"humaneval-plus","model":"hy3-preview-base","score":79.27,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mimo-v2.5-base","score":76.22,"metric":"percent"},{"benchmark":"cruxeval","model":"ling-3.0-flash-base","score":78.5,"metric":"percent"},{"benchmark":"cruxeval","model":"nemotron-3-super-120b-a12b-base","score":72.44,"metric":"percent"},{"benchmark":"cruxeval","model":"hy3-preview-base","score":82.94,"metric":"percent"},{"benchmark":"cruxeval","model":"mimo-v2.5-base","score":70.06,"metric":"percent"},{"benchmark":"multipl-e","model":"ling-3.0-flash-base","score":70.79,"metric":"percent"},{"benchmark":"multipl-e","model":"nemotron-3-super-120b-a12b-base","score":57.28,"metric":"percent"},{"benchmark":"multipl-e","model":"hy3-preview-base","score":45.77,"metric":"percent"},{"benchmark":"multipl-e","model":"mimo-v2.5-base","score":53.57,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-3.0-flash-base","score":40.09,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-super-120b-a12b-base","score":38.99,"metric":"percent"},{"benchmark":"livecodebench","model":"hy3-preview-base","score":35.9,"metric":"percent"},{"benchmark":"bigcodebench","model":"ling-3.0-flash-base","score":52.19,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"nemotron-3-super-120b-a12b-base","score":25.53,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"hy3-preview-base","score":52.02,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"mimo-v2.5-base","score":50.18,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"ling-3.0-flash-base","score":51.16,"metric":"percent"},{"benchmark":"fullstackbench","model":"nemotron-3-super-120b-a12b-base","score":49.61,"metric":"percent"},{"benchmark":"fullstackbench","model":"hy3-preview-base","score":54.95,"metric":"percent"},{"benchmark":"fullstackbench","model":"mimo-v2.5-base","score":50.39,"metric":"percent"},{"benchmark":"math500","model":"ling-3.0-flash-base","score":79,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3-super-120b-a12b-base","score":70.8,"metric":"percent"},{"benchmark":"math500","model":"hy3-preview-base","score":60.6,"metric":"percent"},{"benchmark":"math500","model":"mimo-v2.5-base","score":70,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-3.0-flash-base","score":47.89,"metric":"percent"},{"benchmark":"olympiadbench","model":"nemotron-3-super-120b-a12b-base","score":54.52,"metric":"percent"},{"benchmark":"olympiadbench","model":"hy3-preview-base","score":41.27,"metric":"percent"},{"benchmark":"olympiadbench","model":"mimo-v2.5-base","score":35.09,"metric":"percent"},{"benchmark":"omni-math","model":"ling-3.0-flash-base","score":47.65,"metric":"percent"},{"benchmark":"omni-math","model":"nemotron-3-super-120b-a12b-base","score":38.55,"metric":"percent"},{"benchmark":"omni-math","model":"hy3-preview-base","score":33.33,"metric":"percent"},{"benchmark":"omni-math","model":"mimo-v2.5-base","score":27.03,"metric":"percent"},{"benchmark":"commonsenseqa","model":"ling-3.0-flash-base","score":89.93,"metric":"percent"},{"benchmark":"commonsenseqa","model":"nemotron-3-super-120b-a12b-base","score":86.24,"metric":"percent"},{"benchmark":"commonsenseqa","model":"hy3-preview-base","score":86.98,"metric":"percent"},{"benchmark":"commonsenseqa","model":"mimo-v2.5-base","score":84.6,"metric":"percent"},{"benchmark":"bbh","model":"ling-3.0-flash-base","score":89.17,"metric":"percent"},{"benchmark":"bbh","model":"nemotron-3-super-120b-a12b-base","score":89,"metric":"percent"},{"benchmark":"bbh","model":"hy3-preview-base","score":76,"metric":"percent"},{"benchmark":"bbh","model":"mimo-v2.5-base","score":86.22,"metric":"percent"},{"benchmark":"longbench","model":"ling-3.0-flash-base","score":52.62,"metric":"percent"},{"benchmark":"longbench","model":"nemotron-3-super-120b-a12b-base","score":31.05,"metric":"percent"},{"benchmark":"longbench","model":"hy3-preview-base","score":20.58,"metric":"percent"},{"benchmark":"longbench","model":"mimo-v2.5-base","score":29.57,"metric":"percent"},{"benchmark":"arc-challenge","model":"ling-3.0-tiny-base","score":92.2,"metric":"percent"},{"benchmark":"agieval","model":"ling-3.0-tiny-base","score":64.49,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"ling-3.0-tiny-base","score":7.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-3.0-tiny-base","score":51.83,"metric":"percent"},{"benchmark":"c-eval","model":"ling-3.0-tiny-base","score":80.59,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-3.0-tiny-base","score":79.27,"metric":"percent"},{"benchmark":"cruxeval","model":"ling-3.0-tiny-base","score":67.44,"metric":"percent"},{"benchmark":"multipl-e","model":"ling-3.0-tiny-base","score":64.38,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-3.0-tiny-base","score":24.23,"metric":"percent"},{"benchmark":"bigcodebench","model":"ling-3.0-tiny-base","score":42.89,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"ling-3.0-tiny-base","score":39.48,"metric":"percent"},{"benchmark":"math500","model":"ling-3.0-tiny-base","score":65.6,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-3.0-tiny-base","score":25.9,"metric":"percent"},{"benchmark":"omni-math","model":"ling-3.0-tiny-base","score":29.7,"metric":"percent"},{"benchmark":"commonsenseqa","model":"ling-3.0-tiny-base","score":83.46,"metric":"percent"},{"benchmark":"bbh","model":"ling-3.0-tiny-base","score":80.64,"metric":"percent"},{"benchmark":"longbench","model":"ling-3.0-tiny-base","score":43.85,"metric":"percent"},{"benchmark":"tau2-airline","model":"areal-sea-235b-a22b","score":71,"metric":"percent"},{"benchmark":"tau2-airline","model":"gemini-3-pro","score":73,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-sonnet-4.5","score":70,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-5","score":62.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-max-thinking","score":71,"metric":"percent"},{"benchmark":"tau2-retail","model":"areal-sea-235b-a22b","score":79,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-5","score":81.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-max-thinking","score":75.4,"metric":"percent"},{"benchmark":"tau2-retail","model":"deepseek-v3.2-thinking","score":81.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"areal-sea-235b-a22b","score":93,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-max-thinking","score":95.8,"metric":"percent"},{"benchmark":"browsecomp","model":"dr-venus-4b-sft","score":26.8,"metric":"percent"},{"benchmark":"browsecomp","model":"dr-venus-4b-rl","score":29.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"dr-venus-4b-sft","score":35.7,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"dr-venus-4b-rl","score":37.7,"metric":"percent"},{"benchmark":"gaia-text-only","model":"dr-venus-4b-sft","score":65.4,"metric":"percent"},{"benchmark":"gaia-text-only","model":"dr-venus-4b-rl","score":64.4,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"dr-venus-4b-sft","score":69,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"dr-venus-4b-rl","score":74.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"dr-venus-4b-sft","score":35.3,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"dr-venus-4b-rl","score":40.7,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"dr-venus-4b-sft","score":37.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"dr-venus-4b-rl","score":39.6,"metric":"percent"},{"benchmark":"csimpleqa","model":"ling-2.6-1t","score":76.53,"metric":"percent"},{"benchmark":"csimpleqa","model":"glm-5","score":71.97,"metric":"percent"},{"benchmark":"csimpleqa","model":"gpt-5.4-none","score":70.57,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"ling-2.6-1t","score":31.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"glm-5","score":28.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.4-none","score":30.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ling-2.6-1t","score":76.17,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5","score":70.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4-none","score":76.89,"metric":"percent"},{"benchmark":"supergpqa","model":"ling-2.6-1t","score":58.32,"metric":"percent"},{"benchmark":"supergpqa","model":"glm-5","score":57.63,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5.4-none","score":62.97,"metric":"percent"},{"benchmark":"hle","model":"ling-2.6-1t","score":10.06,"metric":"avg@3"},{"benchmark":"hle","model":"glm-5","score":7.09,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4-none","score":10.75,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v3.2","score":10.47,"metric":"avg@3"},{"benchmark":"hle","model":"kimi-k2.5","score":12.92,"metric":"avg@3"},{"benchmark":"livecodebench","model":"ling-2.6-1t","score":65.58,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-5","score":52.09,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.4-none","score":70.76,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"ling-2.6-1t","score":52.37,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"glm-5","score":27.8,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gpt-5.4-none","score":25.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ling-2.6-1t","score":87.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"glm-5","score":49.22,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.4-none","score":72.92,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"ling-2.6-1t","score":81.93,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-5","score":46.09,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-5.4-none","score":47.76,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ling-2.6-1t","score":65.81,"metric":"percent"},{"benchmark":"imo-answerbench","model":"glm-5","score":39.34,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.4-none","score":44.75,"metric":"percent"},{"benchmark":"arc-agi-2","model":"ling-2.6-1t","score":50.94,"metric":"percent"},{"benchmark":"arc-agi-2","model":"glm-5","score":12.31,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-none","score":26,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ling-2.6-1t","score":72.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5","score":73.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.4-none","score":69.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3.2","score":66.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.5","score":66.8,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"ling-2.6-1t","score":85.24,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"glm-5","score":83.29,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gpt-5.4-none","score":73.4,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"deepseek-v3.2","score":85.38,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"kimi-k2.5","score":85.48,"metric":"percent"},{"benchmark":"claweval-pass3","model":"ling-2.6-1t","score":51,"metric":"percent"},{"benchmark":"claweval-pass3","model":"glm-5","score":40.38,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gpt-5.4-none","score":43.26,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v3.2","score":46.15,"metric":"percent"},{"benchmark":"claweval-pass3","model":"kimi-k2.5","score":48.08,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ling-2.6-1t","score":70.64,"metric":"percent"},{"benchmark":"bfcl-v4","model":"glm-5","score":67.57,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.4-none","score":56.09,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"ling-2.6-1t","score":40.45,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-5","score":48.31,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.4-none","score":46.07,"metric":"percent"},{"benchmark":"ifbench","model":"ling-2.6-1t","score":57.62,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5","score":57.14,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.4-none","score":49.73,"metric":"percent"},{"benchmark":"longbench-v2","model":"ling-2.6-1t","score":48.31,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5.4-none","score":49.3,"metric":"percent"},{"benchmark":"mmlu","model":"ling-flash-base-2.0","score":82.98,"metric":"percent"},{"benchmark":"mmlu","model":"ling-2.6-flash-base","score":84.13,"metric":"percent"},{"benchmark":"mmlu","model":"ling-2.6-1t-base","score":86.82,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-flash-base-2.0","score":60.73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-2.6-flash-base","score":61.36,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-2.6-1t-base","score":67.79,"metric":"percent"},{"benchmark":"gpqa","model":"ling-flash-base-2.0","score":35.35,"metric":"percent"},{"benchmark":"gpqa","model":"ling-2.6-flash-base","score":37.88,"metric":"percent"},{"benchmark":"gpqa","model":"ling-2.6-1t-base","score":45.45,"metric":"percent"},{"benchmark":"supergpqa","model":"ling-flash-base-2.0","score":38.79,"metric":"percent"},{"benchmark":"supergpqa","model":"ling-2.6-flash-base","score":40.17,"metric":"percent"},{"benchmark":"supergpqa","model":"ling-2.6-1t-base","score":44.72,"metric":"percent"},{"benchmark":"triviaqa","model":"ling-flash-base-2.0","score":74.32,"metric":"percent"},{"benchmark":"triviaqa","model":"ling-2.6-flash-base","score":75.52,"metric":"percent"},{"benchmark":"triviaqa","model":"ling-2.6-1t-base","score":82.62,"metric":"percent"},{"benchmark":"simpleqa","model":"ling-flash-base-2.0","score":10.01,"metric":"percent"},{"benchmark":"simpleqa","model":"ling-2.6-flash-base","score":18.33,"metric":"percent"},{"benchmark":"simpleqa","model":"ling-2.6-1t-base","score":38.26,"metric":"percent"},{"benchmark":"csimpleqa","model":"ling-flash-base-2.0","score":49.43,"metric":"percent"},{"benchmark":"csimpleqa","model":"ling-2.6-flash-base","score":63.53,"metric":"percent"},{"benchmark":"csimpleqa","model":"ling-2.6-1t-base","score":76.83,"metric":"percent"},{"benchmark":"mmmlu","model":"ling-flash-base-2.0","score":62.76,"metric":"percent"},{"benchmark":"mmmlu","model":"ling-2.6-flash-base","score":64.76,"metric":"percent"},{"benchmark":"mmmlu","model":"ling-2.6-1t-base","score":71.53,"metric":"percent"},{"benchmark":"gsm8k","model":"ling-flash-base-2.0","score":90.6,"metric":"percent"},{"benchmark":"gsm8k","model":"ling-2.6-flash-base","score":91.89,"metric":"percent"},{"benchmark":"gsm8k","model":"ling-2.6-1t-base","score":93.93,"metric":"percent"},{"benchmark":"cmath","model":"ling-flash-base-2.0","score":93.35,"metric":"percent"},{"benchmark":"cmath","model":"ling-2.6-flash-base","score":93.53,"metric":"percent"},{"benchmark":"cmath","model":"ling-2.6-1t-base","score":94.72,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-flash-base-2.0","score":35.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-2.6-flash-base","score":39.31,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-2.6-1t-base","score":39.85,"metric":"percent"},{"benchmark":"omni-math","model":"ling-flash-base-2.0","score":28.3,"metric":"percent"},{"benchmark":"omni-math","model":"ling-2.6-flash-base","score":29.9,"metric":"percent"},{"benchmark":"omni-math","model":"ling-2.6-1t-base","score":38.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-flash-base-2.0","score":83.54,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-2.6-flash-base","score":81.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-2.6-1t-base","score":85.98,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ling-flash-base-2.0","score":74.07,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ling-2.6-flash-base","score":73.28,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ling-2.6-1t-base","score":77.78,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-flash-base-2.0","score":30.4,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-2.6-flash-base","score":33.48,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-2.6-1t-base","score":44.27,"metric":"percent"},{"benchmark":"bird-sql","model":"ling-flash-base-2.0","score":38.69,"metric":"percent"},{"benchmark":"bird-sql","model":"ling-2.6-flash-base","score":38.4,"metric":"percent"},{"benchmark":"bird-sql","model":"ling-2.6-1t-base","score":44.59,"metric":"percent"},{"benchmark":"bbh","model":"ling-flash-base-2.0","score":84.82,"metric":"percent"},{"benchmark":"bbh","model":"ling-2.6-flash-base","score":85.06,"metric":"percent"},{"benchmark":"bbh","model":"ling-2.6-1t-base","score":89.73,"metric":"percent"},{"benchmark":"bbh-zh","model":"ling-flash-base-2.0","score":83.59,"metric":"percent"},{"benchmark":"bbh-zh","model":"ling-2.6-flash-base","score":83.91,"metric":"percent"},{"benchmark":"bbh-zh","model":"ling-2.6-1t-base","score":87.15,"metric":"percent"},{"benchmark":"kor-bench","model":"ling-flash-base-2.0","score":43.52,"metric":"percent"},{"benchmark":"kor-bench","model":"ling-2.6-flash-base","score":44.96,"metric":"percent"},{"benchmark":"kor-bench","model":"ling-2.6-1t-base","score":50.64,"metric":"percent"},{"benchmark":"commonsenseqa","model":"ling-flash-base-2.0","score":87.71,"metric":"percent"},{"benchmark":"commonsenseqa","model":"ling-2.6-flash-base","score":87.31,"metric":"percent"},{"benchmark":"commonsenseqa","model":"ling-2.6-1t-base","score":90.99,"metric":"percent"},{"benchmark":"zebralogic","model":"ling-flash-base-2.0","score":20.1,"metric":"percent"},{"benchmark":"zebralogic","model":"ling-2.6-flash-base","score":21,"metric":"percent"},{"benchmark":"zebralogic","model":"ling-2.6-1t-base","score":30,"metric":"percent"},{"benchmark":"squad-v2.0","model":"ling-flash-base-2.0","score":89.27,"metric":"percent"},{"benchmark":"squad-v2.0","model":"ling-2.6-flash-base","score":88.81,"metric":"percent"},{"benchmark":"squad-v2.0","model":"ling-2.6-1t-base","score":92.98,"metric":"percent"},{"benchmark":"longbench-v2","model":"ling-flash-base-2.0","score":33.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"ling-2.6-flash-base","score":34.19,"metric":"percent"},{"benchmark":"longbench-v2","model":"ling-2.6-1t-base","score":43.54,"metric":"percent"},{"benchmark":"csimpleqa","model":"ling-2.6-flash","score":60.23,"metric":"percent"},{"benchmark":"csimpleqa","model":"nemotron-3-super-120b-a12b","score":47.03,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"ling-2.6-flash","score":15.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"nemotron-3-super-120b-a12b","score":17.1,"metric":"percent"},{"benchmark":"hle","model":"ling-2.6-flash","score":6.3,"metric":"avg@3"},{"benchmark":"hle","model":"nemotron-3-super-120b-a12b","score":11.26,"metric":"avg@3"},{"benchmark":"aime-2026-i","model":"ling-2.6-flash","score":73.85,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-3-super-120b-a12b","score":88.59,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"ling-2.6-flash","score":49.29,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"nemotron-3-super-120b-a12b","score":76.23,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ling-2.6-flash","score":54.28,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nemotron-3-super-120b-a12b","score":79.53,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-2.6-flash","score":62.28,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-super-120b-a12b","score":74.67,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ling-2.6-flash","score":61.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-super-120b-a12b","score":61,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"ling-2.6-flash","score":81.3,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"nemotron-3-super-120b-a12b","score":73.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ling-2.6-flash","score":66.81,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nemotron-3-super-120b-a12b","score":35.12,"metric":"percent"},{"benchmark":"claweval-pass3","model":"ling-2.6-flash","score":64.56,"metric":"percent"},{"benchmark":"claweval-pass3","model":"nemotron-3-super-120b-a12b","score":56,"metric":"percent"},{"benchmark":"ifbench","model":"ling-2.6-flash","score":57.4,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-super-120b-a12b","score":39.87,"metric":"percent"},{"benchmark":"lifebench","model":"ling-2.6-flash","score":57.2,"metric":"percent"},{"benchmark":"lifebench","model":"nemotron-3-super-120b-a12b","score":44.6,"metric":"percent"},{"benchmark":"multichallenge","model":"ling-2.6-flash","score":39.71,"metric":"percent"},{"benchmark":"multichallenge","model":"nemotron-3-super-120b-a12b","score":35.16,"metric":"percent"},{"benchmark":"multi-if","model":"ling-2.6-flash","score":74.8,"metric":"percent"},{"benchmark":"multi-if","model":"nemotron-3-super-120b-a12b","score":64.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ling-3.0-flash","score":56.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ring-2.6-1t-xhigh","score":53.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"minimax-m2.7","score":56.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"nemotron-3-super-120b-a12b","score":34.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.4-mini","score":47.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-sonnet-4.6","score":48.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ling-3.0-flash","score":72.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ring-2.6-1t-xhigh","score":56.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3-super-120b-a12b","score":42.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.4-mini","score":71,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ling-3.0-flash","score":57,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ring-2.6-1t-xhigh","score":43.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minimax-m2.7","score":55,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"step-3.7-flash","score":39.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-super-120b-a12b","score":39,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.4-mini","score":55.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-sonnet-4.6","score":71.2,"metric":"percent"},{"benchmark":"artifactsbench","model":"ling-3.0-flash","score":77,"metric":"percent"},{"benchmark":"artifactsbench","model":"ring-2.6-1t-xhigh","score":65.1,"metric":"percent"},{"benchmark":"artifactsbench","model":"minimax-m2.7","score":55.8,"metric":"percent"},{"benchmark":"artifactsbench","model":"step-3.7-flash","score":59.2,"metric":"percent"},{"benchmark":"artifactsbench","model":"deepseek-v4-flash-thinking-max","score":64,"metric":"percent"},{"benchmark":"artifactsbench","model":"nemotron-3-super-120b-a12b","score":51.6,"metric":"percent"},{"benchmark":"artifactsbench","model":"gpt-5.4-mini","score":66.8,"metric":"percent"},{"benchmark":"artifactsbench","model":"claude-sonnet-4.6","score":68.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"ling-3.0-flash","score":28,"metric":"percent"},{"benchmark":"tau3-banking","model":"ring-2.6-1t-xhigh","score":14.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"step-3.7-flash","score":11.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-super-120b-a12b","score":10.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.4-mini","score":11.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-sonnet-4.6","score":30.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ling-3.0-flash","score":65.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ring-2.6-1t-xhigh","score":61.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"minimax-m2.7","score":53.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"step-3.7-flash","score":52.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"nemotron-3-super-120b-a12b","score":49.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.4-mini","score":55.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-sonnet-4.6","score":66.7,"metric":"percent"},{"benchmark":"skillsbench","model":"ling-3.0-flash","score":44.8,"metric":"percent"},{"benchmark":"skillsbench","model":"ring-2.6-1t-xhigh","score":11.9,"metric":"percent"},{"benchmark":"skillsbench","model":"minimax-m2.7","score":28.4,"metric":"percent"},{"benchmark":"skillsbench","model":"step-3.7-flash","score":24.9,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-flash-thinking-max","score":53.5,"metric":"percent"},{"benchmark":"skillsbench","model":"nemotron-3-super-120b-a12b","score":20.3,"metric":"percent"},{"benchmark":"skillsbench","model":"gpt-5.4-mini","score":44.8,"metric":"percent"},{"benchmark":"skillsbench","model":"claude-sonnet-4.6","score":54.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ling-3.0-flash","score":73,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ring-2.6-1t-xhigh","score":64.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"minimax-m2.7","score":63.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"step-3.7-flash","score":65.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"deepseek-v4-flash-thinking-max","score":59.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nemotron-3-super-120b-a12b","score":60.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.4-mini","score":68.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"claude-sonnet-4.6","score":73.1,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"ling-3.0-flash","score":1107,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"ring-2.6-1t-xhigh","score":920,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"step-3.7-flash","score":1017,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-3-super-120b-a12b","score":699,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-sonnet-4.6","score":1377,"metric":"elo"},{"benchmark":"wide-search","model":"ling-3.0-flash","score":73.6,"metric":"percent"},{"benchmark":"wide-search","model":"ring-2.6-1t-xhigh","score":62.2,"metric":"percent"},{"benchmark":"wide-search","model":"minimax-m2.7","score":75.2,"metric":"percent"},{"benchmark":"wide-search","model":"step-3.7-flash","score":56.8,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-flash-thinking-max","score":74.4,"metric":"percent"},{"benchmark":"wide-search","model":"nemotron-3-super-120b-a12b","score":19.5,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5.4-mini","score":70.2,"metric":"percent"},{"benchmark":"wide-search","model":"claude-sonnet-4.6","score":79.5,"metric":"percent"},{"benchmark":"browsecomp","model":"ling-3.0-flash","score":72.2,"metric":"percent"},{"benchmark":"browsecomp","model":"ring-2.6-1t-xhigh","score":71.7,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-super-120b-a12b","score":31.3,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-sonnet-4.6","score":74,"metric":"percent"},{"benchmark":"draco","model":"ling-3.0-flash","score":70.4,"metric":"percent"},{"benchmark":"draco","model":"deepseek-v4-flash-thinking-max","score":71.3,"metric":"percent"},{"benchmark":"draco","model":"gpt-5.4-mini","score":61.3,"metric":"percent"},{"benchmark":"ifbench","model":"ling-3.0-flash","score":74.5,"metric":"percent"},{"benchmark":"ifbench","model":"ring-2.6-1t-xhigh","score":44.6,"metric":"percent"},{"benchmark":"ifbench","model":"step-3.7-flash","score":67.3,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.4-mini","score":69,"metric":"percent"},{"benchmark":"ifbench","model":"claude-sonnet-4.6","score":56.6,"metric":"percent"},{"benchmark":"sysbench","model":"ling-3.0-flash","score":93.6,"metric":"percent"},{"benchmark":"sysbench","model":"ring-2.6-1t-xhigh","score":86.5,"metric":"percent"},{"benchmark":"sysbench","model":"minimax-m2.7","score":86.2,"metric":"percent"},{"benchmark":"sysbench","model":"step-3.7-flash","score":91.4,"metric":"percent"},{"benchmark":"sysbench","model":"deepseek-v4-flash-thinking-max","score":93.9,"metric":"percent"},{"benchmark":"sysbench","model":"nemotron-3-super-120b-a12b","score":90.7,"metric":"percent"},{"benchmark":"sysbench","model":"gpt-5.4-mini","score":93.3,"metric":"percent"},{"benchmark":"sysbench","model":"claude-sonnet-4.6","score":94.9,"metric":"percent"},{"benchmark":"lifebench","model":"ling-3.0-flash","score":77.3,"metric":"percent"},{"benchmark":"lifebench","model":"ring-2.6-1t-xhigh","score":72.5,"metric":"percent"},{"benchmark":"lifebench","model":"minimax-m2.7","score":66.9,"metric":"percent"},{"benchmark":"lifebench","model":"step-3.7-flash","score":71.3,"metric":"percent"},{"benchmark":"lifebench","model":"deepseek-v4-flash-thinking-max","score":74.1,"metric":"percent"},{"benchmark":"lifebench","model":"nemotron-3-super-120b-a12b","score":60.2,"metric":"percent"},{"benchmark":"lifebench","model":"gpt-5.4-mini","score":69.2,"metric":"percent"},{"benchmark":"lifebench","model":"claude-sonnet-4.6","score":71.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ling-3.0-flash","score":93.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ring-2.6-1t-xhigh","score":95.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minimax-m2.7","score":94.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"step-3.7-flash","score":95,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-flash-thinking-max","score":96.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-3-super-120b-a12b","score":91.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.4-mini","score":92.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-sonnet-4.6","score":94.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"ling-3.0-flash","score":87,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"ring-2.6-1t-xhigh","score":93.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"minimax-m2.7","score":71.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"step-3.7-flash","score":87.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"nemotron-3-super-120b-a12b","score":84.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.4-mini","score":83.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-sonnet-4.6","score":85.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ling-3.0-flash","score":83.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ring-2.6-1t-xhigh","score":86.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"minimax-m2.7","score":66.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-flash-thinking-max","score":87,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nemotron-3-super-120b-a12b","score":77,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.4-mini","score":74.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-sonnet-4.6","score":82.1,"metric":"percent"},{"benchmark":"hle","model":"ling-3.0-flash","score":22.7,"metric":"avg@3"},{"benchmark":"hle","model":"ring-2.6-1t-xhigh","score":18.3,"metric":"avg@3"},{"benchmark":"hle","model":"minimax-m2.7","score":28.1,"metric":"avg@3"},{"benchmark":"hle","model":"step-3.7-flash","score":19.9,"metric":"avg@3"},{"benchmark":"hle","model":"nemotron-3-super-120b-a12b","score":18.3,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4-mini","score":20.6,"metric":"avg@3"},{"benchmark":"hle","model":"claude-sonnet-4.6","score":30,"metric":"avg@3"},{"benchmark":"livecodebench","model":"ling-3.0-flash","score":82.8,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-2.6-1t-xhigh","score":87,"metric":"percent"},{"benchmark":"livecodebench","model":"minimax-m2.7","score":75.6,"metric":"percent"},{"benchmark":"livecodebench","model":"step-3.7-flash","score":78.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.4-mini","score":80.8,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-sonnet-4.6","score":83.7,"metric":"percent"},{"benchmark":"mrcr-128k","model":"ling-3.0-flash","score":90.8,"metric":"percent"},{"benchmark":"mrcr-128k","model":"ring-2.6-1t-xhigh","score":90.1,"metric":"percent"},{"benchmark":"mrcr-128k","model":"minimax-m2.7","score":27.7,"metric":"percent"},{"benchmark":"mrcr-128k","model":"step-3.7-flash","score":39.2,"metric":"percent"},{"benchmark":"mrcr-128k","model":"deepseek-v4-flash-thinking-max","score":88.5,"metric":"percent"},{"benchmark":"mrcr-128k","model":"nemotron-3-super-120b-a12b","score":40.8,"metric":"percent"},{"benchmark":"mrcr-128k","model":"gpt-5.4-mini","score":56.1,"metric":"percent"},{"benchmark":"mrcr-128k","model":"claude-sonnet-4.6","score":92.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"ling-3.0-flash","score":65.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"ring-2.6-1t-xhigh","score":64.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"minimax-m2.7","score":68.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"step-3.7-flash","score":63.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-flash-thinking-max","score":63,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.4-mini","score":63.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-sonnet-4.6","score":70.7,"metric":"percent"},{"benchmark":"multi-if","model":"ling-3.0-flash","score":87.7,"metric":"percent"},{"benchmark":"multi-if","model":"ring-2.6-1t-xhigh","score":89.3,"metric":"percent"},{"benchmark":"multi-if","model":"minimax-m2.7","score":82.9,"metric":"percent"},{"benchmark":"multi-if","model":"step-3.7-flash","score":84.6,"metric":"percent"},{"benchmark":"multi-if","model":"deepseek-v4-flash-thinking-max","score":86.2,"metric":"percent"},{"benchmark":"multi-if","model":"nemotron-3-super-120b-a12b","score":82.3,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-5.4-mini","score":84.6,"metric":"percent"},{"benchmark":"multi-if","model":"claude-sonnet-4.6","score":84.8,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"ling-3.0-flash-fin","score":69.19,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"hy3","score":64.05,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"minimax-m3","score":63,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"deepseek-v4-pro-0813","score":57.5,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"glm-5.2","score":66.5,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"kimi-k3","score":67,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gemini-3.7-flash","score":71,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"claude-opus-5","score":70.5,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.6-sol","score":64.18,"metric":"percent"},{"benchmark":"financeagent-v2","model":"ling-3.0-flash-fin","score":59.81,"metric":"percent"},{"benchmark":"financeagent-v2","model":"hy3","score":44.9,"metric":"percent"},{"benchmark":"financeagent-v2","model":"minimax-m3","score":48.61,"metric":"percent"},{"benchmark":"financeagent-v2","model":"deepseek-v4-pro-0813","score":53.09,"metric":"percent"},{"benchmark":"financeagent-v2","model":"glm-5.2","score":53.89,"metric":"percent"},{"benchmark":"financeagent-v2","model":"kimi-k3","score":61.11,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gemini-3.7-flash","score":64.2,"metric":"percent"},{"benchmark":"financeagent-v2","model":"claude-opus-5","score":62.96,"metric":"percent"},{"benchmark":"financeagent-v2","model":"gpt-5.6-sol","score":56.48,"metric":"percent"},{"benchmark":"apex-agents","model":"ling-3.0-flash-fin","score":29.17,"metric":"percent"},{"benchmark":"apex-agents","model":"hy3","score":25.6,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-pro-0813","score":34.79,"metric":"percent"},{"benchmark":"apex-agents","model":"kimi-k3","score":39.3,"metric":"percent"},{"benchmark":"apex-agents","model":"gemini-3.7-flash","score":42.92,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-5","score":43.5,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.6-sol","score":40,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"ling-3.0-flash-fin","score":86.5,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"hy3","score":81.75,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"minimax-m3","score":83.75,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"deepseek-v4-pro-0813","score":84,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"glm-5.2","score":87.5,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"kimi-k3","score":86.25,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"gemini-3.7-flash","score":87.25,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"claude-opus-5","score":87,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"ling-3.0-flash-fin","score":21.81,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"hy3","score":19.94,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"minimax-m3","score":16.82,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"deepseek-v4-pro-0813","score":24.92,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"glm-5.2","score":23.99,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"kimi-k3","score":26.48,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"gemini-3.7-flash","score":26.79,"metric":"percent"},{"benchmark":"spreadsheetbench-2","model":"claude-opus-5","score":28.35,"metric":"percent"},{"benchmark":"tau3-banking","model":"ling-3.0-flash-fin","score":41,"metric":"percent"},{"benchmark":"tau3-banking","model":"hy3","score":22.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"minimax-m3","score":15.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-pro-0813","score":39.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.2","score":34.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"kimi-k3","score":46,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemini-3.7-flash","score":32.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-opus-5","score":42.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.6-sol","score":44.3,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"ling-3.0-tiny","score":772,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.5-9b","score":644,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemma-4-e4b-it","score":228,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemma-4-12b-it","score":645,"metric":"elo"},{"benchmark":"tau3-banking","model":"ling-3.0-tiny","score":20.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-4b","score":6.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-9b","score":7,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-e4b-it","score":5.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-12b-it","score":8.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ling-3.0-tiny","score":62.72,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":62.47,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-9b","score":65.83,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":41.64,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-12b-it","score":59.68,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ling-3.0-tiny","score":27.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-4b","score":25.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-9b","score":29.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-e4b-it","score":1.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-12b-it","score":27.3,"metric":"percent"},{"benchmark":"artifactsbench","model":"ling-3.0-tiny","score":47.93,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3.5-4b","score":30.61,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3.5-9b","score":38.8,"metric":"percent"},{"benchmark":"artifactsbench","model":"gemma-4-e4b-it","score":45.14,"metric":"percent"},{"benchmark":"artifactsbench","model":"gemma-4-12b-it","score":48.08,"metric":"percent"},{"benchmark":"scicode","model":"ling-3.0-tiny","score":24.2,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-4b","score":16.1,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-9b","score":27.5,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-e4b-it","score":24.4,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-12b-it","score":38.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"ling-3.0-tiny","score":58.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-4b","score":61,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-9b","score":65.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-e4b-it","score":33,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-12b-it","score":61.7,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"ling-3.0-tiny","score":8.52,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.5-4b","score":15.12,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.5-9b","score":16.42,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gemma-4-e4b-it","score":8.58,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gemma-4-12b-it","score":15.62,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"ling-3.0-tiny","score":69.54,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"qwen3.5-4b","score":13.45,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"qwen3.5-9b","score":16.39,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"gemma-4-e4b-it","score":69.06,"metric":"percent"},{"benchmark":"aa-omniscience-non-hallucination","model":"gemma-4-12b-it","score":19.02,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ling-3.0-tiny","score":73.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-4b","score":77.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-9b","score":80.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e4b-it","score":57.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-12b-it","score":75.3,"metric":"percent"},{"benchmark":"hle","model":"ling-3.0-tiny","score":9.3,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-4b","score":9.9,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-9b","score":14.9,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-e4b-it","score":3.8,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-12b-it","score":15.7,"metric":"avg@3"},{"benchmark":"hmmt-feb-2026","model":"ling-3.0-tiny","score":70.31,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-4b","score":72.87,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-9b","score":71.21,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-e4b-it","score":33.85,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-12b-it","score":67.95,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ling-3.0-tiny","score":71.03,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-4b","score":63.69,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-9b","score":70,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-e4b-it","score":31.75,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-12b-it","score":64.09,"metric":"percent"},{"benchmark":"ifbench","model":"ling-3.0-tiny","score":63.61,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":52,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-9b","score":66.7,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":44.2,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-12b-it","score":73.5,"metric":"percent"},{"benchmark":"lifebench","model":"ling-3.0-tiny","score":62.3,"metric":"percent"},{"benchmark":"lifebench","model":"qwen3.5-4b","score":63.3,"metric":"percent"},{"benchmark":"lifebench","model":"qwen3.5-9b","score":63.9,"metric":"percent"},{"benchmark":"lifebench","model":"gemma-4-e4b-it","score":52.8,"metric":"percent"},{"benchmark":"lifebench","model":"gemma-4-12b-it","score":65.3,"metric":"percent"},{"benchmark":"multi-if","model":"ling-3.0-tiny","score":83.15,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-4b","score":79.84,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-9b","score":83.03,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e4b-it","score":80.92,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-12b-it","score":88.44,"metric":"percent"},{"benchmark":"countbench","model":"ling-3.0-flash-vl","score":97.33,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.8-27b","score":96.7,"metric":"percent"},{"benchmark":"countbench","model":"gemini-3.5-flash-lite","score":97.1,"metric":"percent"},{"benchmark":"countbench","model":"kimi-k2.6-thinking","score":95.7,"metric":"percent"},{"benchmark":"worldvqa","model":"ling-3.0-flash-vl","score":45.67,"metric":"percent"},{"benchmark":"worldvqa","model":"qwen3.8-27b","score":22.87,"metric":"percent"},{"benchmark":"worldvqa","model":"gemini-3.5-flash-lite","score":42.83,"metric":"percent"},{"benchmark":"worldvqa","model":"kimi-k2.6-thinking","score":50.63,"metric":"percent"},{"benchmark":"mmmu-pro","model":"ling-3.0-flash-vl","score":79,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.8-27b","score":76,"metric":"percent"},{"benchmark":"mathvision","model":"ling-3.0-flash-vl","score":84.87,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.8-27b","score":87.4,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.5-flash-lite","score":79.24,"metric":"percent"},{"benchmark":"charxiv-rq","model":"ling-3.0-flash-vl","score":81.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.8-27b","score":83.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.5-flash-lite","score":71.4,"metric":"percent"},{"benchmark":"mmsearch","model":"ling-3.0-flash-vl","score":79,"metric":"percent"},{"benchmark":"mmsearch","model":"qwen3.8-27b","score":79.7,"metric":"percent"},{"benchmark":"mmsearch","model":"gemini-3.5-flash-lite","score":78.67,"metric":"percent"},{"benchmark":"mmsearch","model":"kimi-k2.6-thinking","score":80,"metric":"percent"},{"benchmark":"webvoyager","model":"ling-3.0-flash-vl","score":90.83,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen3.8-27b","score":90.8,"metric":"percent"},{"benchmark":"webvoyager","model":"gemini-3.5-flash-lite","score":90.1,"metric":"percent"},{"benchmark":"webvoyager","model":"kimi-k2.6-thinking","score":85.43,"metric":"percent"},{"benchmark":"vision2web","model":"ling-3.0-flash-vl","score":57.69,"metric":"percent"},{"benchmark":"vision2web","model":"gemini-3.5-flash-lite","score":54.85,"metric":"percent"},{"benchmark":"vision2web","model":"kimi-k2.6-thinking","score":55.42,"metric":"percent"},{"benchmark":"hle","model":"ling-3.1-flash","score":37.44,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4.1-flash","score":39.2,"metric":"avg@3"},{"benchmark":"hle","model":"kimi-k3","score":46.9,"metric":"avg@3"},{"benchmark":"hle","model":"glm-5.3","score":42.3,"metric":"avg@3"},{"benchmark":"hle","model":"glm-5.3-flash","score":39.9,"metric":"avg@3"},{"benchmark":"hle","model":"claude-opus-5","score":54.9,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.6-sol","score":49.5,"metric":"avg@3"},{"benchmark":"critpt","model":"ling-3.1-flash","score":16.29,"metric":"percent"},{"benchmark":"critpt","model":"glm-5.3-flash","score":15.4,"metric":"percent"},{"benchmark":"critpt","model":"claude-opus-5","score":29.1,"metric":"percent"},{"benchmark":"healthbench-professional","model":"ling-3.1-flash","score":65.35,"metric":"percent"},{"benchmark":"healthbench-professional","model":"deepseek-v4.1-flash","score":50.37,"metric":"percent"},{"benchmark":"healthbench-professional","model":"kimi-k3","score":49.56,"metric":"percent"},{"benchmark":"healthbench-professional","model":"glm-5.3","score":49.56,"metric":"percent"},{"benchmark":"healthbench-professional","model":"glm-5.3-flash","score":49.07,"metric":"percent"},{"benchmark":"healthbench-professional","model":"gpt-5.6-sol","score":60.76,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ling-3.1-flash","score":88.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4.1-flash","score":90,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k3","score":90.33,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.3","score":90.67,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.3-flash","score":90,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ling-3.1-flash","score":68.74,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4.1-flash","score":56.77,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k3","score":64.84,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"glm-5.3","score":61.83,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"glm-5.3-flash","score":63.06,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"ling-3.1-flash","score":64.51,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"deepseek-v4.1-flash","score":54.03,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"glm-5.3-flash","score":61.29,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-opus-5","score":62,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"gpt-5.6-sol","score":54,"metric":"percent"},{"benchmark":"deepswe","model":"ling-3.1-flash","score":59.7,"metric":"percent"},{"benchmark":"deepswe","model":"deepseek-v4.1-flash","score":74.2,"metric":"percent"},{"benchmark":"deepswe","model":"kimi-k3","score":67.5,"metric":"percent"},{"benchmark":"deepswe","model":"glm-5.3","score":66.9,"metric":"percent"},{"benchmark":"deepswe","model":"glm-5.3-flash","score":63.4,"metric":"percent"},{"benchmark":"deepswe","model":"gpt-5.6-sol","score":72.67,"metric":"percent"},{"benchmark":"frontierswe","model":"ling-3.1-flash","score":75.16,"metric":"percent"},{"benchmark":"frontierswe","model":"kimi-k3","score":73.52,"metric":"percent"},{"benchmark":"frontierswe","model":"glm-5.3","score":74.34,"metric":"percent"},{"benchmark":"frontierswe","model":"glm-5.3-flash","score":58.55,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ling-3.1-flash","score":81.18,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"ling-3.1-flash","score":46.03,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"glm-5.3-flash","score":32.8,"metric":"percent"},{"benchmark":"cybergym","model":"ling-3.1-flash","score":87.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"ling-3.1-flash","score":47.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4.1-flash","score":42.5,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.3","score":50.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.3-flash","score":47.2,"metric":"percent"},{"benchmark":"automationbench","model":"ling-3.1-flash","score":52.5,"metric":"percent"},{"benchmark":"skillsbench","model":"ling-3.1-flash","score":68.7,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4.1-flash","score":71.3,"metric":"percent"},{"benchmark":"skillsbench","model":"kimi-k3","score":63.6,"metric":"percent"},{"benchmark":"skillsbench","model":"glm-5.3","score":59.4,"metric":"percent"},{"benchmark":"skillsbench","model":"glm-5.3-flash","score":61.3,"metric":"percent"},{"benchmark":"skillsbench","model":"claude-opus-5","score":63.7,"metric":"percent"},{"benchmark":"skillsbench","model":"gpt-5.6-sol","score":73.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ling-3.1-flash","score":83,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4.1-flash","score":82.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5.3","score":81.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5.3-flash","score":81,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"ling-3.1-flash","score":1673,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4.1-flash","score":1600,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.3","score":1644,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.3-flash","score":1641,"metric":"elo"},{"benchmark":"browsecomp","model":"ling-3.1-flash","score":91.67,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5.3","score":76.33,"metric":"percent"},{"benchmark":"draco","model":"ling-3.1-flash","score":85.49,"metric":"percent"},{"benchmark":"draco","model":"deepseek-v4.1-flash","score":79.85,"metric":"percent"},{"benchmark":"draco","model":"kimi-k3","score":77.5,"metric":"percent"},{"benchmark":"draco","model":"glm-5.3","score":78.1,"metric":"percent"},{"benchmark":"draco","model":"glm-5.3-flash","score":78.55,"metric":"percent"},{"benchmark":"draco","model":"claude-opus-5","score":88.6,"metric":"percent"},{"benchmark":"draco","model":"gpt-5.6-sol","score":77.7,"metric":"percent"},{"benchmark":"wide-search","model":"ling-3.1-flash","score":83.32,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4.1-flash","score":80.81,"metric":"percent"},{"benchmark":"wide-search","model":"kimi-k3","score":78.86,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5.3","score":81.83,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5.3-flash","score":80.24,"metric":"percent"},{"benchmark":"wide-search","model":"claude-opus-5","score":84,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5.6-sol","score":86.3,"metric":"percent"},{"benchmark":"financeagent-v2","model":"ling-3.1-flash","score":57.87,"metric":"percent"},{"benchmark":"financeagent-v2","model":"deepseek-v4.1-flash","score":61.57,"metric":"percent"},{"benchmark":"financeagent-v2","model":"glm-5.3","score":60.49,"metric":"percent"},{"benchmark":"financeagent-v2","model":"glm-5.3-flash","score":59.26,"metric":"percent"},{"benchmark":"multichallenge","model":"ling-3.1-flash","score":69.78,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v4.1-flash","score":72.12,"metric":"percent"},{"benchmark":"multichallenge","model":"kimi-k3","score":55.98,"metric":"percent"},{"benchmark":"multichallenge","model":"glm-5.3","score":63.89,"metric":"percent"},{"benchmark":"multichallenge","model":"glm-5.3-flash","score":62.6,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-opus-5","score":64.98,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5.6-sol","score":66.32,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"llada2.2-flash","score":49.28,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"llada2.2-flash","score":30.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ling-2.6-flash","score":31.88,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"llada2.2-flash","score":25,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ling-2.6-flash","score":33.73,"metric":"percent"},{"benchmark":"claweval-pass3","model":"llada2.2-flash","score":64.22,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"llada2.2-flash","score":81.66,"metric":"percent"},{"benchmark":"mcp-atlas","model":"llada2.2-flash","score":46.21,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ling-2.6-flash","score":41.12,"metric":"percent"},{"benchmark":"bfcl-v4","model":"llada2.2-flash","score":60.78,"metric":"percent"},{"benchmark":"bfcl-v4","model":"llada2.0-mini","score":25.05,"metric":"percent"},{"benchmark":"bfcl-v4","model":"llada2.1-mini","score":28.44,"metric":"percent"},{"benchmark":"bfcl-v4","model":"llada2.2-mini","score":47.68,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llada2.1-mini","score":72.06,"metric":"percent"},{"benchmark":"bfcl-v3","model":"llada2.2-mini","score":69.02,"metric":"percent"},{"benchmark":"aime-2026-i","model":"llada2.0-mini","score":37.71,"metric":"percent"},{"benchmark":"aime-2026-i","model":"llada2.1-mini","score":40.37,"metric":"percent"},{"benchmark":"aime-2026-i","model":"llada2.2-mini","score":35.05,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.1-mini","score":64.3,"metric":"percent"},{"benchmark":"olympiadbench","model":"llada2.2-mini","score":61.11,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.0-mini","score":27.7,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.1-mini","score":28.8,"metric":"percent"},{"benchmark":"livecodebench","model":"llada2.2-mini","score":28.14,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.1-mini","score":64.16,"metric":"percent"},{"benchmark":"multipl-e","model":"llada2.2-mini","score":65.26,"metric":"percent"},{"benchmark":"ifbench","model":"llada2.0-mini","score":32.33,"metric":"percent"},{"benchmark":"ifbench","model":"llada2.1-mini","score":31.6,"metric":"percent"},{"benchmark":"ifbench","model":"llada2.2-mini","score":24.93,"metric":"percent"},{"benchmark":"multi-if","model":"llada2.0-mini","score":60.58,"metric":"percent"},{"benchmark":"multi-if","model":"llada2.1-mini","score":58.43,"metric":"percent"},{"benchmark":"multi-if","model":"llada2.2-mini","score":57.03,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.1-mini","score":46.64,"metric":"percent"},{"benchmark":"kor-bench","model":"llada2.2-mini","score":43.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llada2.0-mini","score":47.76,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llada2.1-mini","score":48.36,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llada2.2-mini","score":44.41,"metric":"percent"},{"benchmark":"longbench-v2","model":"llada2.0-mini","score":15.51,"metric":"percent"},{"benchmark":"longbench-v2","model":"llada2.1-mini","score":12.13,"metric":"percent"},{"benchmark":"longbench-v2","model":"llada2.2-mini","score":34.99,"metric":"percent"},{"benchmark":"claweval-pass3","model":"llada2.2-mini","score":57.16,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"llada2.2-mini","score":62.33,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gpt-4o","score":20.1,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen2.5-vl-7b","score":86,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-8b-instruct","score":93,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3.5-9b","score":94,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-tars-1.5-7b","score":91.6,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-venus-1.5-2b","score":92.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"llada-ui","score":90.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-4o","score":0.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2.5-vl-7b","score":26.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-tars-1.5-7b","score":35.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-venus-1.5-2b","score":57.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"llada-ui","score":52.9,"metric":"percent"},{"benchmark":"androidworld","model":"gpt-4o","score":30.6,"metric":"percent"},{"benchmark":"androidworld","model":"qwen2.5-vl-7b","score":25.5,"metric":"percent"},{"benchmark":"androidworld","model":"qwen3-vl-8b-instruct","score":47.9,"metric":"percent"},{"benchmark":"androidworld","model":"ui-tars-1.5-7b","score":30,"metric":"percent"},{"benchmark":"androidworld","model":"ui-venus-7b","score":49.1,"metric":"percent"},{"benchmark":"androidworld","model":"ui-venus-1.5-2b","score":55.6,"metric":"percent"},{"benchmark":"androidworld","model":"llada-ui","score":53.5,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen2.5-vl-7b","score":7,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3-vl-8b-instruct","score":9.4,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3.5-9b","score":17.9,"metric":"percent"},{"benchmark":"mobileworld","model":"ui-venus-7b","score":8.5,"metric":"percent"},{"benchmark":"mobileworld","model":"llada-ui","score":25.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen2.5-vl-7b","score":3,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3-vl-8b-instruct","score":33.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"llada-ui","score":29.4,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen2.5-vl-7b","score":11,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen3-vl-8b-instruct","score":45.2,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen3.5-9b","score":46.6,"metric":"percent"},{"benchmark":"webvoyager","model":"ui-venus-1.5-2b","score":56.4,"metric":"percent"},{"benchmark":"webvoyager","model":"llada-ui","score":56.9,"metric":"percent"},{"benchmark":"mmstar","model":"ming-flash-omni-2.0","score":74.88,"metric":"percent"},{"benchmark":"mmstar","model":"longcat-flash-omni","score":70.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ming-flash-omni-2.0","score":87,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.5-pro","score":90.81,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"longcat-flash-omni","score":87.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-omni-30b-a3b-instruct","score":84.73,"metric":"percent"},{"benchmark":"hallusionbench","model":"ming-flash-omni-2.0","score":66.14,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-omni-30b-a3b-instruct","score":59.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"glm-4.6v","score":63.2,"metric":"percent"},{"benchmark":"mmvet","model":"ming-flash-omni-2.0","score":85.64,"metric":"percent"},{"benchmark":"mmvet","model":"longcat-flash-omni","score":69,"metric":"percent"},{"benchmark":"mmvet","model":"qwen3-omni-30b-a3b-instruct","score":73.85,"metric":"percent"},{"benchmark":"ai2d","model":"ming-flash-omni-2.0","score":89.28,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-omni-30b-a3b-instruct","score":85.2,"metric":"percent"},{"benchmark":"chartqa","model":"ming-flash-omni-2.0","score":87,"metric":"percent"},{"benchmark":"chartqa","model":"longcat-flash-omni","score":87.6,"metric":"percent"},{"benchmark":"ocrbench","model":"ming-flash-omni-2.0","score":89.1,"metric":"percent"},{"benchmark":"ocrbench","model":"longcat-flash-omni","score":84.9,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-omni-30b-a3b-instruct","score":86,"metric":"percent"},{"benchmark":"mmmu","model":"ming-flash-omni-2.0","score":77.11,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-pro","score":80.9,"metric":"percent"},{"benchmark":"mmmu","model":"longcat-flash-omni","score":70.7,"metric":"percent"},{"benchmark":"mathverse-vision","model":"ming-flash-omni-2.0","score":75.51,"metric":"percent"},{"benchmark":"mathverse-vision","model":"gemini-2.5-pro","score":73.09,"metric":"percent"},{"benchmark":"mathverse-vision","model":"qwen3-omni-30b-a3b-instruct","score":49.62,"metric":"percent"},{"benchmark":"mathverse-vision","model":"glm-4.6v","score":72.8,"metric":"percent"},{"benchmark":"mathvision","model":"ming-flash-omni-2.0","score":65.59,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.5-pro","score":66,"metric":"percent"},{"benchmark":"logicvista","model":"ming-flash-omni-2.0","score":67.56,"metric":"percent"},{"benchmark":"logicvista","model":"gemini-2.5-pro","score":68.7,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3-omni-30b-a3b-instruct","score":48.32,"metric":"percent"},{"benchmark":"logicvista","model":"glm-4.6v","score":64.88,"metric":"percent"},{"benchmark":"fsc-147","model":"ming-flash-omni-2.0","score":15.33,"metric":"percent"},{"benchmark":"fsc-147","model":"glm-4.6v","score":29.7,"metric":"percent"},{"benchmark":"refcoco","model":"ming-flash-omni-2.0","score":88.47,"metric":"percent"},{"benchmark":"refcoco","model":"gemini-2.5-pro","score":87.48,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-omni-30b-a3b-instruct","score":87.43,"metric":"percent"},{"benchmark":"refcoco","model":"glm-4.6v","score":85.92,"metric":"percent"},{"benchmark":"mvbench","model":"ming-flash-omni-2.0","score":77.5,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-2.5-pro","score":74.2,"metric":"percent"},{"benchmark":"mvbench","model":"longcat-flash-omni","score":75.2,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-omni-30b-a3b-instruct","score":71.2,"metric":"percent"},{"benchmark":"mvbench","model":"glm-4.6v","score":74.9,"metric":"percent"},{"benchmark":"charades-sta","model":"ming-flash-omni-2.0","score":59.33,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen3-omni-30b-a3b-instruct","score":28.9,"metric":"percent"},{"benchmark":"charades-sta","model":"glm-4.6v","score":27.11,"metric":"percent"},{"benchmark":"mlvu","model":"ming-flash-omni-2.0","score":77.72,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-2.5-pro","score":81.2,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-omni-30b-a3b-instruct","score":75.2,"metric":"percent"},{"benchmark":"mlvu","model":"glm-4.6v","score":75.07,"metric":"percent"},{"benchmark":"asr-librispeech-other","model":"ming-flash-omni-2.0","score":2.2,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"gemini-2.5-pro","score":3.56,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"longcat-flash-omni","score":4.01,"metric":"wer"},{"benchmark":"voicebench-alpacaeval","model":"ming-flash-omni-2.0","score":95.6,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"longcat-flash-omni","score":98.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ring-2.6-1t-xhigh","score":95.78,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ring-2.6-1t-high","score":87.86,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.6","score":96.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-pro-thinking-max","score":95.83,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.6","score":96.67,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.7","score":96.41,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.4","score":99.17,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3.1-pro","score":98.33,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"ring-2.6-1t-xhigh","score":93.47,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"ring-2.6-1t-high","score":67.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"kimi-k2.6","score":92.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-opus-4.6","score":83.38,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-opus-4.7","score":94.08,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.4","score":95.64,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ring-2.6-1t-xhigh","score":86.12,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ring-2.6-1t-high","score":66.44,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2.6","score":86,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.6","score":80.28,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.7","score":87.31,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.4","score":77.53,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-2.6-1t-xhigh","score":86.95,"metric":"percent"},{"benchmark":"livecodebench","model":"ring-2.6-1t-high","score":76.71,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2.6","score":89.8,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-5.1","score":82.49,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.6","score":85.68,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.7","score":85.46,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.4","score":81.39,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3.1-pro","score":93.28,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ring-2.6-1t-xhigh","score":85.89,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ring-2.6-1t-high","score":76.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.6","score":91.1,"metric":"percent"},{"benchmark":"arc-agi-2","model":"ring-2.6-1t-xhigh","score":66.18,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k2.6","score":29.38,"metric":"percent"},{"benchmark":"arc-agi-2","model":"glm-5.1","score":21.74,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-pro-thinking-max","score":62.43,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4","score":74,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"ring-2.6-1t-high","score":87.6,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"glm-5.1","score":70.3,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"claude-opus-4.6","score":74.95,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"claude-opus-4.7","score":75.83,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gpt-5.4","score":79.95,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gemini-3.1-pro","score":80,"metric":"percent"},{"benchmark":"claweval-pass3","model":"ring-2.6-1t-high","score":63.82,"metric":"percent"},{"benchmark":"claweval-pass3","model":"kimi-k2.6","score":62.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ring-2.6-1t-high","score":74,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.6","score":80.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.4","score":80.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ring-2.6-1t-high","score":53.76,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.4","score":59.1,"metric":"percent"},{"benchmark":"tau2-retail","model":"ring-2.6-1t-xhigh","score":77.85,"metric":"percent"},{"benchmark":"tau2-retail","model":"ring-2.6-1t-high","score":78.07,"metric":"percent"},{"benchmark":"tau2-retail","model":"kimi-k2.6","score":72.15,"metric":"percent"},{"benchmark":"tau2-retail","model":"glm-5.1","score":85.09,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4.6","score":81.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-opus-4.7","score":81.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-5.4","score":74.34,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemini-3.1-pro","score":83.77,"metric":"percent"},{"benchmark":"tau2-airline","model":"ring-2.6-1t-xhigh","score":77.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"ring-2.6-1t-high","score":78,"metric":"percent"},{"benchmark":"tau2-airline","model":"kimi-k2.6","score":82,"metric":"percent"},{"benchmark":"tau2-airline","model":"glm-5.1","score":82,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-opus-4.6","score":82.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-opus-4.7","score":88.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-5.4","score":80.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"gemini-3.1-pro","score":76.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"ring-2.6-1t-xhigh","score":94.96,"metric":"percent"},{"benchmark":"tau2-telecom","model":"ring-2.6-1t-high","score":96.71,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2.6","score":98.68,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-5.1","score":99.12,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-opus-4.7","score":87.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.4","score":96.05,"metric":"percent"},{"benchmark":"streamingbench","model":"internvl3.5-8b","score":60.8,"metric":"percent"},{"benchmark":"streamingbench","model":"qwen3-vl-8b-instruct","score":53.5,"metric":"percent"},{"benchmark":"streamingbench","model":"qwen3.5-9b","score":57,"metric":"percent"},{"benchmark":"streamingbench","model":"qwen3-omni-30b-a3b-instruct","score":64.3,"metric":"percent"},{"benchmark":"streamingbench","model":"gemini-3.5-flash","score":77.3,"metric":"percent"},{"benchmark":"streamingbench","model":"minicpm-o-4.5","score":67.9,"metric":"percent"},{"benchmark":"streamingbench","model":"realtime-venus-omni","score":70.2,"metric":"percent"},{"benchmark":"ovobench","model":"internvl3.5-8b","score":53.8,"metric":"percent"},{"benchmark":"ovobench","model":"qwen3-vl-8b-instruct","score":49.8,"metric":"percent"},{"benchmark":"ovobench","model":"qwen3.5-9b","score":55,"metric":"percent"},{"benchmark":"ovobench","model":"qwen3-omni-30b-a3b-instruct","score":61.4,"metric":"percent"},{"benchmark":"ovobench","model":"gemini-3.5-flash","score":71.6,"metric":"percent"},{"benchmark":"ovobench","model":"minicpm-o-4.5","score":60.7,"metric":"percent"},{"benchmark":"ovobench","model":"realtime-venus-omni","score":64.7,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"minicpm-o-4.5","score":76.9,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"realtime-venus-omni","score":76.9,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"realtime-venus-audio","score":78,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"minicpm-o-4.5","score":65.8,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"realtime-venus-omni","score":64.6,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"realtime-venus-audio","score":66,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2.5-vl-7b","score":63.9,"metric":"percent"},{"benchmark":"mmstar","model":"llada2.0-uni","score":64.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llada2.0-uni","score":81.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llada2.0-uni","score":81.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2.5-vl-7b","score":51.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"llada2.0-uni","score":50.2,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2.5-vl-7b","score":68.5,"metric":"percent"},{"benchmark":"realworldqa","model":"llada2.0-uni","score":66.7,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen2.5-vl-7b","score":47.9,"metric":"percent"},{"benchmark":"simplevqa","model":"llada2.0-uni","score":44,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2.5-vl-7b","score":51.3,"metric":"percent"},{"benchmark":"mmmu","model":"llada2.0-uni","score":50.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2.5-vl-7b","score":38.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llada2.0-uni","score":34,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2.5-vl-7b","score":68.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llada2.0-uni","score":68.1,"metric":"percent"},{"benchmark":"wemath","model":"qwen2.5-vl-7b","score":33.3,"metric":"percent"},{"benchmark":"wemath","model":"llada2.0-uni","score":29.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llada2.0-uni","score":68.4,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2.5-vl-7b","score":84.1,"metric":"percent"},{"benchmark":"chartqa","model":"llada2.0-uni","score":80.1,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2.5-vl-7b","score":84.2,"metric":"percent"},{"benchmark":"ocrbench","model":"llada2.0-uni","score":75.7,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2.5-vl-7b","score":94.9,"metric":"percent"},{"benchmark":"docvqa","model":"llada2.0-uni","score":89.5,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2.5-vl-7b","score":82.6,"metric":"percent"},{"benchmark":"ai2d","model":"llada2.0-uni","score":82,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2.5-vl-7b","score":80.3,"metric":"percent"},{"benchmark":"infovqa","model":"llada2.0-uni","score":70.1,"metric":"percent"},{"benchmark":"countbench","model":"qwen2.5-vl-7b","score":84.9,"metric":"percent"},{"benchmark":"countbench","model":"llada2.0-uni","score":86,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"qwen2.5-vl-7b","score":45.2,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"llada2.0-uni","score":47.8,"metric":"percent"},{"benchmark":"v-star","model":"qwen2.5-vl-7b","score":80.1,"metric":"percent"},{"benchmark":"v-star","model":"llada2.0-uni","score":61.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"seed1.8","score":64.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-2b-instruct","score":40.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-30b-a3b-instruct","score":53.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gta1-32b","score":63.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-venus-1.5-8b","score":68.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-venus-1.5-30b-a3b","score":69.6,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-2b-instruct","score":85.6,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-30b-a3b-instruct","score":91.7,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gta1-32b","score":95.2,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-venus-1.5-8b","score":95.9,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-venus-1.5-30b-a3b","score":96.2,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-2b-instruct","score":47.7,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-30b-a3b-instruct","score":61.2,"metric":"percent"},{"benchmark":"osworld-g","model":"gta1-32b","score":65.2,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-tars-1.5-7b","score":52.8,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-venus-7b","score":54.6,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-venus-72b","score":62.2,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-venus-1.5-2b","score":59.4,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-venus-1.5-8b","score":69.7,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-venus-1.5-30b-a3b","score":70.6,"metric":"percent"},{"benchmark":"androidworld","model":"ui-venus-72b","score":65.9,"metric":"percent"},{"benchmark":"androidworld","model":"ui-venus-1.5-8b","score":73.7,"metric":"percent"},{"benchmark":"androidworld","model":"ui-venus-1.5-30b-a3b","score":77.6,"metric":"percent"},{"benchmark":"androidworld","model":"ui-venus-2-9b","score":80.2,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3.5-9b","score":18,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3.6-27b","score":36.8,"metric":"percent"},{"benchmark":"mobileworld","model":"seed2.0-pro","score":63.2,"metric":"percent"},{"benchmark":"mobileworld","model":"ui-venus-1.5-30b-a3b","score":17.1,"metric":"percent"},{"benchmark":"mobileworld","model":"ui-venus-2-9b","score":65.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.6-27b","score":62,"metric":"percent"},{"benchmark":"osworld-verified","model":"kimi-k2.6","score":73.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"ui-venus-2-9b","score":70.8,"metric":"percent"},{"benchmark":"osworld-2.0","model":"qwen3.5-9b","score":2.5,"metric":"percent"},{"benchmark":"osworld-2.0","model":"qwen3.6-27b","score":3.8,"metric":"percent"},{"benchmark":"osworld-2.0","model":"kimi-k2.6","score":7.1,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-5.5","score":46.7,"metric":"percent"},{"benchmark":"osworld-2.0","model":"ui-venus-2-9b","score":7.5,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen3.5-9b","score":46.9,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen3.6-27b","score":84.3,"metric":"percent"},{"benchmark":"webvoyager","model":"seed2.0-pro","score":85.1,"metric":"percent"},{"benchmark":"webvoyager","model":"ui-venus-2-9b","score":90.8,"metric":"percent"},{"benchmark":"online-mind2web","model":"qwen3.5-9b","score":27.3,"metric":"percent"},{"benchmark":"online-mind2web","model":"qwen3.6-27b","score":55.3,"metric":"percent"},{"benchmark":"online-mind2web","model":"seed2.0-pro","score":68.5,"metric":"percent"},{"benchmark":"online-mind2web","model":"ui-venus-2-9b","score":74,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.6-27b","score":65.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.7-plus","score":68.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-venus-2-9b","score":73,"metric":"percent"},{"benchmark":"screenspot-pro","model":"vista-4b","score":64.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"vista-9b","score":69.2,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3.5-4b","score":90.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"vista-4b","score":93.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3.5-9b","score":91.9,"metric":"percent"},{"benchmark":"screenspot-v2","model":"vista-9b","score":95.8,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3.5-4b","score":54.4,"metric":"percent"},{"benchmark":"osworld-g","model":"vista-4b","score":61.2,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3.5-9b","score":63.1,"metric":"percent"},{"benchmark":"osworld-g","model":"vista-9b","score":68.1,"metric":"percent"},{"benchmark":"hrbench4k","model":"gpt-5.1","score":67,"metric":"percent"},{"benchmark":"hrbench4k","model":"gemini-3-flash","score":87.88,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-4b-instruct","score":78.25,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen2.5-vl-7b","score":71.62,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-8b-instruct","score":78.88,"metric":"percent"},{"benchmark":"hrbench4k","model":"mimo-vl-7b-rl","score":74.38,"metric":"percent"},{"benchmark":"hrbench4k","model":"minicpm-v-4.5-8b","score":69.88,"metric":"percent"},{"benchmark":"hrbench4k","model":"glm-4.5v","score":81.63,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-235b-a22b-instruct","score":84.5,"metric":"percent"},{"benchmark":"hrbench4k","model":"kimi-k2.5","score":81.87,"metric":"percent"},{"benchmark":"hrbench4k","model":"zwz-4b","score":81.75,"metric":"percent"},{"benchmark":"hrbench4k","model":"zwz-7b","score":75.38,"metric":"percent"},{"benchmark":"hrbench4k","model":"zwz-8b","score":84.38,"metric":"percent"},{"benchmark":"hrbench8k","model":"gpt-5.1","score":65.25,"metric":"percent"},{"benchmark":"hrbench8k","model":"gemini-3-flash","score":85,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-4b-instruct","score":72.88,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen2.5-vl-7b","score":67.88,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-8b-instruct","score":74.63,"metric":"percent"},{"benchmark":"hrbench8k","model":"mimo-vl-7b-rl","score":72.88,"metric":"percent"},{"benchmark":"hrbench8k","model":"minicpm-v-4.5-8b","score":63.62,"metric":"percent"},{"benchmark":"hrbench8k","model":"glm-4.5v","score":74.88,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-235b-a22b-instruct","score":81.62,"metric":"percent"},{"benchmark":"hrbench8k","model":"kimi-k2.5","score":75.38,"metric":"percent"},{"benchmark":"hrbench8k","model":"zwz-4b","score":79.5,"metric":"percent"},{"benchmark":"hrbench8k","model":"zwz-7b","score":73.25,"metric":"percent"},{"benchmark":"hrbench8k","model":"zwz-8b","score":82,"metric":"percent"},{"benchmark":"v-star","model":"gpt-5.1","score":70.16,"metric":"percent"},{"benchmark":"v-star","model":"gemini-3-flash","score":86.39,"metric":"percent"},{"benchmark":"v-star","model":"qwen2.5-vl-7b","score":78.53,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-8b-instruct","score":86.39,"metric":"percent"},{"benchmark":"v-star","model":"mimo-vl-7b-rl","score":81.15,"metric":"percent"},{"benchmark":"v-star","model":"minicpm-v-4.5-8b","score":70.16,"metric":"percent"},{"benchmark":"v-star","model":"glm-4.5v","score":83.25,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-235b-a22b-instruct","score":87.96,"metric":"percent"},{"benchmark":"v-star","model":"kimi-k2.5","score":85.86,"metric":"percent"},{"benchmark":"v-star","model":"zwz-4b","score":92.67,"metric":"percent"},{"benchmark":"v-star","model":"zwz-7b","score":88.48,"metric":"percent"},{"benchmark":"v-star","model":"zwz-8b","score":91.1,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-5.1","score":84.22,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-3-flash","score":89.57,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-4b-instruct","score":84.95,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen2.5-vl-7b","score":75.34,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-8b-instruct","score":85.44,"metric":"percent"},{"benchmark":"cv-bench","model":"mimo-vl-7b-rl","score":84.31,"metric":"percent"},{"benchmark":"cv-bench","model":"minicpm-v-4.5-8b","score":80.25,"metric":"percent"},{"benchmark":"cv-bench","model":"glm-4.5v","score":87.59,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-235b-a22b-instruct","score":86.72,"metric":"percent"},{"benchmark":"cv-bench","model":"kimi-k2.5","score":89.18,"metric":"percent"},{"benchmark":"cv-bench","model":"zwz-4b","score":87.9,"metric":"percent"},{"benchmark":"cv-bench","model":"zwz-7b","score":79.83,"metric":"percent"},{"benchmark":"cv-bench","model":"zwz-8b","score":87.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gpt-5.1","score":64.04,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gemini-3-flash","score":74.86,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen3-vl-4b-instruct","score":63.47,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen2.5-vl-7b","score":60.8,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen3-vl-8b-instruct","score":65.96,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"mimo-vl-7b-rl","score":63.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"minicpm-v-4.5-8b","score":58.16,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"glm-4.5v","score":66.04,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen3-vl-235b-a22b-instruct","score":67.07,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"kimi-k2.5","score":71.51,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"zwz-4b","score":68.52,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"zwz-7b","score":66.21,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"zwz-8b","score":69.87,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"gpt-5.1","score":55.57,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"gemini-3-flash","score":72.62,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"qwen3-vl-4b-instruct","score":63.63,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"qwen2.5-vl-7b","score":58.3,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"qwen3-vl-8b-instruct","score":66.67,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"mimo-vl-7b-rl","score":59.78,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"minicpm-v-4.5-8b","score":56.23,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"glm-4.5v","score":60.71,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"qwen3-vl-235b-a22b-instruct","score":65.29,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"kimi-k2.5","score":68.4,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"zwz-4b","score":68.09,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"zwz-7b","score":66.96,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"zwz-8b","score":70.59,"metric":"percent"},{"benchmark":"countqa","model":"gpt-5.1","score":31.41,"metric":"percent"},{"benchmark":"countqa","model":"gemini-3-flash","score":66.88,"metric":"percent"},{"benchmark":"countqa","model":"qwen3-vl-4b-instruct","score":28.14,"metric":"percent"},{"benchmark":"countqa","model":"qwen2.5-vl-7b","score":18.91,"metric":"percent"},{"benchmark":"countqa","model":"qwen3-vl-8b-instruct","score":28.99,"metric":"percent"},{"benchmark":"countqa","model":"mimo-vl-7b-rl","score":28.27,"metric":"percent"},{"benchmark":"countqa","model":"minicpm-v-4.5-8b","score":23.43,"metric":"percent"},{"benchmark":"countqa","model":"glm-4.5v","score":35.93,"metric":"percent"},{"benchmark":"countqa","model":"qwen3-vl-235b-a22b-instruct","score":40.58,"metric":"percent"},{"benchmark":"countqa","model":"kimi-k2.5","score":52.81,"metric":"percent"},{"benchmark":"countqa","model":"zwz-4b","score":30.82,"metric":"percent"},{"benchmark":"countqa","model":"zwz-7b","score":20.72,"metric":"percent"},{"benchmark":"countqa","model":"zwz-8b","score":32.4,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5.1","score":71.6,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-3-flash","score":83.6,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-4b-instruct","score":69.73,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2.5-vl-7b","score":61.93,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-8b-instruct","score":70.93,"metric":"percent"},{"benchmark":"mmstar","model":"mimo-vl-7b-rl","score":73.53,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-v-4.5-8b","score":67.87,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4.5v","score":75.87,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-235b-a22b-instruct","score":76.33,"metric":"percent"},{"benchmark":"mmstar","model":"kimi-k2.5","score":81.8,"metric":"percent"},{"benchmark":"mmstar","model":"zwz-4b","score":71.13,"metric":"percent"},{"benchmark":"mmstar","model":"zwz-7b","score":63.4,"metric":"percent"},{"benchmark":"mmstar","model":"zwz-8b","score":73.13,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.1","score":13.92,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3-flash","score":34.51,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-vl-4b-instruct","score":13.66,"metric":"percent"},{"benchmark":"babyvision","model":"qwen2.5-vl-7b","score":12.89,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-vl-8b-instruct","score":12.89,"metric":"percent"},{"benchmark":"babyvision","model":"mimo-vl-7b-rl","score":16.24,"metric":"percent"},{"benchmark":"babyvision","model":"minicpm-v-4.5-8b","score":14.95,"metric":"percent"},{"benchmark":"babyvision","model":"glm-4.5v","score":15.72,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-vl-235b-a22b-instruct","score":18.3,"metric":"percent"},{"benchmark":"babyvision","model":"kimi-k2.5","score":33.25,"metric":"percent"},{"benchmark":"babyvision","model":"zwz-4b","score":16.24,"metric":"percent"},{"benchmark":"babyvision","model":"zwz-7b","score":15.98,"metric":"percent"},{"benchmark":"babyvision","model":"zwz-8b","score":16.75,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kat-coder-v2.5-dev","score":69.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-27b","score":68.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-35b-a3b","score":64.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-31b-it","score":60.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-35b-a3b","score":58.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-26b-a4b-it","score":35.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-30b-a3b-instruct","score":31.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kat-coder-v2.5-dev","score":63,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-27b","score":57.67,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.6-35b-a3b","score":57,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemma-4-31b-it","score":49.33,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-35b-a3b","score":47.67,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemma-4-26b-a4b-it","score":27.33,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3-coder-30b-a3b-instruct","score":20.67,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kat-coder-v2.5-dev","score":45.96,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-27b","score":42.13,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.6-35b-a3b","score":40.63,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemma-4-31b-it","score":32.97,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-35b-a3b","score":38.03,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemma-4-26b-a4b-it","score":9.58,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3-coder-30b-a3b-instruct","score":19.84,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kat-coder-v2.5-dev","score":32.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-27b","score":41.57,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":34.83,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-31b-it","score":30.34,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-35b-a3b","score":26.44,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-26b-a4b-it","score":27.27,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3-coder-30b-a3b-instruct","score":10.11,"metric":"percent"},{"benchmark":"pinchbench","model":"kat-coder-v2.5-dev","score":93.43,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-27b","score":90.71,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.6-35b-a3b","score":92.21,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-31b-it","score":85.53,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-35b-a3b","score":88.75,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-26b-a4b-it","score":82.01,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3-coder-30b-a3b-instruct","score":72.3,"metric":"percent"},{"benchmark":"scicode","model":"kat-coder-v2.5-dev","score":44.2,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-27b","score":25.58,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-35b-a3b","score":37.53,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-31b-it","score":33.19,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-35b-a3b","score":27.73,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-26b-a4b-it","score":30.84,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-coder-30b-a3b-instruct","score":18.27,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kat-coder-pro-v2.5","score":65.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"glm-5.2","score":62.1,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"kat-coder-pro-v2.5","score":94.9,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"glm-5.2","score":87,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"claude-opus-4.8","score":93.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kat-coder-pro-v2.5","score":60.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.1","score":61.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.2","score":77.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k2.6-thinking","score":73,"metric":"percent"},{"benchmark":"scicode","model":"kat-coder-pro-v2.5","score":50.3,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k2.6-thinking","score":53.5,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"kimi-k2.7-code","score":80.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kat-coder-pro-v2","score":79.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kat-coder-pro-v2","score":75.4,"metric":"percent"},{"benchmark":"pinchbench-best","model":"kat-coder-pro-v2","score":88.7,"metric":"percent"},{"benchmark":"pinchbench-best","model":"minimax-m2.7","score":87.1,"metric":"percent"},{"benchmark":"pinchbench-best","model":"claude-opus-4.6","score":87.4,"metric":"percent"},{"benchmark":"pinchbench-best","model":"gpt-5.4","score":90.5,"metric":"percent"},{"benchmark":"pinchbench-best","model":"gemini-3.1-pro","score":86.7,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"kat-coder-pro-v2","score":81.9,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"glm-5","score":80.3,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"minimax-m2.7","score":81.8,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"claude-opus-4.6","score":82.3,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gpt-5.4","score":81.6,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gemini-3.1-pro","score":75.9,"metric":"percent"},{"benchmark":"claweval-pass3","model":"kat-coder-pro-v2","score":55.6,"metric":"percent"},{"benchmark":"claweval-pass3","model":"minimax-m2.7","score":51.9,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gpt-5.4","score":66.3,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gemini-3.1-pro","score":50,"metric":"percent"},{"benchmark":"claw-eval","model":"kat-coder-pro-v2","score":73.4,"metric":"percent"},{"benchmark":"claw-eval","model":"minimax-m2.7","score":70.7,"metric":"percent"},{"benchmark":"claw-eval","model":"claude-opus-4.6","score":79.3,"metric":"percent"},{"benchmark":"claw-eval","model":"gpt-5.4","score":80.6,"metric":"percent"},{"benchmark":"claw-eval","model":"gemini-3.1-pro","score":74.2,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"kat-coder-pro-v2","score":46.8,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"glm-5","score":43.2,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"minimax-m2.7","score":39.4,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-opus-4.6","score":46.2,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5.4","score":57.6,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gemini-3.1-pro","score":53.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kat-coder-pro-v2","score":93.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"kat-coder-pro-v2","score":68,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-opus-4.6","score":70.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.4","score":74,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-3.1-pro","score":72.7,"metric":"percent"},{"benchmark":"ifbench","model":"kat-coder-pro-v2","score":67,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.4","score":73.9,"metric":"percent"},{"benchmark":"longvideobench","model":"keye-vl-2.0-30b-a3b","score":74.1,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3.5-35b-a3b","score":61.6,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl3.5-241b","score":67.1,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-vl-235b-a22b-thinking","score":70.5,"metric":"percent"},{"benchmark":"videomme-v2","model":"keye-vl-2.0-30b-a3b","score":42.4,"metric":"percent"},{"benchmark":"videomme-v2","model":"qwen3.5-35b-a3b","score":28.5,"metric":"percent"},{"benchmark":"videomme-v2","model":"qwen3-vl-235b-a22b-thinking","score":36.8,"metric":"percent"},{"benchmark":"mlvu","model":"keye-vl-2.0-30b-a3b","score":82.8,"metric":"percent"},{"benchmark":"mlvu","model":"internvl3.5-241b","score":78.2,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-30b-a3b-thinking","score":78.9,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-32b-thinking","score":82.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"keye-vl-2.0-30b-a3b","score":78.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl3.5-241b","score":72.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-30b-a3b-thinking","score":73.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-vl-32b-thinking","score":77.3,"metric":"percent"},{"benchmark":"timelens-activitynet","model":"keye-vl-2.0-30b-a3b","score":58.5,"metric":"percent"},{"benchmark":"timelens-activitynet","model":"qwen3.5-35b-a3b","score":53.2,"metric":"percent"},{"benchmark":"timelens-activitynet","model":"qwen3-vl-235b-a22b-thinking","score":52.1,"metric":"percent"},{"benchmark":"timelens-qvhighlights","model":"keye-vl-2.0-30b-a3b","score":70.1,"metric":"percent"},{"benchmark":"timelens-qvhighlights","model":"qwen3.5-35b-a3b","score":65.7,"metric":"percent"},{"benchmark":"timelens-qvhighlights","model":"qwen3-vl-235b-a22b-thinking","score":64.6,"metric":"percent"},{"benchmark":"timelens-charades","model":"keye-vl-2.0-30b-a3b","score":58.4,"metric":"percent"},{"benchmark":"timelens-charades","model":"qwen3.5-35b-a3b","score":49.1,"metric":"percent"},{"benchmark":"timelens-charades","model":"qwen3-vl-235b-a22b-thinking","score":47.8,"metric":"percent"},{"benchmark":"videommmu","model":"keye-vl-2.0-30b-a3b","score":80,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-30b-a3b-thinking","score":75,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3-vl-32b-thinking","score":79,"metric":"percent"},{"benchmark":"livecodebench","model":"keye-vl-2.0-30b-a3b","score":64.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-35b-a3b","score":62.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini","score":51.5,"metric":"percent"},{"benchmark":"ojbench","model":"keye-vl-2.0-30b-a3b","score":71.5,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-35b-a3b","score":70.2,"metric":"percent"},{"benchmark":"ojbench","model":"gpt-5-mini","score":58.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"keye-vl-2.0-30b-a3b","score":62,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-35b-a3b","score":63.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-mini","score":55.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"keye-vl-2.0-30b-a3b","score":65.7,"metric":"percent"},{"benchmark":"vitabench","model":"keye-vl-2.0-30b-a3b","score":33.1,"metric":"percent"},{"benchmark":"mlvu","model":"videotemp-o3-7b","score":54.2,"metric":"percent"},{"benchmark":"mlvu","model":"qwen2.5-vl-7b","score":45.2,"metric":"percent"},{"benchmark":"mlvu","model":"gpt-4o","score":54.9,"metric":"percent"},{"benchmark":"videommmu","model":"videotemp-o3-7b","score":53.2,"metric":"percent"},{"benchmark":"videommmu","model":"qwen2.5-vl-7b","score":43.2,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-1.5-pro","score":53.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"videotemp-o3-7b","score":64.5,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen2.5-vl-7b","score":59.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-1.5-pro","score":75,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-4o","score":71.9,"metric":"percent"},{"benchmark":"lvbench","model":"videotemp-o3-7b","score":43,"metric":"percent"},{"benchmark":"lvbench","model":"qwen2.5-vl-7b","score":39.2,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-1.5-pro","score":33.1,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-4o","score":30.8,"metric":"percent"},{"benchmark":"charades-sta","model":"videotemp-o3-7b","score":57.8,"metric":"percent"},{"benchmark":"charades-sta","model":"qwen2.5-vl-7b","score":38.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5","score":62.82,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-2.5-pro","score":65.72,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-max-thinking-preview","score":57.89,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-r1-0528","score":59.48,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-235b-a22b-thinking-2507","score":57.46,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-2.5-flash-thinking","score":56.77,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-oss-120b","score":47.01,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5-nano","score":43.74,"metric":"percent"},{"benchmark":"docmath","model":"qwen3.5-4b","score":65.87,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-4b","score":45.92,"metric":"percent"},{"benchmark":"frames","model":"qwen3.5-4b","score":70.87,"metric":"percent"},{"benchmark":"docmath","model":"qwen3.5-35b-a3b","score":68.87,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-35b-a3b","score":59.44,"metric":"percent"},{"benchmark":"frames","model":"qwen3.5-35b-a3b","score":74.88,"metric":"percent"},{"benchmark":"docmath","model":"qwen3-4b-thinking-2507","score":61,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-4b-thinking-2507","score":40.2,"metric":"percent"},{"benchmark":"frames","model":"qwen3-4b-thinking-2507","score":64.4,"metric":"percent"},{"benchmark":"docmath","model":"qwenlong-l1.5-30b-a3b","score":66.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwenlong-l1.5-30b-a3b","score":55.2,"metric":"percent"},{"benchmark":"frames","model":"qwenlong-l1.5-30b-a3b","score":74.5,"metric":"percent"},{"benchmark":"docmath","model":"qwen3-30b-a3b-thinking-2507","score":63.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3-30b-a3b-thinking-2507","score":48.7,"metric":"percent"},{"benchmark":"frames","model":"qwen3-30b-a3b-thinking-2507","score":70.2,"metric":"percent"},{"benchmark":"docmath","model":"golongrl-30b-a3b","score":65.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"golongrl-30b-a3b","score":55.1,"metric":"percent"},{"benchmark":"frames","model":"golongrl-30b-a3b","score":74.5,"metric":"percent"},{"benchmark":"docmath","model":"golongrl-4b","score":62.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"golongrl-4b","score":47.1,"metric":"percent"},{"benchmark":"frames","model":"golongrl-4b","score":67.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b-thinking-2507","score":73.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"golongrl-4b","score":74.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwenlong-l1.5-30b-a3b","score":81.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-thinking-2507","score":80.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"golongrl-30b-a3b","score":81,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-4b-thinking-2507","score":82.6,"metric":"percent"},{"benchmark":"aime-2024","model":"golongrl-4b","score":84.2,"metric":"percent"},{"benchmark":"aime-2024","model":"qwenlong-l1.5-30b-a3b","score":89.8,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-30b-a3b-thinking-2507","score":90.5,"metric":"percent"},{"benchmark":"aime-2024","model":"golongrl-30b-a3b","score":91.3,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-thinking-2507","score":80.2,"metric":"percent"},{"benchmark":"aime-2025","model":"golongrl-4b","score":80.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwenlong-l1.5-30b-a3b","score":87.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-30b-a3b-thinking-2507","score":85.1,"metric":"percent"},{"benchmark":"aime-2025","model":"golongrl-30b-a3b","score":86.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b-thinking-2507","score":65.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"golongrl-4b","score":67.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwenlong-l1.5-30b-a3b","score":72.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-thinking-2507","score":70.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"golongrl-30b-a3b","score":72.3,"metric":"percent"},{"benchmark":"longmemeval","model":"qwen3-4b-thinking-2507","score":47.6,"metric":"percent"},{"benchmark":"longmemeval","model":"golongrl-4b","score":61.2,"metric":"percent"},{"benchmark":"longmemeval","model":"qwenlong-l1.5-30b-a3b","score":72.2,"metric":"percent"},{"benchmark":"longmemeval","model":"qwen3-30b-a3b-thinking-2507","score":61.6,"metric":"percent"},{"benchmark":"longmemeval","model":"golongrl-30b-a3b","score":75.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"spark-x2.5-4b","score":65.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"spark-x2.5-1.7b","score":46.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-12b-it","score":37.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":36.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e2b-it","score":30.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"spark-x2.5-4b","score":54.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"spark-x2.5-1.7b","score":23.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.5-9b","score":47.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.5-4b","score":40.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.5-2b","score":14.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemma-4-12b-it","score":30.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemma-4-e4b-it","score":15,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemma-4-e2b-it","score":12.6,"metric":"percent"},{"benchmark":"mcpmark","model":"spark-x2.5-4b","score":14.2,"metric":"percent"},{"benchmark":"mcpmark","model":"spark-x2.5-1.7b","score":2.3,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.5-9b","score":13.4,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.5-4b","score":12.5,"metric":"percent"},{"benchmark":"browsecomp","model":"spark-x2.5-4b","score":40.9,"metric":"percent"},{"benchmark":"browsecomp","model":"spark-x2.5-1.7b","score":29.7,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-9b","score":8.3,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-4b","score":14.3,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-2b","score":3.1,"metric":"percent"},{"benchmark":"browsecomp","model":"gemma-4-12b-it","score":10,"metric":"percent"},{"benchmark":"browsecomp","model":"gemma-4-e4b-it","score":8.3,"metric":"percent"},{"benchmark":"browsecomp","model":"gemma-4-e2b-it","score":3.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"spark-x2.5-4b","score":44.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"spark-x2.5-1.7b","score":10.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-9b","score":33.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-4b","score":29.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-2b","score":1.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemma-4-12b-it","score":21.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemma-4-e4b-it","score":4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"spark-x2.5-4b","score":41.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"spark-x2.5-1.7b","score":28.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-9b","score":53.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-4b","score":38.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-2b","score":6.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-12b-it","score":44.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-e4b-it","score":14,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"spark-x2.5-4b","score":53.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"spark-x2.5-1.7b","score":23.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-9b","score":43.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-4b","score":27.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-2b","score":5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemma-4-12b-it","score":32.5,"metric":"percent"},{"benchmark":"scicode","model":"spark-x2.5-4b","score":34.7,"metric":"percent"},{"benchmark":"scicode","model":"spark-x2.5-1.7b","score":18.2,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-9b","score":32.7,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-4b","score":24,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-2b","score":6,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-12b-it","score":39.8,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-e4b-it","score":27.5,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-e2b-it","score":20.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"spark-x2.5-4b","score":90.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"spark-x2.5-1.7b","score":69.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-9b","score":88.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-4b","score":83,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-2b","score":30.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-12b-it","score":82.1,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"spark-x2.5-4b","score":81.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"spark-x2.5-1.7b","score":48.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-9b","score":70.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-4b","score":69.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-2b","score":21.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-12b-it","score":65.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-e4b-it","score":34.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-e2b-it","score":20.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"spark-x2.5-4b","score":74.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"spark-x2.5-1.7b","score":45.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-9b","score":69.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-4b","score":68.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-12b-it","score":57.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-e4b-it","score":26.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-e2b-it","score":22.6,"metric":"percent"},{"benchmark":"ifeval","model":"spark-x2.5-4b","score":93,"metric":"percent"},{"benchmark":"ifeval","model":"spark-x2.5-1.7b","score":89.5,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-12b-it","score":94.8,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e4b-it","score":45.3,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e2b-it","score":34.8,"metric":"percent"},{"benchmark":"ifbench","model":"spark-x2.5-4b","score":75,"metric":"percent"},{"benchmark":"ifbench","model":"spark-x2.5-1.7b","score":66.3,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":44,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e2b-it","score":22.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"spark-x2.5-4b","score":56.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"spark-x2.5-1.7b","score":24.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-12b-it","score":55.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-e4b-it","score":34.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-e2b-it","score":18.3,"metric":"percent"},{"benchmark":"hle","model":"spark-x2.5-4b","score":12.3,"metric":"avg@3"},{"benchmark":"hle","model":"spark-x2.5-1.7b","score":6.3,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-9b","score":14.3,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-4b","score":8.6,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-2b","score":2.1,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-12b-it","score":13.1,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-e4b-it","score":3.9,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-e2b-it","score":2.5,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"spark-x2.5-4b","score":67.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"spark-x2.5-1.7b","score":43.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-9b","score":77.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-4b","score":67.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-2b","score":44.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-12b-it","score":72.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e4b-it","score":54.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e2b-it","score":43.8,"metric":"percent"},{"benchmark":"tomato","model":"minicpm-o-4.5","score":30.66,"metric":"percent"},{"benchmark":"tomato","model":"mage-vl","score":36.05,"metric":"percent"},{"benchmark":"tomato","model":"moss-vl-realtime","score":38.68,"metric":"percent"},{"benchmark":"tomato","model":"joyai-vl-interaction","score":41.85,"metric":"percent"},{"benchmark":"tvbench","model":"minicpm-o-4.5","score":52,"metric":"percent"},{"benchmark":"tvbench","model":"mage-vl","score":58.1,"metric":"percent"},{"benchmark":"tvbench","model":"moss-vl-realtime","score":56.83,"metric":"percent"},{"benchmark":"tvbench","model":"qwen3-vl-8b-instruct","score":57.94,"metric":"percent"},{"benchmark":"tvbench","model":"joyai-vl-interaction","score":64.91,"metric":"percent"},{"benchmark":"mvbench","model":"minicpm-o-4.5","score":64.31,"metric":"percent"},{"benchmark":"mvbench","model":"mage-vl","score":66.73,"metric":"percent"},{"benchmark":"mvbench","model":"moss-vl-realtime","score":61.18,"metric":"percent"},{"benchmark":"mvbench","model":"joyai-vl-interaction","score":73.7,"metric":"percent"},{"benchmark":"tempcompass","model":"minicpm-o-4.5","score":74.36,"metric":"percent"},{"benchmark":"tempcompass","model":"mage-vl","score":74.64,"metric":"percent"},{"benchmark":"tempcompass","model":"moss-vl-realtime","score":73.99,"metric":"percent"},{"benchmark":"tempcompass","model":"qwen3-vl-8b-instruct","score":76.4,"metric":"percent"},{"benchmark":"tempcompass","model":"joyai-vl-interaction","score":76.05,"metric":"percent"},{"benchmark":"perceptiontest","model":"minicpm-o-4.5","score":67.52,"metric":"percent"},{"benchmark":"perceptiontest","model":"mage-vl","score":67.48,"metric":"percent"},{"benchmark":"perceptiontest","model":"moss-vl-realtime","score":65.88,"metric":"percent"},{"benchmark":"perceptiontest","model":"joyai-vl-interaction","score":75.89,"metric":"percent"},{"benchmark":"motionbench","model":"minicpm-o-4.5","score":59.56,"metric":"percent"},{"benchmark":"motionbench","model":"mage-vl","score":60.08,"metric":"percent"},{"benchmark":"motionbench","model":"moss-vl-realtime","score":60.25,"metric":"percent"},{"benchmark":"motionbench","model":"qwen3-vl-8b-instruct","score":58.4,"metric":"percent"},{"benchmark":"motionbench","model":"joyai-vl-interaction","score":60.05,"metric":"percent"},{"benchmark":"timelens-charades","model":"minicpm-o-4.5","score":20.29,"metric":"percent"},{"benchmark":"timelens-charades","model":"mage-vl","score":44.26,"metric":"percent"},{"benchmark":"timelens-charades","model":"moss-vl-realtime","score":39.29,"metric":"percent"},{"benchmark":"timelens-charades","model":"qwen3-vl-8b-instruct","score":45.77,"metric":"percent"},{"benchmark":"timelens-charades","model":"joyai-vl-interaction","score":50.45,"metric":"percent"},{"benchmark":"timelens-activitynet","model":"minicpm-o-4.5","score":13.44,"metric":"percent"},{"benchmark":"timelens-activitynet","model":"mage-vl","score":42.99,"metric":"percent"},{"benchmark":"timelens-activitynet","model":"moss-vl-realtime","score":36.6,"metric":"percent"},{"benchmark":"timelens-activitynet","model":"qwen3-vl-8b-instruct","score":45.59,"metric":"percent"},{"benchmark":"timelens-activitynet","model":"joyai-vl-interaction","score":52.12,"metric":"percent"},{"benchmark":"timelens-qvhighlights","model":"minicpm-o-4.5","score":9.02,"metric":"percent"},{"benchmark":"timelens-qvhighlights","model":"mage-vl","score":54.63,"metric":"percent"},{"benchmark":"timelens-qvhighlights","model":"moss-vl-realtime","score":50.52,"metric":"percent"},{"benchmark":"timelens-qvhighlights","model":"qwen3-vl-8b-instruct","score":59.08,"metric":"percent"},{"benchmark":"timelens-qvhighlights","model":"joyai-vl-interaction","score":65.03,"metric":"percent"},{"benchmark":"videomme-v2","model":"minicpm-o-4.5","score":27.31,"metric":"percent"},{"benchmark":"videomme-v2","model":"mage-vl","score":23.5,"metric":"percent"},{"benchmark":"videomme-v2","model":"moss-vl-realtime","score":26.63,"metric":"percent"},{"benchmark":"videomme-v2","model":"qwen3-vl-8b-instruct","score":32.5,"metric":"percent"},{"benchmark":"videomme-v2","model":"joyai-vl-interaction","score":31.84,"metric":"percent"},{"benchmark":"longvideobench","model":"minicpm-o-4.5","score":62.9,"metric":"percent"},{"benchmark":"longvideobench","model":"mage-vl","score":63.35,"metric":"percent"},{"benchmark":"longvideobench","model":"moss-vl-realtime","score":60.51,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-vl-8b-instruct","score":66.6,"metric":"percent"},{"benchmark":"longvideobench","model":"joyai-vl-interaction","score":66.94,"metric":"percent"},{"benchmark":"videoevalpro","model":"minicpm-o-4.5","score":29.09,"metric":"percent"},{"benchmark":"videoevalpro","model":"mage-vl","score":22.11,"metric":"percent"},{"benchmark":"videoevalpro","model":"moss-vl-realtime","score":28.7,"metric":"percent"},{"benchmark":"videoevalpro","model":"qwen3-vl-8b-instruct","score":31.57,"metric":"percent"},{"benchmark":"videoevalpro","model":"joyai-vl-interaction","score":33.51,"metric":"percent"},{"benchmark":"egoschema","model":"minicpm-o-4.5","score":59.4,"metric":"percent"},{"benchmark":"egoschema","model":"mage-vl","score":68,"metric":"percent"},{"benchmark":"egoschema","model":"moss-vl-realtime","score":57.4,"metric":"percent"},{"benchmark":"egoschema","model":"joyai-vl-interaction","score":75.6,"metric":"percent"},{"benchmark":"videoholmes","model":"minicpm-o-4.5","score":58.36,"metric":"percent"},{"benchmark":"videoholmes","model":"mage-vl","score":38.05,"metric":"percent"},{"benchmark":"videoholmes","model":"moss-vl-realtime","score":44.96,"metric":"percent"},{"benchmark":"videoholmes","model":"qwen3-vl-8b-instruct","score":45.3,"metric":"percent"},{"benchmark":"videoholmes","model":"joyai-vl-interaction","score":46.92,"metric":"percent"},{"benchmark":"vcrbench","model":"minicpm-o-4.5","score":38.2,"metric":"percent"},{"benchmark":"vcrbench","model":"mage-vl","score":35.4,"metric":"percent"},{"benchmark":"vcrbench","model":"moss-vl-realtime","score":35.98,"metric":"percent"},{"benchmark":"vcrbench","model":"qwen3-vl-8b-instruct","score":42.7,"metric":"percent"},{"benchmark":"vcrbench","model":"joyai-vl-interaction","score":43.04,"metric":"percent"},{"benchmark":"videomathqa","model":"minicpm-o-4.5","score":52.05,"metric":"percent"},{"benchmark":"videomathqa","model":"mage-vl","score":51.05,"metric":"percent"},{"benchmark":"videomathqa","model":"moss-vl-realtime","score":50.76,"metric":"percent"},{"benchmark":"videomathqa","model":"qwen3-vl-8b-instruct","score":52.7,"metric":"percent"},{"benchmark":"videomathqa","model":"joyai-vl-interaction","score":56.24,"metric":"percent"},{"benchmark":"videommmu","model":"minicpm-o-4.5","score":53,"metric":"percent"},{"benchmark":"videommmu","model":"mage-vl","score":48.78,"metric":"percent"},{"benchmark":"videommmu","model":"moss-vl-realtime","score":46.67,"metric":"percent"},{"benchmark":"videommmu","model":"joyai-vl-interaction","score":64.67,"metric":"percent"},{"benchmark":"mmvu","model":"minicpm-o-4.5","score":60.2,"metric":"percent"},{"benchmark":"mmvu","model":"mage-vl","score":53.1,"metric":"percent"},{"benchmark":"mmvu","model":"moss-vl-realtime","score":50.2,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3-vl-8b-instruct","score":58.7,"metric":"percent"},{"benchmark":"mmvu","model":"joyai-vl-interaction","score":60,"metric":"percent"},{"benchmark":"ovobench","model":"minicpm-o-4.5","score":57.89,"metric":"percent"},{"benchmark":"ovobench","model":"mage-vl","score":51.8,"metric":"percent"},{"benchmark":"ovobench","model":"qwen3-vl-8b-instruct","score":57.2,"metric":"percent"},{"benchmark":"ovobench","model":"joyai-vl-interaction","score":59.2,"metric":"percent"},{"benchmark":"ovbench","model":"minicpm-o-4.5","score":49.3,"metric":"percent"},{"benchmark":"ovbench","model":"mage-vl","score":49.91,"metric":"percent"},{"benchmark":"ovbench","model":"qwen3-vl-8b-instruct","score":52,"metric":"percent"},{"benchmark":"ovbench","model":"joyai-vl-interaction","score":58.9,"metric":"percent"},{"benchmark":"odvbench","model":"minicpm-o-4.5","score":47.68,"metric":"percent"},{"benchmark":"odvbench","model":"mage-vl","score":53.84,"metric":"percent"},{"benchmark":"odvbench","model":"qwen3-vl-8b-instruct","score":56.1,"metric":"percent"},{"benchmark":"odvbench","model":"joyai-vl-interaction","score":68.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"amazon-nova-lite-v1.0","score":59,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-4.5-haiku","score":80,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nova-2-lite","score":80.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"amazon-nova-pro-v1.0","score":69.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"amazon-nova-premier","score":73.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-sonnet-4.5","score":87.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.1","score":87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3-pro-preview","score":89.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nova-2-pro","score":81.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"amazon-nova-lite-v1.0","score":43.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nova-2-lite","score":79.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"amazon-nova-pro-v1.0","score":49.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"amazon-nova-premier","score":56.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3-pro-preview","score":91.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nova-2-pro","score":81.4,"metric":"percent"},{"benchmark":"aime-2025","model":"amazon-nova-lite-v1.0","score":7,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-4.5-haiku","score":80.7,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-mini","score":91.1,"metric":"percent"},{"benchmark":"aime-2025","model":"nova-2-lite","score":91,"metric":"percent"},{"benchmark":"aime-2025","model":"amazon-nova-pro-v1.0","score":7,"metric":"percent"},{"benchmark":"aime-2025","model":"amazon-nova-premier","score":17.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3-pro-preview","score":95,"metric":"percent"},{"benchmark":"aime-2025","model":"nova-2-pro","score":92.3,"metric":"percent"},{"benchmark":"ifbench","model":"amazon-nova-lite-v1.0","score":34.1,"metric":"percent"},{"benchmark":"ifbench","model":"nova-2-lite","score":70.8,"metric":"percent"},{"benchmark":"ifbench","model":"amazon-nova-pro-v1.0","score":38.1,"metric":"percent"},{"benchmark":"ifbench","model":"amazon-nova-premier","score":36.2,"metric":"percent"},{"benchmark":"ifbench","model":"claude-sonnet-4.5","score":57.3,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.1","score":72.9,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-3-pro-preview","score":70.4,"metric":"percent"},{"benchmark":"ifbench","model":"nova-2-pro","score":80.2,"metric":"percent"},{"benchmark":"multichallenge","model":"amazon-nova-lite-v1.0","score":18.7,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-4.5-haiku","score":57.1,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5-mini","score":67.8,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-2.5-flash","score":62.6,"metric":"percent"},{"benchmark":"multichallenge","model":"nova-2-lite","score":76.6,"metric":"percent"},{"benchmark":"multichallenge","model":"amazon-nova-pro-v1.0","score":26.7,"metric":"percent"},{"benchmark":"multichallenge","model":"amazon-nova-premier","score":22,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-sonnet-4.5","score":63.1,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5.1","score":72.2,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-2.5-pro","score":62.3,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-3-pro-preview","score":73.6,"metric":"percent"},{"benchmark":"multichallenge","model":"nova-2-pro","score":77.7,"metric":"percent"},{"benchmark":"longcodebench","model":"gemini-2.5-flash","score":78,"metric":"percent"},{"benchmark":"longcodebench","model":"nova-2-lite","score":84,"metric":"percent"},{"benchmark":"longcodebench","model":"amazon-nova-premier","score":42,"metric":"percent"},{"benchmark":"longcodebench","model":"claude-sonnet-4.5","score":82,"metric":"percent"},{"benchmark":"longcodebench","model":"gemini-2.5-pro","score":74,"metric":"percent"},{"benchmark":"longcodebench","model":"gemini-3-pro-preview","score":82,"metric":"percent"},{"benchmark":"longcodebench","model":"nova-2-pro","score":84,"metric":"percent"},{"benchmark":"tau2-telecom","model":"amazon-nova-lite-v1.0","score":17.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-mini","score":71.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nova-2-lite","score":76,"metric":"percent"},{"benchmark":"tau2-telecom","model":"amazon-nova-pro-v1.0","score":14,"metric":"percent"},{"benchmark":"tau2-telecom","model":"amazon-nova-premier","score":38.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-sonnet-4.5","score":78.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5","score":86.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5.1","score":81.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-3-pro-preview","score":87.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nova-2-pro","score":92.7,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"claude-4.5-haiku","score":69.1,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"gpt-5-mini","score":73.7,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"gemini-2.5-flash","score":57.7,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"nova-2-lite","score":76.5,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"claude-sonnet-4.5","score":77.2,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"gpt-5","score":78.3,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"gpt-5.1","score":77.5,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"gemini-2.5-pro","score":71.3,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"gemini-3-pro-preview","score":77.7,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"nova-2-pro","score":77.7,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"claude-4.5-haiku","score":54,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"gpt-5-mini","score":68.8,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"gemini-2.5-flash","score":44,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"nova-2-lite","score":64.8,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"claude-sonnet-4.5","score":66.8,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"gpt-5","score":72,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"gpt-5.1","score":72.4,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"gemini-2.5-pro","score":60,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"gemini-3-pro-preview","score":70.8,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"nova-2-pro","score":65.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"amazon-nova-lite-v1.0","score":33.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"claude-4.5-haiku","score":61.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5-mini","score":56,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemini-2.5-flash","score":55.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nova-2-lite","score":60.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"amazon-nova-pro-v1.0","score":38,"metric":"percent"},{"benchmark":"bfcl-v4","model":"amazon-nova-premier","score":53.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5","score":61.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.1","score":60.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nova-2-pro","score":61.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5-mini","score":22.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"nova-2-lite","score":24.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5","score":44.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemini-3-pro-preview","score":54.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"amazon-nova-lite-v1.0","score":38,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-flash","score":69,"metric":"percent"},{"benchmark":"mmmu-pro","model":"nova-2-lite","score":61.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"amazon-nova-pro-v1.0","score":44,"metric":"percent"},{"benchmark":"mmmu-pro","model":"amazon-nova-premier","score":52.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-sonnet-4.5","score":69,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3-pro-preview","score":81,"metric":"percent"},{"benchmark":"mmmu-pro","model":"nova-2-pro","score":63.5,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"amazon-nova-lite-v1.0","score":40.4,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"claude-4.5-haiku","score":52.2,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"gpt-5-mini","score":53.1,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"gemini-2.5-flash","score":50.1,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"nova-2-lite","score":62.1,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"amazon-nova-pro-v1.0","score":49.7,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"amazon-nova-premier","score":54.6,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"claude-sonnet-4.5","score":62.4,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"gpt-5","score":51.9,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"gpt-5.1","score":53.6,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"gemini-2.5-pro","score":54.9,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"gemini-3-pro-preview","score":71.7,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"nova-2-pro","score":67,"metric":"percent"},{"benchmark":"qvhighlights","model":"amazon-nova-lite-v1.0","score":11.9,"metric":"percent"},{"benchmark":"qvhighlights","model":"gemini-2.5-flash","score":52.4,"metric":"percent"},{"benchmark":"qvhighlights","model":"nova-2-lite","score":77.2,"metric":"percent"},{"benchmark":"qvhighlights","model":"amazon-nova-pro-v1.0","score":10.7,"metric":"percent"},{"benchmark":"qvhighlights","model":"amazon-nova-premier","score":4.5,"metric":"percent"},{"benchmark":"qvhighlights","model":"gemini-2.5-pro","score":75,"metric":"percent"},{"benchmark":"qvhighlights","model":"gemini-3-pro-preview","score":48.1,"metric":"percent"},{"benchmark":"qvhighlights","model":"nova-2-pro","score":76.7,"metric":"percent"},{"benchmark":"screenspot","model":"amazon-nova-lite-v1.0","score":80.1,"metric":"percent"},{"benchmark":"screenspot","model":"gpt-5-mini","score":24.8,"metric":"percent"},{"benchmark":"screenspot","model":"gemini-2.5-flash","score":27.2,"metric":"percent"},{"benchmark":"screenspot","model":"nova-2-lite","score":83.3,"metric":"percent"},{"benchmark":"screenspot","model":"amazon-nova-pro-v1.0","score":83.5,"metric":"percent"},{"benchmark":"screenspot","model":"amazon-nova-premier","score":86.2,"metric":"percent"},{"benchmark":"screenspot","model":"gpt-5","score":31,"metric":"percent"},{"benchmark":"screenspot","model":"gpt-5.1","score":28.5,"metric":"percent"},{"benchmark":"screenspot","model":"gemini-2.5-pro","score":44.7,"metric":"percent"},{"benchmark":"screenspot","model":"gemini-3-pro-preview","score":66.8,"metric":"percent"},{"benchmark":"screenspot","model":"nova-2-pro","score":88.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-mini","score":71,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-2.5-flash","score":48.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nova-2-lite","score":53.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"amazon-nova-premier","score":42.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3-pro-preview","score":76.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nova-2-pro","score":61.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-4.5-haiku","score":41.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5-mini","score":30.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-2.5-flash","score":16.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"nova-2-lite","score":32.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"amazon-nova-premier","score":11.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-sonnet-4.5","score":51,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5","score":41.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5.1","score":53.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"gemini-3-pro-preview","score":56.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"nova-2-pro","score":41.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"claude-4.5-haiku","score":61.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-5-mini","score":83.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-2.5-flash","score":69.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nova-2-lite","score":71,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"amazon-nova-premier","score":31.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"claude-sonnet-4.5","score":71.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-5","score":84.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-5.1","score":86.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-2.5-pro","score":80.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-3-pro-preview","score":91.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"nova-2-pro","score":74.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nova-2-omni","score":80.7,"metric":"percent"},{"benchmark":"aime-2025","model":"nova-2-omni","score":92.1,"metric":"percent"},{"benchmark":"ifbench","model":"nova-2-omni","score":68.7,"metric":"percent"},{"benchmark":"multichallenge","model":"nova-2-omni","score":75.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nova-2-omni","score":80,"metric":"percent"},{"benchmark":"tau2-retail-verified","model":"nova-2-omni","score":78.3,"metric":"percent"},{"benchmark":"tau2-airline-verified","model":"nova-2-omni","score":68.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nova-2-omni","score":58.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"nova-2-omni","score":61.4,"metric":"percent"},{"benchmark":"realkie-fcc-verified","model":"nova-2-omni","score":59.8,"metric":"percent"},{"benchmark":"refcocog","model":"gemini-2.5-flash","score":19.8,"metric":"percent"},{"benchmark":"refcocog","model":"gpt-5-mini","score":32,"metric":"percent"},{"benchmark":"refcocog","model":"nova-2-omni","score":86.3,"metric":"percent"},{"benchmark":"video-mme","model":"gemini-2.5-flash","score":74.4,"metric":"percent"},{"benchmark":"video-mme","model":"nova-2-omni","score":77.9,"metric":"percent"},{"benchmark":"maverix","model":"gemini-2.5-flash","score":67.4,"metric":"percent"},{"benchmark":"maverix","model":"nova-2-omni","score":66.6,"metric":"percent"},{"benchmark":"qvhighlights","model":"nova-2-omni","score":76.7,"metric":"percent"},{"benchmark":"screenspot","model":"nova-2-omni","score":85.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"lar-9b","score":64.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"lar-27b","score":84.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"lar-9b","score":32.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"lar-27b","score":68.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"lar-9b","score":29.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"lar-27b","score":77.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-1.7b","score":82.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"alodlm-1.7b","score":77.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-8b","score":93.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llada-8b-instruct","score":85.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"dream-7b-instruct","score":84.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"wedlm-8b-instruct","score":91.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"alodlm-8b","score":94.4,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen3-1.7b","score":90,"metric":"percent"},{"benchmark":"arc-easy","model":"alodlm-1.7b","score":88.7,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen3-8b","score":96.1,"metric":"percent"},{"benchmark":"arc-easy","model":"llada-8b-instruct","score":92.6,"metric":"percent"},{"benchmark":"arc-easy","model":"dream-7b-instruct","score":93,"metric":"percent"},{"benchmark":"arc-easy","model":"wedlm-8b-instruct","score":97.5,"metric":"percent"},{"benchmark":"arc-easy","model":"alodlm-8b","score":98.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-1.7b","score":60.3,"metric":"percent"},{"benchmark":"mmlu","model":"alodlm-1.7b","score":59.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b","score":76.6,"metric":"percent"},{"benchmark":"mmlu","model":"llada-8b-instruct","score":62.4,"metric":"percent"},{"benchmark":"mmlu","model":"dream-7b-instruct","score":68.4,"metric":"percent"},{"benchmark":"mmlu","model":"wedlm-8b-instruct","score":78,"metric":"percent"},{"benchmark":"mmlu","model":"alodlm-8b","score":76.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":39,"metric":"percent"},{"benchmark":"mmlu-pro","model":"alodlm-1.7b","score":39.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b","score":56.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada-8b-instruct","score":35.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"dream-7b-instruct","score":42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"wedlm-8b-instruct","score":58.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"alodlm-8b","score":63.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-1.7b","score":83.2,"metric":"percent"},{"benchmark":"gsm8k","model":"alodlm-1.7b","score":85.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-8b","score":93.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llada-8b-instruct","score":73.8,"metric":"percent"},{"benchmark":"gsm8k","model":"dream-7b-instruct","score":82,"metric":"percent"},{"benchmark":"gsm8k","model":"wedlm-8b-instruct","score":93.3,"metric":"percent"},{"benchmark":"gsm8k","model":"alodlm-8b","score":94.2,"metric":"percent"},{"benchmark":"math500","model":"qwen3-1.7b","score":72,"metric":"percent"},{"benchmark":"math500","model":"alodlm-1.7b","score":61.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b","score":81.8,"metric":"percent"},{"benchmark":"math500","model":"llada-8b-instruct","score":42.2,"metric":"percent"},{"benchmark":"math500","model":"dream-7b-instruct","score":42,"metric":"percent"},{"benchmark":"math500","model":"wedlm-8b-instruct","score":77.8,"metric":"percent"},{"benchmark":"math500","model":"alodlm-8b","score":80.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-1.7b","score":31.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"alodlm-1.7b","score":41.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-8b","score":47,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llada-8b-instruct","score":22.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"dream-7b-instruct","score":23.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"wedlm-8b-instruct","score":37.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"alodlm-8b","score":49.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-1.7b","score":61.9,"metric":"percent"},{"benchmark":"mbpp","model":"alodlm-1.7b","score":65.5,"metric":"percent"},{"benchmark":"mbpp","model":"llada-8b-instruct","score":46,"metric":"percent"},{"benchmark":"mbpp","model":"dream-7b-instruct","score":65.5,"metric":"percent"},{"benchmark":"mbpp","model":"wedlm-8b-instruct","score":74.3,"metric":"percent"},{"benchmark":"mbpp","model":"alodlm-8b","score":81.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"alodlm-1.7b","score":60.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-8b","score":74.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llada-8b-instruct","score":43.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"dream-7b-instruct","score":60.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"wedlm-8b-instruct","score":63.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"alodlm-8b","score":72.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-1.7b","score":62.8,"metric":"percent"},{"benchmark":"humaneval","model":"alodlm-1.7b","score":72.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-8b","score":85.4,"metric":"percent"},{"benchmark":"humaneval","model":"llada-8b-instruct","score":43.3,"metric":"percent"},{"benchmark":"humaneval","model":"dream-7b-instruct","score":53.7,"metric":"percent"},{"benchmark":"humaneval","model":"wedlm-8b-instruct","score":79.9,"metric":"percent"},{"benchmark":"humaneval","model":"alodlm-8b","score":87.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-1.7b","score":60.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"alodlm-1.7b","score":67.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-8b","score":79.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llada-8b-instruct","score":38.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"dream-7b-instruct","score":50,"metric":"percent"},{"benchmark":"humaneval-plus","model":"wedlm-8b-instruct","score":74.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"alodlm-8b","score":84.2,"metric":"percent"},{"benchmark":"ai2d","model":"phi-4-reasoning-vision-15b","score":84.8,"metric":"percent"},{"benchmark":"ai2d","model":"phi-4-multimodal-instruct","score":68.6,"metric":"percent"},{"benchmark":"ai2d","model":"kimi-vl-a3b-instruct","score":84.6,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-3-12b-it","score":80.4,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-8b-instruct","score":83,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-32b-instruct","score":85,"metric":"percent"},{"benchmark":"chartqa","model":"phi-4-reasoning-vision-15b","score":83.3,"metric":"percent"},{"benchmark":"chartqa","model":"phi-4-multimodal-instruct","score":23.5,"metric":"percent"},{"benchmark":"chartqa","model":"kimi-vl-a3b-instruct","score":87,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-3-12b-it","score":39,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-8b-instruct","score":83.2,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-32b-instruct","score":84,"metric":"percent"},{"benchmark":"hallusionbench","model":"phi-4-reasoning-vision-15b","score":64.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"phi-4-multimodal-instruct","score":56,"metric":"percent"},{"benchmark":"hallusionbench","model":"kimi-vl-a3b-instruct","score":65.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-3-12b-it","score":65.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-8b-instruct","score":74.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-32b-instruct","score":74.9,"metric":"percent"},{"benchmark":"mathverse-mini","model":"phi-4-reasoning-vision-15b","score":44.9,"metric":"percent"},{"benchmark":"mathverse-mini","model":"phi-4-multimodal-instruct","score":32.4,"metric":"percent"},{"benchmark":"mathverse-mini","model":"kimi-vl-a3b-instruct","score":41.7,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gemma-3-12b-it","score":29.8,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-8b-instruct","score":57.4,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-32b-instruct","score":64.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"phi-4-reasoning-vision-15b","score":75.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"phi-4-multimodal-instruct","score":50.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"kimi-vl-a3b-instruct","score":67.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemma-3-12b-it","score":57.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-8b-instruct","score":76.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-32b-instruct","score":81.8,"metric":"percent"},{"benchmark":"mmmu","model":"phi-4-reasoning-vision-15b","score":54.3,"metric":"percent"},{"benchmark":"mmmu","model":"phi-4-multimodal-instruct","score":42.3,"metric":"percent"},{"benchmark":"mmmu","model":"kimi-vl-a3b-instruct","score":52,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-3-12b-it","score":50,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-8b-instruct","score":64.6,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-32b-instruct","score":70.6,"metric":"percent"},{"benchmark":"mmstar","model":"phi-4-reasoning-vision-15b","score":64.5,"metric":"percent"},{"benchmark":"mmstar","model":"phi-4-multimodal-instruct","score":45.9,"metric":"percent"},{"benchmark":"mmstar","model":"kimi-vl-a3b-instruct","score":60,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-3-12b-it","score":59.4,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-8b-instruct","score":69.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-32b-instruct","score":74.3,"metric":"percent"},{"benchmark":"ocrbench","model":"phi-4-reasoning-vision-15b","score":76,"metric":"percent"},{"benchmark":"ocrbench","model":"phi-4-multimodal-instruct","score":62.6,"metric":"percent"},{"benchmark":"ocrbench","model":"kimi-vl-a3b-instruct","score":86.5,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-3-12b-it","score":75.3,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-8b-instruct","score":90,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-32b-instruct","score":88.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"phi-4-reasoning-vision-15b","score":88.2,"metric":"percent"},{"benchmark":"screenspot-v2","model":"phi-4-multimodal-instruct","score":28.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"kimi-vl-a3b-instruct","score":89.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gemma-3-12b-it","score":3.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-8b-instruct","score":91.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-32b-instruct","score":93.9,"metric":"percent"},{"benchmark":"ai2d","model":"kimi-vl-a3b-thinking","score":81.2,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-8b-thinking","score":83.9,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-32b-thinking","score":87.2,"metric":"percent"},{"benchmark":"chartqa","model":"kimi-vl-a3b-thinking","score":73.3,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-8b-thinking","score":78.6,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-32b-thinking","score":79.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"kimi-vl-a3b-thinking","score":70.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-8b-thinking","score":73,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-32b-thinking","score":76.6,"metric":"percent"},{"benchmark":"mathverse-mini","model":"kimi-vl-a3b-thinking","score":61,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-8b-thinking","score":73.3,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3-vl-32b-thinking","score":78.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"kimi-vl-a3b-thinking","score":78.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-8b-thinking","score":79.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-32b-thinking","score":83.8,"metric":"percent"},{"benchmark":"mmmu","model":"kimi-vl-a3b-thinking","score":60.2,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-8b-thinking","score":65.3,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-32b-thinking","score":72.2,"metric":"percent"},{"benchmark":"mmstar","model":"kimi-vl-a3b-thinking","score":69.6,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-8b-thinking","score":72.3,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-32b-thinking","score":75.7,"metric":"percent"},{"benchmark":"ocrbench","model":"kimi-vl-a3b-thinking","score":79.9,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-8b-thinking","score":82,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-32b-thinking","score":85,"metric":"percent"},{"benchmark":"screenspot-v2","model":"kimi-vl-a3b-thinking","score":81.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-8b-thinking","score":92.7,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-32b-thinking","score":83.1,"metric":"percent"},{"benchmark":"webvoyager","model":"fara1.5-4b","score":80.8,"metric":"percent"},{"benchmark":"webvoyager","model":"fara1.5-9b","score":86.6,"metric":"percent"},{"benchmark":"webvoyager","model":"fara1.5-27b","score":89.3,"metric":"percent"},{"benchmark":"online-mind2web","model":"fara1.5-4b","score":57.3,"metric":"percent"},{"benchmark":"online-mind2web","model":"fara1.5-9b","score":63.4,"metric":"percent"},{"benchmark":"online-mind2web","model":"fara1.5-27b","score":72.3,"metric":"percent"},{"benchmark":"webtailbench","model":"fara1.5-4b","score":27.4,"metric":"percent"},{"benchmark":"webtailbench","model":"fara1.5-9b","score":32.3,"metric":"percent"},{"benchmark":"webtailbench","model":"fara1.5-27b","score":40.2,"metric":"percent"},{"benchmark":"docvqa","model":"mage-vl","score":95.14,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-4b-instruct","score":94.69,"metric":"percent"},{"benchmark":"docvqa","model":"phi-4-multimodal-instruct","score":92.79,"metric":"percent"},{"benchmark":"docvqa","model":"phi-4-reasoning-vision-15b","score":76.2,"metric":"percent"},{"benchmark":"infovqa","model":"mage-vl","score":80.33,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-4b-instruct","score":79.5,"metric":"percent"},{"benchmark":"infovqa","model":"phi-4-multimodal-instruct","score":71.84,"metric":"percent"},{"benchmark":"infovqa","model":"phi-4-reasoning-vision-15b","score":55.41,"metric":"percent"},{"benchmark":"chartqa","model":"mage-vl","score":84.88,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-4b-instruct","score":83.96,"metric":"percent"},{"benchmark":"chartqa","model":"phi-4-multimodal-instruct","score":83.76,"metric":"percent"},{"benchmark":"chartqa","model":"phi-4-reasoning-vision-15b","score":83.4,"metric":"percent"},{"benchmark":"ocrbench","model":"mage-vl","score":81.8,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-4b-instruct","score":81.6,"metric":"percent"},{"benchmark":"ocrbench","model":"phi-4-multimodal-instruct","score":81.7,"metric":"percent"},{"benchmark":"ocrbench","model":"phi-4-reasoning-vision-15b","score":73.9,"metric":"percent"},{"benchmark":"chartqa-pro","model":"mage-vl","score":32.57,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3-vl-4b-instruct","score":26.79,"metric":"percent"},{"benchmark":"chartqa-pro","model":"phi-4-multimodal-instruct","score":0.13,"metric":"percent"},{"benchmark":"chartqa-pro","model":"phi-4-reasoning-vision-15b","score":25.38,"metric":"percent"},{"benchmark":"textvqa","model":"mage-vl","score":77.28,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-4b-instruct","score":80.55,"metric":"percent"},{"benchmark":"textvqa","model":"phi-4-multimodal-instruct","score":39.93,"metric":"percent"},{"benchmark":"textvqa","model":"phi-4-reasoning-vision-15b","score":76.06,"metric":"percent"},{"benchmark":"mmstar","model":"mage-vl","score":67.32,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-4b-instruct","score":62.04,"metric":"percent"},{"benchmark":"mmstar","model":"phi-4-multimodal-instruct","score":61.24,"metric":"percent"},{"benchmark":"mmstar","model":"phi-4-reasoning-vision-15b","score":59.63,"metric":"percent"},{"benchmark":"seedbench","model":"mage-vl","score":76.78,"metric":"percent"},{"benchmark":"seedbench","model":"qwen3-vl-4b-instruct","score":75.65,"metric":"percent"},{"benchmark":"seedbench","model":"phi-4-multimodal-instruct","score":68.28,"metric":"percent"},{"benchmark":"seedbench","model":"phi-4-reasoning-vision-15b","score":73.7,"metric":"percent"},{"benchmark":"cv-bench","model":"mage-vl","score":87.79,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-4b-instruct","score":85.37,"metric":"percent"},{"benchmark":"cv-bench","model":"phi-4-multimodal-instruct","score":57.09,"metric":"percent"},{"benchmark":"cv-bench","model":"phi-4-reasoning-vision-15b","score":81.31,"metric":"percent"},{"benchmark":"blink","model":"mage-vl","score":65.11,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-4b-instruct","score":65.1,"metric":"percent"},{"benchmark":"blink","model":"phi-4-multimodal-instruct","score":35.24,"metric":"percent"},{"benchmark":"blink","model":"phi-4-reasoning-vision-15b","score":57.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"mage-vl","score":82.67,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-4b-instruct","score":77.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"phi-4-multimodal-instruct","score":41.51,"metric":"percent"},{"benchmark":"embspatialbench","model":"phi-4-reasoning-vision-15b","score":72.67,"metric":"percent"},{"benchmark":"mvbench","model":"mage-vl","score":65.1,"metric":"percent"},{"benchmark":"mvbench","model":"qwen3-vl-4b-instruct","score":66.7,"metric":"percent"},{"benchmark":"mvbench","model":"phi-4-multimodal-instruct","score":44.9,"metric":"percent"},{"benchmark":"mvbench","model":"phi-4-reasoning-vision-15b","score":49.2,"metric":"percent"},{"benchmark":"video-mme","model":"mage-vl","score":64,"metric":"percent"},{"benchmark":"video-mme","model":"qwen3-vl-4b-instruct","score":59.7,"metric":"percent"},{"benchmark":"video-mme","model":"phi-4-multimodal-instruct","score":44.7,"metric":"percent"},{"benchmark":"video-mme","model":"phi-4-reasoning-vision-15b","score":55.3,"metric":"percent"},{"benchmark":"longvideobench","model":"mage-vl","score":61.3,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-vl-4b-instruct","score":57.7,"metric":"percent"},{"benchmark":"longvideobench","model":"phi-4-multimodal-instruct","score":41.14,"metric":"percent"},{"benchmark":"longvideobench","model":"phi-4-reasoning-vision-15b","score":51.2,"metric":"percent"},{"benchmark":"lvbench","model":"mage-vl","score":41.8,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-vl-4b-instruct","score":39.2,"metric":"percent"},{"benchmark":"lvbench","model":"phi-4-multimodal-instruct","score":25.31,"metric":"percent"},{"benchmark":"lvbench","model":"phi-4-reasoning-vision-15b","score":34.4,"metric":"percent"},{"benchmark":"mlvu","model":"mage-vl","score":68.7,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3-vl-4b-instruct","score":61.5,"metric":"percent"},{"benchmark":"mlvu","model":"phi-4-multimodal-instruct","score":44.18,"metric":"percent"},{"benchmark":"mlvu","model":"phi-4-reasoning-vision-15b","score":51.8,"metric":"percent"},{"benchmark":"vsi-bench","model":"mage-vl","score":64.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-4b-instruct","score":53.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"phi-4-multimodal-instruct","score":24.09,"metric":"percent"},{"benchmark":"vsi-bench","model":"phi-4-reasoning-vision-15b","score":25.5,"metric":"percent"},{"benchmark":"aime-2025","model":"mai-thinking-1","score":97,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4.6","score":95.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"mai-thinking-1","score":94.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"mai-thinking-1","score":84.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mai-thinking-1","score":84.2,"metric":"percent"},{"benchmark":"livecodebench","model":"mai-thinking-1","score":87.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"mai-thinking-1","score":46,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mai-thinking-1","score":73.5,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"mai-thinking-1","score":52.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mai-code-1-flash","score":71.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-4.5-haiku","score":66.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"mai-code-1-flash","score":51.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"claude-4.5-haiku","score":35.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"mai-code-1-flash","score":65.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-4.5-haiku","score":62.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"mai-code-1-flash","score":54.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-4.5-haiku","score":41.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"mai-code-1-flash","score":92.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-4.5-haiku","score":83.3,"metric":"percent"},{"benchmark":"amobench","model":"mai-code-1-flash","score":40,"metric":"percent"},{"benchmark":"amobench","model":"claude-4.5-haiku","score":16,"metric":"percent"},{"benchmark":"frontiermath","model":"mai-code-1-flash","score":6.3,"metric":"percent"},{"benchmark":"frontiermath","model":"claude-4.5-haiku","score":2.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"mai-code-1-flash","score":18,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-4.5-haiku","score":9.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mai-code-1-flash","score":84.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-4.5-haiku","score":73.2,"metric":"percent"},{"benchmark":"frontierscience","model":"mai-code-1-flash","score":58.2,"metric":"percent"},{"benchmark":"frontierscience","model":"claude-4.5-haiku","score":42.3,"metric":"percent"},{"benchmark":"artifactsbench","model":"mai-code-1-flash","score":36.4,"metric":"percent"},{"benchmark":"artifactsbench","model":"claude-4.5-haiku","score":36.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"mai-code-1-flash","score":71.7,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.1-3b","score":67.02,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.1-8b","score":73.84,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.1-30b","score":80.16,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.1-3b","score":49.83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.1-8b","score":55.99,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.1-30b","score":64.09,"metric":"percent"},{"benchmark":"bbh","model":"granite-4.1-3b","score":75.83,"metric":"percent"},{"benchmark":"bbh","model":"granite-4.1-8b","score":80.51,"metric":"percent"},{"benchmark":"bbh","model":"granite-4.1-30b","score":83.74,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.1-3b","score":65.16,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.1-8b","score":72.43,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.1-30b","score":77.8,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.1-3b","score":31.7,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.1-8b","score":41.96,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.1-30b","score":45.76,"metric":"percent"},{"benchmark":"simpleqa","model":"granite-4.1-3b","score":3.68,"metric":"percent"},{"benchmark":"simpleqa","model":"granite-4.1-8b","score":4.82,"metric":"percent"},{"benchmark":"simpleqa","model":"granite-4.1-30b","score":6.81,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-4.1-3b","score":38.57,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-4.1-8b","score":50.08,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"granite-4.1-30b","score":56.16,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.1-3b","score":82.3,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.1-8b","score":87.06,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.1-30b","score":89.65,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-4.1-3b","score":37.8,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-4.1-8b","score":68.98,"metric":"percent"},{"benchmark":"arena-hard","model":"granite-4.1-30b","score":71.02,"metric":"percent"},{"benchmark":"mt-bench","model":"granite-4.1-3b","score":7.57,"metric":"percent"},{"benchmark":"mt-bench","model":"granite-4.1-8b","score":8.61,"metric":"percent"},{"benchmark":"mt-bench","model":"granite-4.1-30b","score":8.61,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.1-3b","score":86.88,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.1-8b","score":92.49,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.1-30b","score":94.16,"metric":"percent"},{"benchmark":"gsm-symbolic","model":"granite-4.1-3b","score":81.32,"metric":"percent"},{"benchmark":"gsm-symbolic","model":"granite-4.1-8b","score":83.7,"metric":"percent"},{"benchmark":"gsm-symbolic","model":"granite-4.1-30b","score":75.7,"metric":"percent"},{"benchmark":"minerva-math","model":"granite-4.1-3b","score":67.94,"metric":"percent"},{"benchmark":"minerva-math","model":"granite-4.1-8b","score":80.1,"metric":"percent"},{"benchmark":"minerva-math","model":"granite-4.1-30b","score":81.32,"metric":"percent"},{"benchmark":"deepmind-math","model":"granite-4.1-3b","score":64.64,"metric":"percent"},{"benchmark":"deepmind-math","model":"granite-4.1-8b","score":80.07,"metric":"percent"},{"benchmark":"deepmind-math","model":"granite-4.1-30b","score":81.93,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.1-3b","score":81.71,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.1-8b","score":85.37,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.1-30b","score":88.41,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.1-3b","score":76.83,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.1-8b","score":79.88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"granite-4.1-30b","score":85.37,"metric":"percent"},{"benchmark":"mbpp","model":"granite-4.1-3b","score":71.16,"metric":"percent"},{"benchmark":"mbpp","model":"granite-4.1-8b","score":87.3,"metric":"percent"},{"benchmark":"mbpp","model":"granite-4.1-30b","score":85.45,"metric":"percent"},{"benchmark":"mbpp-plus","model":"granite-4.1-3b","score":62.17,"metric":"percent"},{"benchmark":"mbpp-plus","model":"granite-4.1-8b","score":73.81,"metric":"percent"},{"benchmark":"mbpp-plus","model":"granite-4.1-30b","score":73.54,"metric":"percent"},{"benchmark":"crux-o","model":"granite-4.1-3b","score":40.75,"metric":"percent"},{"benchmark":"crux-o","model":"granite-4.1-8b","score":47.63,"metric":"percent"},{"benchmark":"crux-o","model":"granite-4.1-30b","score":55.75,"metric":"percent"},{"benchmark":"bigcodebench","model":"granite-4.1-3b","score":32.19,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"granite-4.1-8b","score":35,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"granite-4.1-30b","score":38.77,"metric":"pass@1"},{"benchmark":"multipl-e","model":"granite-4.1-3b","score":52.54,"metric":"percent"},{"benchmark":"multipl-e","model":"granite-4.1-8b","score":60.26,"metric":"percent"},{"benchmark":"multipl-e","model":"granite-4.1-30b","score":62.31,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.1-3b","score":60.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.1-8b","score":68.27,"metric":"percent"},{"benchmark":"bfcl-v3","model":"granite-4.1-30b","score":73.68,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.1-3b","score":57.61,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.1-8b","score":64.84,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.1-30b","score":73.71,"metric":"percent"},{"benchmark":"include","model":"granite-4.1-3b","score":52.05,"metric":"percent"},{"benchmark":"include","model":"granite-4.1-8b","score":58.89,"metric":"percent"},{"benchmark":"include","model":"granite-4.1-30b","score":67.26,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.1-3b","score":70,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.1-8b","score":82.32,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.1-30b","score":71.12,"metric":"percent"},{"benchmark":"salad-bench","model":"granite-4.1-3b","score":93.95,"metric":"percent"},{"benchmark":"salad-bench","model":"granite-4.1-8b","score":95.8,"metric":"percent"},{"benchmark":"salad-bench","model":"granite-4.1-30b","score":96.41,"metric":"percent"},{"benchmark":"attaq","model":"granite-4.1-3b","score":81.88,"metric":"percent"},{"benchmark":"attaq","model":"granite-4.1-8b","score":81.19,"metric":"percent"},{"benchmark":"attaq","model":"granite-4.1-30b","score":85.76,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"granite-4.2-8b","score":30.78,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"granite-4.2-30b","score":41.89,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"granite-4.2-8b","score":19.11,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"granite-4.2-30b","score":33.29,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"granite-4.2-8b","score":47.67,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"granite-4.2-30b","score":57,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"granite-4.2-8b","score":20.56,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"granite-4.2-30b","score":29.24,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4.2-3b","score":52.41,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4.2-8b","score":52.39,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4.2-30b","score":61.39,"metric":"percent"},{"benchmark":"bird-sql","model":"granite-4.2-8b","score":41.07,"metric":"percent"},{"benchmark":"bird-sql","model":"granite-4.2-30b","score":41.85,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"granite-4.2-8b","score":1189,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"granite-4.2-30b","score":1225,"metric":"elo"},{"benchmark":"aime-2025","model":"granite-4.2-3b","score":78.33,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-4.2-8b","score":86.67,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-4.2-30b","score":89.17,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"granite-4.2-3b","score":66.67,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"granite-4.2-8b","score":78.33,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"granite-4.2-30b","score":89.17,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.2-3b","score":54.8,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.2-8b","score":64.14,"metric":"percent"},{"benchmark":"gpqa","model":"granite-4.2-30b","score":66.41,"metric":"percent"},{"benchmark":"livecodebench","model":"granite-4.2-3b","score":69.71,"metric":"percent"},{"benchmark":"livecodebench","model":"granite-4.2-8b","score":73.24,"metric":"percent"},{"benchmark":"livecodebench","model":"granite-4.2-30b","score":75.77,"metric":"percent"},{"benchmark":"scicode","model":"granite-4.2-3b","score":24.11,"metric":"percent"},{"benchmark":"scicode","model":"granite-4.2-8b","score":36.09,"metric":"percent"},{"benchmark":"scicode","model":"granite-4.2-30b","score":38.76,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.2-3b","score":67.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.2-8b","score":74.04,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.2-30b","score":77.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"granite-4.2-3b","score":34.96,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"granite-4.2-8b","score":65.19,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"granite-4.2-30b","score":67.93,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.2-3b","score":74.33,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.2-8b","score":79.33,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.2-30b","score":77.17,"metric":"percent"},{"benchmark":"ruler-64k","model":"granite-4.2-3b","score":67.52,"metric":"percent"},{"benchmark":"ruler-64k","model":"granite-4.2-8b","score":80.99,"metric":"percent"},{"benchmark":"ruler-64k","model":"granite-4.2-30b","score":89.96,"metric":"percent"},{"benchmark":"ruler-128k","model":"granite-4.2-3b","score":55.3,"metric":"percent"},{"benchmark":"ruler-128k","model":"granite-4.2-8b","score":71.41,"metric":"percent"},{"benchmark":"ruler-128k","model":"granite-4.2-30b","score":81.38,"metric":"percent"},{"benchmark":"mmlu","model":"granite-swash-3b-a600m","score":54.09,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-swash-3b-a600m","score":39.58,"metric":"percent"},{"benchmark":"mmlu","model":"granite-swash-2b","score":55.19,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-swash-2b","score":42.23,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-instruct-2507","score":42.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-30b-a3b-instruct-2507","score":45.8,"metric":"percent"},{"benchmark":"livecodebench","model":"simplesd-30b-instruct","score":55.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"simplesd-30b-instruct","score":54.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-instruct-2507","score":34,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-4b-instruct-2507","score":34.3,"metric":"percent"},{"benchmark":"livecodebench","model":"simplesd-4b-instruct","score":41.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"simplesd-4b-instruct","score":45.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-thinking-2507","score":54.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-4b-thinking-2507","score":59.6,"metric":"percent"},{"benchmark":"livecodebench","model":"simplesd-4b-thinking","score":57.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"simplesd-4b-thinking","score":63.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"command-a-plus-05-2026","score":85,"metric":"percent"},{"benchmark":"tau2-telecom","model":"command-a-reasoning-08-2025","score":37,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"command-a-plus-05-2026","score":25,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"command-a-reasoning-08-2025","score":3,"metric":"percent"},{"benchmark":"ifbench","model":"command-a-plus-05-2026","score":74,"metric":"percent"},{"benchmark":"ifbench","model":"command-a-reasoning-08-2025","score":36,"metric":"percent"},{"benchmark":"aime-2025","model":"command-a-plus-05-2026","score":90,"metric":"percent"},{"benchmark":"aime-2025","model":"command-a-reasoning-08-2025","score":57,"metric":"percent"},{"benchmark":"scicode","model":"command-a-plus-05-2026","score":38,"metric":"percent"},{"benchmark":"scicode","model":"command-a-reasoning-08-2025","score":30,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"command-a-plus-05-2026","score":81,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"command-a-reasoning-08-2025","score":73,"metric":"percent"},{"benchmark":"mmmu","model":"command-a-plus-05-2026","score":75.1,"metric":"percent"},{"benchmark":"mmmu","model":"command-a-vision-07-2025","score":65.3,"metric":"percent"},{"benchmark":"mathvista","model":"command-a-plus-05-2026","score":80.6,"metric":"percent"},{"benchmark":"mathvista","model":"command-a-vision-07-2025","score":73.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"command-a-plus-05-2026","score":52.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"command-a-vision-07-2025","score":46.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"command-a-plus-05-2026","score":88,"metric":"percent"},{"benchmark":"charxiv-dq","model":"command-a-vision-07-2025","score":82,"metric":"percent"},{"benchmark":"mmmu-pro","model":"command-a-plus-05-2026","score":63,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"north-mini-code-1.0","score":36,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"north-mini-code-1.0","score":31.1,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"qwen3.6-35b-a3b","score":35,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gemma-4-26b-a4b-it","score":25,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"devstral-small-2","score":17,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"north-mini-code-1.0","score":67.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"devstral-small-2","score":68.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"north-mini-code-1.0","score":40.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemma-4-26b-a4b-it","score":13,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"devstral-small-2","score":35.7,"metric":"percent"},{"benchmark":"scicode","model":"north-mini-code-1.0","score":38.2,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-35b-a3b","score":35.8,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-26b-a4b-it","score":40,"metric":"percent"},{"benchmark":"scicode","model":"devstral-small-2","score":28.8,"metric":"percent"},{"benchmark":"livecodebench","model":"north-mini-code-1.0","score":70.3,"metric":"percent"},{"benchmark":"livecodebench","model":"devstral-small-2","score":40.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"north-micro-vision-instruct","score":68.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"ministral-3-3b-instruct","score":69.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"lfm2.5-vl-1.6b","score":69.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"phi-3.5-vision-instruct","score":73.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemma-4-e2b-it","score":69.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3-vl-2b-instruct","score":74.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen3.5-2b","score":76,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"smolvlm2-2.2b","score":67.4,"metric":"percent"},{"benchmark":"mmstar","model":"north-micro-vision-instruct","score":51.8,"metric":"percent"},{"benchmark":"mmstar","model":"ministral-3-3b-instruct","score":53.1,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2.5-vl-1.6b","score":50.8,"metric":"percent"},{"benchmark":"mmstar","model":"phi-3.5-vision-instruct","score":49.5,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-e2b-it","score":52.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-2b-instruct","score":50.6,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-2b","score":61.4,"metric":"percent"},{"benchmark":"realworldqa","model":"north-micro-vision-instruct","score":62.2,"metric":"percent"},{"benchmark":"realworldqa","model":"ministral-3-3b-instruct","score":58.3,"metric":"percent"},{"benchmark":"realworldqa","model":"lfm2.5-vl-1.6b","score":64.2,"metric":"percent"},{"benchmark":"realworldqa","model":"phi-3.5-vision-instruct","score":58,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-e2b-it","score":50.7,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3-vl-2b-instruct","score":64.6,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-2b","score":69.3,"metric":"percent"},{"benchmark":"realworldqa","model":"smolvlm2-2.2b","score":56.7,"metric":"percent"},{"benchmark":"mmmb","model":"north-micro-vision-instruct","score":72.8,"metric":"percent"},{"benchmark":"mmmb","model":"ministral-3-3b-instruct","score":73.4,"metric":"percent"},{"benchmark":"mmmb","model":"lfm2.5-vl-1.6b","score":71.7,"metric":"percent"},{"benchmark":"mmmb","model":"phi-3.5-vision-instruct","score":68.6,"metric":"percent"},{"benchmark":"mmmb","model":"gemma-4-e2b-it","score":74.3,"metric":"percent"},{"benchmark":"mmmb","model":"qwen3-vl-2b-instruct","score":72.3,"metric":"percent"},{"benchmark":"mmmb","model":"qwen3.5-2b","score":74.5,"metric":"percent"},{"benchmark":"mmmb","model":"smolvlm2-2.2b","score":57.7,"metric":"percent"},{"benchmark":"blink","model":"north-micro-vision-instruct","score":52.7,"metric":"percent"},{"benchmark":"blink","model":"ministral-3-3b-instruct","score":47.1,"metric":"percent"},{"benchmark":"blink","model":"lfm2.5-vl-1.6b","score":48.4,"metric":"percent"},{"benchmark":"blink","model":"phi-3.5-vision-instruct","score":56.1,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-e2b-it","score":46.8,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-2b-instruct","score":51.4,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-2b","score":56.3,"metric":"percent"},{"benchmark":"blink","model":"smolvlm2-2.2b","score":42,"metric":"percent"},{"benchmark":"chartqa","model":"north-micro-vision-instruct","score":80.8,"metric":"percent"},{"benchmark":"chartqa","model":"ministral-3-3b-instruct","score":79.1,"metric":"percent"},{"benchmark":"chartqa","model":"lfm2.5-vl-1.6b","score":73.9,"metric":"percent"},{"benchmark":"chartqa","model":"phi-3.5-vision-instruct","score":82.1,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-4-e2b-it","score":42.2,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-2b-instruct","score":69.3,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3.5-2b","score":77.5,"metric":"percent"},{"benchmark":"chartqa","model":"smolvlm2-2.2b","score":68.2,"metric":"percent"},{"benchmark":"docvqa","model":"north-micro-vision-instruct","score":92.1,"metric":"percent"},{"benchmark":"docvqa","model":"ministral-3-3b-instruct","score":89.6,"metric":"percent"},{"benchmark":"docvqa","model":"lfm2.5-vl-1.6b","score":87.7,"metric":"percent"},{"benchmark":"docvqa","model":"phi-3.5-vision-instruct","score":86,"metric":"percent"},{"benchmark":"docvqa","model":"gemma-4-e2b-it","score":73.2,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-2b-instruct","score":82.5,"metric":"percent"},{"benchmark":"docvqa","model":"smolvlm2-2.2b","score":79.9,"metric":"percent"},{"benchmark":"infovqa","model":"north-micro-vision-instruct","score":65.2,"metric":"percent"},{"benchmark":"infovqa","model":"ministral-3-3b-instruct","score":58.9,"metric":"percent"},{"benchmark":"infovqa","model":"lfm2.5-vl-1.6b","score":62.7,"metric":"percent"},{"benchmark":"infovqa","model":"phi-3.5-vision-instruct","score":56.1,"metric":"percent"},{"benchmark":"infovqa","model":"gemma-4-e2b-it","score":38,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3-vl-2b-instruct","score":62.2,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3.5-2b","score":73.1,"metric":"percent"},{"benchmark":"infovqa","model":"smolvlm2-2.2b","score":38.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"north-micro-vision-instruct","score":36.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"ministral-3-3b-instruct","score":41.4,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"lfm2.5-vl-1.6b","score":41.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"phi-3.5-vision-instruct","score":33.9,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemma-4-e2b-it","score":43.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-2b-instruct","score":41.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-2b","score":48.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"smolvlm2-2.2b","score":30.4,"metric":"percent"},{"benchmark":"ocrbench","model":"north-micro-vision-instruct","score":79.2,"metric":"percent"},{"benchmark":"ocrbench","model":"ministral-3-3b-instruct","score":73.5,"metric":"percent"},{"benchmark":"ocrbench","model":"lfm2.5-vl-1.6b","score":80.2,"metric":"percent"},{"benchmark":"ocrbench","model":"phi-3.5-vision-instruct","score":64.2,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-4-e2b-it","score":71.9,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-2b-instruct","score":75.1,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-2b","score":86.1,"metric":"percent"},{"benchmark":"ocrbench","model":"smolvlm2-2.2b","score":72.7,"metric":"percent"},{"benchmark":"ai2d","model":"north-micro-vision-instruct","score":77.5,"metric":"percent"},{"benchmark":"ai2d","model":"ministral-3-3b-instruct","score":74.1,"metric":"percent"},{"benchmark":"ai2d","model":"lfm2.5-vl-1.6b","score":72.8,"metric":"percent"},{"benchmark":"ai2d","model":"phi-3.5-vision-instruct","score":79,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-4-e2b-it","score":71.2,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-2b-instruct","score":71.3,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-2b","score":75.2,"metric":"percent"},{"benchmark":"ai2d","model":"smolvlm2-2.2b","score":69.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"north-micro-vision-instruct","score":60,"metric":"percent"},{"benchmark":"charxiv-dq","model":"ministral-3-3b-instruct","score":76.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"lfm2.5-vl-1.6b","score":51.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"phi-3.5-vision-instruct","score":63.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemma-4-e2b-it","score":75.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-2b-instruct","score":59.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3.5-2b","score":76.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"smolvlm2-2.2b","score":48.2,"metric":"percent"},{"benchmark":"mmmu","model":"north-micro-vision-instruct","score":32.9,"metric":"percent"},{"benchmark":"mmmu","model":"ministral-3-3b-instruct","score":50.8,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2.5-vl-1.6b","score":38,"metric":"percent"},{"benchmark":"mmmu","model":"phi-3.5-vision-instruct","score":43.2,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-e2b-it","score":47.7,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-2b-instruct","score":37.9,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-2b","score":47.4,"metric":"percent"},{"benchmark":"mmmu","model":"smolvlm2-2.2b","score":39.9,"metric":"percent"},{"benchmark":"refcoco","model":"north-micro-vision-instruct","score":73.2,"metric":"percent"},{"benchmark":"refcoco","model":"ministral-3-3b-instruct","score":31.7,"metric":"percent"},{"benchmark":"refcoco","model":"lfm2.5-vl-1.6b","score":58.1,"metric":"percent"},{"benchmark":"refcoco","model":"phi-3.5-vision-instruct","score":45.1,"metric":"percent"},{"benchmark":"refcoco","model":"gemma-4-e2b-it","score":8.4,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-2b-instruct","score":30.4,"metric":"percent"},{"benchmark":"refcoco","model":"smolvlm2-2.2b","score":1.8,"metric":"percent"},{"benchmark":"countbench","model":"north-micro-vision-instruct","score":72.5,"metric":"percent"},{"benchmark":"countbench","model":"ministral-3-3b-instruct","score":73.7,"metric":"percent"},{"benchmark":"countbench","model":"lfm2.5-vl-1.6b","score":91,"metric":"percent"},{"benchmark":"countbench","model":"phi-3.5-vision-instruct","score":64.5,"metric":"percent"},{"benchmark":"countbench","model":"gemma-4-e2b-it","score":53.4,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-2b-instruct","score":84.8,"metric":"percent"},{"benchmark":"countbench","model":"qwen3.5-2b","score":80.5,"metric":"percent"},{"benchmark":"countbench","model":"smolvlm2-2.2b","score":76.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"north-micro-vision-instruct","score":61.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"ministral-3-3b-instruct","score":65.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"lfm2.5-vl-1.6b","score":60.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"phi-3.5-vision-instruct","score":58.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-4-e2b-it","score":59.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-2b-instruct","score":67.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-2b","score":65.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"smolvlm2-2.2b","score":60,"metric":"percent"},{"benchmark":"mmlu","model":"north-micro-vision-instruct","score":50.4,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-3-3b-instruct","score":66,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2.5-vl-1.6b","score":46.4,"metric":"percent"},{"benchmark":"mmlu","model":"phi-3.5-vision-instruct","score":35.5,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-e2b-it","score":69.2,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-2b-instruct","score":63,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-2b","score":54.3,"metric":"percent"},{"benchmark":"mmlu","model":"smolvlm2-2.2b","score":8.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"north-micro-vision-instruct","score":30.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ministral-3-3b-instruct","score":47.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-vl-1.6b","score":19.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3.5-vision-instruct","score":28.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-e2b-it","score":44.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-vl-2b-instruct","score":42.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-2b","score":29.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smolvlm2-2.2b","score":9.9,"metric":"percent"},{"benchmark":"multi-if","model":"north-micro-vision-instruct","score":37.3,"metric":"percent"},{"benchmark":"multi-if","model":"ministral-3-3b-instruct","score":47,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-vl-1.6b","score":44.3,"metric":"percent"},{"benchmark":"multi-if","model":"phi-3.5-vision-instruct","score":30.4,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e2b-it","score":68.7,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-vl-2b-instruct","score":52.3,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-2b","score":46.4,"metric":"percent"},{"benchmark":"multi-if","model":"smolvlm2-2.2b","score":23.6,"metric":"percent"},{"benchmark":"ifeval","model":"north-micro-vision-instruct","score":74.9,"metric":"percent"},{"benchmark":"ifeval","model":"ministral-3-3b-instruct","score":72.5,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-vl-1.6b","score":77.6,"metric":"percent"},{"benchmark":"ifeval","model":"phi-3.5-vision-instruct","score":54.3,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e2b-it","score":86.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-2b-instruct","score":73.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-2b","score":67.9,"metric":"percent"},{"benchmark":"ifeval","model":"smolvlm2-2.2b","score":50.1,"metric":"percent"},{"benchmark":"ifbench","model":"jamba2-mini","score":38,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-30b-a3b-instruct-2507","score":32,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-nano-30b-a3b","score":33,"metric":"percent"},{"benchmark":"ifbench","model":"ministral-3-14b-instruct","score":27,"metric":"percent"},{"benchmark":"collie","model":"jamba2-mini","score":33,"metric":"percent"},{"benchmark":"collie","model":"qwen3-30b-a3b-instruct-2507","score":28,"metric":"percent"},{"benchmark":"collie","model":"nemotron-3-nano-30b-a3b","score":30,"metric":"percent"},{"benchmark":"collie","model":"ministral-3-14b-instruct","score":26,"metric":"percent"},{"benchmark":"ifeval","model":"jamba2-mini","score":97,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-instruct-2507","score":91,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-3-nano-30b-a3b","score":88,"metric":"percent"},{"benchmark":"ifeval","model":"ministral-3-14b-instruct","score":73,"metric":"percent"},{"benchmark":"facts-grounding","model":"jamba2-mini","score":57,"metric":"percent"},{"benchmark":"facts-grounding","model":"qwen3-30b-a3b-instruct-2507","score":54,"metric":"percent"},{"benchmark":"facts-grounding","model":"nemotron-3-nano-30b-a3b","score":48,"metric":"percent"},{"benchmark":"facts-grounding","model":"ministral-3-14b-instruct","score":49,"metric":"percent"},{"benchmark":"ifbench","model":"jamba2-3b","score":36,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-4b-instruct-2507","score":32,"metric":"percent"},{"benchmark":"ifbench","model":"ministral-3-3b-instruct","score":22,"metric":"percent"},{"benchmark":"ifeval","model":"jamba2-3b","score":93,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b-instruct-2507","score":90,"metric":"percent"},{"benchmark":"ifeval","model":"ministral-3-3b-instruct","score":67,"metric":"percent"},{"benchmark":"facts-grounding","model":"jamba2-3b","score":54,"metric":"percent"},{"benchmark":"facts-grounding","model":"qwen3-4b-instruct-2507","score":54,"metric":"percent"},{"benchmark":"facts-grounding","model":"ministral-3-3b-instruct","score":44,"metric":"percent"},{"benchmark":"bfcl-v3","model":"apriel-1.6-15b-thinker","score":63.5,"metric":"percent"},{"benchmark":"bfcl-v3","model":"apriel-1.5-15b-thinker","score":51.88,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gpt-oss-120b","score":50.62,"metric":"percent"},{"benchmark":"bfcl-v3","model":"deepseek-r1-0528","score":39.75,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gemini-2.5-flash-preview-09-2025","score":39.75,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gpt-5-mini-high","score":17.62,"metric":"percent"},{"benchmark":"bfcl-v3","model":"o3-mini-high","score":50,"metric":"percent"},{"benchmark":"tau2-telecom","model":"apriel-1.6-15b-thinker","score":69,"metric":"percent"},{"benchmark":"tau2-telecom","model":"apriel-1.5-15b-thinker","score":57.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemini-2.5-flash-preview-09-2025","score":32,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-5-mini-high","score":68,"metric":"percent"},{"benchmark":"tau2-telecom","model":"claude-4.5-sonnet-thinking","score":50.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"o3-mini-high","score":31,"metric":"percent"},{"benchmark":"tau2-retail","model":"apriel-1.6-15b-thinker","score":66.67,"metric":"percent"},{"benchmark":"tau2-retail","model":"apriel-1.5-15b-thinker","score":46.78,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-oss-120b","score":61.4,"metric":"percent"},{"benchmark":"tau2-retail","model":"deepseek-r1-0528","score":59.94,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemini-2.5-flash-preview-09-2025","score":61.69,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-5-mini-high","score":73.39,"metric":"percent"},{"benchmark":"tau2-retail","model":"claude-4.5-sonnet-thinking","score":69.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"o3-mini-high","score":75.73,"metric":"percent"},{"benchmark":"tau2-airline","model":"apriel-1.6-15b-thinker","score":58,"metric":"percent"},{"benchmark":"tau2-airline","model":"apriel-1.5-15b-thinker","score":52,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-oss-120b","score":45.3,"metric":"percent"},{"benchmark":"tau2-airline","model":"deepseek-r1-0528","score":47.33,"metric":"percent"},{"benchmark":"tau2-airline","model":"gemini-2.5-flash-preview-09-2025","score":56.66,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-5-mini-high","score":59.33,"metric":"percent"},{"benchmark":"tau2-airline","model":"claude-4.5-sonnet-thinking","score":58,"metric":"percent"},{"benchmark":"tau2-airline","model":"o3-mini-high","score":61.33,"metric":"percent"},{"benchmark":"complexfuncbench","model":"apriel-1.6-15b-thinker","score":33.2,"metric":"percent"},{"benchmark":"complexfuncbench","model":"apriel-1.5-15b-thinker","score":19,"metric":"percent"},{"benchmark":"complexfuncbench","model":"gpt-oss-120b","score":24.6,"metric":"percent"},{"benchmark":"complexfuncbench","model":"deepseek-r1-0528","score":24.2,"metric":"percent"},{"benchmark":"complexfuncbench","model":"gemini-2.5-flash-preview-09-2025","score":26.3,"metric":"percent"},{"benchmark":"complexfuncbench","model":"gpt-5-mini-high","score":37.5,"metric":"percent"},{"benchmark":"complexfuncbench","model":"claude-4.5-sonnet-thinking","score":24.6,"metric":"percent"},{"benchmark":"complexfuncbench","model":"o3-mini-high","score":18.9,"metric":"percent"},{"benchmark":"multi-if","model":"apriel-1.6-15b-thinker","score":83.34,"metric":"percent"},{"benchmark":"multi-if","model":"apriel-1.5-15b-thinker","score":76.91,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-oss-120b","score":82.95,"metric":"percent"},{"benchmark":"multi-if","model":"deepseek-r1-0528","score":73.76,"metric":"percent"},{"benchmark":"multi-if","model":"gemini-2.5-flash-preview-09-2025","score":82.49,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-5-mini-high","score":85.37,"metric":"percent"},{"benchmark":"multi-if","model":"claude-4.5-sonnet-thinking","score":84.32,"metric":"percent"},{"benchmark":"multi-if","model":"o3-mini-high","score":87.28,"metric":"percent"},{"benchmark":"multichallenge","model":"apriel-1.6-15b-thinker","score":46.15,"metric":"percent"},{"benchmark":"multichallenge","model":"apriel-1.5-15b-thinker","score":41.39,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-oss-120b","score":46.9,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-r1-0528","score":44.5,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-2.5-flash-preview-09-2025","score":49.08,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5-mini-high","score":57.9,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-4.5-sonnet-thinking","score":42.49,"metric":"percent"},{"benchmark":"multichallenge","model":"o3-mini-high","score":38.46,"metric":"percent"},{"benchmark":"ifbench","model":"apriel-1.6-15b-thinker","score":69,"metric":"percent"},{"benchmark":"ifbench","model":"apriel-1.5-15b-thinker","score":62,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-r1-0528","score":40,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-2.5-flash-preview-09-2025","score":50,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5-mini-high","score":75,"metric":"percent"},{"benchmark":"ifbench","model":"claude-4.5-sonnet-thinking","score":57,"metric":"percent"},{"benchmark":"ifbench","model":"o3-mini-high","score":70.07,"metric":"percent"},{"benchmark":"aime-2025","model":"apriel-1.6-15b-thinker","score":88,"metric":"percent"},{"benchmark":"aime-2025","model":"apriel-1.5-15b-thinker","score":88,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":93,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0528","score":76,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash-preview-09-2025","score":73,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-mini-high","score":91,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-4.5-sonnet-thinking","score":88,"metric":"percent"},{"benchmark":"aime-2025","model":"o3-mini-high","score":86.67,"metric":"percent"},{"benchmark":"livecodebench","model":"apriel-1.6-15b-thinker","score":81,"metric":"percent"},{"benchmark":"livecodebench","model":"apriel-1.5-15b-thinker","score":73,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":88,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash-preview-09-2025","score":70,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini-high","score":84,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-4.5-sonnet-thinking","score":71,"metric":"percent"},{"benchmark":"livecodebench","model":"o3-mini-high","score":73,"metric":"percent"},{"benchmark":"scicode","model":"apriel-1.6-15b-thinker","score":37,"metric":"percent"},{"benchmark":"scicode","model":"apriel-1.5-15b-thinker","score":35,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-r1-0528","score":40,"metric":"percent"},{"benchmark":"scicode","model":"gemini-2.5-flash-preview-09-2025","score":41,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5-mini-high","score":39,"metric":"percent"},{"benchmark":"scicode","model":"claude-4.5-sonnet-thinking","score":45,"metric":"percent"},{"benchmark":"scicode","model":"o3-mini-high","score":40,"metric":"percent"},{"benchmark":"deepresearchbench","model":"apriel-1.6-15b-thinker","score":36.47,"metric":"percent"},{"benchmark":"deepresearchbench","model":"apriel-1.5-15b-thinker","score":32.73,"metric":"percent"},{"benchmark":"deepresearchbench","model":"gpt-oss-120b","score":36.3,"metric":"percent"},{"benchmark":"deepresearchbench","model":"deepseek-r1-0528","score":34.19,"metric":"percent"},{"benchmark":"deepresearchbench","model":"gemini-2.5-flash-preview-09-2025","score":38.15,"metric":"percent"},{"benchmark":"deepresearchbench","model":"o3-mini-high","score":33.4,"metric":"percent"},{"benchmark":"gaia","model":"apriel-1.6-15b-thinker","score":40,"metric":"percent"},{"benchmark":"gaia","model":"apriel-1.5-15b-thinker","score":30.91,"metric":"percent"},{"benchmark":"gaia","model":"gpt-oss-120b","score":21.21,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-r1-0528","score":32.12,"metric":"percent"},{"benchmark":"gaia","model":"gemini-2.5-flash-preview-09-2025","score":47.88,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5-mini-high","score":65.45,"metric":"percent"},{"benchmark":"gaia","model":"claude-4.5-sonnet-thinking","score":69.09,"metric":"percent"},{"benchmark":"gaia","model":"o3-mini-high","score":23.03,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"apriel-1.6-15b-thinker","score":23,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"apriel-1.5-15b-thinker","score":16,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-120b","score":31,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-r1-0528","score":29.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-2.5-flash-preview-09-2025","score":34.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5-mini-high","score":61,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-4.5-sonnet-thinking","score":64.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"o3-mini-high","score":22.6,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"apriel-1.6-15b-thinker","score":14,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gemini-2.5-flash-preview-09-2025","score":13,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"gpt-5-mini-high","score":31,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"claude-4.5-sonnet-thinking","score":33,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"o3-mini-high","score":5.67,"metric":"percent"},{"benchmark":"aider-polyglot","model":"apriel-1.6-15b-thinker","score":37.68,"metric":"percent"},{"benchmark":"aider-polyglot","model":"apriel-1.5-15b-thinker","score":26.37,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-oss-120b","score":42,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-flash-preview-09-2025","score":40,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-5-mini-high","score":71.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-4.5-sonnet-thinking","score":78,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apriel-1.6-15b-thinker","score":79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apriel-1.5-15b-thinker","score":77,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-flash-preview-09-2025","score":83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5-mini-high","score":84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-4.5-sonnet-thinking","score":88,"metric":"percent"},{"benchmark":"mmlu-pro","model":"o3-mini-high","score":80,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apriel-1.6-15b-thinker","score":73,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apriel-1.5-15b-thinker","score":71,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b","score":78,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-2.5-flash-preview-09-2025","score":79,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-mini-high","score":83,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-4.5-sonnet-thinking","score":83,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o3-mini-high","score":77,"metric":"percent"},{"benchmark":"hle","model":"apriel-1.6-15b-thinker","score":10,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-2.5-flash-preview-09-2025","score":11.1,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5-mini-high","score":19.7,"metric":"avg@3"},{"benchmark":"hle","model":"claude-4.5-sonnet-thinking","score":17.3,"metric":"avg@3"},{"benchmark":"hle","model":"o3-mini-high","score":12.3,"metric":"avg@3"},{"benchmark":"aa-lcr","model":"gemini-2.5-flash-preview-09-2025","score":62,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5-mini-high","score":68,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-4.5-sonnet-thinking","score":66,"metric":"percent"},{"benchmark":"mmmu","model":"apriel-1.6-15b-thinker","score":72,"metric":"percent"},{"benchmark":"mmmu","model":"apriel-1.5-15b-thinker","score":70.22,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-high","score":81.33,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4.5v","score":74.33,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-flash","score":70.66,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3.7-sonnet-thinking","score":73.66,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-minimal","score":66.66,"metric":"percent"},{"benchmark":"mmmu","model":"grok-4-fast-thinking","score":70.11,"metric":"percent"},{"benchmark":"mmmu-pro","model":"apriel-1.6-15b-thinker","score":60.28,"metric":"percent"},{"benchmark":"mmmu-pro","model":"apriel-1.5-15b-thinker","score":55.38,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-high","score":74.73,"metric":"percent"},{"benchmark":"mmmu-pro","model":"glm-4.5v","score":64.16,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-2.5-flash","score":67.86,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-3.7-sonnet-thinking","score":64.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-minimal","score":66.06,"metric":"percent"},{"benchmark":"mmmu-pro","model":"grok-4-fast-thinking","score":61.61,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"apriel-1.6-15b-thinker","score":52.89,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"apriel-1.5-15b-thinker","score":48.21,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"gpt-5-high","score":66.93,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"glm-4.5v","score":61.5,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"gemini-2.5-flash","score":56.76,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"claude-3.7-sonnet-thinking","score":60.11,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"gpt-5-minimal","score":57.68,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"grok-4-fast-thinking","score":22.94,"metric":"percent"},{"benchmark":"logicvista","model":"apriel-1.6-15b-thinker","score":58.61,"metric":"percent"},{"benchmark":"logicvista","model":"apriel-1.5-15b-thinker","score":58.39,"metric":"percent"},{"benchmark":"logicvista","model":"gpt-5-high","score":69.35,"metric":"percent"},{"benchmark":"logicvista","model":"glm-4.5v","score":63.53,"metric":"percent"},{"benchmark":"logicvista","model":"gemini-2.5-flash","score":63.75,"metric":"percent"},{"benchmark":"logicvista","model":"claude-3.7-sonnet-thinking","score":69.12,"metric":"percent"},{"benchmark":"logicvista","model":"gpt-5-minimal","score":44.51,"metric":"percent"},{"benchmark":"logicvista","model":"grok-4-fast-thinking","score":47.42,"metric":"percent"},{"benchmark":"mathvision","model":"apriel-1.6-15b-thinker","score":60.85,"metric":"percent"},{"benchmark":"mathvision","model":"apriel-1.5-15b-thinker","score":50.99,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-high","score":67.1,"metric":"percent"},{"benchmark":"mathvision","model":"glm-4.5v","score":59.53,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.5-flash","score":59.21,"metric":"percent"},{"benchmark":"mathvision","model":"claude-3.7-sonnet-thinking","score":50.32,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-minimal","score":35.52,"metric":"percent"},{"benchmark":"mathvision","model":"grok-4-fast-thinking","score":48.35,"metric":"percent"},{"benchmark":"mathvista","model":"apriel-1.6-15b-thinker","score":79.9,"metric":"percent"},{"benchmark":"mathvista","model":"apriel-1.5-15b-thinker","score":75.5,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5-high","score":83.3,"metric":"percent"},{"benchmark":"mathvista","model":"glm-4.5v","score":83.6,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-flash","score":78.5,"metric":"percent"},{"benchmark":"mathvista","model":"claude-3.7-sonnet-thinking","score":74.6,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5-minimal","score":61.2,"metric":"percent"},{"benchmark":"mathvista","model":"grok-4-fast-thinking","score":68.2,"metric":"percent"},{"benchmark":"mmstar","model":"apriel-1.6-15b-thinker","score":70.66,"metric":"percent"},{"benchmark":"mmstar","model":"apriel-1.5-15b-thinker","score":67.73,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-high","score":77.74,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4.5v","score":74.46,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-flash","score":73.86,"metric":"percent"},{"benchmark":"mmstar","model":"claude-3.7-sonnet-thinking","score":70,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-minimal","score":63.6,"metric":"percent"},{"benchmark":"mmstar","model":"grok-4-fast-thinking","score":64.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"apriel-1.6-15b-thinker","score":89.85,"metric":"percent"},{"benchmark":"charxiv-dq","model":"apriel-1.5-15b-thinker","score":88.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5-high","score":91.25,"metric":"percent"},{"benchmark":"charxiv-dq","model":"glm-4.5v","score":90.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-2.5-flash","score":83.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-3.7-sonnet-thinking","score":93.27,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5-minimal","score":82.45,"metric":"percent"},{"benchmark":"charxiv-dq","model":"grok-4-fast-thinking","score":68.15,"metric":"percent"},{"benchmark":"charxiv-rq","model":"apriel-1.6-15b-thinker","score":56,"metric":"percent"},{"benchmark":"charxiv-rq","model":"apriel-1.5-15b-thinker","score":50.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5-high","score":71.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"glm-4.5v","score":63,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-flash","score":56.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-3.7-sonnet-thinking","score":70.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5-minimal","score":52.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"grok-4-fast-thinking","score":33.5,"metric":"percent"},{"benchmark":"ai2d","model":"apriel-1.6-15b-thinker","score":86.04,"metric":"percent"},{"benchmark":"ai2d","model":"apriel-1.5-15b-thinker","score":82.87,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-high","score":90.05,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4.5v","score":87.75,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-flash","score":82.09,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3.7-sonnet-thinking","score":84.19,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-minimal","score":85.16,"metric":"percent"},{"benchmark":"ai2d","model":"grok-4-fast-thinking","score":81.86,"metric":"percent"},{"benchmark":"blink","model":"apriel-1.6-15b-thinker","score":63.96,"metric":"percent"},{"benchmark":"blink","model":"apriel-1.5-15b-thinker","score":58.71,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-high","score":70.22,"metric":"percent"},{"benchmark":"blink","model":"glm-4.5v","score":66.59,"metric":"percent"},{"benchmark":"blink","model":"gemini-2.5-flash","score":65.64,"metric":"percent"},{"benchmark":"blink","model":"claude-3.7-sonnet-thinking","score":64.49,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-minimal","score":64.59,"metric":"percent"},{"benchmark":"blink","model":"grok-4-fast-thinking","score":54.39,"metric":"percent"},{"benchmark":"aime-2024","model":"superapriel-15b-instruct","score":93.3,"metric":"percent"},{"benchmark":"aime-2025","model":"superapriel-15b-instruct","score":86.7,"metric":"percent"},{"benchmark":"math500","model":"superapriel-15b-instruct","score":91.8,"metric":"percent"},{"benchmark":"gsm8k","model":"superapriel-15b-instruct","score":92.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"superapriel-15b-instruct","score":76.8,"metric":"percent"},{"benchmark":"gpqa","model":"superapriel-15b-instruct","score":72,"metric":"percent"},{"benchmark":"hle","model":"superapriel-15b-instruct","score":8.2,"metric":"avg@3"},{"benchmark":"livecodebench","model":"superapriel-15b-instruct","score":68.6,"metric":"percent"},{"benchmark":"ifbench","model":"superapriel-15b-instruct","score":63.1,"metric":"percent"},{"benchmark":"mmlu","model":"kimi-k2-base","score":88.24,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3-base","score":87.68,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.5-base","score":87.73,"metric":"percent"},{"benchmark":"mmlu","model":"hy3-preview-base","score":87.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2-base","score":65.98,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3-base","score":63.98,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-base","score":63.67,"metric":"percent"},{"benchmark":"mmlu-pro","model":"hy3-preview-base","score":65.76,"metric":"percent"},{"benchmark":"mmlu-redux","model":"kimi-k2-base","score":87.18,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3-base","score":86.81,"metric":"percent"},{"benchmark":"mmlu-redux","model":"glm-4.5-base","score":86.56,"metric":"percent"},{"benchmark":"mmlu-redux","model":"hy3-preview-base","score":86.86,"metric":"percent"},{"benchmark":"arc-challenge","model":"kimi-k2-base","score":96.66,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v3-base","score":94.65,"metric":"percent"},{"benchmark":"arc-challenge","model":"glm-4.5-base","score":96.32,"metric":"percent"},{"benchmark":"arc-challenge","model":"hy3-preview-base","score":95.99,"metric":"percent"},{"benchmark":"drop","model":"kimi-k2-base","score":86.4,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v3-base","score":86.5,"metric":"percent"},{"benchmark":"drop","model":"glm-4.5-base","score":82.9,"metric":"percent"},{"benchmark":"drop","model":"hy3-preview-base","score":85.5,"metric":"percent"},{"benchmark":"piqa","model":"kimi-k2-base","score":84.93,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-v3-base","score":84.22,"metric":"percent"},{"benchmark":"piqa","model":"glm-4.5-base","score":84.71,"metric":"percent"},{"benchmark":"piqa","model":"hy3-preview-base","score":84.39,"metric":"percent"},{"benchmark":"supergpqa","model":"kimi-k2-base","score":51.1,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v3-base","score":46.17,"metric":"percent"},{"benchmark":"supergpqa","model":"glm-4.5-base","score":49.64,"metric":"percent"},{"benchmark":"supergpqa","model":"hy3-preview-base","score":51.6,"metric":"percent"},{"benchmark":"simpleqa","model":"kimi-k2-base","score":34.37,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3-base","score":26.15,"metric":"percent"},{"benchmark":"simpleqa","model":"glm-4.5-base","score":29.26,"metric":"percent"},{"benchmark":"simpleqa","model":"hy3-preview-base","score":26.47,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kimi-k2-base","score":81.35,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3-base","score":75.47,"metric":"percent"},{"benchmark":"mbpp-plus","model":"glm-4.5-base","score":78.05,"metric":"percent"},{"benchmark":"mbpp-plus","model":"hy3-preview-base","score":78.71,"metric":"percent"},{"benchmark":"crux-i","model":"kimi-k2-base","score":68.01,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v3-base","score":67.79,"metric":"percent"},{"benchmark":"crux-i","model":"glm-4.5-base","score":68.51,"metric":"percent"},{"benchmark":"crux-i","model":"hy3-preview-base","score":71.19,"metric":"percent"},{"benchmark":"crux-o","model":"kimi-k2-base","score":69.62,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v3-base","score":71,"metric":"percent"},{"benchmark":"crux-o","model":"glm-4.5-base","score":67.75,"metric":"percent"},{"benchmark":"crux-o","model":"hy3-preview-base","score":68.38,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2-base","score":30.86,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3-base","score":29.31,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-base","score":27.43,"metric":"percent"},{"benchmark":"livecodebench","model":"hy3-preview-base","score":34.86,"metric":"percent"},{"benchmark":"gsm8k","model":"kimi-k2-base","score":93.46,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3-base","score":88.15,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4.5-base","score":90.06,"metric":"percent"},{"benchmark":"gsm8k","model":"hy3-preview-base","score":95.37,"metric":"percent"},{"benchmark":"math","model":"kimi-k2-base","score":71.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3-base","score":59.37,"metric":"percent"},{"benchmark":"math","model":"hy3-preview-base","score":76.28,"metric":"percent"},{"benchmark":"cmath","model":"kimi-k2-base","score":90.83,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v3-base","score":85.5,"metric":"percent"},{"benchmark":"cmath","model":"glm-4.5-base","score":89.33,"metric":"percent"},{"benchmark":"cmath","model":"hy3-preview-base","score":91.17,"metric":"percent"},{"benchmark":"c-eval","model":"kimi-k2-base","score":91.51,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3-base","score":90.35,"metric":"percent"},{"benchmark":"c-eval","model":"glm-4.5-base","score":85.84,"metric":"percent"},{"benchmark":"c-eval","model":"hy3-preview-base","score":89.8,"metric":"percent"},{"benchmark":"cmmlu","model":"kimi-k2-base","score":90.72,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v3-base","score":87.9,"metric":"percent"},{"benchmark":"cmmlu","model":"glm-4.5-base","score":86.46,"metric":"percent"},{"benchmark":"cmmlu","model":"hy3-preview-base","score":89.61,"metric":"percent"},{"benchmark":"csimpleqa","model":"kimi-k2-base","score":74.58,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v3-base","score":68.72,"metric":"percent"},{"benchmark":"csimpleqa","model":"glm-4.5-base","score":68.49,"metric":"percent"},{"benchmark":"csimpleqa","model":"hy3-preview-base","score":69.73,"metric":"percent"},{"benchmark":"mmmlu","model":"kimi-k2-base","score":77.63,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v3-base","score":79.54,"metric":"percent"},{"benchmark":"mmmlu","model":"glm-4.5-base","score":79.26,"metric":"percent"},{"benchmark":"mmmlu","model":"hy3-preview-base","score":80.15,"metric":"percent"},{"benchmark":"include","model":"kimi-k2-base","score":75.66,"metric":"percent"},{"benchmark":"include","model":"deepseek-v3-base","score":77.86,"metric":"percent"},{"benchmark":"include","model":"glm-4.5-base","score":76.27,"metric":"percent"},{"benchmark":"include","model":"hy3-preview-base","score":78.64,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"hy3-preview","score":70,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"hy-2.0-thinking","score":63.3,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"glm-5","score":65.9,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"kimi-k2.5-thinking","score":67.8,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gemini-3.1-pro","score":76.8,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.4","score":76.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"hy3-preview","score":84.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"hy-2.0-thinking","score":74.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3.1-pro","score":89.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.4","score":91.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"hy3-preview","score":30,"metric":"percent"},{"benchmark":"hle-text-only","model":"hy-2.0-thinking","score":17.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5","score":30.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2.5-thinking","score":31.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hy3-preview","score":87.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hy-2.0-thinking","score":80.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"hy3-preview","score":66.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"hy-2.0-thinking","score":56,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5","score":63,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2.5-thinking","score":65.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"hy3-preview","score":65.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"hy-2.0-thinking","score":56.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"glm-5","score":62.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"kimi-k2.5-thinking","score":65.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemini-3.1-pro","score":67.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5.4","score":67.4,"metric":"percent"},{"benchmark":"cl-bench","model":"hy3-preview","score":22.8,"metric":"percent"},{"benchmark":"cl-bench","model":"hy-2.0-thinking","score":17.2,"metric":"percent"},{"benchmark":"cl-bench","model":"glm-5","score":19.3,"metric":"percent"},{"benchmark":"cl-bench","model":"kimi-k2.5-thinking","score":20.1,"metric":"percent"},{"benchmark":"cl-bench","model":"gemini-3.1-pro","score":21.3,"metric":"percent"},{"benchmark":"cl-bench","model":"gpt-5.4","score":26.7,"metric":"percent"},{"benchmark":"cl-bench-life","model":"hy3-preview","score":15.7,"metric":"percent"},{"benchmark":"cl-bench-life","model":"hy-2.0-thinking","score":8.5,"metric":"percent"},{"benchmark":"cl-bench-life","model":"kimi-k2.5-thinking","score":13,"metric":"percent"},{"benchmark":"cl-bench-life","model":"glm-5","score":13,"metric":"percent"},{"benchmark":"cl-bench-life","model":"gemini-3.1-pro","score":16.5,"metric":"percent"},{"benchmark":"cl-bench-life","model":"gpt-5.4","score":19.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"hy3-preview","score":74.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"hy-2.0-thinking","score":53,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.5","score":81,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2-thinking","score":66,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"hy3-preview","score":54.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"hy-2.0-thinking","score":23.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.5","score":60,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2-thinking","score":36,"metric":"percent"},{"benchmark":"browsecomp","model":"hy3-preview","score":67.1,"metric":"percent"},{"benchmark":"browsecomp","model":"hy-2.0-thinking","score":28.7,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5","score":75.9,"metric":"percent"},{"benchmark":"wide-search","model":"hy3-preview","score":70.2,"metric":"percent"},{"benchmark":"wide-search","model":"hy-2.0-thinking","score":53.9,"metric":"percent"},{"benchmark":"wide-search","model":"claude-opus-4.5","score":73.5,"metric":"percent"},{"benchmark":"wide-search","model":"claude-opus-4.6","score":77.2,"metric":"percent"},{"benchmark":"wide-search","model":"kimi-k2-thinking","score":61.2,"metric":"percent"},{"benchmark":"wide-search","model":"glm-4.7","score":65.8,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5","score":69.8,"metric":"percent"},{"benchmark":"wildclawbench","model":"hy3-preview","score":45.3,"metric":"percent"},{"benchmark":"wildclawbench","model":"hy-2.0-thinking","score":33.7,"metric":"percent"},{"benchmark":"wildclawbench","model":"kimi-k2.5-thinking","score":39.5,"metric":"percent"},{"benchmark":"wildclawbench","model":"glm-5","score":46.4,"metric":"percent"},{"benchmark":"wildclawbench","model":"claude-opus-4.6","score":60.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"hy3-preview","score":55,"metric":"percent"},{"benchmark":"claweval-pass3","model":"hy-2.0-thinking","score":32.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"hy3-preview","score":68.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"hy3","score":75.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.2","score":83,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"seed2.1-pro","score":75.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.5","score":77.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"hy3","score":78,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5.1","score":75,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5.2","score":84.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"seed2.1-pro","score":76,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.5","score":84.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"hy3-preview","score":46,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"hy3","score":57.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.7-max","score":60.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"hy3-preview","score":58,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"hy3","score":71.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash-thinking-max","score":52.58,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"seed2.1-pro","score":71,"metric":"percent"},{"benchmark":"nl2repo","model":"hy3-preview","score":35.3,"metric":"percent"},{"benchmark":"nl2repo","model":"hy3","score":45.6,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-pro-thinking-max","score":41.5,"metric":"percent"},{"benchmark":"nl2repo","model":"seed2.1-pro","score":47,"metric":"percent"},{"benchmark":"deepswe","model":"hy3-preview","score":0.9,"metric":"percent"},{"benchmark":"deepswe","model":"hy3","score":28,"metric":"percent"},{"benchmark":"deepswe","model":"glm-5.1","score":18,"metric":"percent"},{"benchmark":"deepswe","model":"deepseek-v4-flash-thinking-max","score":7.1,"metric":"percent"},{"benchmark":"browsecomp","model":"hy3","score":84.2,"metric":"percent"},{"benchmark":"browsecomp","model":"seed2.1-pro","score":86.2,"metric":"percent"},{"benchmark":"wide-search","model":"hy3-preview","score":67.8,"metric":"percent"},{"benchmark":"wide-search","model":"hy3","score":76.4,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5.1","score":76.1,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-flash-thinking-max","score":74.3,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-pro-thinking-max","score":75.7,"metric":"percent"},{"benchmark":"wide-search","model":"seed2.1-pro","score":76.4,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.7-max","score":72.3,"metric":"percent"},{"benchmark":"wide-search","model":"gemini-3.1-pro","score":71.7,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5.5","score":80,"metric":"percent"},{"benchmark":"deepsearchqa","model":"hy3-preview","score":82.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"hy3","score":91,"metric":"percent"},{"benchmark":"deepsearchqa","model":"glm-5.1","score":89.1,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v4-flash-thinking-max","score":87.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v4-pro-thinking-max","score":90.4,"metric":"percent"},{"benchmark":"deepsearchqa","model":"seed2.1-pro","score":90.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"qwen3.7-max","score":88.4,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gemini-3.1-pro","score":90.4,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-5.5","score":95.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"hy3-preview","score":66.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"hy3","score":79.1,"metric":"percent"},{"benchmark":"toolathlon","model":"hy3-preview","score":32.1,"metric":"percent"},{"benchmark":"toolathlon","model":"hy3","score":48.5,"metric":"percent"},{"benchmark":"toolathlon","model":"qwen3.7-max","score":45.1,"metric":"percent"},{"benchmark":"apex-agents","model":"hy3-preview","score":12.4,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-5.1","score":24.3,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-5.2","score":29.9,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-flash-thinking-max","score":18.3,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-pro-thinking-max","score":20.4,"metric":"percent"},{"benchmark":"apex-agents","model":"seed2.1-pro","score":33.8,"metric":"percent"},{"benchmark":"apex-agents","model":"qwen3.7-max","score":22.2,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-4.8","score":42.5,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.5","score":38.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"hy3","score":68.5,"metric":"percent"},{"benchmark":"claweval-pass3","model":"glm-5.2","score":62.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v4-flash-thinking-max","score":61.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"seed2.1-pro","score":62.1,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.7-max","score":65.2,"metric":"percent"},{"benchmark":"claweval-pass3","model":"claude-opus-4.8","score":72.1,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gpt-5.5","score":67.8,"metric":"percent"},{"benchmark":"wildclawbench","model":"hy3","score":53.6,"metric":"percent"},{"benchmark":"wildclawbench","model":"glm-5.1","score":48.7,"metric":"percent"},{"benchmark":"wildclawbench","model":"glm-5.2","score":59.2,"metric":"percent"},{"benchmark":"wildclawbench","model":"deepseek-v4-flash-thinking-max","score":43.5,"metric":"percent"},{"benchmark":"wildclawbench","model":"deepseek-v4-pro-thinking-max","score":50.5,"metric":"percent"},{"benchmark":"wildclawbench","model":"qwen3.7-max","score":41.5,"metric":"percent"},{"benchmark":"wildclawbench","model":"gemini-3.1-pro","score":46.2,"metric":"percent"},{"benchmark":"wildclawbench","model":"claude-opus-4.8","score":58.4,"metric":"percent"},{"benchmark":"wildclawbench","model":"gpt-5.5","score":63.2,"metric":"percent"},{"benchmark":"skillsbench","model":"hy3-preview","score":29.1,"metric":"percent"},{"benchmark":"skillsbench","model":"hy3","score":55.3,"metric":"percent"},{"benchmark":"skillsbench","model":"glm-5.1","score":43,"metric":"percent"},{"benchmark":"skillsbench","model":"glm-5.2","score":51.9,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-flash-thinking-max","score":35.4,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-pro-thinking-max","score":40.5,"metric":"percent"},{"benchmark":"skillsbench","model":"seed2.1-pro","score":53.2,"metric":"percent"},{"benchmark":"skillsbench","model":"claude-opus-4.8","score":64.6,"metric":"percent"},{"benchmark":"skillsbench","model":"gpt-5.5","score":61.6,"metric":"percent"},{"benchmark":"hle-with-tools","model":"hy3-preview","score":35.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"hy3","score":53.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"seed2.1-pro","score":55.7,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"hy3","score":90.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed2.1-pro","score":89.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"hy3","score":37,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.1","score":31,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-flash-thinking-max","score":34.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-pro-thinking-max","score":37.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"seed2.1-pro","score":35.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.7-max","score":41.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3.1-pro","score":45,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-opus-4.8","score":49.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.5","score":46.9,"metric":"percent"},{"benchmark":"frontierscience-research","model":"hy3-preview","score":19,"metric":"percent"},{"benchmark":"frontierscience-research","model":"hy3","score":21.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"glm-5.1","score":13.5,"metric":"percent"},{"benchmark":"frontierscience-research","model":"glm-5.2","score":19.8,"metric":"percent"},{"benchmark":"frontierscience-research","model":"deepseek-v4-flash-thinking-max","score":16.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"deepseek-v4-pro-thinking-max","score":21.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"qwen3.7-max","score":24.8,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gemini-3.1-pro","score":16.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"claude-opus-4.8","score":32.9,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.5","score":33.9,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"hy3","score":74.8,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"glm-5.1","score":65,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"glm-5.2","score":72.5,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"deepseek-v4-flash-thinking-max","score":73,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"deepseek-v4-pro-thinking-max","score":70,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"qwen3.7-max","score":74.3,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gemini-3.1-pro","score":79,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"claude-opus-4.8","score":74.3,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.5","score":73.8,"metric":"percent"},{"benchmark":"usamo-2026","model":"hy3-preview","score":37.3,"metric":"percent"},{"benchmark":"usamo-2026","model":"hy3","score":72,"metric":"percent"},{"benchmark":"usamo-2026","model":"glm-5.1","score":37.3,"metric":"percent"},{"benchmark":"usamo-2026","model":"glm-5.2","score":41.3,"metric":"percent"},{"benchmark":"usamo-2026","model":"deepseek-v4-flash-thinking-max","score":57.9,"metric":"percent"},{"benchmark":"usamo-2026","model":"deepseek-v4-pro-thinking-max","score":59.2,"metric":"percent"},{"benchmark":"usamo-2026","model":"seed2.1-pro","score":60.3,"metric":"percent"},{"benchmark":"usamo-2026","model":"qwen3.7-max","score":57.1,"metric":"percent"},{"benchmark":"usamo-2026","model":"gemini-3.1-pro","score":61.3,"metric":"percent"},{"benchmark":"usamo-2026","model":"claude-opus-4.8","score":92.9,"metric":"percent"},{"benchmark":"usamo-2026","model":"gpt-5.5","score":98.4,"metric":"percent"},{"benchmark":"matharena-apex","model":"hy3-preview","score":12.6,"metric":"percent"},{"benchmark":"matharena-apex","model":"hy3","score":38.7,"metric":"percent"},{"benchmark":"matharena-apex","model":"glm-5.2","score":16.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"seed2.1-pro","score":31.3,"metric":"percent"},{"benchmark":"matharena-apex","model":"gpt-5.5","score":85.4,"metric":"percent"},{"benchmark":"arxivmath","model":"hy3-preview","score":46.1,"metric":"percent"},{"benchmark":"arxivmath","model":"hy3","score":52.2,"metric":"percent"},{"benchmark":"arxivmath","model":"glm-5.2","score":44.2,"metric":"percent"},{"benchmark":"arxivmath","model":"deepseek-v4-flash-thinking-max","score":52.6,"metric":"percent"},{"benchmark":"arxivmath","model":"deepseek-v4-pro-thinking-max","score":56.4,"metric":"percent"},{"benchmark":"arxivmath","model":"seed2.1-pro","score":53.4,"metric":"percent"},{"benchmark":"arxivmath","model":"qwen3.7-max","score":56,"metric":"percent"},{"benchmark":"phybench","model":"hy3-preview","score":71.4,"metric":"percent"},{"benchmark":"phybench","model":"hy3","score":77.4,"metric":"percent"},{"benchmark":"phybench","model":"glm-5.1","score":70.9,"metric":"percent"},{"benchmark":"phybench","model":"glm-5.2","score":71.5,"metric":"percent"},{"benchmark":"phybench","model":"deepseek-v4-flash-thinking-max","score":76.6,"metric":"percent"},{"benchmark":"phybench","model":"deepseek-v4-pro-thinking-max","score":75.4,"metric":"percent"},{"benchmark":"phybench","model":"seed2.1-pro","score":77.5,"metric":"percent"},{"benchmark":"phybench","model":"qwen3.7-max","score":76.5,"metric":"percent"},{"benchmark":"phybench","model":"gemini-3.1-pro","score":82,"metric":"percent"},{"benchmark":"phybench","model":"claude-opus-4.8","score":79.6,"metric":"percent"},{"benchmark":"phybench","model":"gpt-5.5","score":77.5,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"hy3-preview","score":19.4,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"hy3","score":37.8,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"glm-5.1","score":25.3,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"glm-5.2","score":34.1,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"deepseek-v4-flash-thinking-max","score":26.8,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"deepseek-v4-pro-thinking-max","score":35,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"seed2.1-pro","score":31,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"qwen3.7-max","score":40,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"gemini-3.1-pro","score":47,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"claude-opus-4.8","score":43.8,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"gpt-5.5","score":43.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"hy3","score":90,"metric":"percent"},{"benchmark":"imo-answerbench","model":"seed2.1-pro","score":88.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.5","score":92.1,"metric":"percent"},{"benchmark":"superchem","model":"hy3-preview","score":47,"metric":"percent"},{"benchmark":"superchem","model":"hy3","score":54.9,"metric":"percent"},{"benchmark":"superchem","model":"glm-5.1","score":51.4,"metric":"percent"},{"benchmark":"superchem","model":"glm-5.2","score":60.2,"metric":"percent"},{"benchmark":"superchem","model":"deepseek-v4-flash-thinking-max","score":51.8,"metric":"percent"},{"benchmark":"superchem","model":"deepseek-v4-pro-thinking-max","score":61.2,"metric":"percent"},{"benchmark":"superchem","model":"seed2.1-pro","score":59.8,"metric":"percent"},{"benchmark":"superchem","model":"qwen3.7-max","score":60.5,"metric":"percent"},{"benchmark":"superchem","model":"gemini-3.1-pro","score":69.2,"metric":"percent"},{"benchmark":"superchem","model":"claude-opus-4.8","score":66.9,"metric":"percent"},{"benchmark":"superchem","model":"gpt-5.5","score":66.2,"metric":"percent"},{"benchmark":"cl-bench","model":"hy3","score":23.8,"metric":"percent"},{"benchmark":"cl-bench","model":"glm-5.1","score":21,"metric":"percent"},{"benchmark":"cl-bench","model":"glm-5.2","score":23.1,"metric":"percent"},{"benchmark":"cl-bench","model":"deepseek-v4-flash-thinking-max","score":16.4,"metric":"percent"},{"benchmark":"cl-bench","model":"deepseek-v4-pro-thinking-max","score":18.1,"metric":"percent"},{"benchmark":"cl-bench","model":"seed2.1-pro","score":23.5,"metric":"percent"},{"benchmark":"cl-bench","model":"qwen3.7-max","score":18.4,"metric":"percent"},{"benchmark":"cl-bench","model":"claude-opus-4.8","score":24.8,"metric":"percent"},{"benchmark":"cl-bench","model":"gpt-5.5","score":27.8,"metric":"percent"},{"benchmark":"cl-bench-life","model":"hy3","score":17,"metric":"percent"},{"benchmark":"cl-bench-life","model":"glm-5.1","score":14,"metric":"percent"},{"benchmark":"cl-bench-life","model":"glm-5.2","score":21,"metric":"percent"},{"benchmark":"cl-bench-life","model":"deepseek-v4-flash-thinking-max","score":11.4,"metric":"percent"},{"benchmark":"cl-bench-life","model":"deepseek-v4-pro-thinking-max","score":14.3,"metric":"percent"},{"benchmark":"cl-bench-life","model":"seed2.1-pro","score":13.3,"metric":"percent"},{"benchmark":"cl-bench-life","model":"qwen3.7-max","score":13,"metric":"percent"},{"benchmark":"cl-bench-life","model":"claude-opus-4.8","score":16.9,"metric":"percent"},{"benchmark":"cl-bench-life","model":"gpt-5.5","score":21.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"hy3","score":73.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.1","score":71,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.2","score":73.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-flash-thinking-max","score":64.8,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-pro-thinking-max","score":71.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"seed2.1-pro","score":70,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.7-max","score":70.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-3.1-pro","score":74.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-opus-4.8","score":72.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.5","score":76.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"hy4-preview","score":82.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-pro-0813","score":77.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.8-max","score":82.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.3","score":81.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k3","score":80.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.6-sol","score":74.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"hy4-preview","score":65.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-pro-0813","score":60.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"glm-5.3","score":64.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k3","score":63.3,"metric":"percent"},{"benchmark":"deepswe","model":"hy4-preview","score":64.3,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"hy3","score":30.8,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"hy4-preview","score":64,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"deepseek-v4-pro-0813","score":53.4,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"qwen3.8-max","score":55.4,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"glm-5.3","score":55.8,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"kimi-k3","score":35.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"gpt-5.6-sol","score":58.1,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-opus-5","score":57.5,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"hy3","score":35.9,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"hy4-preview","score":57.8,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"deepseek-v4-pro-0813","score":45.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"qwen3.8-max","score":52.8,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"glm-5.3","score":49.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"kimi-k3","score":35.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"gpt-5.6-sol","score":49.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"claude-opus-5","score":68.7,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"hy3","score":32.9,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"hy4-preview","score":53.3,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"deepseek-v4-pro-0813","score":48.6,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"qwen3.8-max","score":51,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"glm-5.3","score":51.9,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"kimi-k3","score":37.4,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"gpt-5.6-sol","score":52.4,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"claude-opus-5","score":60,"metric":"percent"},{"benchmark":"swe-marathon","model":"hy3","score":5,"metric":"percent"},{"benchmark":"swe-marathon","model":"hy4-preview","score":31.9,"metric":"percent"},{"benchmark":"swe-marathon","model":"deepseek-v4-pro-0813","score":19,"metric":"percent"},{"benchmark":"swe-marathon","model":"qwen3.8-max","score":31,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"hy3","score":70.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"hy4-preview","score":85.4,"metric":"percent"},{"benchmark":"nl2repo","model":"hy4-preview","score":58.9,"metric":"percent"},{"benchmark":"cybergym","model":"hy3","score":51.8,"metric":"percent"},{"benchmark":"cybergym","model":"hy4-preview","score":78.4,"metric":"percent"},{"benchmark":"programbench","model":"hy3","score":3,"metric":"percent"},{"benchmark":"programbench","model":"hy4-preview","score":17.5,"metric":"percent"},{"benchmark":"programbench","model":"qwen3.8-max","score":17.5,"metric":"percent"},{"benchmark":"programbench","model":"glm-5.3","score":18,"metric":"percent"},{"benchmark":"programbench","model":"kimi-k3","score":24.5,"metric":"percent"},{"benchmark":"programbench","model":"claude-opus-5","score":39.5,"metric":"percent"},{"benchmark":"posttrainbench","model":"hy3","score":14.5,"metric":"percent"},{"benchmark":"posttrainbench","model":"hy4-preview","score":35.6,"metric":"percent"},{"benchmark":"posttrainbench","model":"deepseek-v4-pro-0813","score":24.5,"metric":"percent"},{"benchmark":"posttrainbench","model":"glm-5.3","score":33.2,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-5","score":35,"metric":"percent"},{"benchmark":"harbor-index","model":"hy3","score":15.6,"metric":"percent"},{"benchmark":"harbor-index","model":"hy4-preview","score":39.6,"metric":"percent"},{"benchmark":"harbor-index","model":"deepseek-v4-pro-0813","score":36.9,"metric":"percent"},{"benchmark":"harbor-index","model":"qwen3.8-max","score":38.8,"metric":"percent"},{"benchmark":"harbor-index","model":"glm-5.3","score":42.5,"metric":"percent"},{"benchmark":"harbor-index","model":"gpt-5.6-sol","score":46.3,"metric":"percent"},{"benchmark":"harbor-index","model":"claude-opus-5","score":56.9,"metric":"percent"},{"benchmark":"wide-search","model":"hy3","score":81.9,"metric":"percent"},{"benchmark":"wide-search","model":"hy4-preview","score":83.9,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-pro-0813","score":81.8,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5.3","score":83.2,"metric":"percent"},{"benchmark":"wide-search","model":"kimi-k3","score":81,"metric":"percent"},{"benchmark":"onemillionbench","model":"hy3","score":51.5,"metric":"percent"},{"benchmark":"onemillionbench","model":"hy4-preview","score":65.4,"metric":"percent"},{"benchmark":"onemillionbench","model":"deepseek-v4-pro-0813","score":62,"metric":"percent"},{"benchmark":"onemillionbench","model":"qwen3.8-max","score":63.1,"metric":"percent"},{"benchmark":"onemillionbench","model":"glm-5.3","score":64.5,"metric":"percent"},{"benchmark":"onemillionbench","model":"kimi-k3","score":63.5,"metric":"percent"},{"benchmark":"onemillionbench","model":"gpt-5.6-sol","score":67.1,"metric":"percent"},{"benchmark":"onemillionbench","model":"claude-opus-5","score":68.1,"metric":"percent"},{"benchmark":"draco","model":"hy3","score":65.2,"metric":"percent"},{"benchmark":"draco","model":"hy4-preview","score":77.2,"metric":"percent"},{"benchmark":"draco","model":"deepseek-v4-pro-0813","score":77.3,"metric":"percent"},{"benchmark":"draco","model":"qwen3.8-max","score":76.4,"metric":"percent"},{"benchmark":"officeqa-pro","model":"hy3","score":54.1,"metric":"percent"},{"benchmark":"officeqa-pro","model":"hy4-preview","score":66.2,"metric":"percent"},{"benchmark":"officeqa-pro","model":"deepseek-v4-pro-0813","score":65.4,"metric":"percent"},{"benchmark":"officeqa-pro","model":"qwen3.8-max","score":65.4,"metric":"percent"},{"benchmark":"officeqa-pro","model":"glm-5.3","score":66.2,"metric":"percent"},{"benchmark":"officeqa-pro","model":"kimi-k3","score":65.4,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.6-sol","score":65.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"hy3","score":75,"metric":"percent"},{"benchmark":"mcp-atlas","model":"hy4-preview","score":83.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-pro-0813","score":82.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.8-max","score":81.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"glm-5.3","score":81.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.6-sol","score":82.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"claude-opus-5","score":85.7,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"hy3","score":56.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"hy4-preview","score":74.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gpt-5.6-sol","score":73.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"claude-opus-5","score":76.5,"metric":"percent"},{"benchmark":"apex-agents","model":"hy3","score":24.4,"metric":"percent"},{"benchmark":"apex-agents","model":"hy4-preview","score":37.1,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-pro-0813","score":32.4,"metric":"percent"},{"benchmark":"apex-agents","model":"qwen3.8-max","score":34,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-5.3","score":38.1,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-5","score":41.8,"metric":"percent"},{"benchmark":"skillsbench","model":"hy4-preview","score":62.9,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-pro-0813","score":65,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.8-max","score":66.7,"metric":"percent"},{"benchmark":"skillsbench","model":"glm-5.3","score":63.3,"metric":"percent"},{"benchmark":"skillsbench","model":"kimi-k3","score":51.9,"metric":"percent"},{"benchmark":"skillsbench","model":"gpt-5.6-sol","score":62.5,"metric":"percent"},{"benchmark":"jobbench","model":"hy3","score":34.6,"metric":"percent"},{"benchmark":"jobbench","model":"hy4-preview","score":61.7,"metric":"percent"},{"benchmark":"jobbench","model":"deepseek-v4-pro-0813","score":54.1,"metric":"percent"},{"benchmark":"jobbench","model":"glm-5.3","score":58.2,"metric":"percent"},{"benchmark":"jobbench","model":"claude-opus-5","score":68,"metric":"percent"},{"benchmark":"workspacebench","model":"hy3","score":58.2,"metric":"percent"},{"benchmark":"workspacebench","model":"hy4-preview","score":60.2,"metric":"percent"},{"benchmark":"workspacebench","model":"deepseek-v4-pro-0813","score":65.4,"metric":"percent"},{"benchmark":"workspacebench","model":"glm-5.3","score":68.2,"metric":"percent"},{"benchmark":"workspacebench","model":"kimi-k3","score":65,"metric":"percent"},{"benchmark":"workspacebench","model":"gpt-5.6-sol","score":65.3,"metric":"percent"},{"benchmark":"workspacebench","model":"claude-opus-5","score":75,"metric":"percent"},{"benchmark":"agents-last-exam","model":"hy3","score":17.1,"metric":"percent"},{"benchmark":"agents-last-exam","model":"hy4-preview","score":22.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4-pro-0813","score":21.9,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.8-max","score":25.4,"metric":"percent"},{"benchmark":"agents-last-exam","model":"glm-5.3","score":23.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"kimi-k3","score":23.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol","score":27.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5","score":25.1,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"hy3","score":1213,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"hy4-preview","score":1678,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4-pro-0813","score":1580,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.8-max","score":1717,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.3","score":1763,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"kimi-k3","score":1675,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"claude-opus-5","score":1831,"metric":"elo"},{"benchmark":"automationbench","model":"hy3","score":16.1,"metric":"percent"},{"benchmark":"automationbench","model":"hy4-preview","score":32.1,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-pro-0813","score":30.4,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-5","score":48.7,"metric":"percent"},{"benchmark":"bankertoolbench","model":"hy3","score":68.8,"metric":"percent"},{"benchmark":"bankertoolbench","model":"hy4-preview","score":78.6,"metric":"percent"},{"benchmark":"bankertoolbench","model":"deepseek-v4-pro-0813","score":73.1,"metric":"percent"},{"benchmark":"bankertoolbench","model":"qwen3.8-max","score":74.7,"metric":"percent"},{"benchmark":"bankertoolbench","model":"glm-5.3","score":77.8,"metric":"percent"},{"benchmark":"bankertoolbench","model":"kimi-k3","score":73.5,"metric":"percent"},{"benchmark":"bankertoolbench","model":"gpt-5.6-sol","score":79,"metric":"percent"},{"benchmark":"bankertoolbench","model":"claude-opus-5","score":81.9,"metric":"percent"},{"benchmark":"biomysterybench","model":"hy3","score":54.9,"metric":"percent"},{"benchmark":"biomysterybench","model":"hy4-preview","score":71.3,"metric":"percent"},{"benchmark":"biomysterybench","model":"deepseek-v4-pro-0813","score":61.6,"metric":"percent"},{"benchmark":"biomysterybench","model":"qwen3.8-max","score":58.9,"metric":"percent"},{"benchmark":"biomysterybench","model":"glm-5.3","score":69,"metric":"percent"},{"benchmark":"biomysterybench","model":"kimi-k3","score":61.3,"metric":"percent"},{"benchmark":"biomysterybench","model":"gpt-5.6-sol","score":73.1,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-opus-5","score":72.1,"metric":"percent"},{"benchmark":"hle-with-tools","model":"hy3","score":51.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"hy4-preview","score":55.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"kimi-k3","score":57,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5.6-sol","score":60.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"claude-opus-5","score":60.9,"metric":"avg@3"},{"benchmark":"critpt","model":"hy3","score":4.9,"metric":"percent"},{"benchmark":"critpt","model":"hy4-preview","score":16.9,"metric":"percent"},{"benchmark":"critpt","model":"deepseek-v4-pro-0813","score":18,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hy3","score":90.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hy4-preview","score":92.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"hy3","score":34.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"hy4-preview","score":43.4,"metric":"percent"},{"benchmark":"superchem","model":"hy3","score":52.6,"metric":"percent"},{"benchmark":"superchem","model":"hy4-preview","score":66.4,"metric":"percent"},{"benchmark":"superchem","model":"deepseek-v4-pro-0813","score":62,"metric":"percent"},{"benchmark":"superchem","model":"qwen3.8-max","score":61.9,"metric":"percent"},{"benchmark":"superchem","model":"glm-5.3","score":58.5,"metric":"percent"},{"benchmark":"superchem","model":"kimi-k3","score":66.9,"metric":"percent"},{"benchmark":"superchem","model":"gpt-5.6-sol","score":73.6,"metric":"percent"},{"benchmark":"superchem","model":"claude-opus-5","score":76.7,"metric":"percent"},{"benchmark":"arxivmath","model":"hy3","score":51.7,"metric":"percent"},{"benchmark":"arxivmath","model":"hy4-preview","score":66.6,"metric":"percent"},{"benchmark":"arxivmath","model":"deepseek-v4-pro-0813","score":62.1,"metric":"percent"},{"benchmark":"arxivmath","model":"qwen3.8-max","score":67.1,"metric":"percent"},{"benchmark":"arxivmath","model":"kimi-k3","score":60.8,"metric":"percent"},{"benchmark":"arxivmath","model":"gpt-5.6-sol","score":79.5,"metric":"percent"},{"benchmark":"arxivmath","model":"claude-opus-5","score":71.5,"metric":"percent"},{"benchmark":"matharena-apex","model":"hy4-preview","score":74.2,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-pro-0813","score":66.3,"metric":"percent"},{"benchmark":"matharena-apex","model":"qwen3.8-max","score":72.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"kimi-k3","score":68.4,"metric":"percent"},{"benchmark":"matharena-apex","model":"gpt-5.6-sol","score":90,"metric":"percent"},{"benchmark":"matharena-apex","model":"claude-opus-5","score":91.4,"metric":"percent"},{"benchmark":"brokenarxiv","model":"hy3","score":26.7,"metric":"percent"},{"benchmark":"brokenarxiv","model":"hy4-preview","score":54.6,"metric":"percent"},{"benchmark":"brokenarxiv","model":"deepseek-v4-pro-0813","score":43.1,"metric":"percent"},{"benchmark":"brokenarxiv","model":"qwen3.8-max","score":42.7,"metric":"percent"},{"benchmark":"brokenarxiv","model":"kimi-k3","score":56.3,"metric":"percent"},{"benchmark":"brokenarxiv","model":"gpt-5.6-sol","score":64.4,"metric":"percent"},{"benchmark":"brokenarxiv","model":"claude-opus-5","score":77.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed2.0-lite-0428","score":88.4,"metric":"percent"},{"benchmark":"supergpqa","model":"seed2.0-lite-0428","score":69.6,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5.4-mini","score":63.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"seed2.0-lite-0428","score":25.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.4-mini","score":28.2,"metric":"percent"},{"benchmark":"beyondaime","model":"seed2.0-lite-0428","score":79,"metric":"percent"},{"benchmark":"beyondaime","model":"gpt-5.4-mini","score":80,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"seed2.0-lite-0428","score":72,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.4-mini","score":70,"metric":"percent"},{"benchmark":"superchem","model":"seed2.0-lite-0428","score":55,"metric":"percent"},{"benchmark":"superchem","model":"gpt-5.4-mini","score":29.1,"metric":"percent"},{"benchmark":"babe","model":"seed2.0-lite-0428","score":57.9,"metric":"percent"},{"benchmark":"babe","model":"seed2.0-pro","score":53.5,"metric":"percent"},{"benchmark":"babe","model":"gpt-5.4-mini","score":49,"metric":"percent"},{"benchmark":"cl-bench","model":"seed2.0-lite-0428","score":20.1,"metric":"percent"},{"benchmark":"cl-bench","model":"gpt-5.4-mini","score":14.9,"metric":"percent"},{"benchmark":"multichallenge","model":"seed2.0-lite-0428","score":69.9,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5.4-mini","score":62.5,"metric":"percent"},{"benchmark":"wide-search","model":"seed2.0-lite-0428","score":70.3,"metric":"percent"},{"benchmark":"wide-search","model":"seed2.0-lite","score":74.5,"metric":"percent"},{"benchmark":"wide-search","model":"seed2.0-pro","score":74.7,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5.4-mini","score":73,"metric":"percent"},{"benchmark":"wide-search","model":"gemini-3-flash","score":64,"metric":"percent"},{"benchmark":"browsecomp","model":"seed2.0-lite-0428","score":64,"metric":"percent"},{"benchmark":"browsecomp","model":"seed2.0-lite","score":72.1,"metric":"percent"},{"benchmark":"browsecomp","model":"seed2.0-pro","score":77.3,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.4-mini","score":61.3,"metric":"percent"},{"benchmark":"browsecomp","model":"gemini-3-flash","score":41.5,"metric":"percent"},{"benchmark":"researchrubrics","model":"seed2.0-lite-0428","score":59.2,"metric":"percent"},{"benchmark":"researchrubrics","model":"seed2.0-lite","score":50.8,"metric":"percent"},{"benchmark":"researchrubrics","model":"seed2.0-pro","score":50.7,"metric":"percent"},{"benchmark":"researchrubrics","model":"gpt-5.4-mini","score":47.1,"metric":"percent"},{"benchmark":"researchrubrics","model":"gemini-3-flash","score":36.9,"metric":"percent"},{"benchmark":"skillsbench","model":"seed2.0-lite-0428","score":43.7,"metric":"percent"},{"benchmark":"skillsbench","model":"seed2.0-lite","score":42.1,"metric":"percent"},{"benchmark":"skillsbench","model":"seed2.0-pro","score":42.3,"metric":"percent"},{"benchmark":"skillsbench","model":"gpt-5.4-mini","score":45.4,"metric":"percent"},{"benchmark":"skillsbench","model":"gemini-3-flash","score":26.4,"metric":"percent"},{"benchmark":"gdpval","model":"seed2.0-lite-0428","score":53.1,"metric":"percent"},{"benchmark":"gdpval","model":"seed2.0-lite","score":47.3,"metric":"percent"},{"benchmark":"gdpval","model":"seed2.0-pro","score":54.4,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.4-mini","score":50.6,"metric":"percent"},{"benchmark":"gdpval","model":"gemini-3-flash","score":13.7,"metric":"percent"},{"benchmark":"finsearchcomp","model":"seed2.0-lite-0428","score":63.8,"metric":"percent"},{"benchmark":"finsearchcomp","model":"seed2.0-lite","score":65.1,"metric":"percent"},{"benchmark":"finsearchcomp","model":"seed2.0-pro","score":70.2,"metric":"percent"},{"benchmark":"finsearchcomp","model":"gpt-5.4-mini","score":61.8,"metric":"percent"},{"benchmark":"finsearchcomp","model":"gemini-3-flash","score":43.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"seed2.0-lite-0428","score":66.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"seed2.0-lite","score":64.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"seed2.0-pro","score":71.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.4-mini","score":73.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemini-3-flash","score":71.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"seed2.0-lite-0428","score":46.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"seed2.0-lite","score":46,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"seed2.0-pro","score":46.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.4-mini","score":54.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemini-3-flash","score":46.7,"metric":"percent"},{"benchmark":"nl2repo","model":"seed2.0-lite-0428","score":28.7,"metric":"percent"},{"benchmark":"nl2repo","model":"seed2.0-lite","score":24.6,"metric":"percent"},{"benchmark":"nl2repo","model":"seed2.0-pro","score":27.9,"metric":"percent"},{"benchmark":"nl2repo","model":"gpt-5.4-mini","score":37.3,"metric":"percent"},{"benchmark":"nl2repo","model":"gemini-3-flash","score":27.6,"metric":"percent"},{"benchmark":"paperbench","model":"seed2.0-lite-0428","score":52.5,"metric":"percent"},{"benchmark":"paperbench","model":"seed2.0-lite","score":54.6,"metric":"percent"},{"benchmark":"paperbench","model":"seed2.0-pro","score":53.8,"metric":"percent"},{"benchmark":"paperbench","model":"gpt-5.4-mini","score":49.1,"metric":"percent"},{"benchmark":"paperbench","model":"gemini-3-flash","score":33.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"seed2.0-lite-0428","score":43.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"seed2.0-lite","score":45,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"seed2.0-pro","score":55.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-flash","score":60,"metric":"percent"},{"benchmark":"mathvision","model":"seed2.0-lite-0428","score":89.8,"metric":"percent"},{"benchmark":"mathvision","model":"seed2.0-lite","score":86.4,"metric":"percent"},{"benchmark":"mathvision","model":"seed2.0-pro","score":88.8,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.4","score":90.6,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3-flash","score":87.5,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.1-pro","score":89,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed2.0-lite-0428","score":78.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed2.0-lite","score":76,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed2.0-pro","score":78.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.4","score":79.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3-flash","score":80.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-pro","score":82.5,"metric":"percent"},{"benchmark":"hipho","model":"seed2.0-lite-0428","score":83.8,"metric":"percent"},{"benchmark":"hipho","model":"seed2.0-lite","score":72.5,"metric":"percent"},{"benchmark":"hipho","model":"seed2.0-pro","score":74.1,"metric":"percent"},{"benchmark":"hipho","model":"gpt-5.4","score":84.3,"metric":"percent"},{"benchmark":"hipho","model":"gemini-3-flash","score":78,"metric":"percent"},{"benchmark":"hipho","model":"gemini-3.1-pro","score":86.6,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"seed2.0-lite-0428","score":79.6,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"seed2.0-lite","score":64,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"seed2.0-pro","score":68.1,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gpt-5.4","score":76.9,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemini-3-flash","score":78,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemini-3.1-pro","score":80.2,"metric":"percent"},{"benchmark":"babyvision","model":"seed2.0-lite-0428","score":64.7,"metric":"percent"},{"benchmark":"babyvision","model":"seed2.0-lite","score":57.5,"metric":"percent"},{"benchmark":"babyvision","model":"seed2.0-pro","score":60.6,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.4","score":53.4,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3-flash","score":47.2,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3.1-pro","score":54.4,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"seed2.0-lite-0428","score":80.6,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"seed2.0-lite","score":74.8,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"seed2.0-pro","score":77.4,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gpt-5.4","score":42.8,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gemini-3-flash","score":66.1,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gemini-3.1-pro","score":73.5,"metric":"percent"},{"benchmark":"simplevqa","model":"seed2.0-lite-0428","score":72.7,"metric":"percent"},{"benchmark":"simplevqa","model":"seed2.0-lite","score":67.2,"metric":"percent"},{"benchmark":"simplevqa","model":"seed2.0-pro","score":71.4,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5.4","score":56,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3-flash","score":68.4,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3.1-pro","score":70.5,"metric":"percent"},{"benchmark":"worldvqa","model":"seed2.0-lite-0428","score":50.2,"metric":"percent"},{"benchmark":"worldvqa","model":"seed2.0-lite","score":44,"metric":"percent"},{"benchmark":"worldvqa","model":"seed2.0-pro","score":49.9,"metric":"percent"},{"benchmark":"worldvqa","model":"gpt-5.4","score":30.2,"metric":"percent"},{"benchmark":"worldvqa","model":"gemini-3-flash","score":46.5,"metric":"percent"},{"benchmark":"worldvqa","model":"gemini-3.1-pro","score":44.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"seed2.0-lite-0428","score":94.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"seed2.0-lite","score":93.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"seed2.0-pro","score":93.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5.4","score":94.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-3-flash","score":94,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-3.1-pro","score":94.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed2.0-lite-0428","score":82.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed2.0-lite","score":79.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed2.0-pro","score":80.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.4","score":82.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3-flash","score":79.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.1-pro","score":84,"metric":"percent"},{"benchmark":"erqa","model":"seed2.0-lite-0428","score":71.5,"metric":"percent"},{"benchmark":"erqa","model":"seed2.0-lite","score":65.8,"metric":"percent"},{"benchmark":"erqa","model":"seed2.0-pro","score":68.5,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.4","score":64.5,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3-flash","score":65.8,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3.1-pro","score":70.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"seed2.0-lite-0428","score":64.4,"metric":"percent"},{"benchmark":"osworld-verified","model":"seed1.8","score":61.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"claude-sonnet-4.5","score":62.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"gemini-3.1-pro","score":64,"metric":"percent"},{"benchmark":"mobileworld","model":"seed2.0-lite-0428","score":64.6,"metric":"percent"},{"benchmark":"mobileworld","model":"seed1.8","score":52.1,"metric":"percent"},{"benchmark":"mobileworld","model":"claude-opus-4.7","score":56.4,"metric":"percent"},{"benchmark":"mobileworld","model":"claude-sonnet-4.5","score":47.8,"metric":"percent"},{"benchmark":"mobileworld","model":"gemini-3.1-pro","score":57.3,"metric":"percent"},{"benchmark":"videommmu","model":"seed2.0-lite-0428","score":88.3,"metric":"percent"},{"benchmark":"videommmu","model":"seed2.0-lite","score":84.1,"metric":"percent"},{"benchmark":"videommmu","model":"seed2.0-pro","score":86.9,"metric":"percent"},{"benchmark":"videommmu","model":"seed2.0-mini","score":80.6,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-3-flash","score":88.1,"metric":"percent"},{"benchmark":"mmvu","model":"seed2.0-lite-0428","score":76.7,"metric":"percent"},{"benchmark":"mmvu","model":"seed2.0-lite","score":75,"metric":"percent"},{"benchmark":"mmvu","model":"seed2.0-pro","score":78.2,"metric":"percent"},{"benchmark":"mmvu","model":"seed2.0-mini","score":69,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-3-flash","score":77.9,"metric":"percent"},{"benchmark":"videosimpleqa","model":"seed2.0-lite-0428","score":71.7,"metric":"percent"},{"benchmark":"videosimpleqa","model":"seed2.0-lite","score":66.6,"metric":"percent"},{"benchmark":"videosimpleqa","model":"seed2.0-pro","score":71.9,"metric":"percent"},{"benchmark":"videosimpleqa","model":"seed2.0-mini","score":67.7,"metric":"percent"},{"benchmark":"videosimpleqa","model":"gemini-3-pro","score":72.4,"metric":"percent"},{"benchmark":"videosimpleqa","model":"gemini-3-flash","score":70,"metric":"percent"},{"benchmark":"videoreasonbench","model":"seed2.0-lite-0428","score":59.4,"metric":"percent"},{"benchmark":"videoreasonbench","model":"seed2.0-lite","score":64.2,"metric":"percent"},{"benchmark":"videoreasonbench","model":"seed2.0-pro","score":77.8,"metric":"percent"},{"benchmark":"videoreasonbench","model":"seed2.0-mini","score":40.5,"metric":"percent"},{"benchmark":"videoreasonbench","model":"gemini-3-flash","score":61.2,"metric":"percent"},{"benchmark":"videoholmes","model":"seed2.0-lite-0428","score":67.4,"metric":"percent"},{"benchmark":"videoholmes","model":"seed2.0-lite","score":63.8,"metric":"percent"},{"benchmark":"videoholmes","model":"seed2.0-pro","score":67.4,"metric":"percent"},{"benchmark":"videoholmes","model":"seed2.0-mini","score":58.6,"metric":"percent"},{"benchmark":"videoholmes","model":"gemini-3-flash","score":65.6,"metric":"percent"},{"benchmark":"minerva-video","model":"seed2.0-lite-0428","score":68.5,"metric":"percent"},{"benchmark":"minerva-video","model":"seed2.0-lite","score":63.8,"metric":"percent"},{"benchmark":"minerva-video","model":"seed2.0-pro","score":66.5,"metric":"percent"},{"benchmark":"minerva-video","model":"seed2.0-mini","score":54.7,"metric":"percent"},{"benchmark":"minerva-video","model":"gemini-3-pro","score":65,"metric":"percent"},{"benchmark":"minerva-video","model":"gemini-3-flash","score":64.4,"metric":"percent"},{"benchmark":"tvbench","model":"seed2.0-lite-0428","score":80.4,"metric":"percent"},{"benchmark":"tvbench","model":"seed2.0-lite","score":71.5,"metric":"percent"},{"benchmark":"tvbench","model":"seed2.0-pro","score":75,"metric":"percent"},{"benchmark":"tvbench","model":"seed2.0-mini","score":70.5,"metric":"percent"},{"benchmark":"tvbench","model":"gemini-3-flash","score":69.6,"metric":"percent"},{"benchmark":"tomato","model":"seed2.0-lite-0428","score":72.5,"metric":"percent"},{"benchmark":"tomato","model":"seed2.0-lite","score":57.3,"metric":"percent"},{"benchmark":"tomato","model":"seed2.0-pro","score":59.9,"metric":"percent"},{"benchmark":"tomato","model":"seed2.0-mini","score":47.4,"metric":"percent"},{"benchmark":"tomato","model":"gemini-3-flash","score":60.8,"metric":"percent"},{"benchmark":"egotempo","model":"seed2.0-lite-0428","score":68.4,"metric":"percent"},{"benchmark":"egotempo","model":"seed2.0-lite","score":61.8,"metric":"percent"},{"benchmark":"egotempo","model":"seed2.0-pro","score":71.8,"metric":"percent"},{"benchmark":"egotempo","model":"seed2.0-mini","score":67.2,"metric":"percent"},{"benchmark":"egotempo","model":"gemini-3-flash","score":58.4,"metric":"percent"},{"benchmark":"motionbench","model":"seed2.0-lite-0428","score":72.4,"metric":"percent"},{"benchmark":"motionbench","model":"seed2.0-lite","score":70.9,"metric":"percent"},{"benchmark":"motionbench","model":"seed2.0-pro","score":75.2,"metric":"percent"},{"benchmark":"motionbench","model":"seed2.0-mini","score":65.1,"metric":"percent"},{"benchmark":"motionbench","model":"gemini-3-flash","score":68.9,"metric":"percent"},{"benchmark":"contphy","model":"seed2.0-lite-0428","score":62.4,"metric":"percent"},{"benchmark":"contphy","model":"seed2.0-lite","score":56.1,"metric":"percent"},{"benchmark":"contphy","model":"seed2.0-pro","score":67.4,"metric":"percent"},{"benchmark":"contphy","model":"seed2.0-mini","score":55.9,"metric":"percent"},{"benchmark":"contphy","model":"gemini-3-pro","score":61.1,"metric":"percent"},{"benchmark":"contphy","model":"gemini-3-flash","score":62,"metric":"percent"},{"benchmark":"videomme","model":"seed2.0-lite-0428","score":89,"metric":"percent"},{"benchmark":"videomme","model":"seed2.0-lite","score":87.7,"metric":"percent"},{"benchmark":"videomme","model":"seed2.0-pro","score":89.5,"metric":"percent"},{"benchmark":"videomme","model":"seed2.0-mini","score":81.2,"metric":"percent"},{"benchmark":"videomme","model":"gemini-3-flash","score":85.2,"metric":"percent"},{"benchmark":"videomme-v2","model":"seed2.0-lite-0428","score":64.9,"metric":"percent"},{"benchmark":"videomme-v2","model":"seed2.0-pro","score":60.5,"metric":"percent"},{"benchmark":"videomme-v2","model":"gemini-3-pro","score":66.1,"metric":"percent"},{"benchmark":"videomme-v2","model":"gemini-3-flash","score":61.1,"metric":"percent"},{"benchmark":"cgbench","model":"seed2.0-lite-0428","score":65.5,"metric":"percent"},{"benchmark":"cgbench","model":"seed2.0-lite","score":59.3,"metric":"percent"},{"benchmark":"cgbench","model":"seed2.0-pro","score":65,"metric":"percent"},{"benchmark":"cgbench","model":"gemini-3-pro","score":65.5,"metric":"percent"},{"benchmark":"cgbench","model":"gemini-3-flash","score":65.3,"metric":"percent"},{"benchmark":"longvideobench","model":"seed2.0-lite-0428","score":79,"metric":"percent"},{"benchmark":"longvideobench","model":"seed2.0-lite","score":77.3,"metric":"percent"},{"benchmark":"longvideobench","model":"seed2.0-pro","score":80.3,"metric":"percent"},{"benchmark":"longvideobench","model":"seed2.0-mini","score":74.8,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-3-pro","score":78.2,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-3-flash","score":74.5,"metric":"percent"},{"benchmark":"lvbench","model":"seed2.0-lite-0428","score":76.4,"metric":"percent"},{"benchmark":"lvbench","model":"seed2.0-lite","score":73,"metric":"percent"},{"benchmark":"lvbench","model":"seed2.0-pro","score":76.4,"metric":"percent"},{"benchmark":"lvbench","model":"seed2.0-mini","score":66.6,"metric":"percent"},{"benchmark":"ovbench","model":"seed2.0-lite-0428","score":63.2,"metric":"percent"},{"benchmark":"ovbench","model":"seed2.0-lite","score":65.5,"metric":"percent"},{"benchmark":"ovbench","model":"seed2.0-pro","score":69.2,"metric":"percent"},{"benchmark":"ovbench","model":"seed2.0-mini","score":60.1,"metric":"percent"},{"benchmark":"ovbench","model":"gemini-3-pro","score":63.5,"metric":"percent"},{"benchmark":"ovbench","model":"gemini-3-flash","score":59.2,"metric":"percent"},{"benchmark":"livesports-3k","model":"seed2.0-lite-0428","score":78.1,"metric":"percent"},{"benchmark":"livesports-3k","model":"seed2.0-lite","score":77.8,"metric":"percent"},{"benchmark":"livesports-3k","model":"seed2.0-pro","score":78,"metric":"percent"},{"benchmark":"livesports-3k","model":"seed2.0-mini","score":73.3,"metric":"percent"},{"benchmark":"livesports-3k","model":"gemini-3-flash","score":73.2,"metric":"percent"},{"benchmark":"ovobench","model":"seed2.0-lite-0428","score":75.4,"metric":"percent"},{"benchmark":"ovobench","model":"seed2.0-lite","score":76.7,"metric":"percent"},{"benchmark":"ovobench","model":"seed2.0-pro","score":77,"metric":"percent"},{"benchmark":"ovobench","model":"seed2.0-mini","score":70.4,"metric":"percent"},{"benchmark":"ovobench","model":"gemini-3-flash","score":68.7,"metric":"percent"},{"benchmark":"vispeak","model":"seed2.0-lite-0428","score":87,"metric":"percent"},{"benchmark":"vispeak","model":"seed2.0-lite","score":84,"metric":"percent"},{"benchmark":"vispeak","model":"seed2.0-pro","score":78.5,"metric":"percent"},{"benchmark":"vispeak","model":"seed2.0-mini","score":77.5,"metric":"percent"},{"benchmark":"vispeak","model":"gemini-3-flash","score":88,"metric":"percent"},{"benchmark":"crossvid","model":"seed2.0-lite-0428","score":63.7,"metric":"percent"},{"benchmark":"crossvid","model":"seed2.0-lite","score":57.7,"metric":"percent"},{"benchmark":"crossvid","model":"seed2.0-pro","score":61,"metric":"percent"},{"benchmark":"crossvid","model":"seed2.0-mini","score":58.6,"metric":"percent"},{"benchmark":"crossvid","model":"gemini-3-pro","score":53,"metric":"percent"},{"benchmark":"crossvid","model":"gemini-3-flash","score":48.7,"metric":"percent"},{"benchmark":"workspacebench","model":"gpt-5.5","score":58.7,"metric":"percent"},{"benchmark":"workspacebench","model":"claude-opus-4.7","score":55.1,"metric":"percent"},{"benchmark":"workspacebench","model":"gemini-3.1-pro","score":32.8,"metric":"percent"},{"benchmark":"workspacebench","model":"seed2.1-turbo","score":54.7,"metric":"percent"},{"benchmark":"workspacebench","model":"seed2.1-pro","score":53,"metric":"percent"},{"benchmark":"presentbench","model":"gpt-5.5","score":68.9,"metric":"percent"},{"benchmark":"presentbench","model":"claude-opus-4.7","score":61.8,"metric":"percent"},{"benchmark":"presentbench","model":"gemini-3.1-pro","score":52.1,"metric":"percent"},{"benchmark":"presentbench","model":"seed2.1-turbo","score":48.3,"metric":"percent"},{"benchmark":"presentbench","model":"seed2.1-pro","score":54.6,"metric":"percent"},{"benchmark":"onemillionbench","model":"gpt-5.5","score":69.6,"metric":"percent"},{"benchmark":"onemillionbench","model":"claude-opus-4.7","score":73,"metric":"percent"},{"benchmark":"onemillionbench","model":"gemini-3.1-pro","score":60.2,"metric":"percent"},{"benchmark":"onemillionbench","model":"seed2.1-turbo","score":66.6,"metric":"percent"},{"benchmark":"onemillionbench","model":"seed2.1-pro","score":68.8,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.5","score":62.9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"claude-opus-4.7","score":76.5,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gemini-3.1-pro","score":72.5,"metric":"percent"},{"benchmark":"officeqa-pro","model":"seed2.1-turbo","score":62.8,"metric":"percent"},{"benchmark":"officeqa-pro","model":"seed2.1-pro","score":70.9,"metric":"percent"},{"benchmark":"gdpval","model":"claude-opus-4.7","score":82.7,"metric":"percent"},{"benchmark":"gdpval","model":"seed2.1-turbo","score":82.7,"metric":"percent"},{"benchmark":"gdpval","model":"seed2.1-pro","score":87.9,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"gpt-5.5","score":65.3,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"seed2.1-turbo","score":56,"metric":"percent"},{"benchmark":"financeagent-v1.1","model":"seed2.1-pro","score":60.7,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.5","score":35.4,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-4.7","score":33.9,"metric":"percent"},{"benchmark":"apex-agents","model":"seed2.1-turbo","score":29.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gpt-5.5","score":81.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"seed2.1-turbo","score":80.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"seed2.1-pro","score":83.8,"metric":"percent"},{"benchmark":"toolathlon","model":"claude-opus-4.7","score":52.8,"metric":"percent"},{"benchmark":"toolathlon","model":"seed2.1-turbo","score":49.1,"metric":"percent"},{"benchmark":"toolathlon","model":"seed2.1-pro","score":50.6,"metric":"percent"},{"benchmark":"wildclawbench","model":"gpt-5.5","score":65.6,"metric":"percent"},{"benchmark":"wildclawbench","model":"claude-opus-4.7","score":67,"metric":"percent"},{"benchmark":"wildclawbench","model":"gemini-3.1-pro","score":61.1,"metric":"percent"},{"benchmark":"wildclawbench","model":"seed2.1-turbo","score":62.8,"metric":"percent"},{"benchmark":"wildclawbench","model":"seed2.1-pro","score":61.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"seed2.1-turbo","score":67.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"seed2.1-turbo","score":57,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"seed2.1-pro","score":57.5,"metric":"percent"},{"benchmark":"cybergym","model":"seed2.1-turbo","score":67,"metric":"percent"},{"benchmark":"cybergym","model":"seed2.1-pro","score":70.2,"metric":"percent"},{"benchmark":"nl2repo","model":"gpt-5.5","score":45.1,"metric":"percent"},{"benchmark":"nl2repo","model":"claude-opus-4.7","score":58.2,"metric":"percent"},{"benchmark":"nl2repo","model":"seed2.1-turbo","score":43.7,"metric":"percent"},{"benchmark":"deepswe","model":"gpt-5.5","score":70,"metric":"percent"},{"benchmark":"deepswe","model":"claude-opus-4.7","score":54,"metric":"percent"},{"benchmark":"deepswe","model":"gemini-3.1-pro","score":10,"metric":"percent"},{"benchmark":"deepswe","model":"seed2.1-turbo","score":23,"metric":"percent"},{"benchmark":"deepswe","model":"seed2.1-pro","score":32.7,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.5","score":25,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-4.7","score":27.4,"metric":"percent"},{"benchmark":"posttrainbench","model":"seed2.1-turbo","score":18.3,"metric":"percent"},{"benchmark":"posttrainbench","model":"seed2.1-pro","score":16.5,"metric":"percent"},{"benchmark":"frontierscience-research","model":"claude-opus-4.7","score":20,"metric":"percent"},{"benchmark":"frontierscience-research","model":"seed2.1-turbo","score":33.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"seed2.1-pro","score":28.3,"metric":"percent"},{"benchmark":"supergpqa","model":"gpt-5.5","score":72.7,"metric":"percent"},{"benchmark":"supergpqa","model":"claude-opus-4.7","score":68.5,"metric":"percent"},{"benchmark":"supergpqa","model":"gemini-3.1-pro","score":76.6,"metric":"percent"},{"benchmark":"supergpqa","model":"seed2.1-turbo","score":67.4,"metric":"percent"},{"benchmark":"supergpqa","model":"seed2.1-pro","score":70.8,"metric":"percent"},{"benchmark":"kina","model":"gpt-5.5","score":52.6,"metric":"percent"},{"benchmark":"kina","model":"claude-opus-4.7","score":46.7,"metric":"percent"},{"benchmark":"kina","model":"gemini-3.1-pro","score":53.2,"metric":"percent"},{"benchmark":"kina","model":"seed2.1-turbo","score":46.6,"metric":"percent"},{"benchmark":"kina","model":"seed2.1-pro","score":48.3,"metric":"percent"},{"benchmark":"hle-verified","model":"gpt-5.5","score":50.4,"metric":"percent"},{"benchmark":"hle-verified","model":"claude-opus-4.7","score":46.9,"metric":"percent"},{"benchmark":"hle-verified","model":"gemini-3.1-pro","score":48.2,"metric":"percent"},{"benchmark":"hle-verified","model":"seed2.1-turbo","score":42.4,"metric":"percent"},{"benchmark":"hle-verified","model":"seed2.1-pro","score":42.9,"metric":"percent"},{"benchmark":"superchem","model":"gpt-5.5","score":61.1,"metric":"percent"},{"benchmark":"superchem","model":"claude-opus-4.7","score":55,"metric":"percent"},{"benchmark":"superchem","model":"gemini-3.1-pro","score":71.4,"metric":"percent"},{"benchmark":"superchem","model":"seed2.1-turbo","score":56.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"seed2.1-turbo","score":61.3,"metric":"percent"},{"benchmark":"arc-agi-2","model":"seed2.1-pro","score":62.5,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.5","score":58.4,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.7","score":56.4,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3.1-pro","score":62.3,"metric":"percent"},{"benchmark":"scicode","model":"seed2.1-turbo","score":57.8,"metric":"percent"},{"benchmark":"scicode","model":"seed2.1-pro","score":59.8,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.5","score":69,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"claude-opus-4.7","score":69,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"seed2.1-turbo","score":76,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"seed2.1-pro","score":75,"metric":"percent"},{"benchmark":"livemathematicianbench","model":"gpt-5.5","score":50.8,"metric":"percent"},{"benchmark":"livemathematicianbench","model":"claude-opus-4.7","score":36.7,"metric":"percent"},{"benchmark":"livemathematicianbench","model":"gemini-3.1-pro","score":43.5,"metric":"percent"},{"benchmark":"livemathematicianbench","model":"seed2.1-turbo","score":27.7,"metric":"percent"},{"benchmark":"livemathematicianbench","model":"seed2.1-pro","score":20.9,"metric":"percent"},{"benchmark":"matharena-apex","model":"gpt-5.5","score":69.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"gemini-3.1-pro","score":58.9,"metric":"percent"},{"benchmark":"matharena-apex","model":"seed2.1-turbo","score":35.4,"metric":"percent"},{"benchmark":"aethercode","model":"gpt-5.5","score":81.6,"metric":"percent"},{"benchmark":"aethercode","model":"claude-opus-4.7","score":52,"metric":"percent"},{"benchmark":"aethercode","model":"gemini-3.1-pro","score":74.7,"metric":"percent"},{"benchmark":"aethercode","model":"seed2.1-turbo","score":67.9,"metric":"percent"},{"benchmark":"aethercode","model":"seed2.1-pro","score":65.8,"metric":"percent"},{"benchmark":"beyondaime","model":"gpt-5.5","score":91,"metric":"percent"},{"benchmark":"beyondaime","model":"claude-opus-4.7","score":79,"metric":"percent"},{"benchmark":"beyondaime","model":"gemini-3.1-pro","score":90,"metric":"percent"},{"benchmark":"beyondaime","model":"seed2.1-turbo","score":88,"metric":"percent"},{"benchmark":"beyondaime","model":"seed2.1-pro","score":87,"metric":"percent"},{"benchmark":"hle-with-tools","model":"seed2.1-turbo","score":54.6,"metric":"avg@3"},{"benchmark":"browsecomp","model":"seed2.1-turbo","score":84.9,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gpt-5.5","score":69.4,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gemini-3.1-pro","score":70.2,"metric":"percent"},{"benchmark":"chartqa-pro","model":"claude-opus-4.7","score":65.5,"metric":"percent"},{"benchmark":"chartqa-pro","model":"seed2.1-turbo","score":70.9,"metric":"percent"},{"benchmark":"chartqa-pro","model":"seed2.1-pro","score":70.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5.5","score":95,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-opus-4.7","score":93.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"seed2.1-turbo","score":94.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"seed2.1-pro","score":95.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.5","score":83.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.1-pro","score":83.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed2.1-turbo","score":82.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed2.1-pro","score":85.4,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5.5","score":84.2,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-3.1-pro","score":90.2,"metric":"percent"},{"benchmark":"mathvista","model":"claude-opus-4.7","score":84.4,"metric":"percent"},{"benchmark":"mathvista","model":"seed2.1-turbo","score":90.5,"metric":"percent"},{"benchmark":"mathvista","model":"seed2.1-pro","score":90.7,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.1-pro","score":89.2,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.7","score":83.1,"metric":"percent"},{"benchmark":"mathvision","model":"seed2.1-turbo","score":90.1,"metric":"percent"},{"benchmark":"mathvision","model":"seed2.1-pro","score":92.6,"metric":"percent"},{"benchmark":"dynamath","model":"gpt-5.5","score":75.9,"metric":"percent"},{"benchmark":"dynamath","model":"gemini-3.1-pro","score":72.1,"metric":"percent"},{"benchmark":"dynamath","model":"claude-opus-4.7","score":63.1,"metric":"percent"},{"benchmark":"dynamath","model":"seed2.1-turbo","score":68.1,"metric":"percent"},{"benchmark":"dynamath","model":"seed2.1-pro","score":73.1,"metric":"percent"},{"benchmark":"mathverse-vision","model":"gpt-5.5","score":84.6,"metric":"percent"},{"benchmark":"mathverse-vision","model":"gemini-3.1-pro","score":87.7,"metric":"percent"},{"benchmark":"mathverse-vision","model":"claude-opus-4.7","score":77.4,"metric":"percent"},{"benchmark":"mathverse-vision","model":"seed2.1-turbo","score":89.2,"metric":"percent"},{"benchmark":"mathverse-vision","model":"seed2.1-pro","score":89.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.7","score":74,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed2.1-turbo","score":80.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"seed2.1-pro","score":81.6,"metric":"percent"},{"benchmark":"emma","model":"gpt-5.5","score":79,"metric":"percent"},{"benchmark":"emma","model":"gemini-3.1-pro","score":72.1,"metric":"percent"},{"benchmark":"emma","model":"claude-opus-4.7","score":68.7,"metric":"percent"},{"benchmark":"emma","model":"seed2.1-turbo","score":78.4,"metric":"percent"},{"benchmark":"emma","model":"seed2.1-pro","score":79.3,"metric":"percent"},{"benchmark":"zerobench","model":"gpt-5.5","score":13,"metric":"percent"},{"benchmark":"zerobench","model":"gemini-3.1-pro","score":12,"metric":"percent"},{"benchmark":"zerobench","model":"claude-opus-4.7","score":8,"metric":"percent"},{"benchmark":"zerobench","model":"seed2.1-turbo","score":11,"metric":"percent"},{"benchmark":"zerobench","model":"seed2.1-pro","score":18,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gpt-5.5","score":41,"metric":"percent"},{"benchmark":"zerobench-sub","model":"gemini-3.1-pro","score":41.9,"metric":"percent"},{"benchmark":"zerobench-sub","model":"claude-opus-4.7","score":37.1,"metric":"percent"},{"benchmark":"zerobench-sub","model":"seed2.1-turbo","score":49.1,"metric":"percent"},{"benchmark":"zerobench-sub","model":"seed2.1-pro","score":49.4,"metric":"percent"},{"benchmark":"visulogic","model":"gpt-5.5","score":43.5,"metric":"percent"},{"benchmark":"visulogic","model":"gemini-3.1-pro","score":44.8,"metric":"percent"},{"benchmark":"visulogic","model":"claude-opus-4.7","score":32.6,"metric":"percent"},{"benchmark":"visulogic","model":"seed2.1-turbo","score":52.9,"metric":"percent"},{"benchmark":"visulogic","model":"seed2.1-pro","score":54.3,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"gpt-5.5","score":49.8,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"claude-opus-4.7","score":30.2,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"seed2.1-turbo","score":68.3,"metric":"percent"},{"benchmark":"vlmsarebiased","model":"seed2.1-pro","score":83.6,"metric":"percent"},{"benchmark":"visfactor","model":"gpt-5.5","score":56.2,"metric":"percent"},{"benchmark":"visfactor","model":"gemini-3.1-pro","score":54,"metric":"percent"},{"benchmark":"visfactor","model":"claude-opus-4.7","score":30.5,"metric":"percent"},{"benchmark":"visfactor","model":"seed2.1-turbo","score":43.9,"metric":"percent"},{"benchmark":"visfactor","model":"seed2.1-pro","score":51.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5.5","score":82.2,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-3.1-pro","score":85.4,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-opus-4.7","score":75.6,"metric":"percent"},{"benchmark":"realworldqa","model":"seed2.1-turbo","score":86.3,"metric":"percent"},{"benchmark":"realworldqa","model":"seed2.1-pro","score":86.7,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5.5","score":55.9,"metric":"percent"},{"benchmark":"babyvision","model":"claude-opus-4.7","score":22.2,"metric":"percent"},{"benchmark":"babyvision","model":"seed2.1-turbo","score":62.9,"metric":"percent"},{"benchmark":"babyvision","model":"seed2.1-pro","score":73.7,"metric":"percent"},{"benchmark":"measurebench","model":"gpt-5.5","score":49.9,"metric":"percent"},{"benchmark":"measurebench","model":"gemini-3.1-pro","score":44.4,"metric":"percent"},{"benchmark":"measurebench","model":"claude-opus-4.7","score":29.7,"metric":"percent"},{"benchmark":"measurebench","model":"seed2.1-turbo","score":58.9,"metric":"percent"},{"benchmark":"measurebench","model":"seed2.1-pro","score":62.9,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5.5","score":58.6,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3.1-pro","score":69.9,"metric":"percent"},{"benchmark":"simplevqa","model":"claude-opus-4.7","score":56.5,"metric":"percent"},{"benchmark":"simplevqa","model":"seed2.1-turbo","score":71.1,"metric":"percent"},{"benchmark":"simplevqa","model":"seed2.1-pro","score":74.5,"metric":"percent"},{"benchmark":"worldvqa","model":"gpt-5.5","score":34.6,"metric":"percent"},{"benchmark":"worldvqa","model":"gemini-3.1-pro","score":44.3,"metric":"percent"},{"benchmark":"worldvqa","model":"claude-opus-4.7","score":35.9,"metric":"percent"},{"benchmark":"worldvqa","model":"seed2.1-turbo","score":48.6,"metric":"percent"},{"benchmark":"worldvqa","model":"seed2.1-pro","score":53,"metric":"percent"},{"benchmark":"worldbench","model":"gpt-5.5","score":58.4,"metric":"percent"},{"benchmark":"worldbench","model":"gemini-3.1-pro","score":62.9,"metric":"percent"},{"benchmark":"worldbench","model":"claude-opus-4.7","score":52.9,"metric":"percent"},{"benchmark":"worldbench","model":"seed2.1-turbo","score":63.7,"metric":"percent"},{"benchmark":"worldbench","model":"seed2.1-pro","score":67.6,"metric":"percent"},{"benchmark":"blink","model":"gpt-5.5","score":78.3,"metric":"percent"},{"benchmark":"blink","model":"gemini-3.1-pro","score":79.1,"metric":"percent"},{"benchmark":"blink","model":"claude-opus-4.7","score":70.4,"metric":"percent"},{"benchmark":"blink","model":"seed2.1-turbo","score":79.4,"metric":"percent"},{"benchmark":"blink","model":"seed2.1-pro","score":81.4,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"gpt-5.5","score":36,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"gemini-3.1-pro","score":27.4,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"claude-opus-4.7","score":17.4,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"seed2.1-turbo","score":31.4,"metric":"percent"},{"benchmark":"mmsibench-circular","model":"seed2.1-pro","score":35.9,"metric":"percent"},{"benchmark":"treebench","model":"gpt-5.5","score":61.5,"metric":"percent"},{"benchmark":"treebench","model":"gemini-3.1-pro","score":60.5,"metric":"percent"},{"benchmark":"treebench","model":"claude-opus-4.7","score":36.8,"metric":"percent"},{"benchmark":"treebench","model":"seed2.1-turbo","score":71.1,"metric":"percent"},{"benchmark":"treebench","model":"seed2.1-pro","score":71.1,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.5","score":64.5,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-4.7","score":52.5,"metric":"percent"},{"benchmark":"erqa","model":"seed2.1-turbo","score":71.3,"metric":"percent"},{"benchmark":"erqa","model":"seed2.1-pro","score":72,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-5.5","score":81.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-3.1-pro","score":84.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"claude-opus-4.7","score":77.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"seed2.1-turbo","score":82.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"seed2.1-pro","score":83.4,"metric":"percent"},{"benchmark":"dude","model":"gpt-5.5","score":81.7,"metric":"percent"},{"benchmark":"dude","model":"gemini-3.1-pro","score":82.1,"metric":"percent"},{"benchmark":"dude","model":"claude-opus-4.7","score":84.5,"metric":"percent"},{"benchmark":"dude","model":"seed2.1-turbo","score":83.1,"metric":"percent"},{"benchmark":"dude","model":"seed2.1-pro","score":82.8,"metric":"percent"},{"benchmark":"mmlongbench-128k","model":"gemini-3.1-pro","score":70.7,"metric":"percent"},{"benchmark":"mmlongbench-128k","model":"seed2.1-turbo","score":76.9,"metric":"percent"},{"benchmark":"mmlongbench-128k","model":"seed2.1-pro","score":78.3,"metric":"percent"},{"benchmark":"videosimpleqa","model":"gemini-3.1-pro","score":70,"metric":"percent"},{"benchmark":"videosimpleqa","model":"gemini-3.5-flash","score":76,"metric":"percent"},{"benchmark":"videosimpleqa","model":"seed2.1-turbo","score":71.4,"metric":"percent"},{"benchmark":"videosimpleqa","model":"seed2.1-pro","score":76.4,"metric":"percent"},{"benchmark":"videoholmes","model":"gemini-3.1-pro","score":65.9,"metric":"percent"},{"benchmark":"videoholmes","model":"gemini-3.5-flash","score":67.1,"metric":"percent"},{"benchmark":"videoholmes","model":"seed2.1-turbo","score":67.6,"metric":"percent"},{"benchmark":"videoholmes","model":"seed2.1-pro","score":68.2,"metric":"percent"},{"benchmark":"minerva-video","model":"gemini-3.1-pro","score":63.5,"metric":"percent"},{"benchmark":"minerva-video","model":"gemini-3.5-flash","score":68.6,"metric":"percent"},{"benchmark":"minerva-video","model":"seed2.1-turbo","score":65.9,"metric":"percent"},{"benchmark":"minerva-video","model":"seed2.1-pro","score":70.7,"metric":"percent"},{"benchmark":"tvbench","model":"gemini-3.1-pro","score":71,"metric":"percent"},{"benchmark":"tvbench","model":"gemini-3.5-flash","score":76.4,"metric":"percent"},{"benchmark":"tvbench","model":"seed2.1-turbo","score":77.2,"metric":"percent"},{"benchmark":"tvbench","model":"seed2.1-pro","score":80.5,"metric":"percent"},{"benchmark":"tomato","model":"gemini-3.1-pro","score":60.4,"metric":"percent"},{"benchmark":"tomato","model":"gemini-3.5-flash","score":71.9,"metric":"percent"},{"benchmark":"tomato","model":"seed2.1-turbo","score":56.8,"metric":"percent"},{"benchmark":"tomato","model":"seed2.1-pro","score":79.5,"metric":"percent"},{"benchmark":"motionbench","model":"gemini-3.1-pro","score":69.9,"metric":"percent"},{"benchmark":"motionbench","model":"gemini-3.5-flash","score":70.6,"metric":"percent"},{"benchmark":"motionbench","model":"seed2.1-turbo","score":74.8,"metric":"percent"},{"benchmark":"motionbench","model":"seed2.1-pro","score":74.9,"metric":"percent"},{"benchmark":"contphy","model":"gemini-3.1-pro","score":64.5,"metric":"percent"},{"benchmark":"contphy","model":"gemini-3.5-flash","score":63.8,"metric":"percent"},{"benchmark":"contphy","model":"seed2.1-turbo","score":61.1,"metric":"percent"},{"benchmark":"contphy","model":"seed2.1-pro","score":63.6,"metric":"percent"},{"benchmark":"videomme","model":"gemini-3.1-pro","score":86.7,"metric":"percent"},{"benchmark":"videomme","model":"gemini-3.5-flash","score":87.2,"metric":"percent"},{"benchmark":"videomme","model":"seed2.1-turbo","score":89,"metric":"percent"},{"benchmark":"videomme","model":"seed2.1-pro","score":89.2,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3.1-pro","score":66.2,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-3.5-flash","score":76.3,"metric":"percent"},{"benchmark":"lvbench","model":"seed2.1-turbo","score":76.8,"metric":"percent"},{"benchmark":"lvbench","model":"seed2.1-pro","score":78,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-3.1-pro","score":76.5,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-3.5-flash","score":77.6,"metric":"percent"},{"benchmark":"longvideobench","model":"seed2.1-turbo","score":80.6,"metric":"percent"},{"benchmark":"longvideobench","model":"seed2.1-pro","score":80.6,"metric":"percent"},{"benchmark":"crossvid","model":"gemini-3.1-pro","score":48.8,"metric":"percent"},{"benchmark":"crossvid","model":"gemini-3.5-flash","score":58.6,"metric":"percent"},{"benchmark":"crossvid","model":"seed2.1-turbo","score":63.2,"metric":"percent"},{"benchmark":"crossvid","model":"seed2.1-pro","score":65,"metric":"percent"},{"benchmark":"livesports-3k","model":"gemini-3.1-pro","score":89,"metric":"percent"},{"benchmark":"livesports-3k","model":"gemini-3.5-flash","score":86.5,"metric":"percent"},{"benchmark":"livesports-3k","model":"seed2.1-turbo","score":77.1,"metric":"percent"},{"benchmark":"livesports-3k","model":"seed2.1-pro","score":76.8,"metric":"percent"},{"benchmark":"ovobench","model":"gemini-3.1-pro","score":64.1,"metric":"percent"},{"benchmark":"ovobench","model":"gemini-3.5-flash","score":64.5,"metric":"percent"},{"benchmark":"ovobench","model":"seed2.1-turbo","score":79.2,"metric":"percent"},{"benchmark":"ovobench","model":"seed2.1-pro","score":80.7,"metric":"percent"},{"benchmark":"ovbench","model":"gemini-3.1-pro","score":58.8,"metric":"percent"},{"benchmark":"ovbench","model":"gemini-3.5-flash","score":56.5,"metric":"percent"},{"benchmark":"ovbench","model":"seed2.1-turbo","score":69.7,"metric":"percent"},{"benchmark":"ovbench","model":"seed2.1-pro","score":70,"metric":"percent"},{"benchmark":"imo-2025","model":"seed2.1-pro","score":65.2,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"seed2.1-pro","score":54.3,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gemini-3.1-pro","score":49,"metric":"percent"},{"benchmark":"infovqa","model":"penguin-vl-8b","score":86.8,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-8b","score":79.1,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-5-nano","score":49.2,"metric":"percent"},{"benchmark":"chartqa","model":"penguin-vl-8b","score":90.5,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5-nano","score":48.6,"metric":"percent"},{"benchmark":"docvqa","model":"penguin-vl-8b","score":96.2,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5-nano","score":78.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"penguin-vl-8b","score":75.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3.5-8b","score":72.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5-nano","score":64.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"penguin-vl-8b","score":40,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3.5-8b","score":44.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5-nano","score":31.7,"metric":"percent"},{"benchmark":"ocrbench","model":"penguin-vl-8b","score":85.2,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3.5-8b","score":84,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5-nano","score":70.1,"metric":"percent"},{"benchmark":"ai2d","model":"penguin-vl-8b","score":86.1,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-nano","score":65.7,"metric":"percent"},{"benchmark":"realworldqa","model":"penguin-vl-8b","score":75.8,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5-nano","score":60.7,"metric":"percent"},{"benchmark":"v-star","model":"penguin-vl-8b","score":90.2,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-8b-instruct","score":90.1,"metric":"percent"},{"benchmark":"v-star","model":"internvl3.5-8b","score":70.7,"metric":"percent"},{"benchmark":"v-star","model":"gpt-5-nano","score":63.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"penguin-vl-8b","score":40.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl3.5-8b","score":39.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-nano","score":36.5,"metric":"percent"},{"benchmark":"blink","model":"penguin-vl-8b","score":58.2,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-nano","score":42.2,"metric":"percent"},{"benchmark":"mathvista","model":"penguin-vl-8b","score":77.4,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3.5-8b","score":74.2,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5-nano","score":40.9,"metric":"percent"},{"benchmark":"mathverse","model":"penguin-vl-8b","score":50.8,"metric":"percent"},{"benchmark":"mathverse","model":"qwen3-vl-8b-instruct","score":62.1,"metric":"percent"},{"benchmark":"mathverse","model":"internvl3.5-8b","score":55.8,"metric":"percent"},{"benchmark":"mathverse","model":"gpt-5-nano","score":27,"metric":"percent"},{"benchmark":"logicvista","model":"penguin-vl-8b","score":53.8,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3-vl-8b-instruct","score":55.3,"metric":"percent"},{"benchmark":"logicvista","model":"internvl3.5-8b","score":57.3,"metric":"percent"},{"benchmark":"logicvista","model":"gpt-5-nano","score":40.5,"metric":"percent"},{"benchmark":"mvbench","model":"penguin-vl-8b","score":71.7,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-5-nano","score":52.9,"metric":"percent"},{"benchmark":"longvideobench","model":"penguin-vl-8b","score":67,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-vl-8b-instruct","score":62.6,"metric":"percent"},{"benchmark":"longvideobench","model":"gpt-5-nano","score":38.1,"metric":"percent"},{"benchmark":"videomme","model":"penguin-vl-8b","score":66.2,"metric":"percent"},{"benchmark":"videomme","model":"qwen3-vl-8b-instruct","score":71.4,"metric":"percent"},{"benchmark":"videomme","model":"internvl3.5-8b","score":66,"metric":"percent"},{"benchmark":"videomme","model":"gpt-5-nano","score":49.4,"metric":"percent"},{"benchmark":"egoschema","model":"penguin-vl-8b","score":67,"metric":"percent"},{"benchmark":"egoschema","model":"qwen3-vl-8b-instruct","score":70.2,"metric":"percent"},{"benchmark":"egoschema","model":"internvl3.5-8b","score":61,"metric":"percent"},{"benchmark":"egoschema","model":"gpt-5-nano","score":34.8,"metric":"percent"},{"benchmark":"mmvu","model":"penguin-vl-8b","score":53.9,"metric":"percent"},{"benchmark":"mmvu","model":"internvl3.5-8b","score":51.5,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5-nano","score":51,"metric":"percent"},{"benchmark":"charades-sta","model":"penguin-vl-8b","score":61.4,"metric":"percent"},{"benchmark":"charades-sta","model":"internvl3.5-8b","score":32.8,"metric":"percent"},{"benchmark":"charades-sta","model":"gpt-5-nano","score":5,"metric":"percent"},{"benchmark":"infovqa","model":"penguin-vl-2b","score":77.8,"metric":"percent"},{"benchmark":"infovqa","model":"gemma-3n-e2b-it","score":51.9,"metric":"percent"},{"benchmark":"infovqa","model":"smolvlm2-2.2b","score":43,"metric":"percent"},{"benchmark":"chartqa","model":"penguin-vl-2b","score":86.6,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-2b-instruct","score":76.9,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-3n-e2b-it","score":65.8,"metric":"percent"},{"benchmark":"chartqa","model":"smolvlm2-2.2b","score":68.7,"metric":"percent"},{"benchmark":"docvqa","model":"penguin-vl-2b","score":94.1,"metric":"percent"},{"benchmark":"docvqa","model":"gemma-3n-e2b-it","score":78.4,"metric":"percent"},{"benchmark":"docvqa","model":"smolvlm2-2.2b","score":80,"metric":"percent"},{"benchmark":"charxiv-dq","model":"penguin-vl-2b","score":66.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemma-3n-e2b-it","score":60.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"smolvlm2-2.2b","score":36.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"penguin-vl-2b","score":35.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemma-3n-e2b-it","score":27,"metric":"percent"},{"benchmark":"charxiv-rq","model":"smolvlm2-2.2b","score":15.5,"metric":"percent"},{"benchmark":"ocrbench","model":"penguin-vl-2b","score":81,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-3n-e2b-it","score":70,"metric":"percent"},{"benchmark":"ocrbench","model":"smolvlm2-2.2b","score":72.9,"metric":"percent"},{"benchmark":"ai2d","model":"penguin-vl-2b","score":80.7,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-3n-e2b-it","score":74.6,"metric":"percent"},{"benchmark":"ai2d","model":"smolvlm2-2.2b","score":70,"metric":"percent"},{"benchmark":"realworldqa","model":"penguin-vl-2b","score":70.2,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-3n-e2b-it","score":59.9,"metric":"percent"},{"benchmark":"realworldqa","model":"smolvlm2-2.2b","score":58.3,"metric":"percent"},{"benchmark":"v-star","model":"penguin-vl-2b","score":83.8,"metric":"percent"},{"benchmark":"v-star","model":"internvl3.5-2b","score":69.1,"metric":"percent"},{"benchmark":"v-star","model":"gemma-3n-e2b-it","score":46,"metric":"percent"},{"benchmark":"v-star","model":"smolvlm2-2.2b","score":51.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"penguin-vl-2b","score":31.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl3.5-2b","score":31.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-3n-e2b-it","score":28,"metric":"percent"},{"benchmark":"mmmu-pro","model":"smolvlm2-2.2b","score":20.1,"metric":"percent"},{"benchmark":"blink","model":"penguin-vl-2b","score":51.7,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-2b","score":36.6,"metric":"percent"},{"benchmark":"blink","model":"gemma-3n-e2b-it","score":44.1,"metric":"percent"},{"benchmark":"blink","model":"smolvlm2-2.2b","score":44,"metric":"percent"},{"benchmark":"mathvista","model":"penguin-vl-2b","score":67.3,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-2b-instruct","score":61.3,"metric":"percent"},{"benchmark":"mathvista","model":"internvl3.5-2b","score":60.8,"metric":"percent"},{"benchmark":"mathvista","model":"gemma-3n-e2b-it","score":50.4,"metric":"percent"},{"benchmark":"mathverse","model":"penguin-vl-2b","score":35.9,"metric":"percent"},{"benchmark":"mathverse","model":"qwen3-vl-2b-instruct","score":52.1,"metric":"percent"},{"benchmark":"mathverse","model":"internvl3.5-2b","score":39.6,"metric":"percent"},{"benchmark":"mathverse","model":"gemma-3n-e2b-it","score":22.5,"metric":"percent"},{"benchmark":"mathverse","model":"smolvlm2-2.2b","score":21.5,"metric":"percent"},{"benchmark":"logicvista","model":"penguin-vl-2b","score":41.3,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3-vl-2b-instruct","score":35.8,"metric":"percent"},{"benchmark":"logicvista","model":"internvl3.5-2b","score":47.7,"metric":"percent"},{"benchmark":"logicvista","model":"gemma-3n-e2b-it","score":33.9,"metric":"percent"},{"benchmark":"logicvista","model":"smolvlm2-2.2b","score":24.8,"metric":"percent"},{"benchmark":"mvbench","model":"penguin-vl-2b","score":65.5,"metric":"percent"},{"benchmark":"mvbench","model":"internvl3.5-2b","score":65.9,"metric":"percent"},{"benchmark":"mvbench","model":"gemma-3n-e2b-it","score":46.8,"metric":"percent"},{"benchmark":"mvbench","model":"smolvlm2-2.2b","score":46.3,"metric":"percent"},{"benchmark":"longvideobench","model":"penguin-vl-2b","score":59.5,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-vl-2b-instruct","score":52.1,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl3.5-2b","score":57.4,"metric":"percent"},{"benchmark":"longvideobench","model":"gemma-3n-e2b-it","score":43,"metric":"percent"},{"benchmark":"longvideobench","model":"smolvlm2-2.2b","score":49.7,"metric":"percent"},{"benchmark":"videomme","model":"penguin-vl-2b","score":57.4,"metric":"percent"},{"benchmark":"videomme","model":"qwen3-vl-2b-instruct","score":61.9,"metric":"percent"},{"benchmark":"videomme","model":"internvl3.5-2b","score":58.4,"metric":"percent"},{"benchmark":"videomme","model":"gemma-3n-e2b-it","score":47,"metric":"percent"},{"benchmark":"videomme","model":"smolvlm2-2.2b","score":52.1,"metric":"percent"},{"benchmark":"egoschema","model":"penguin-vl-2b","score":57.6,"metric":"percent"},{"benchmark":"egoschema","model":"qwen3-vl-2b-instruct","score":55.7,"metric":"percent"},{"benchmark":"egoschema","model":"internvl3.5-2b","score":50.5,"metric":"percent"},{"benchmark":"egoschema","model":"gemma-3n-e2b-it","score":48,"metric":"percent"},{"benchmark":"egoschema","model":"smolvlm2-2.2b","score":34,"metric":"percent"},{"benchmark":"mmvu","model":"penguin-vl-2b","score":42.7,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3-vl-2b-instruct","score":41.7,"metric":"percent"},{"benchmark":"mmvu","model":"internvl3.5-2b","score":42.7,"metric":"percent"},{"benchmark":"mmvu","model":"gemma-3n-e2b-it","score":34.5,"metric":"percent"},{"benchmark":"mmvu","model":"smolvlm2-2.2b","score":33.5,"metric":"percent"},{"benchmark":"charades-sta","model":"penguin-vl-2b","score":56.2,"metric":"percent"},{"benchmark":"charades-sta","model":"internvl3.5-2b","score":21.9,"metric":"percent"},{"benchmark":"charades-sta","model":"gemma-3n-e2b-it","score":5.5,"metric":"percent"},{"benchmark":"charades-sta","model":"smolvlm2-2.2b","score":9.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen3-vl-8b-instruct","score":84.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen3-vl-4b-instruct","score":83.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"youtu-vl-4b-instruct","score":83.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-vl-8b-instruct","score":84.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3.5-4b","score":80.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-vl-4b-instruct","score":83.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"youtu-vl-4b-instruct","score":83.9,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-4b","score":65,"metric":"percent"},{"benchmark":"mmstar","model":"youtu-vl-4b-instruct","score":71.1,"metric":"percent"},{"benchmark":"scienceqa","model":"qwen3-vl-4b-instruct","score":94.7,"metric":"percent"},{"benchmark":"scienceqa","model":"youtu-vl-4b-instruct","score":97,"metric":"percent"},{"benchmark":"seedbench","model":"qwen3-vl-4b-instruct","score":77,"metric":"percent"},{"benchmark":"seedbench","model":"youtu-vl-4b-instruct","score":76.9,"metric":"percent"},{"benchmark":"mmvet","model":"qwen3-vl-4b-instruct","score":68.3,"metric":"percent"},{"benchmark":"mmvet","model":"youtu-vl-4b-instruct","score":64.6,"metric":"percent"},{"benchmark":"visulogic","model":"qwen3-vl-8b-instruct","score":22.5,"metric":"percent"},{"benchmark":"visulogic","model":"qwen3-vl-4b-instruct","score":19,"metric":"percent"},{"benchmark":"visulogic","model":"youtu-vl-4b-instruct","score":25.7,"metric":"percent"},{"benchmark":"mmmu","model":"youtu-vl-4b-instruct","score":61.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"youtu-vl-4b-instruct","score":43,"metric":"percent"},{"benchmark":"mathvista-mini","model":"youtu-vl-4b-instruct","score":76.5,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl3.5-4b","score":45.8,"metric":"percent"},{"benchmark":"mathverse-mini","model":"youtu-vl-4b-instruct","score":56.5,"metric":"percent"},{"benchmark":"logicvista","model":"internvl3.5-4b","score":41.8,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3-vl-4b-instruct","score":53.2,"metric":"percent"},{"benchmark":"logicvista","model":"youtu-vl-4b-instruct","score":52.4,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3-vl-8b-instruct","score":74,"metric":"percent"},{"benchmark":"vlmsareblind","model":"qwen3-vl-4b-instruct","score":71.9,"metric":"percent"},{"benchmark":"vlmsareblind","model":"youtu-vl-4b-instruct","score":88.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl3.5-4b","score":44.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"youtu-vl-4b-instruct","score":59.1,"metric":"percent"},{"benchmark":"pope","model":"qwen3-vl-4b-instruct","score":89.3,"metric":"percent"},{"benchmark":"pope","model":"youtu-vl-4b-instruct","score":86.4,"metric":"percent"},{"benchmark":"ai2d","model":"youtu-vl-4b-instruct","score":85.6,"metric":"percent"},{"benchmark":"infovqa","model":"youtu-vl-4b-instruct","score":79.1,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-4b-instruct","score":80.8,"metric":"percent"},{"benchmark":"textvqa","model":"youtu-vl-4b-instruct","score":79.6,"metric":"percent"},{"benchmark":"docvqa","model":"youtu-vl-4b-instruct","score":94.4,"metric":"percent"},{"benchmark":"chartqa","model":"youtu-vl-4b-instruct","score":85.3,"metric":"percent"},{"benchmark":"ocrbench","model":"youtu-vl-4b-instruct","score":81.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3.5-4b","score":71.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"youtu-vl-4b-instruct","score":79.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"youtu-vl-4b-instruct","score":43.8,"metric":"percent"},{"benchmark":"blink","model":"youtu-vl-4b-instruct","score":64.3,"metric":"percent"},{"benchmark":"realworldqa","model":"youtu-vl-4b-instruct","score":74.6,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen3-vl-4b-instruct","score":63,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"youtu-vl-4b-instruct","score":61.5,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"internvl3.5-4b","score":59.8,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"qwen3-vl-4b-instruct","score":61.3,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"youtu-vl-4b-instruct","score":63.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"youtu-vl-4b-instruct","score":59.6,"metric":"percent"},{"benchmark":"osworld","model":"youtu-vl-4b-instruct","score":38.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"youtu-vl-4b-instruct","score":56.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"youtu-vl-4b-instruct","score":76.8,"metric":"percent"},{"benchmark":"c-eval","model":"internvl3.5-4b","score":71.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-vl-4b-instruct","score":76.5,"metric":"percent"},{"benchmark":"c-eval","model":"youtu-vl-4b-instruct","score":69.1,"metric":"percent"},{"benchmark":"musr","model":"qwen3-vl-4b-instruct","score":46.6,"metric":"percent"},{"benchmark":"musr","model":"youtu-vl-4b-instruct","score":58.3,"metric":"percent"},{"benchmark":"ifeval","model":"youtu-vl-4b-instruct","score":76.9,"metric":"percent"},{"benchmark":"drop","model":"qwen3-vl-4b-instruct","score":85,"metric":"percent"},{"benchmark":"drop","model":"youtu-vl-4b-instruct","score":79.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-vl-4b-instruct","score":84.8,"metric":"percent"},{"benchmark":"bbh","model":"youtu-vl-4b-instruct","score":71.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-vl-4b-instruct","score":42.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"youtu-vl-4b-instruct","score":39.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"ui-mate-27b","score":77,"metric":"percent"},{"benchmark":"osworld-verified","model":"ui-mate-9b","score":66.2,"metric":"percent"},{"benchmark":"cv-bench","model":"hy-embodied-0.5-mot-2b","score":89.2,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-2b-instruct","score":80,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-4b-instruct","score":85.7,"metric":"percent"},{"benchmark":"cv-bench","model":"robobrain-2.5-4b","score":86.9,"metric":"percent"},{"benchmark":"cv-bench","model":"mimo-embodied-7b","score":88.8,"metric":"percent"},{"benchmark":"da-2k","model":"hy-embodied-0.5-mot-2b","score":92.3,"metric":"percent"},{"benchmark":"da-2k","model":"qwen3-vl-2b-instruct","score":69.5,"metric":"percent"},{"benchmark":"da-2k","model":"qwen3-vl-4b-instruct","score":76.5,"metric":"percent"},{"benchmark":"da-2k","model":"robobrain-2.5-4b","score":79.4,"metric":"percent"},{"benchmark":"da-2k","model":"mimo-embodied-7b","score":72.2,"metric":"percent"},{"benchmark":"erqa","model":"hy-embodied-0.5-mot-2b","score":54.5,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-2b-instruct","score":41.8,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-4b-instruct","score":47.3,"metric":"percent"},{"benchmark":"erqa","model":"robobrain-2.5-4b","score":43.3,"metric":"percent"},{"benchmark":"erqa","model":"mimo-embodied-7b","score":46.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"hy-embodied-0.5-mot-2b","score":82.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-2b-instruct","score":75.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-4b-instruct","score":80.7,"metric":"percent"},{"benchmark":"embspatialbench","model":"robobrain-2.5-4b","score":73.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"mimo-embodied-7b","score":76.2,"metric":"percent"},{"benchmark":"robospatialhome","model":"hy-embodied-0.5-mot-2b","score":55.7,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-2b-instruct","score":45.3,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-4b-instruct","score":63.2,"metric":"percent"},{"benchmark":"robospatialhome","model":"robobrain-2.5-4b","score":62.3,"metric":"percent"},{"benchmark":"robospatialhome","model":"mimo-embodied-7b","score":61.8,"metric":"percent"},{"benchmark":"all-angles-bench","model":"hy-embodied-0.5-mot-2b","score":55.1,"metric":"percent"},{"benchmark":"all-angles-bench","model":"qwen3-vl-2b-instruct","score":42.3,"metric":"percent"},{"benchmark":"all-angles-bench","model":"qwen3-vl-4b-instruct","score":46.7,"metric":"percent"},{"benchmark":"all-angles-bench","model":"robobrain-2.5-4b","score":43.8,"metric":"percent"},{"benchmark":"all-angles-bench","model":"mimo-embodied-7b","score":49,"metric":"percent"},{"benchmark":"mindcube","model":"hy-embodied-0.5-mot-2b","score":66.3,"metric":"percent"},{"benchmark":"mindcube","model":"qwen3-vl-2b-instruct","score":28.4,"metric":"percent"},{"benchmark":"mindcube","model":"qwen3-vl-4b-instruct","score":31,"metric":"percent"},{"benchmark":"mindcube","model":"robobrain-2.5-4b","score":26.9,"metric":"percent"},{"benchmark":"mindcube","model":"mimo-embodied-7b","score":36.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"hy-embodied-0.5-mot-2b","score":45.8,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-2b-instruct","score":28.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-4b-instruct","score":45.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"robobrain-2.5-4b","score":56,"metric":"percent"},{"benchmark":"refspatialbench","model":"mimo-embodied-7b","score":48,"metric":"percent"},{"benchmark":"vsi-bench","model":"hy-embodied-0.5-mot-2b","score":60.5,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-2b-instruct","score":48,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-4b-instruct","score":55.2,"metric":"percent"},{"benchmark":"vsi-bench","model":"robobrain-2.5-4b","score":41.7,"metric":"percent"},{"benchmark":"vsi-bench","model":"mimo-embodied-7b","score":48.5,"metric":"percent"},{"benchmark":"blink","model":"hy-embodied-0.5-mot-2b","score":82.7,"metric":"percent"},{"benchmark":"blink","model":"qwen3.6-35b-a3b","score":87.9,"metric":"percent"},{"benchmark":"blink","model":"hy-embodied-vlm-1.0","score":87.3,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3.6-35b-a3b","score":88.6,"metric":"percent"},{"benchmark":"cv-bench","model":"hy-embodied-vlm-1.0","score":89.7,"metric":"percent"},{"benchmark":"all-angles-bench","model":"qwen3.6-35b-a3b","score":64,"metric":"percent"},{"benchmark":"all-angles-bench","model":"hy-embodied-vlm-1.0","score":63.4,"metric":"percent"},{"benchmark":"da-2k","model":"qwen3.6-35b-a3b","score":81.4,"metric":"percent"},{"benchmark":"da-2k","model":"hy-embodied-vlm-1.0","score":83.2,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.6-35b-a3b","score":57.5,"metric":"percent"},{"benchmark":"erqa","model":"hy-embodied-vlm-1.0","score":60.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.6-35b-a3b","score":83.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"hy-embodied-vlm-1.0","score":82.7,"metric":"percent"},{"benchmark":"mindcube","model":"qwen3.6-35b-a3b","score":55,"metric":"percent"},{"benchmark":"mindcube","model":"hy-embodied-vlm-1.0","score":70,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.6-35b-a3b","score":53.1,"metric":"percent"},{"benchmark":"refspatialbench","model":"hy-embodied-vlm-1.0","score":53.4,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3.6-35b-a3b","score":70.9,"metric":"percent"},{"benchmark":"robospatialhome","model":"hy-embodied-vlm-1.0","score":69.4,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3.6-35b-a3b","score":57.5,"metric":"percent"},{"benchmark":"vsi-bench","model":"hy-embodied-vlm-1.0","score":58.9,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-7b-instruct","score":40.9,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b-instruct","score":54,"metric":"percent"},{"benchmark":"bigcodebench","model":"codellama-7b-instruct","score":25.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-7b-instruct","score":4.1,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"codellama-7b-instruct","score":3.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-6.7b-instruct","score":43.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-6.7b-instruct","score":15.5,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"deepseek-coder-6.7b-instruct","score":9.6,"metric":"percent"},{"benchmark":"mbpp","model":"codeqwen1.5-7b-chat","score":77.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"codeqwen1.5-7b-chat","score":43.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codeqwen1.5-7b-chat","score":15.5,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"codeqwen1.5-7b-chat","score":3,"metric":"percent"},{"benchmark":"humaneval","model":"yi-coder-9b-chat","score":82.3,"metric":"percent"},{"benchmark":"mbpp","model":"yi-coder-9b-chat","score":82,"metric":"percent"},{"benchmark":"bigcodebench","model":"yi-coder-9b-chat","score":49,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"yi-coder-9b-chat","score":17.6,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"yi-coder-9b-chat","score":17.5,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-8b-instruct","score":68.3,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-8b-instruct","score":70.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"llama-3.1-8b-instruct","score":40.5,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"llama-3.1-8b-instruct","score":11.5,"metric":"percent"},{"benchmark":"humaneval","model":"opencoder-8b-instruct","score":83.5,"metric":"percent"},{"benchmark":"mbpp","model":"opencoder-8b-instruct","score":79.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"opencoder-8b-instruct","score":50.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"opencoder-8b-instruct","score":18.9,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"opencoder-8b-instruct","score":17.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-7b-instruct","score":88.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-7b-instruct","score":83.5,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-7b-instruct","score":48.8,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"qwen2.5-coder-7b-instruct","score":17.3,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-8b","score":77,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen3-8b","score":51.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen3-8b","score":23,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"qwen3-8b","score":23.5,"metric":"percent"},{"benchmark":"humaneval","model":"seed-coder-8b-instruct","score":84.8,"metric":"percent"},{"benchmark":"mbpp","model":"seed-coder-8b-instruct","score":85.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"seed-coder-8b-instruct","score":53.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"seed-coder-8b-instruct","score":26.4,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"seed-coder-8b-instruct","score":24.7,"metric":"percent"},{"benchmark":"humaneval","model":"stable-diffcoder-8b-instruct","score":86.6,"metric":"percent"},{"benchmark":"mbpp","model":"stable-diffcoder-8b-instruct","score":85.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"stable-diffcoder-8b-instruct","score":54.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"stable-diffcoder-8b-instruct","score":31.8,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"stable-diffcoder-8b-instruct","score":23.5,"metric":"percent"},{"benchmark":"humaneval","model":"llada-8b-instruct","score":49.4,"metric":"percent"},{"benchmark":"mbpp","model":"llada-8b-instruct","score":41,"metric":"percent"},{"benchmark":"bigcodebench","model":"llada-8b-instruct","score":16.5,"metric":"pass@1"},{"benchmark":"humaneval","model":"dream-7b-instruct","score":63.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"dream-7b-instruct","score":10.6,"metric":"pass@1"},{"benchmark":"humaneval","model":"wedlm-8b-instruct","score":80.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"wedlm-8b-instruct","score":73.8,"metric":"percent"},{"benchmark":"mbpp","model":"wedlm-8b-instruct","score":70.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"stable-diffcoder-8b-instruct","score":82.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"stable-diffcoder-8b-instruct","score":72.8,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-6.7b-base","score":70.2,"metric":"percent"},{"benchmark":"multipl-e","model":"deepseek-coder-6.7b-base","score":44.7,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-6.7b-base","score":41,"metric":"percent"},{"benchmark":"humaneval","model":"seed-coder-8b-base","score":77.4,"metric":"percent"},{"benchmark":"mbpp","model":"seed-coder-8b-base","score":82,"metric":"percent"},{"benchmark":"multipl-e","model":"seed-coder-8b-base","score":67.6,"metric":"percent"},{"benchmark":"crux-o","model":"seed-coder-8b-base","score":54.8,"metric":"percent"},{"benchmark":"humaneval","model":"stable-diffcoder-8b-base","score":79.3,"metric":"percent"},{"benchmark":"mbpp","model":"stable-diffcoder-8b-base","score":83.6,"metric":"percent"},{"benchmark":"multipl-e","model":"stable-diffcoder-8b-base","score":71.2,"metric":"percent"},{"benchmark":"crux-o","model":"stable-diffcoder-8b-base","score":60,"metric":"percent"},{"benchmark":"humaneval","model":"fast-dllm-v2-7b","score":43.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"fast-dllm-v2-7b","score":40.2,"metric":"percent"},{"benchmark":"mbpp","model":"fast-dllm-v2-7b","score":50,"metric":"percent"},{"benchmark":"mbpp-plus","model":"fast-dllm-v2-7b","score":41.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"fast-dllm-v2-7b","score":49,"metric":"pass@1"},{"benchmark":"humaneval","model":"sdar-8b-chat","score":78.7,"metric":"percent"},{"benchmark":"mbpp","model":"sdar-8b-chat","score":72,"metric":"percent"},{"benchmark":"cl-bench","model":"openpangu-2.0-pro-thinking","score":19.7,"metric":"percent"},{"benchmark":"cl-bench","model":"openpangu-2.0-pro","score":17.8,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-2.0-pro-thinking","score":94.5,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-2.0-pro","score":90.4,"metric":"percent"},{"benchmark":"ifbench","model":"openpangu-2.0-pro-thinking","score":79.9,"metric":"percent"},{"benchmark":"ifbench","model":"openpangu-2.0-pro","score":59.5,"metric":"percent"},{"benchmark":"agentif","model":"openpangu-2.0-pro-thinking","score":44.4,"metric":"percent"},{"benchmark":"agentif","model":"openpangu-2.0-pro","score":42.2,"metric":"percent"},{"benchmark":"sysbench","model":"openpangu-2.0-pro-thinking","score":90.8,"metric":"percent"},{"benchmark":"sysbench","model":"openpangu-2.0-pro","score":82.6,"metric":"percent"},{"benchmark":"multichallenge","model":"openpangu-2.0-pro-thinking","score":62.9,"metric":"percent"},{"benchmark":"multichallenge","model":"openpangu-2.0-pro","score":52.2,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"openpangu-2.0-pro-thinking","score":34.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"openpangu-2.0-pro","score":27.1,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"openpangu-2.0-pro-thinking","score":74.2,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"openpangu-2.0-pro","score":75.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"openpangu-2.0-pro-thinking","score":86.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"openpangu-2.0-pro","score":63.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"openpangu-2.0-pro-thinking","score":95.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"openpangu-2.0-pro","score":87.3,"metric":"percent"},{"benchmark":"matharena-apex","model":"openpangu-2.0-pro-thinking","score":17.7,"metric":"percent"},{"benchmark":"matharena-apex","model":"openpangu-2.0-pro","score":2.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"openpangu-2.0-pro-thinking","score":84.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"openpangu-2.0-pro","score":60.8,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"openpangu-2.0-pro-thinking","score":69.7,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"openpangu-2.0-pro","score":55,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-2.0-pro-thinking","score":87.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-2.0-pro","score":81.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"openpangu-2.0-pro-thinking","score":27.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"openpangu-2.0-pro","score":9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"openpangu-2.0-pro-thinking","score":61.3,"metric":"percent"},{"benchmark":"mcp-atlas","model":"openpangu-2.0-pro","score":48.8,"metric":"percent"},{"benchmark":"skillsbench","model":"openpangu-2.0-pro-thinking","score":48.9,"metric":"percent"},{"benchmark":"skillsbench","model":"openpangu-2.0-pro","score":47.5,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"openpangu-2.0-pro-thinking","score":84,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"openpangu-2.0-pro","score":88.9,"metric":"percent"},{"benchmark":"wildclawbench","model":"openpangu-2.0-pro-thinking","score":46.5,"metric":"percent"},{"benchmark":"wildclawbench","model":"openpangu-2.0-pro","score":43.1,"metric":"percent"},{"benchmark":"claweval-pass3","model":"openpangu-2.0-pro-thinking","score":61.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"openpangu-2.0-pro","score":49.4,"metric":"percent"},{"benchmark":"gdpval","model":"openpangu-2.0-pro-thinking","score":74.9,"metric":"percent"},{"benchmark":"gdpval","model":"openpangu-2.0-pro","score":51.2,"metric":"percent"},{"benchmark":"browsecomp","model":"openpangu-2.0-pro-thinking","score":65.7,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-2.0-pro-thinking","score":85.7,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-2.0-pro","score":74.5,"metric":"percent"},{"benchmark":"featbench","model":"openpangu-2.0-pro-thinking","score":47.1,"metric":"percent"},{"benchmark":"featbench","model":"openpangu-2.0-pro","score":48.4,"metric":"percent"},{"benchmark":"deepcodebench","model":"openpangu-2.0-pro-thinking","score":74.2,"metric":"percent"},{"benchmark":"deepcodebench","model":"openpangu-2.0-pro","score":72.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"openpangu-2.0-pro-thinking","score":68.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"openpangu-2.0-pro","score":66.8,"metric":"percent"},{"benchmark":"cl-bench","model":"openpangu-2.0-flash-thinking","score":20.4,"metric":"percent"},{"benchmark":"cl-bench","model":"openpangu-2.0-flash","score":15.5,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-2.0-flash-thinking","score":95.9,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-2.0-flash","score":89.3,"metric":"percent"},{"benchmark":"ifbench","model":"openpangu-2.0-flash-thinking","score":79.6,"metric":"percent"},{"benchmark":"ifbench","model":"openpangu-2.0-flash","score":54.4,"metric":"percent"},{"benchmark":"agentif","model":"openpangu-2.0-flash-thinking","score":44.9,"metric":"percent"},{"benchmark":"agentif","model":"openpangu-2.0-flash","score":43.9,"metric":"percent"},{"benchmark":"sysbench","model":"openpangu-2.0-flash-thinking","score":91.1,"metric":"percent"},{"benchmark":"sysbench","model":"openpangu-2.0-flash","score":87.9,"metric":"percent"},{"benchmark":"multichallenge","model":"openpangu-2.0-flash-thinking","score":68.4,"metric":"percent"},{"benchmark":"multichallenge","model":"openpangu-2.0-flash","score":51.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"openpangu-2.0-flash-thinking","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"openpangu-2.0-flash","score":86.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"openpangu-2.0-flash-thinking","score":91.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"openpangu-2.0-flash","score":67.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"openpangu-2.0-flash-thinking","score":76.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"openpangu-2.0-flash","score":62.3,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"openpangu-2.0-flash-thinking","score":62.5,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"openpangu-2.0-flash","score":51.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-2.0-flash-thinking","score":83.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-2.0-flash","score":79.8,"metric":"percent"},{"benchmark":"browsecomp","model":"openpangu-2.0-flash-thinking","score":57,"metric":"percent"},{"benchmark":"skillsbench","model":"openpangu-2.0-flash-thinking","score":42.6,"metric":"percent"},{"benchmark":"skillsbench","model":"openpangu-2.0-flash","score":40,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"openpangu-2.0-flash-thinking","score":85.6,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"openpangu-2.0-flash","score":82.5,"metric":"percent"},{"benchmark":"claweval-pass3","model":"openpangu-2.0-flash-thinking","score":57.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"openpangu-2.0-flash","score":58.2,"metric":"percent"},{"benchmark":"wildclawbench","model":"openpangu-2.0-flash-thinking","score":41.5,"metric":"percent"},{"benchmark":"wildclawbench","model":"openpangu-2.0-flash","score":35,"metric":"percent"},{"benchmark":"mcp-atlas","model":"openpangu-2.0-flash-thinking","score":58.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"openpangu-2.0-flash","score":47.9,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-2.0-flash-thinking","score":85.1,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-2.0-flash","score":50.9,"metric":"percent"},{"benchmark":"deepcodebench","model":"openpangu-2.0-flash-thinking","score":76.5,"metric":"percent"},{"benchmark":"deepcodebench","model":"openpangu-2.0-flash","score":70.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"openpangu-2.0-flash-thinking","score":63.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"openpangu-2.0-flash","score":57.6,"metric":"percent"},{"benchmark":"featbench","model":"openpangu-2.0-flash-thinking","score":45.9,"metric":"percent"},{"benchmark":"featbench","model":"openpangu-2.0-flash","score":45.8,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"openpangu-2.0-flash-thinking","score":24.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"openpangu-2.0-flash","score":21.6,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"openpangu-2.0-flash-thinking","score":66.7,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"openpangu-2.0-flash","score":66,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"openpangu-2.0-flash-thinking","score":76.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"openpangu-2.0-flash","score":63.2,"metric":"percent"},{"benchmark":"matharena-apex","model":"openpangu-2.0-flash-thinking","score":1,"metric":"percent"},{"benchmark":"hle-text-only","model":"openpangu-2.0-flash-thinking","score":20.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"openpangu-2.0-flash","score":8.5,"metric":"percent"},{"benchmark":"gdpval","model":"openpangu-2.0-flash-thinking","score":51.4,"metric":"percent"},{"benchmark":"livebench","model":"openpangu-r-7b-2512-slow-thinking","score":58.1,"metric":"percent"},{"benchmark":"livebench","model":"openpangu-r-7b-2512-fast-thinking","score":44.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openpangu-r-7b-2512-slow-thinking","score":79.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openpangu-r-7b-2512-fast-thinking","score":76.6,"metric":"percent"},{"benchmark":"mmlu-prox","model":"openpangu-r-7b-2512-slow-thinking","score":68.7,"metric":"percent"},{"benchmark":"mmlu-prox","model":"openpangu-r-7b-2512-fast-thinking","score":61.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"openpangu-r-7b-2512-slow-thinking","score":33.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"openpangu-r-7b-2512-fast-thinking","score":30.4,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-r-7b-2512-slow-thinking","score":72.8,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-r-7b-2512-fast-thinking","score":78,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"openpangu-r-7b-2512-slow-thinking","score":3.6,"metric":"percent"},{"benchmark":"hhem-v2.1","model":"openpangu-r-7b-2512-fast-thinking","score":3.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-r-7b-2512-slow-thinking","score":75.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-r-7b-2512-fast-thinking","score":63.1,"metric":"percent"},{"benchmark":"supergpqa","model":"openpangu-r-7b-2512-slow-thinking","score":53.1,"metric":"percent"},{"benchmark":"supergpqa","model":"openpangu-r-7b-2512-fast-thinking","score":48.7,"metric":"percent"},{"benchmark":"aime-2024","model":"openpangu-r-7b-2512-slow-thinking","score":86.5,"metric":"percent"},{"benchmark":"aime-2024","model":"openpangu-r-7b-2512-fast-thinking","score":65.4,"metric":"percent"},{"benchmark":"aime-2025","model":"openpangu-r-7b-2512-slow-thinking","score":75.2,"metric":"percent"},{"benchmark":"aime-2025","model":"openpangu-r-7b-2512-fast-thinking","score":56.9,"metric":"percent"},{"benchmark":"cnmo-2024","model":"openpangu-r-7b-2512-slow-thinking","score":78.5,"metric":"percent"},{"benchmark":"cnmo-2024","model":"openpangu-r-7b-2512-fast-thinking","score":67,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"openpangu-r-7b-2512-slow-thinking","score":62.9,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"openpangu-r-7b-2512-fast-thinking","score":34,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-r-7b-2512-slow-thinking","score":57.1,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-r-7b-2512-fast-thinking","score":35.8,"metric":"percent"},{"benchmark":"codeforces","model":"openpangu-r-7b-2512-slow-thinking","score":1411.6,"metric":"ELO"},{"benchmark":"codeforces","model":"openpangu-r-7b-2512-fast-thinking","score":774.4,"metric":"ELO"},{"benchmark":"acebench","model":"openpangu-r-7b-2512-slow-thinking","score":61.8,"metric":"percent"},{"benchmark":"acebench","model":"openpangu-r-7b-2512-fast-thinking","score":49.8,"metric":"percent"},{"benchmark":"tau1-airline","model":"openpangu-r-7b-2512-slow-thinking","score":50,"metric":"percent"},{"benchmark":"tau1-airline","model":"openpangu-r-7b-2512-fast-thinking","score":42.7,"metric":"percent"},{"benchmark":"tau1-retail","model":"openpangu-r-7b-2512-slow-thinking","score":69,"metric":"percent"},{"benchmark":"tau1-retail","model":"openpangu-r-7b-2512-fast-thinking","score":61.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"openpangu-r-7b-2512-slow-thinking","score":58,"metric":"percent"},{"benchmark":"tau2-airline","model":"openpangu-r-7b-2512-fast-thinking","score":59.3,"metric":"percent"},{"benchmark":"tau2-retail","model":"openpangu-r-7b-2512-slow-thinking","score":71.3,"metric":"percent"},{"benchmark":"tau2-retail","model":"openpangu-r-7b-2512-fast-thinking","score":66.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"openpangu-r-7b-2512-slow-thinking","score":45,"metric":"percent"},{"benchmark":"tau2-telecom","model":"openpangu-r-7b-2512-fast-thinking","score":43,"metric":"percent"},{"benchmark":"bfcl-v3","model":"openpangu-r-7b-2512-slow-thinking","score":70.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"openpangu-r-7b-2512-fast-thinking","score":62.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"openpangu-vl-7b","score":86.5,"metric":"percent"},{"benchmark":"mmstar","model":"openpangu-vl-7b","score":70.1,"metric":"percent"},{"benchmark":"realworldqa","model":"openpangu-vl-7b","score":76.1,"metric":"percent"},{"benchmark":"ai2d","model":"openpangu-vl-7b","score":84.7,"metric":"percent"},{"benchmark":"ocrbench","model":"openpangu-vl-7b","score":90.7,"metric":"percent"},{"benchmark":"textvqa","model":"openpangu-vl-7b","score":85.1,"metric":"percent"},{"benchmark":"docvqa","model":"openpangu-vl-7b","score":96,"metric":"percent"},{"benchmark":"chartqa","model":"openpangu-vl-7b","score":88.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"openpangu-vl-7b","score":83.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"openpangu-vl-7b","score":54.3,"metric":"percent"},{"benchmark":"mmmu","model":"openpangu-vl-7b","score":65.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"openpangu-vl-7b","score":52.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"openpangu-vl-7b","score":75,"metric":"percent"},{"benchmark":"refcoco","model":"openpangu-vl-7b","score":90.6,"metric":"percent"},{"benchmark":"odinw-13","model":"openpangu-vl-7b","score":51.5,"metric":"percent"},{"benchmark":"countbench","model":"openpangu-vl-7b","score":96.1,"metric":"percent"},{"benchmark":"point-bench","model":"openpangu-vl-7b","score":65.4,"metric":"percent"},{"benchmark":"blink","model":"openpangu-vl-7b","score":63.3,"metric":"percent"},{"benchmark":"muirbench","model":"openpangu-vl-7b","score":61.6,"metric":"percent"},{"benchmark":"mvbench","model":"openpangu-vl-7b","score":74,"metric":"percent"},{"benchmark":"videomme-nosub","model":"openpangu-vl-7b","score":68,"metric":"percent"},{"benchmark":"mlvu","model":"openpangu-vl-7b","score":76.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openpangu-vl-7b","score":78.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"openpangu-vl-7b","score":87.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-vl-7b","score":65.2,"metric":"percent"},{"benchmark":"c-eval","model":"openpangu-vl-7b","score":83.2,"metric":"percent"},{"benchmark":"aime-2025","model":"openpangu-vl-7b","score":36.5,"metric":"percent"},{"benchmark":"math500","model":"openpangu-vl-7b","score":89.4,"metric":"percent"},{"benchmark":"livecodebench","model":"openpangu-vl-7b","score":24.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"openpangu-vl-7b","score":68.5,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-vl-7b","score":83,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"internvl3.5-8b","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"minicpm-v-4.5-8b","score":84.2,"metric":"percent"},{"benchmark":"ai2d","model":"keye-vl-1.5-8b","score":88.6,"metric":"percent"},{"benchmark":"realworldqa","model":"keye-vl-1.5-8b","score":71.1,"metric":"percent"},{"benchmark":"mmstar","model":"keye-vl-1.5-8b","score":75.5,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-8b","score":69.3,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-v-4.5-8b","score":72.1,"metric":"percent"},{"benchmark":"ocrbench","model":"mimo-vl-7b-rl-2508","score":88.1,"metric":"percent"},{"benchmark":"ocrbench","model":"keye-vl-1.5-8b","score":83.3,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-v-4.5-8b","score":89,"metric":"percent"},{"benchmark":"chartqa","model":"mimo-vl-7b-rl-2508","score":91,"metric":"percent"},{"benchmark":"mmmu","model":"mimo-vl-7b-rl-2508","score":63.1,"metric":"percent"},{"benchmark":"mmmu","model":"keye-vl-1.5-8b","score":63.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"keye-vl-1.5-8b","score":70.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl3.5-8b","score":78.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"minicpm-v-4.5-8b","score":79.9,"metric":"percent"},{"benchmark":"blink","model":"keye-vl-1.5-8b","score":52.5,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-8b-instruct","score":89.1,"metric":"percent"},{"benchmark":"refcoco","model":"mimo-vl-7b-rl-2508","score":90.3,"metric":"percent"},{"benchmark":"refcoco","model":"internvl3.5-8b","score":89.7,"metric":"percent"},{"benchmark":"point-bench","model":"qwen3-vl-8b-instruct","score":63.4,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-8b-instruct","score":80.5,"metric":"percent"},{"benchmark":"videomme-nosub","model":"mimo-vl-7b-rl-2508","score":70.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"keye-vl-1.5-8b","score":59.7,"metric":"percent"},{"benchmark":"mlvu","model":"internvl3.5-8b","score":70.2,"metric":"percent"},{"benchmark":"mlvu","model":"minicpm-v-4.5-8b","score":75.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openpangu-embedded-7b-v1.1","score":69.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openpangu-embedded-7b-v1.1","score":60.1,"metric":"percent"},{"benchmark":"c-eval","model":"openpangu-embedded-7b-v1.1","score":78.5,"metric":"percent"},{"benchmark":"mmlu","model":"dream-7b-instruct","score":67,"metric":"percent"},{"benchmark":"mmlu","model":"fast-dllm-v2-7b","score":66.6,"metric":"percent"},{"benchmark":"mmlu","model":"llada2.0-mini-preview","score":72.49,"metric":"percent"},{"benchmark":"mmlu","model":"sdar-8b-chat","score":78.6,"metric":"percent"},{"benchmark":"mmlu","model":"openpangu-r-7b-diffusion","score":81.66,"metric":"percent"},{"benchmark":"mmlu-pro","model":"dream-7b-instruct","score":43.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"fast-dllm-v2-7b","score":44.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada2.0-mini-preview","score":49.22,"metric":"percent"},{"benchmark":"mmlu-pro","model":"sdar-8b-chat","score":56.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openpangu-r-7b-diffusion","score":71.26,"metric":"percent"},{"benchmark":"cmmlu","model":"dream-7b-instruct","score":58.82,"metric":"percent"},{"benchmark":"cmmlu","model":"fast-dllm-v2-7b","score":59.67,"metric":"percent"},{"benchmark":"cmmlu","model":"llada2.0-mini-preview","score":67.53,"metric":"percent"},{"benchmark":"cmmlu","model":"sdar-8b-chat","score":75.7,"metric":"percent"},{"benchmark":"cmmlu","model":"openpangu-r-7b-diffusion","score":76.43,"metric":"percent"},{"benchmark":"c-eval","model":"dream-7b-instruct","score":57.98,"metric":"percent"},{"benchmark":"c-eval","model":"fast-dllm-v2-7b","score":66.76,"metric":"percent"},{"benchmark":"c-eval","model":"llada2.0-mini-preview","score":66.54,"metric":"percent"},{"benchmark":"c-eval","model":"sdar-8b-chat","score":72.72,"metric":"percent"},{"benchmark":"c-eval","model":"openpangu-r-7b-diffusion","score":70.81,"metric":"percent"},{"benchmark":"ifeval","model":"dream-7b-instruct","score":62.5,"metric":"percent"},{"benchmark":"ifeval","model":"fast-dllm-v2-7b","score":61.4,"metric":"percent"},{"benchmark":"ifeval","model":"llada2.0-mini-preview","score":62.5,"metric":"percent"},{"benchmark":"ifeval","model":"sdar-8b-chat","score":61.4,"metric":"percent"},{"benchmark":"ifeval","model":"openpangu-r-7b-diffusion","score":60.81,"metric":"percent"},{"benchmark":"gsm8k","model":"dream-7b-instruct","score":81,"metric":"percent"},{"benchmark":"gsm8k","model":"fast-dllm-v2-7b","score":83.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llada2.0-mini-preview","score":89.01,"metric":"percent"},{"benchmark":"gsm8k","model":"sdar-8b-chat","score":91.3,"metric":"percent"},{"benchmark":"gsm8k","model":"openpangu-r-7b-diffusion","score":91.89,"metric":"percent"},{"benchmark":"math","model":"dream-7b-instruct","score":39.2,"metric":"percent"},{"benchmark":"math","model":"fast-dllm-v2-7b","score":61.6,"metric":"percent"},{"benchmark":"math","model":"llada2.0-mini-preview","score":73.5,"metric":"percent"},{"benchmark":"math","model":"sdar-8b-chat","score":78.6,"metric":"percent"},{"benchmark":"math","model":"openpangu-r-7b-diffusion","score":84.26,"metric":"percent"},{"benchmark":"mbpp","model":"dream-7b-instruct","score":58.8,"metric":"percent"},{"benchmark":"mbpp","model":"fast-dllm-v2-7b","score":57.1,"metric":"percent"},{"benchmark":"mbpp","model":"llada2.0-mini-preview","score":77.75,"metric":"percent"},{"benchmark":"mbpp","model":"openpangu-r-7b-diffusion","score":84.05,"metric":"percent"},{"benchmark":"humaneval","model":"dream-7b-instruct","score":55.5,"metric":"percent"},{"benchmark":"humaneval","model":"fast-dllm-v2-7b","score":63.4,"metric":"percent"},{"benchmark":"humaneval","model":"llada2.0-mini-preview","score":80.49,"metric":"percent"},{"benchmark":"humaneval","model":"openpangu-r-7b-diffusion","score":87.8,"metric":"percent"},{"benchmark":"mmlu","model":"llada-8b-base","score":65.9,"metric":"percent"},{"benchmark":"mmlu","model":"llada-moe-7b-a1b-base","score":64.59,"metric":"percent"},{"benchmark":"mmlu","model":"dream-7b-base","score":69.5,"metric":"percent"},{"benchmark":"mmlu","model":"openpangu-7b-diffusion-base","score":70.09,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada-8b-base","score":41.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada-moe-7b-a1b-base","score":39.16,"metric":"percent"},{"benchmark":"mmlu-pro","model":"dream-7b-base","score":48.15,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openpangu-7b-diffusion-base","score":59.05,"metric":"percent"},{"benchmark":"c-eval","model":"llada-8b-base","score":70.5,"metric":"percent"},{"benchmark":"c-eval","model":"llada-moe-7b-a1b-base","score":65.56,"metric":"percent"},{"benchmark":"c-eval","model":"dream-7b-base","score":59.18,"metric":"percent"},{"benchmark":"c-eval","model":"openpangu-7b-diffusion-base","score":73.03,"metric":"percent"},{"benchmark":"cmmlu","model":"llada-8b-base","score":69.9,"metric":"percent"},{"benchmark":"cmmlu","model":"llada-moe-7b-a1b-base","score":65.65,"metric":"percent"},{"benchmark":"cmmlu","model":"dream-7b-base","score":60.87,"metric":"percent"},{"benchmark":"cmmlu","model":"openpangu-7b-diffusion-base","score":77.27,"metric":"percent"},{"benchmark":"bbh","model":"llada-8b-base","score":49.8,"metric":"percent"},{"benchmark":"bbh","model":"llada-moe-7b-a1b-base","score":52.71,"metric":"percent"},{"benchmark":"bbh","model":"dream-7b-base","score":57.9,"metric":"percent"},{"benchmark":"bbh","model":"openpangu-7b-diffusion-base","score":77.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llada-8b-base","score":70.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llada-moe-7b-a1b-base","score":66.41,"metric":"percent"},{"benchmark":"gsm8k","model":"dream-7b-base","score":77.79,"metric":"percent"},{"benchmark":"gsm8k","model":"openpangu-7b-diffusion-base","score":78.77,"metric":"percent"},{"benchmark":"math","model":"llada-8b-base","score":27.3,"metric":"percent"},{"benchmark":"math","model":"llada-moe-7b-a1b-base","score":36.1,"metric":"percent"},{"benchmark":"math","model":"dream-7b-base","score":39.6,"metric":"percent"},{"benchmark":"math","model":"openpangu-7b-diffusion-base","score":46.02,"metric":"percent"},{"benchmark":"mbpp","model":"llada-8b-base","score":38.2,"metric":"percent"},{"benchmark":"mbpp","model":"llada-moe-7b-a1b-base","score":52.4,"metric":"percent"},{"benchmark":"mbpp","model":"dream-7b-base","score":56.2,"metric":"percent"},{"benchmark":"mbpp","model":"openpangu-7b-diffusion-base","score":55.8,"metric":"percent"},{"benchmark":"humaneval","model":"llada-8b-base","score":33.5,"metric":"percent"},{"benchmark":"humaneval","model":"llada-moe-7b-a1b-base","score":45.73,"metric":"percent"},{"benchmark":"humaneval","model":"dream-7b-base","score":57.9,"metric":"percent"},{"benchmark":"humaneval","model":"openpangu-7b-diffusion-base","score":50,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3.2-thinking","score":28.02,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-5-high","score":51.3,"metric":"percent"},{"benchmark":"simpleqa","model":"gemini-3-pro","score":69.33,"metric":"percent"},{"benchmark":"simpleqa","model":"ernie-5.0","score":74.01,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"deepseek-v3.2-thinking","score":72.37,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"gemini-2.5-pro","score":76.5,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"gpt-5-high","score":75.1,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"gemini-3-pro","score":84.08,"metric":"percent"},{"benchmark":"chinese-simpleqa","model":"ernie-5.0","score":86.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5-high","score":87.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3-pro","score":86.88,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ernie-5.0","score":83.8,"metric":"percent"},{"benchmark":"hle","model":"gpt-5-high","score":24.8,"metric":"avg@3"},{"benchmark":"hle","model":"ernie-5.0","score":25.81,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"ernie-5.0","score":86.36,"metric":"percent"},{"benchmark":"aime-2025","model":"ernie-5.0","score":89.06,"metric":"percent"},{"benchmark":"hmmt-2025","model":"deepseek-v3.2-thinking","score":86.67,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-2.5-pro","score":81.2,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gpt-5-high","score":93.3,"metric":"percent"},{"benchmark":"hmmt-2025","model":"gemini-3-pro","score":93.33,"metric":"percent"},{"benchmark":"hmmt-2025","model":"ernie-5.0","score":79.58,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-thinking","score":81.06,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":72.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-high","score":81.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3-pro","score":86.34,"metric":"percent"},{"benchmark":"livecodebench","model":"ernie-5.0","score":76.21,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3.2-thinking","score":90.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-2.5-pro","score":94.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-5-high","score":92.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-3-pro","score":95.12,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ernie-5.0","score":94.48,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v3.2-thinking","score":81.48,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-2.5-pro","score":73.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-5-high","score":83.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-3-pro","score":86.21,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ernie-5.0","score":82.54,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-v3.2-thinking","score":97.6,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-2.5-pro","score":92.9,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-5-high","score":98.8,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-3-pro","score":95.5,"metric":"percent"},{"benchmark":"zebralogic","model":"ernie-5.0","score":96.5,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"deepseek-v3.2-thinking","score":67.04,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemini-2.5-pro","score":68.8,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gpt-5-high","score":69,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"gemini-3-pro","score":78.8,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"ernie-5.0","score":66.63,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v3.2-thinking","score":91.87,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-2.5-pro","score":89.5,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-5-high","score":94.1,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-3-pro","score":92.24,"metric":"percent"},{"benchmark":"ifeval","model":"ernie-5.0","score":93.35,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v3.2-thinking","score":42.43,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-2.5-pro","score":51.5,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5-high","score":58.3,"metric":"percent"},{"benchmark":"multichallenge","model":"gemini-3-pro","score":62.5,"metric":"percent"},{"benchmark":"multichallenge","model":"ernie-5.0","score":65.98,"metric":"percent"},{"benchmark":"multi-if","model":"deepseek-v3.2-thinking","score":71.17,"metric":"percent"},{"benchmark":"multi-if","model":"gemini-2.5-pro","score":76.1,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-5-high","score":70,"metric":"percent"},{"benchmark":"multi-if","model":"gemini-3-pro","score":81.15,"metric":"percent"},{"benchmark":"multi-if","model":"ernie-5.0","score":85.56,"metric":"percent"},{"benchmark":"acebench","model":"deepseek-v3.2-thinking","score":81.4,"metric":"percent"},{"benchmark":"acebench","model":"gemini-2.5-pro","score":80.9,"metric":"percent"},{"benchmark":"acebench","model":"gpt-5-high","score":79.3,"metric":"percent"},{"benchmark":"acebench","model":"gemini-3-pro","score":80.9,"metric":"percent"},{"benchmark":"acebench","model":"ernie-5.0","score":87.7,"metric":"percent"},{"benchmark":"acebench-zh","model":"deepseek-v3.2-thinking","score":83.4,"metric":"percent"},{"benchmark":"acebench-zh","model":"gemini-2.5-pro","score":87.5,"metric":"percent"},{"benchmark":"acebench-zh","model":"gpt-5-high","score":83.6,"metric":"percent"},{"benchmark":"acebench-zh","model":"gemini-3-pro","score":85,"metric":"percent"},{"benchmark":"acebench-zh","model":"ernie-5.0","score":89.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"deepseek-v3.2-thinking","score":61.18,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemini-3-pro","score":68.14,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ernie-5.0","score":66.47,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gemini-2.5-pro","score":28.7,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-5-high","score":61.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gemini-3-pro","score":63.67,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"ernie-5.0","score":64.71,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"deepseek-v3.2-thinking","score":35.29,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"gemini-2.5-pro","score":27.7,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"gpt-5-high","score":34,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"gemini-3-pro","score":55.36,"metric":"percent"},{"benchmark":"spreadsheetbench-v1","model":"ernie-5.0","score":40.08,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-235b-a22b-thinking","score":68.28,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-high","score":78.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"ernie-5.0","score":68.63,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-235b-a22b-thinking","score":86.8,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5-high","score":82.1,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-3-pro","score":89.2,"metric":"percent"},{"benchmark":"mathvista","model":"ernie-5.0","score":84.8,"metric":"percent"},{"benchmark":"mathverse","model":"qwen3-vl-235b-a22b-thinking","score":83.96,"metric":"percent"},{"benchmark":"mathverse","model":"gemini-2.5-pro","score":86.27,"metric":"percent"},{"benchmark":"mathverse","model":"gpt-5-high","score":84.19,"metric":"percent"},{"benchmark":"mathverse","model":"gemini-3-pro","score":91.62,"metric":"percent"},{"benchmark":"mathverse","model":"ernie-5.0","score":85.13,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-235b-a22b-thinking","score":71.84,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-high","score":78.06,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3-pro","score":87.27,"metric":"percent"},{"benchmark":"mathvision","model":"ernie-5.0","score":74.34,"metric":"percent"},{"benchmark":"visualpuzzle","model":"qwen3-vl-235b-a22b-thinking","score":57.01,"metric":"percent"},{"benchmark":"visualpuzzle","model":"gemini-2.5-pro","score":61.51,"metric":"percent"},{"benchmark":"visualpuzzle","model":"gpt-5-high","score":57.75,"metric":"percent"},{"benchmark":"visualpuzzle","model":"gemini-3-pro","score":71.48,"metric":"percent"},{"benchmark":"visualpuzzle","model":"ernie-5.0","score":64.82,"metric":"percent"},{"benchmark":"visulogic","model":"qwen3-vl-235b-a22b-thinking","score":31.93,"metric":"percent"},{"benchmark":"visulogic","model":"gemini-2.5-pro","score":32.8,"metric":"percent"},{"benchmark":"visulogic","model":"gpt-5-high","score":29.8,"metric":"percent"},{"benchmark":"visulogic","model":"gemini-3-pro","score":37.6,"metric":"percent"},{"benchmark":"visulogic","model":"ernie-5.0","score":32,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"qwen3-vl-235b-a22b-thinking","score":75.13,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"gemini-2.5-pro","score":76.54,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"gemini-3-pro","score":80.83,"metric":"percent"},{"benchmark":"vlms-are-blind","model":"ernie-5.0","score":91.38,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-235b-a22b-thinking","score":84.6,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-2.5-pro","score":84.08,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5-high","score":78.24,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-3-pro","score":89.44,"metric":"percent"},{"benchmark":"chartqa","model":"ernie-5.0","score":87.8,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-235b-a22b-thinking","score":96.96,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-pro","score":97.09,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-high","score":95.63,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-3-pro","score":97.7,"metric":"percent"},{"benchmark":"ai2d","model":"ernie-5.0","score":96.89,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-235b-a22b-thinking","score":95.44,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-pro","score":91.43,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5-high","score":94.16,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-3-pro","score":90.7,"metric":"percent"},{"benchmark":"docvqa","model":"ernie-5.0","score":95.45,"metric":"percent"},{"benchmark":"ocrbench-elo","model":"qwen3-vl-235b-a22b-thinking","score":863,"metric":"elo"},{"benchmark":"ocrbench-elo","model":"gpt-5-high","score":804,"metric":"elo"},{"benchmark":"ocrbench-elo","model":"gemini-3-pro","score":909,"metric":"elo"},{"benchmark":"ocrbench-elo","model":"ernie-5.0","score":878,"metric":"elo"},{"benchmark":"charxiv-rq","model":"qwen3-vl-235b-a22b-thinking","score":63,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-2.5-pro","score":67.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"ernie-5.0","score":67.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-235b-a22b-thinking","score":92.92,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-2.5-pro","score":93.38,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-5-high","score":91.17,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-3-pro","score":95.95,"metric":"percent"},{"benchmark":"charxiv-dq","model":"ernie-5.0","score":89.05,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-235b-a22b-thinking","score":62.37,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-2.5-pro","score":68.19,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5-high","score":55.84,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3-pro","score":74.06,"metric":"percent"},{"benchmark":"simplevqa","model":"ernie-5.0","score":67.64,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-235b-a22b-thinking","score":64.01,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5-high","score":66.58,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-3-pro","score":73.48,"metric":"percent"},{"benchmark":"hallusionbench","model":"ernie-5.0","score":63.87,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-235b-a22b-thinking","score":76.88,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-high","score":82.1,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-3-pro","score":82.96,"metric":"percent"},{"benchmark":"mmstar","model":"ernie-5.0","score":75.54,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-235b-a22b-thinking","score":66.6,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-high","score":70.39,"metric":"percent"},{"benchmark":"blink","model":"gemini-3-pro","score":77.49,"metric":"percent"},{"benchmark":"blink","model":"ernie-5.0","score":70.02,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-235b-a22b-thinking","score":87.57,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-2.5-pro","score":84.87,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-5-high","score":84.99,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-3-pro","score":90.07,"metric":"percent"},{"benchmark":"cv-bench","model":"ernie-5.0","score":87.19,"metric":"percent"},{"benchmark":"countbench","model":"qwen3-vl-235b-a22b-thinking","score":92.67,"metric":"percent"},{"benchmark":"countbench","model":"gpt-5-high","score":88.88,"metric":"percent"},{"benchmark":"countbench","model":"gemini-3-pro","score":97.35,"metric":"percent"},{"benchmark":"countbench","model":"ernie-5.0","score":96.54,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen3-vl-235b-a22b-thinking","score":80.97,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-2.5-pro","score":86.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-5-high","score":87.36,"metric":"percent"},{"benchmark":"videomme-sub","model":"ernie-5.0","score":81.35,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5-high","score":84.6,"metric":"percent"},{"benchmark":"videommmu","model":"ernie-5.0","score":81.11,"metric":"percent"},{"benchmark":"mmvu","model":"gpt-5-high","score":87.34,"metric":"percent"},{"benchmark":"mmvu","model":"ernie-5.0","score":72.24,"metric":"percent"},{"benchmark":"aime-2026-i-with-tools","model":"ernie-5.1","score":99.6,"metric":"percent"},{"benchmark":"aime-2026-i-with-tools","model":"deepseek-v4-pro-thinking-max","score":92.6,"metric":"percent"},{"benchmark":"aime-2026-i-with-tools","model":"claude-opus-4.6","score":81.2,"metric":"percent"},{"benchmark":"aime-2026-i-with-tools","model":"gemini-3.1-pro","score":99.9,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"ernie-5.1","score":77.3,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"deepseek-v4-pro-thinking-max","score":86.7,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"claude-opus-4.6","score":82,"metric":"percent"},{"benchmark":"deepsearchqa-f1","model":"gemini-3.1-pro","score":79.3,"metric":"percent"},{"benchmark":"spreadsheetbench-verified","model":"ernie-5.1","score":72.5,"metric":"percent"},{"benchmark":"spreadsheetbench-verified","model":"deepseek-v4-pro-thinking-max","score":67,"metric":"percent"},{"benchmark":"spreadsheetbench-verified","model":"claude-opus-4.6","score":82.4,"metric":"percent"},{"benchmark":"spreadsheetbench-verified","model":"gemini-3.1-pro","score":80.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ernie-5.1","score":95,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-pro-thinking-max","score":95.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ernie-5.1","score":91,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-opus-4.6","score":89.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ernie-5.1","score":84.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.6","score":89.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3.1-pro","score":87.7,"metric":"percent"},{"benchmark":"advancedif","model":"ernie-5.1","score":72.3,"metric":"percent"},{"benchmark":"advancedif","model":"deepseek-v4-pro-thinking-max","score":67.1,"metric":"percent"},{"benchmark":"advancedif","model":"claude-opus-4.6","score":73.4,"metric":"percent"},{"benchmark":"advancedif","model":"gemini-3.1-pro","score":83.9,"metric":"percent"},{"benchmark":"omnidocbench","model":"qianfan-ocr","score":93.12,"metric":"percent"},{"benchmark":"omnidocbench","model":"gemini-3-pro","score":90.33,"metric":"percent"},{"benchmark":"omnidocbench","model":"paddleocr-vl-1.5","score":94.5,"metric":"percent"},{"benchmark":"ocrbench-elo","model":"qianfan-ocr","score":880,"metric":"elo"},{"benchmark":"ocrbenchv2-en","model":"qianfan-ocr","score":56,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qianfan-ocr","score":60.77,"metric":"percent"},{"benchmark":"cc-ocr-multilingual","model":"qianfan-ocr","score":76.7,"metric":"percent"},{"benchmark":"cc-ocr","model":"qianfan-ocr","score":79.3,"metric":"percent"},{"benchmark":"ocrbench-elo","model":"qwen3-vl-4b-instruct","score":873,"metric":"elo"},{"benchmark":"ocrbenchv2-en","model":"qwen3-vl-4b-instruct","score":60.68,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3-vl-4b-instruct","score":59.13,"metric":"percent"},{"benchmark":"cc-ocr-multilingual","model":"qwen3-vl-4b-instruct","score":74.2,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3-vl-4b-instruct","score":76.5,"metric":"percent"},{"benchmark":"ocrbench-elo","model":"deepseek-ocr","score":459,"metric":"elo"},{"benchmark":"ocrbenchv2-en","model":"deepseek-ocr","score":15.98,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"deepseek-ocr","score":38.31,"metric":"percent"},{"benchmark":"cc-ocr-multilingual","model":"deepseek-ocr","score":32.5,"metric":"percent"},{"benchmark":"cc-ocr","model":"deepseek-ocr","score":27.6,"metric":"percent"},{"benchmark":"docvqa","model":"qianfan-ocr","score":92.8,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-4b-instruct","score":94.9,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-2b-instruct","score":92.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qianfan-ocr","score":94,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-4b-instruct","score":81.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen3-vl-2b-instruct","score":69.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qianfan-ocr","score":85.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-4b-instruct","score":48.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-2b-instruct","score":41.3,"metric":"percent"},{"benchmark":"chartqa","model":"qianfan-ocr","score":88.1,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-4b-instruct","score":83.3,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-2b-instruct","score":78.3,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qianfan-ocr","score":42.9,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3-vl-4b-instruct","score":36.2,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3-vl-2b-instruct","score":24.5,"metric":"percent"},{"benchmark":"chartbench","model":"qianfan-ocr","score":85.9,"metric":"percent"},{"benchmark":"chartbench","model":"qwen3-vl-4b-instruct","score":74.9,"metric":"percent"},{"benchmark":"chartbench","model":"qwen3-vl-2b-instruct","score":73.2,"metric":"percent"},{"benchmark":"textvqa","model":"qianfan-ocr","score":80,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-4b-instruct","score":81.8,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-2b-instruct","score":79.9,"metric":"percent"},{"benchmark":"ocrvqa","model":"qianfan-ocr","score":66.8,"metric":"percent"},{"benchmark":"ocrvqa","model":"qwen3-vl-4b-instruct","score":64.7,"metric":"percent"},{"benchmark":"ocrvqa","model":"qwen3-vl-2b-instruct","score":59.3,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"qianfan-ocr","score":95,"metric":"percent"},{"benchmark":"ocrbenchv2-kie-en","model":"qianfan-ocr","score":82.8,"metric":"percent"},{"benchmark":"ocrbenchv2-kie-zh","model":"qianfan-ocr","score":82.3,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"qianfan-ocr","score":92.8,"metric":"percent"},{"benchmark":"nanonets-kie","model":"qianfan-ocr","score":86.5,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"qwen3-vl-235b-a22b","score":94,"metric":"percent"},{"benchmark":"ocrbenchv2-kie-en","model":"qwen3-vl-235b-a22b","score":85.6,"metric":"percent"},{"benchmark":"ocrbenchv2-kie-zh","model":"qwen3-vl-235b-a22b","score":62.9,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"qwen3-vl-235b-a22b","score":95.1,"metric":"percent"},{"benchmark":"nanonets-kie","model":"qwen3-vl-235b-a22b","score":83.8,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"qwen3-vl-4b-instruct","score":89,"metric":"percent"},{"benchmark":"ocrbenchv2-kie-en","model":"qwen3-vl-4b-instruct","score":82.1,"metric":"percent"},{"benchmark":"ocrbenchv2-kie-zh","model":"qwen3-vl-4b-instruct","score":71.3,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"qwen3-vl-4b-instruct","score":91.6,"metric":"percent"},{"benchmark":"nanonets-kie","model":"qwen3-vl-4b-instruct","score":83.3,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"gemini-3.1-pro","score":96,"metric":"percent"},{"benchmark":"ocrbenchv2-kie-en","model":"gemini-3.1-pro","score":87.8,"metric":"percent"},{"benchmark":"ocrbenchv2-kie-zh","model":"gemini-3.1-pro","score":63.4,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"gemini-3.1-pro","score":72.5,"metric":"percent"},{"benchmark":"nanonets-kie","model":"gemini-3.1-pro","score":76.1,"metric":"percent"},{"benchmark":"omnidocbench","model":"mineru2-pp","score":75.51,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-5.2","score":85.5,"metric":"percent"},{"benchmark":"omnidocbench","model":"mistral-ocr-api","score":78.83,"metric":"percent"},{"benchmark":"omnidocbench","model":"deepseek-ocr","score":87.01,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"marker-1.8.2","score":60.1,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"pp-structurev3","score":64.45,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"gpt-5.2","score":78.66,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"qwen2.5-vl-72b","score":86.92,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"gemini-2.5-pro","score":88.21,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"qwen3-vl-235b-a22b","score":88.904,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"gemini-3-pro","score":89.24,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"dolphin-1.5","score":61.48,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"dolphin","score":61.78,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"deepseek-ocr","score":73.99,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"mineru2-vlm","score":76.95,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"monkeyocr-pro-1.2b","score":77.15,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"monkeyocr-3b","score":78.29,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"monkeyocr-pro-3b","score":79.49,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"nanonets-ocr-s","score":84.19,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"paddleocr-vl","score":85.54,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"mineru2.5","score":85.61,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"dots.ocr","score":86.38,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"paddleocr-vl-1.5","score":92.05,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"internvl3.5-241b","score":83.76,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"kimi-k2.5","score":84.53,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"gpt-5.2","score":86.59,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"qwen3-vl-235b-a22b","score":89.78,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"gemini-3-flash","score":92.62,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"gemini-3-pro","score":92.91,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"ovis2.6-30b-a3b","score":93.7,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"points-reader","score":83.37,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"nanonets-ocr-s","score":83.61,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"mistral-ocr-api","score":85.66,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"olmocr","score":85.74,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"dolphin-1.5","score":86.52,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"monkeyocr-pro-3b","score":88.57,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"ocrverse","score":88.6,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"dolphin-v2","score":89.5,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"hunyuanocr","score":89.95,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"deepseek-ocr-2","score":90.25,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"dots.ocr","score":90.77,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"mineru2.5","score":93.04,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"firered-ocr","score":93.26,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"logics-parsing-v2","score":93.33,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"youtu-parsing","score":93.74,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"qianfan-ocr","score":93.9,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"paddleocr-vl","score":94.18,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"paddleocr-vl-1.5","score":94.93,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"glm-ocr","score":95.22,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"mineru2.5-pro","score":95.75,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"paddleocr-vl-1.6","score":96.33,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"deepseek-ocr-2","score":73.01,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"mineru2.5-pro","score":88.96,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"glm-ocr","score":90.32,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"paddleocr-vl-1.6","score":93.19,"metric":"percent"},{"benchmark":"omnidocbench","model":"deepseek-ocr-2","score":89.17,"metric":"percent"},{"benchmark":"omnidocbench","model":"unlimited-ocr","score":93.23,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"unlimited-ocr","score":93.92,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"hpd-parsing","score":94.91,"metric":"percent"},{"benchmark":"deepsearchqa","model":"atria-dawn-preview","score":96,"metric":"percent"},{"benchmark":"deepsearchqa","model":"kimi-k3","score":95.9,"metric":"percent"},{"benchmark":"deepsearchqa","model":"glm-5.3","score":94.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-5.6-sol","score":93.2,"metric":"percent"},{"benchmark":"browsecomp","model":"atria-dawn-preview","score":92.5,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-pro-0813","score":83.4,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.6-sol","score":92.2,"metric":"percent"},{"benchmark":"wide-search","model":"atria-dawn-preview","score":81.9,"metric":"percent"},{"benchmark":"wide-search","model":"kimi-k3","score":79.6,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5.3","score":82.7,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5.6-sol","score":83.3,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"atria-dawn-preview","score":86.2,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"deepseek-v4-pro-0813","score":86.8,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"kimi-k3","score":85.8,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.8-max","score":81.3,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"glm-5.3","score":80.8,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"gpt-5.6-sol","score":88.9,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"claude-opus-5","score":88,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"atria-dawn-preview","score":59.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-pro-0813","score":58.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k3","score":61.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.8-max","score":65.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"glm-5.3","score":60.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.6-sol","score":61.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-5","score":74.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"atria-dawn-preview","score":78.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro-0813","score":78.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-max","score":89.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.3","score":85.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-sol","score":85.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-5","score":90.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"atria-dawn-preview","score":77,"metric":"percent"},{"benchmark":"bfcl-v4","model":"deepseek-v4-pro-0813","score":71.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"kimi-k3","score":69.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"glm-5.3","score":74.1,"metric":"percent"},{"benchmark":"automationbench","model":"atria-dawn-preview","score":53.8,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-pro-0813","score":41.7,"metric":"percent"},{"benchmark":"automationbench","model":"kimi-k3","score":45.9,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.8-max","score":49.7,"metric":"percent"},{"benchmark":"automationbench","model":"glm-5.3","score":49.2,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-sol","score":45.7,"metric":"percent"},{"benchmark":"automationbench","model":"claude-opus-5","score":49.4,"metric":"percent"},{"benchmark":"skillsbench","model":"atria-dawn-preview","score":66.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"atria-dawn-preview","score":41.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-pro-0813","score":44.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.3","score":40.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.6-sol","score":46.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-opus-5","score":48.7,"metric":"percent"},{"benchmark":"jobbench","model":"atria-dawn-preview","score":50.3,"metric":"percent"},{"benchmark":"cybergym","model":"atria-dawn-preview","score":86.5,"metric":"percent"},{"benchmark":"cybergym","model":"kimi-k3","score":78.7,"metric":"percent"},{"benchmark":"cybergym","model":"qwen3.8-max","score":73.8,"metric":"percent"},{"benchmark":"healthbench","model":"baichuan-m3-235b","score":65.1,"metric":"percent"},{"benchmark":"healthbench","model":"qwen3-235b-a22b-thinking-2507","score":55.2,"metric":"percent"},{"benchmark":"healthbench","model":"deepseek-v3.2-thinking","score":53,"metric":"percent"},{"benchmark":"healthbench","model":"gemini-3-pro","score":46.2,"metric":"percent"},{"benchmark":"healthbench-hard","model":"baichuan-m3-235b","score":44.4,"metric":"percent"},{"benchmark":"healthbench-hard","model":"qwen3-235b-a22b-thinking-2507","score":25.9,"metric":"percent"},{"benchmark":"healthbench-hard","model":"deepseek-v3.2-thinking","score":21.7,"metric":"percent"},{"benchmark":"healthbench-hard","model":"gemini-3-pro","score":15.2,"metric":"percent"},{"benchmark":"worldvqa","model":"dots3-note-preview","score":42.7,"metric":"percent"},{"benchmark":"worldvqa","model":"seed2.1-turbo","score":49.4,"metric":"percent"},{"benchmark":"worldvqa","model":"qwen3.7-plus","score":35.5,"metric":"percent"},{"benchmark":"worldvqa","model":"inkling-small","score":16.2,"metric":"percent"},{"benchmark":"worldvqa","model":"gemini-3.5-flash","score":51.9,"metric":"percent"},{"benchmark":"simplevqa","model":"dots3-note-preview","score":72.5,"metric":"percent"},{"benchmark":"simplevqa","model":"seed2.1-turbo","score":73.2,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.7-plus","score":67.2,"metric":"percent"},{"benchmark":"simplevqa","model":"inkling-small","score":50.1,"metric":"percent"},{"benchmark":"simplevqa","model":"kimi-k3","score":71.3,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3.5-flash","score":74.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"dots3-note-preview","score":79.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.7-plus","score":80.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"inkling-small","score":74.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k3","score":80.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-pro","score":84.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.5-flash","score":84.6,"metric":"percent"},{"benchmark":"mathvision","model":"dots3-note-preview","score":87.7,"metric":"percent"},{"benchmark":"mathvision","model":"seed2.1-turbo","score":89.9,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.7-plus","score":89.5,"metric":"percent"},{"benchmark":"mathvision","model":"inkling-small","score":81.8,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-k3","score":93.1,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.1-pro","score":89.7,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.5-flash","score":91.6,"metric":"percent"},{"benchmark":"hipho","model":"dots3-note-preview","score":74.8,"metric":"percent"},{"benchmark":"hipho","model":"seed2.1-turbo","score":81.6,"metric":"percent"},{"benchmark":"hipho","model":"qwen3.7-plus","score":72.9,"metric":"percent"},{"benchmark":"hipho","model":"inkling-small","score":76,"metric":"percent"},{"benchmark":"hipho","model":"kimi-k3","score":80.4,"metric":"percent"},{"benchmark":"hipho","model":"gemini-3.1-pro","score":82,"metric":"percent"},{"benchmark":"hipho","model":"gemini-3.5-flash","score":86.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"dots3-note-preview","score":83.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"seed2.1-turbo","score":83.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.7-plus","score":84.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"inkling-small","score":76.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"kimi-k3","score":83.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-3.5-flash","score":80.6,"metric":"percent"},{"benchmark":"perceptionbench","model":"dots3-note-preview","score":53.4,"metric":"percent"},{"benchmark":"perceptionbench","model":"seed2.1-turbo","score":48.3,"metric":"percent"},{"benchmark":"perceptionbench","model":"qwen3.7-plus","score":52.3,"metric":"percent"},{"benchmark":"perceptionbench","model":"inkling-small","score":37.9,"metric":"percent"},{"benchmark":"perceptionbench","model":"gemini-3.1-pro","score":55.7,"metric":"percent"},{"benchmark":"perceptionbench","model":"gemini-3.5-flash","score":60.9,"metric":"percent"},{"benchmark":"babyvision","model":"dots3-note-preview","score":50,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3.7-plus","score":47.7,"metric":"percent"},{"benchmark":"babyvision","model":"inkling-small","score":27.1,"metric":"percent"},{"benchmark":"babyvision","model":"kimi-k3","score":52.3,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3.1-pro","score":51.3,"metric":"percent"},{"benchmark":"babyvision","model":"gemini-3.5-flash","score":51.3,"metric":"percent"},{"benchmark":"videomme-v2","model":"dots3-note-preview","score":39.3,"metric":"percent"},{"benchmark":"videomme-v2","model":"seed2.1-turbo","score":36.3,"metric":"percent"},{"benchmark":"videomme-v2","model":"qwen3.7-plus","score":32.5,"metric":"percent"},{"benchmark":"videomme-v2","model":"kimi-k3","score":32.5,"metric":"percent"},{"benchmark":"videomme-v2","model":"gemini-3.5-flash","score":52.1,"metric":"percent"},{"benchmark":"mmvu","model":"dots3-note-preview","score":79.9,"metric":"percent"},{"benchmark":"mmvu","model":"seed2.1-turbo","score":80.4,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.7-plus","score":80.7,"metric":"percent"},{"benchmark":"mmvu","model":"kimi-k3","score":83.7,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-3.5-flash","score":81.1,"metric":"percent"},{"benchmark":"videommmu","model":"dots3-note-preview","score":86.8,"metric":"percent"},{"benchmark":"videommmu","model":"seed2.1-turbo","score":85.2,"metric":"percent"},{"benchmark":"videommmu","model":"qwen3.7-plus","score":87,"metric":"percent"},{"benchmark":"videommmu","model":"kimi-k3","score":86.4,"metric":"percent"},{"benchmark":"videommmu","model":"gemini-3.5-flash","score":88,"metric":"percent"},{"benchmark":"longvideobench","model":"dots3-note-preview","score":76.8,"metric":"percent"},{"benchmark":"longvideobench","model":"seed2.1-turbo","score":80.3,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3.7-plus","score":77.8,"metric":"percent"},{"benchmark":"longvideobench","model":"kimi-k3","score":80.2,"metric":"percent"},{"benchmark":"longvideobench","model":"gemini-3.5-flash","score":79.2,"metric":"percent"},{"benchmark":"mmau-pro","model":"dots3-note-preview","score":69.8,"metric":"percent"},{"benchmark":"mmau-pro","model":"inkling-small","score":65.6,"metric":"percent"},{"benchmark":"mmau-pro","model":"gemini-3.5-flash","score":69.9,"metric":"percent"},{"benchmark":"mmau-pro","model":"seed2.0-lite","score":67.4,"metric":"percent"},{"benchmark":"mmau-pro","model":"qwen3.5-omni-plus","score":70,"metric":"percent"},{"benchmark":"imo-answerbench","model":"dots3-note-preview","score":90.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-flash-0731","score":91.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-v4-flash","score":88.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"seed2.1-turbo","score":91.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"seed2.1-pro","score":91.1,"metric":"percent"},{"benchmark":"codeforces","model":"dots3-note-preview","score":3056,"metric":"ELO"},{"benchmark":"codeforces","model":"hy3","score":2758,"metric":"ELO"},{"benchmark":"codeforces","model":"glm-5.2","score":2851,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v4-flash-0731","score":3329,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v4-flash","score":3052,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v4-pro","score":3206,"metric":"ELO"},{"benchmark":"codeforces","model":"claude-opus-4.8","score":3188,"metric":"ELO"},{"benchmark":"codeforces","model":"gpt-5.5","score":3362,"metric":"ELO"},{"benchmark":"livecodebench","model":"dots3-note-preview","score":91.5,"metric":"percent"},{"benchmark":"livecodebench","model":"hy3","score":91,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-5.2","score":83.7,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-0731","score":94.1,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash","score":91.6,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-pro","score":93.5,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.8","score":93.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.5","score":96.2,"metric":"percent"},{"benchmark":"arc-agi-2","model":"dots3-note-preview","score":81.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"hy3","score":35.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"glm-5.2","score":22.8,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-flash-0731","score":61.4,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-flash","score":37,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-pro","score":60.6,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k3","score":60.4,"metric":"percent"},{"benchmark":"ifbench","model":"dots3-note-preview","score":80.4,"metric":"percent"},{"benchmark":"ifbench","model":"hy3","score":74.6,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5.2","score":78,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-flash-0731","score":78.7,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-flash","score":79.2,"metric":"percent"},{"benchmark":"ifbench","model":"seed2.1-turbo","score":65.6,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-pro","score":76.5,"metric":"percent"},{"benchmark":"ifbench","model":"seed2.1-pro","score":69.5,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.5","score":75.9,"metric":"percent"},{"benchmark":"ifeval","model":"dots3-note-preview","score":93.9,"metric":"percent"},{"benchmark":"ifeval","model":"hy3","score":94.1,"metric":"percent"},{"benchmark":"ifeval","model":"glm-5.2","score":92,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v4-flash-0731","score":94.8,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v4-flash","score":95.2,"metric":"percent"},{"benchmark":"ifeval","model":"seed2.1-turbo","score":88.9,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v4-pro","score":94.8,"metric":"percent"},{"benchmark":"ifeval","model":"seed2.1-pro","score":89.8,"metric":"percent"},{"benchmark":"ifeval","model":"claude-opus-4.8","score":89.1,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-5.5","score":94.3,"metric":"percent"},{"benchmark":"claweval-pass3","model":"dots3-note-preview","score":73.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v4-flash-0731","score":78.9,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v4-flash","score":57.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"seed2.1-turbo","score":64,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v4-pro","score":59.8,"metric":"percent"},{"benchmark":"wildclawbench","model":"dots3-note-preview","score":61.7,"metric":"percent"},{"benchmark":"wildclawbench","model":"glm-5.2","score":54.2,"metric":"percent"},{"benchmark":"wildclawbench","model":"deepseek-v4-flash-0731","score":66,"metric":"percent"},{"benchmark":"wildclawbench","model":"deepseek-v4-flash","score":40,"metric":"percent"},{"benchmark":"wildclawbench","model":"deepseek-v4-pro","score":46,"metric":"percent"},{"benchmark":"wildclawbench","model":"claude-opus-4.8","score":68,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"dots3-note-preview","score":75.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash","score":61.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro","score":72.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.5","score":82.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"dots3-note-preview","score":78.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-flash","score":79,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-pro","score":80.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"dots3-note-preview","score":75.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-flash","score":73.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-pro","score":76.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"dots3-note-preview","score":61,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-flash","score":52.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-pro","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k3","score":63.4,"metric":"percent"},{"benchmark":"nl2repo","model":"dots3-note-preview","score":49.8,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-flash","score":39.4,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4-pro","score":41.5,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"dots3-note-preview","score":55.6,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"hy3","score":56.8,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-flash-0731","score":70.7,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-flash","score":50.9,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"deepseek-v4-pro","score":55.9,"metric":"percent"},{"benchmark":"skillsbench","model":"dots3-note-preview","score":52.8,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-flash-0731","score":61.5,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-flash","score":44.7,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-pro","score":50.1,"metric":"percent"},{"benchmark":"skillsbench","model":"seed2.1-pro","score":60.4,"metric":"percent"},{"benchmark":"skillsbench","model":"gpt-5.5","score":66.5,"metric":"percent"},{"benchmark":"apex-agents","model":"dots3-note-preview","score":30.8,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-5.2","score":33.7,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-flash-0731","score":35,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-flash","score":13.2,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-pro","score":24.3,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.5","score":37.7,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"dots3-note-preview","score":83.3,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"hy3","score":84.2,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"glm-5.2","score":76.6,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"deepseek-v4-flash-0731","score":74.5,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"deepseek-v4-flash","score":73.2,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"seed2.1-turbo","score":84.9,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"deepseek-v4-pro","score":83.4,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"kimi-k3","score":91.2,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"seed2.1-pro","score":86.2,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"claude-opus-4.8","score":84.3,"metric":"percent"},{"benchmark":"browsecomp-with-content-manager","model":"gpt-5.5","score":84.4,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"dots3-note-preview","score":75.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"hy3","score":69.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"glm-5.2","score":71.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepseek-v4-flash-0731","score":69.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepseek-v4-flash","score":67.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"seed2.1-turbo","score":73.7,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepseek-v4-pro","score":73,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"seed2.1-pro","score":80.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"claude-opus-4.8","score":80.3,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-5.5","score":75.1,"metric":"percent"},{"benchmark":"hle-with-tools","model":"dots3-note-preview","score":52.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-flash-0731","score":50.1,"metric":"avg@3"},{"benchmark":"wide-search","model":"dots3-note-preview","score":78.9,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5.2","score":82.3,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-flash-0731","score":80.5,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-flash","score":74.3,"metric":"percent"},{"benchmark":"wide-search","model":"seed2.1-turbo","score":77.6,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-pro","score":75.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"dots3-note-preview","score":92.1,"metric":"percent"},{"benchmark":"deepsearchqa","model":"glm-5.2","score":91.8,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v4-flash-0731","score":93.1,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v4-flash","score":87.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"seed2.1-turbo","score":89.6,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v4-pro","score":90.4,"metric":"percent"},{"benchmark":"deepsearchqa","model":"kimi-k3","score":95,"metric":"percent"},{"benchmark":"arc-agi-3","model":"dots3-note-preview","score":6.9,"metric":"percent"},{"benchmark":"arc-agi-3","model":"gpt-5.5","score":0.4,"metric":"percent"},{"benchmark":"olmocr-bench","model":"deepseek-ocr","score":75.7,"metric":"percent"},{"benchmark":"olmocr-bench","model":"dots.mocr","score":83.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"dots.mocr","score":77.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"dots.mocr","score":55.3,"metric":"percent"},{"benchmark":"infovqa","model":"dots.mocr","score":73.76,"metric":"percent"},{"benchmark":"docvqa","model":"dots.mocr","score":91.85,"metric":"percent"},{"benchmark":"ocrbench","model":"dots.mocr","score":86,"metric":"percent"},{"benchmark":"ai2d","model":"dots.mocr","score":82.16,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3-vl-2b-instruct","score":88.4,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3-vl-4b-instruct","score":84.9,"metric":"percent"},{"benchmark":"countbenchqa","model":"dots.mocr","score":94.46,"metric":"percent"},{"benchmark":"ocrreasoning","model":"dots.mocr","score":22.85,"metric":"percent"},{"benchmark":"chartqa","model":"dots.mocr","score":83.2,"metric":"percent"},{"benchmark":"refcoco","model":"dots.mocr","score":80.03,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"iquest-coder-v1-40b-instruct","score":76.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"iquest-coder-v1-14b-instruct","score":66.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"iquest-coder-v1-14b-thinking","score":63.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"iquest-coder-v1-7b-instruct","score":45,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"iquest-coder-v1-7b-thinking","score":38.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"iquest-coder-v1-40b-instruct","score":49.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"iquest-coder-v1-14b-instruct","score":46.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"iquest-coder-v1-14b-thinking","score":47.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"iquest-coder-v1-7b-instruct","score":38.9,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"iquest-coder-v1-7b-thinking","score":40.5,"metric":"pass@1"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-40b-instruct","score":50.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-14b-instruct","score":37.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-14b-thinking","score":72.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-7b-instruct","score":24.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"iquest-coder-v1-7b-thinking","score":37.7,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-40b-instruct","score":42.9,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-14b-instruct","score":40,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-14b-thinking","score":66.3,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-7b-instruct","score":24.6,"metric":"percent"},{"benchmark":"livecodebench","model":"iquest-coder-v1-7b-thinking","score":36.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"iquest-coder-v1-40b-instruct","score":30,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"iquest-coder-v1-14b-instruct","score":48,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"iquest-coder-v1-14b-thinking","score":37,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"iquest-coder-v1-7b-instruct","score":17.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"iquest-coder-v1-7b-thinking","score":13.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"iquest-q1","score":64.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"hy4-preview","score":64.3,"metric":"percent"},{"benchmark":"nl2repo","model":"iquest-q1","score":63,"metric":"percent"},{"benchmark":"cybergym","model":"iquest-q1","score":84.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"iquest-q1","score":83.2,"metric":"percent"},{"benchmark":"jobbench","model":"iquest-q1","score":55.7,"metric":"percent"},{"benchmark":"jobbench","model":"deepseek-v4-flash-0731","score":50,"metric":"percent"},{"benchmark":"jobbench","model":"glm-5.3-flash","score":49.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5","score":32.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"iquest-q1","score":29.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.3-flash","score":39.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"iquest-q1","score":39.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"minimax-m3","score":39,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-flash-0731","score":38.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-2b-instruct","score":41.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-8b-instruct","score":49.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-32b-instruct","score":54.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"mai-ui-2b","score":57.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"mai-ui-8b","score":65.8,"metric":"percent"},{"benchmark":"ui-vision","model":"gpt-4o","score":1.4,"metric":"percent"},{"benchmark":"ui-vision","model":"claude-3.7-sonnet","score":8.3,"metric":"percent"},{"benchmark":"ui-vision","model":"qwen3-vl-2b-instruct","score":6.2,"metric":"percent"},{"benchmark":"ui-vision","model":"qwen2.5-vl-7b","score":0.9,"metric":"percent"},{"benchmark":"ui-vision","model":"qwen3-vl-8b-instruct","score":17.5,"metric":"percent"},{"benchmark":"ui-vision","model":"ui-tars-1.5-7b","score":22.3,"metric":"percent"},{"benchmark":"ui-vision","model":"ui-venus-7b","score":26.5,"metric":"percent"},{"benchmark":"ui-vision","model":"qwen3-vl-32b-instruct","score":26.9,"metric":"percent"},{"benchmark":"ui-vision","model":"ui-venus-72b","score":36.8,"metric":"percent"},{"benchmark":"ui-vision","model":"mai-ui-2b","score":30.3,"metric":"percent"},{"benchmark":"ui-vision","model":"mai-ui-8b","score":40.7,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"gpt-4o","score":2.9,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"claude-3.7-sonnet","score":4.7,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"qwen3-vl-2b-instruct","score":46.5,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"ui-tars-1.5-7b","score":64.3,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"qwen3-vl-8b-instruct","score":81.3,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"gta1-32b","score":83.4,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"qwen3-vl-32b-instruct","score":85.3,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"internvl3-78b","score":72.2,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"mai-ui-2b","score":82.6,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"mai-ui-8b","score":88.8,"metric":"percent"},{"benchmark":"osworld-g","model":"seed-1.5-vl","score":62.9,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-2b-instruct","score":45.9,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-8b-instruct","score":54.8,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-32b-instruct","score":60.6,"metric":"percent"},{"benchmark":"osworld-g","model":"mai-ui-2b","score":52,"metric":"percent"},{"benchmark":"osworld-g","model":"mai-ui-8b","score":60.1,"metric":"percent"},{"benchmark":"androidworld","model":"ui-tars-1.5","score":64.2,"metric":"percent"},{"benchmark":"androidworld","model":"mai-ui-2b","score":49.1,"metric":"percent"},{"benchmark":"androidworld","model":"mai-ui-8b","score":70.7,"metric":"percent"},{"benchmark":"mobileworld","model":"ui-venus-7b","score":5.5,"metric":"percent"},{"benchmark":"mobileworld","model":"ui-venus-72b","score":10.4,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3-vl-8b-instruct","score":5.5,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3-vl-32b-instruct","score":9,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen3-vl-235b-a22b","score":9.5,"metric":"percent"},{"benchmark":"mobileworld","model":"mai-ui-8b","score":24.9,"metric":"percent"},{"benchmark":"androidworld","model":"gpt-5.5","score":74.1,"metric":"percent"},{"benchmark":"androidworld","model":"mai-gym-9b","score":75.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"mai-gym-9b","score":76.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minicpm5-1b","score":48.85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-0.6b","score":35.63,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-0.8b-thinking","score":42.74,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-1.2b-thinking","score":47.98,"metric":"percent"},{"benchmark":"mmlu-redux","model":"minicpm5-1b","score":70.06,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-0.6b","score":55.47,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-0.8b-thinking","score":61.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"lfm2.5-1.2b-thinking","score":66.08,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minicpm5-1b","score":26.26,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-0.6b","score":25.42,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-0.8b-thinking","score":30.98,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2.5-1.2b-thinking","score":34.85,"metric":"percent"},{"benchmark":"supergpqa","model":"minicpm5-1b","score":23.14,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3-0.6b","score":20.79,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-0.8b-thinking","score":22.92,"metric":"percent"},{"benchmark":"supergpqa","model":"lfm2.5-1.2b-thinking","score":22.83,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"minicpm5-1b","score":22.68,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-0.6b","score":4.12,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3.5-0.8b-thinking","score":0,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"lfm2.5-1.2b-thinking","score":6.19,"metric":"percent"},{"benchmark":"ojbench","model":"minicpm5-1b","score":7.33,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-0.6b","score":0.86,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-0.8b-thinking","score":0.43,"metric":"percent"},{"benchmark":"ojbench","model":"lfm2.5-1.2b-thinking","score":1.94,"metric":"percent"},{"benchmark":"livecodebench","model":"minicpm5-1b","score":33.52,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-0.6b","score":16,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-0.8b-thinking","score":5.33,"metric":"percent"},{"benchmark":"livecodebench","model":"lfm2.5-1.2b-thinking","score":21.33,"metric":"percent"},{"benchmark":"ifbench","model":"minicpm5-1b","score":46.67,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-0.6b","score":25.67,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-0.8b-thinking","score":29.33,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-1.2b-thinking","score":41.67,"metric":"percent"},{"benchmark":"ifeval","model":"minicpm5-1b","score":80.41,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-0.6b","score":59.89,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-0.8b-thinking","score":59.89,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-1.2b-thinking","score":84.84,"metric":"percent"},{"benchmark":"multi-if","model":"minicpm5-1b","score":43.54,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3-0.6b","score":36.56,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-0.8b-thinking","score":32.31,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-1.2b-thinking","score":55.61,"metric":"percent"},{"benchmark":"multichallenge","model":"minicpm5-1b","score":19.48,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3-0.6b","score":18.97,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.5-0.8b-thinking","score":23.97,"metric":"percent"},{"benchmark":"multichallenge","model":"lfm2.5-1.2b-thinking","score":23.28,"metric":"percent"},{"benchmark":"aime-2025","model":"minicpm5-1b","score":40.42,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-0.6b","score":16.25,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-0.8b-thinking","score":1.04,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2.5-1.2b-thinking","score":31.88,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minicpm5-1b","score":40.42,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-0.6b","score":12.29,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-0.8b-thinking","score":0.21,"metric":"percent"},{"benchmark":"aime-2026-i","model":"lfm2.5-1.2b-thinking","score":31.67,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"minicpm5-1b","score":25.76,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3-0.6b","score":9.85,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-0.8b-thinking","score":0.57,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"lfm2.5-1.2b-thinking","score":21.21,"metric":"percent"},{"benchmark":"math500","model":"minicpm5-1b","score":91.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-0.6b","score":72.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-0.8b-thinking","score":30.4,"metric":"percent"},{"benchmark":"math500","model":"lfm2.5-1.2b-thinking","score":89,"metric":"percent"},{"benchmark":"bbh","model":"minicpm5-1b","score":71.89,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-0.6b","score":47.86,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-0.8b-thinking","score":54.58,"metric":"percent"},{"benchmark":"bbh","model":"lfm2.5-1.2b-thinking","score":57.32,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"minicpm5-1b","score":12.14,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"qwen3-0.6b","score":3.78,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"qwen3.5-0.8b-thinking","score":8.53,"metric":"percent"},{"benchmark":"big-bench-extra-hard","model":"lfm2.5-1.2b-thinking","score":8.64,"metric":"percent"},{"benchmark":"bfcl-v4","model":"minicpm5-1b","score":25.15,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-0.6b","score":25.43,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-0.8b-thinking","score":25.53,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-1.2b-thinking","score":10.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"minicpm5-1b","score":79.53,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-0.6b","score":21.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-0.8b-thinking","score":47.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"lfm2.5-1.2b-thinking","score":19.6,"metric":"percent"},{"benchmark":"livecodebench","model":"minicpm5-2b","score":69.1,"metric":"percent"},{"benchmark":"livecodebench","model":"lfm2.5-2.6b","score":42.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-2b","score":20.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e2b-it","score":42.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b","score":56.4,"metric":"percent"},{"benchmark":"livecodebench","model":"granite-4.2-3b","score":58.9,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-nano-4b","score":50.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e4b-it","score":53.9,"metric":"percent"},{"benchmark":"livecodebench","model":"lfm2.5-8b-a1b","score":39.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"minicpm5-2b","score":68,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"lfm2.5-2.6b","score":30.9,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3.5-2b","score":10.3,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gemma-4-e2b-it","score":27.1,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3.5-4b","score":58.3,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"granite-4.2-3b","score":54.6,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nemotron-3-nano-4b","score":51.6,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gemma-4-e4b-it","score":45.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"lfm2.5-8b-a1b","score":27.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"minicpm5-2b","score":17.5,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"lfm2.5-2.6b","score":0,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3.5-2b","score":0,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gemma-4-e2b-it","score":0,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3.5-4b","score":7,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"granite-4.2-3b","score":5.3,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"nemotron-3-nano-4b","score":5.3,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gemma-4-e4b-it","score":1.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"lfm2.5-8b-a1b","score":0,"metric":"percent"},{"benchmark":"ojbench","model":"minicpm5-2b","score":32.5,"metric":"percent"},{"benchmark":"ojbench","model":"lfm2.5-2.6b","score":11.2,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-2b","score":2.6,"metric":"percent"},{"benchmark":"ojbench","model":"gemma-4-e2b-it","score":11.6,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-4b","score":24.8,"metric":"percent"},{"benchmark":"ojbench","model":"granite-4.2-3b","score":21.8,"metric":"percent"},{"benchmark":"ojbench","model":"nemotron-3-nano-4b","score":20,"metric":"percent"},{"benchmark":"ojbench","model":"gemma-4-e4b-it","score":19,"metric":"percent"},{"benchmark":"ojbench","model":"lfm2.5-8b-a1b","score":8.2,"metric":"percent"},{"benchmark":"aime-2025","model":"minicpm5-2b","score":86.5,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2.5-2.6b","score":41.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-2b","score":29.6,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e2b-it","score":31.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-4b","score":78.8,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-4.2-3b","score":79.4,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-nano-4b","score":56.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e4b-it","score":37.1,"metric":"percent"},{"benchmark":"aime-2025","model":"lfm2.5-8b-a1b","score":46,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minicpm5-2b","score":86.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"lfm2.5-2.6b","score":45.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-2b","score":29,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-e2b-it","score":39.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-4b","score":82.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"granite-4.2-3b","score":83.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-3-nano-4b","score":62.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-e4b-it","score":45,"metric":"percent"},{"benchmark":"aime-2026-i","model":"lfm2.5-8b-a1b","score":56.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"minicpm5-2b","score":63.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"lfm2.5-2.6b","score":33.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-2b","score":20.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-e2b-it","score":17.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-4b","score":64,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"granite-4.2-3b","score":60.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"nemotron-3-nano-4b","score":51.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-e4b-it","score":30.1,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"lfm2.5-8b-a1b","score":38.5,"metric":"percent"},{"benchmark":"math500","model":"minicpm5-2b","score":94.6,"metric":"percent"},{"benchmark":"math500","model":"lfm2.5-2.6b","score":89.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-2b","score":85.8,"metric":"percent"},{"benchmark":"math500","model":"gemma-4-e2b-it","score":85.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-4b","score":99,"metric":"percent"},{"benchmark":"math500","model":"granite-4.2-3b","score":97,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3-nano-4b","score":91.6,"metric":"percent"},{"benchmark":"math500","model":"gemma-4-e4b-it","score":88.2,"metric":"percent"},{"benchmark":"math500","model":"lfm2.5-8b-a1b","score":93.2,"metric":"percent"},{"benchmark":"ifbench","model":"minicpm5-2b","score":66.3,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-2.6b","score":59,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-2b","score":46,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e2b-it","score":25.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":59,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.2-3b","score":73,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-nano-4b","score":58.3,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":28.3,"metric":"percent"},{"benchmark":"ifbench","model":"lfm2.5-8b-a1b","score":51,"metric":"percent"},{"benchmark":"ifeval","model":"minicpm5-2b","score":86.7,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-2.6b","score":93.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-2b","score":77.5,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e2b-it","score":31.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-4b","score":90.2,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.2-3b","score":93.7,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-3-nano-4b","score":88,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e4b-it","score":44.4,"metric":"percent"},{"benchmark":"ifeval","model":"lfm2.5-8b-a1b","score":90.8,"metric":"percent"},{"benchmark":"multi-if","model":"minicpm5-2b","score":71.8,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-2.6b","score":76.8,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-2b","score":57.1,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e2b-it","score":40.3,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-4b","score":73.6,"metric":"percent"},{"benchmark":"multi-if","model":"granite-4.2-3b","score":75.9,"metric":"percent"},{"benchmark":"multi-if","model":"nemotron-3-nano-4b","score":65.9,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-e4b-it","score":45.9,"metric":"percent"},{"benchmark":"multi-if","model":"lfm2.5-8b-a1b","score":71.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minicpm5-2b","score":70.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-2.6b","score":65.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-2b","score":64.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-e2b-it","score":56,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-4b","score":78,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.2-3b","score":65.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-4b","score":65.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-e4b-it","score":68.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2.5-8b-a1b","score":63.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"minicpm5-2b","score":84.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"lfm2.5-2.6b","score":80,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-2b","score":80,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-4-e2b-it","score":71.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-4b","score":88.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"granite-4.2-3b","score":78.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"nemotron-3-nano-4b","score":79.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-4-e4b-it","score":83.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"lfm2.5-8b-a1b","score":80,"metric":"percent"},{"benchmark":"hle","model":"minicpm5-2b","score":8.9,"metric":"avg@3"},{"benchmark":"hle","model":"lfm2.5-2.6b","score":6.2,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-2b","score":2.6,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-e2b-it","score":4.8,"metric":"avg@3"},{"benchmark":"hle","model":"granite-4.2-3b","score":6.6,"metric":"avg@3"},{"benchmark":"hle","model":"nemotron-3-nano-4b","score":4.9,"metric":"avg@3"},{"benchmark":"hle","model":"lfm2.5-8b-a1b","score":6.9,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"minicpm5-2b","score":70.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2.5-2.6b","score":55.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-2b","score":45.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e2b-it","score":43.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"granite-4.2-3b","score":55.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-nano-4b","score":51.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2.5-8b-a1b","score":51.3,"metric":"percent"},{"benchmark":"supergpqa","model":"minicpm5-2b","score":40.8,"metric":"percent"},{"benchmark":"supergpqa","model":"lfm2.5-2.6b","score":26.2,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-2b","score":38.6,"metric":"percent"},{"benchmark":"supergpqa","model":"gemma-4-e2b-it","score":30.3,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-4b","score":52.8,"metric":"percent"},{"benchmark":"supergpqa","model":"granite-4.2-3b","score":39.9,"metric":"percent"},{"benchmark":"supergpqa","model":"nemotron-3-nano-4b","score":37.8,"metric":"percent"},{"benchmark":"supergpqa","model":"gemma-4-e4b-it","score":38.7,"metric":"percent"},{"benchmark":"supergpqa","model":"lfm2.5-8b-a1b","score":34.5,"metric":"percent"},{"benchmark":"aa-lcr","model":"minicpm5-2b","score":59,"metric":"percent"},{"benchmark":"aa-lcr","model":"lfm2.5-2.6b","score":5.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-2b","score":28.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-e2b-it","score":17,"metric":"percent"},{"benchmark":"aa-lcr","model":"granite-4.2-3b","score":24.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-nano-4b","score":17.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"lfm2.5-8b-a1b","score":0,"metric":"percent"},{"benchmark":"longbench-v2","model":"minicpm5-2b","score":43.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"lfm2.5-2.6b","score":30.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-2b","score":24.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemma-4-e2b-it","score":33.2,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.5-4b","score":47.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"granite-4.2-3b","score":36,"metric":"percent"},{"benchmark":"longbench-v2","model":"nemotron-3-nano-4b","score":32,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemma-4-e4b-it","score":42.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"lfm2.5-8b-a1b","score":30.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"minicpm5-2b","score":20.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"lfm2.5-2.6b","score":7.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-2b","score":2.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-e2b-it","score":3.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"granite-4.2-3b","score":5.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-nano-4b","score":1.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-e4b-it","score":4.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"lfm2.5-8b-a1b","score":3.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"minicpm5-2b","score":97.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"lfm2.5-2.6b","score":90.4,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-2b","score":69,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemma-4-e2b-it","score":20.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-4b","score":92.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"granite-4.2-3b","score":40.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-nano-4b","score":28.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemma-4-e4b-it","score":20.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"lfm2.5-8b-a1b","score":16.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"minicpm5-2b","score":66.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-2.6b","score":61.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e2b-it","score":36.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":56.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4.2-3b","score":52.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nemotron-3-nano-4b","score":43.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":47,"metric":"percent"},{"benchmark":"bfcl-v4","model":"lfm2.5-8b-a1b","score":49.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minicpm5-2b","score":46.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"lfm2.5-2.6b","score":6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-2b","score":5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-e2b-it","score":2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-4b","score":33.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"granite-4.2-3b","score":36.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-nano-4b","score":3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-e4b-it","score":15,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"lfm2.5-8b-a1b","score":0.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"minicpm5-2b","score":14.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"lfm2.5-2.6b","score":0.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-2b","score":0.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemma-4-e2b-it","score":0,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-4b","score":28.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"granite-4.2-3b","score":12.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"nemotron-3-nano-4b","score":0.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemma-4-e4b-it","score":3.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"lfm2.5-8b-a1b","score":0.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minicpm5-2b","score":8.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"lfm2.5-2.6b","score":4.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-2b","score":3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-e2b-it","score":0.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"granite-4.2-3b","score":13.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-nano-4b","score":3.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"lfm2.5-8b-a1b","score":1.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"minicpm5-2b","score":43.5,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"lfm2.5-2.6b","score":9.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"qwen3.5-2b","score":18.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gemma-4-e2b-it","score":4.7,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"qwen3.5-4b","score":39.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"granite-4.2-3b","score":21.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"nemotron-3-nano-4b","score":3.3,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gemma-4-e4b-it","score":7,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"lfm2.5-8b-a1b","score":13.2,"metric":"percent"},{"benchmark":"gaia-text-only","model":"minicpm5-2b","score":88.7,"metric":"percent"},{"benchmark":"gaia-text-only","model":"lfm2.5-2.6b","score":49.5,"metric":"percent"},{"benchmark":"gaia-text-only","model":"qwen3.5-2b","score":47.9,"metric":"percent"},{"benchmark":"gaia-text-only","model":"gemma-4-e2b-it","score":30.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"qwen3.5-4b","score":78.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"granite-4.2-3b","score":57.3,"metric":"percent"},{"benchmark":"gaia-text-only","model":"nemotron-3-nano-4b","score":26.5,"metric":"percent"},{"benchmark":"gaia-text-only","model":"gemma-4-e4b-it","score":39.5,"metric":"percent"},{"benchmark":"gaia-text-only","model":"lfm2.5-8b-a1b","score":41.1,"metric":"percent"},{"benchmark":"wildclawbench","model":"minicpm5-2b","score":23.9,"metric":"percent"},{"benchmark":"wildclawbench","model":"lfm2.5-2.6b","score":10.2,"metric":"percent"},{"benchmark":"wildclawbench","model":"qwen3.5-2b","score":9.2,"metric":"percent"},{"benchmark":"wildclawbench","model":"gemma-4-e2b-it","score":8.9,"metric":"percent"},{"benchmark":"wildclawbench","model":"qwen3.5-4b","score":17,"metric":"percent"},{"benchmark":"wildclawbench","model":"granite-4.2-3b","score":20,"metric":"percent"},{"benchmark":"wildclawbench","model":"nemotron-3-nano-4b","score":8.9,"metric":"percent"},{"benchmark":"wildclawbench","model":"gemma-4-e4b-it","score":14.3,"metric":"percent"},{"benchmark":"wildclawbench","model":"lfm2.5-8b-a1b","score":4.5,"metric":"percent"},{"benchmark":"qwenclawbench","model":"minicpm5-2b","score":42.9,"metric":"percent"},{"benchmark":"qwenclawbench","model":"lfm2.5-2.6b","score":19.3,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.5-2b","score":18.2,"metric":"percent"},{"benchmark":"qwenclawbench","model":"gemma-4-e2b-it","score":14.5,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.5-4b","score":37.1,"metric":"percent"},{"benchmark":"qwenclawbench","model":"granite-4.2-3b","score":36.4,"metric":"percent"},{"benchmark":"qwenclawbench","model":"nemotron-3-nano-4b","score":16.8,"metric":"percent"},{"benchmark":"qwenclawbench","model":"gemma-4-e4b-it","score":16.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"lfm2.5-8b-a1b","score":4.5,"metric":"percent"},{"benchmark":"browsecomp","model":"minimax-m2.5","score":76.3,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2.5","score":78.4,"metric":"percent"},{"benchmark":"browsecomp","model":"mirothinker-1.7-mini","score":67.9,"metric":"percent"},{"benchmark":"browsecomp","model":"mirothinker-1.7","score":74,"metric":"percent"},{"benchmark":"browsecomp","model":"mirothinker-h1","score":88.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"glm-5","score":72.7,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"seed2.0-pro","score":82.4,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"gpt-5","score":65,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"mirothinker-1.7-mini","score":72.3,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"mirothinker-1.7","score":75.3,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"mirothinker-h1","score":84.4,"metric":"percent"},{"benchmark":"hle-with-tools","model":"tongyi-deepresearch","score":32.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"seed2.0-pro","score":54.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gpt-5","score":35.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"gemini-3-pro","score":46.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"mirothinker-1.7-mini","score":36.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"mirothinker-1.7","score":42.9,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"mirothinker-h1","score":47.7,"metric":"avg@3"},{"benchmark":"gaia","model":"gpt-5","score":76.4,"metric":"percent"},{"benchmark":"gaia","model":"mirothinker-1.7-mini","score":80.3,"metric":"percent"},{"benchmark":"gaia","model":"mirothinker-1.7","score":82.7,"metric":"percent"},{"benchmark":"gaia","model":"mirothinker-h1","score":88.5,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"tongyi-deepresearch","score":55,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"kimi-k2.5","score":46,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"gpt-5","score":75,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"gemini-3-pro","score":53,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"mirothinker-1.7-mini","score":57.2,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"mirothinker-1.7","score":62,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"mirothinker-h1","score":72,"metric":"avg@3"},{"benchmark":"seal-0","model":"deepseek-v3.2","score":49.5,"metric":"percent"},{"benchmark":"seal-0","model":"seed2.0-pro","score":49.5,"metric":"percent"},{"benchmark":"seal-0","model":"mirothinker-1.7-mini","score":48.2,"metric":"percent"},{"benchmark":"seal-0","model":"mirothinker-1.7","score":53,"metric":"percent"},{"benchmark":"seal-0","model":"mirothinker-h1","score":61.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-s2-mobius","score":89.05,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-35b-a3b","score":85.31,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"intern-s2-mobius","score":80.81,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-35b-a3b","score":80.24,"metric":"percent"},{"benchmark":"imo-answerbench","model":"intern-s2-mobius","score":81.25,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-35b-a3b","score":77.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"intern-s2-mobius","score":95.31,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-35b-a3b","score":92.08,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"intern-s2-mobius","score":85.51,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-35b-a3b","score":78.5,"metric":"percent"},{"benchmark":"amobench","model":"intern-s2-mobius","score":58,"metric":"percent"},{"benchmark":"amobench","model":"qwen3.5-35b-a3b","score":50,"metric":"percent"},{"benchmark":"simpleqa","model":"intern-s2-mobius","score":28.9,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3.5-35b-a3b","score":21.39,"metric":"percent"},{"benchmark":"hle","model":"intern-s2-mobius","score":19.11,"metric":"avg@3"},{"benchmark":"biology-instruction","model":"intern-s2-mobius","score":51.4,"metric":"percent"},{"benchmark":"biology-instruction","model":"qwen3.5-35b-a3b","score":3.77,"metric":"percent"},{"benchmark":"mol-instructions","model":"intern-s2-mobius","score":45.73,"metric":"percent"},{"benchmark":"mol-instructions","model":"qwen3.5-35b-a3b","score":21.7,"metric":"percent"},{"benchmark":"molecular-iq","model":"intern-s2-mobius","score":59.29,"metric":"percent"},{"benchmark":"molecular-iq","model":"qwen3.5-35b-a3b","score":29.13,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis2.6-80b-a3b","score":88.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis2.6-80b-a3b","score":87.4,"metric":"percent"},{"benchmark":"mmstar","model":"ovis2.6-80b-a3b","score":77,"metric":"percent"},{"benchmark":"mmvet","model":"ovis2.6-80b-a3b","score":82.3,"metric":"percent"},{"benchmark":"mmmu","model":"ovis2.6-80b-a3b","score":75.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"ovis2.6-80b-a3b","score":66.3,"metric":"percent"},{"benchmark":"mathvista","model":"ovis2.6-80b-a3b","score":86.3,"metric":"percent"},{"benchmark":"mathverse","model":"ovis2.6-80b-a3b","score":80.5,"metric":"percent"},{"benchmark":"mathvision","model":"ovis2.6-80b-a3b","score":64.7,"metric":"percent"},{"benchmark":"logicvista","model":"ovis2.6-80b-a3b","score":66.9,"metric":"percent"},{"benchmark":"wemath","model":"ovis2.6-80b-a3b","score":70.9,"metric":"percent"},{"benchmark":"dynamath","model":"ovis2.6-80b-a3b","score":47.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"ovis2.6-80b-a3b","score":68.9,"metric":"percent"},{"benchmark":"blink","model":"ovis2.6-80b-a3b","score":71.1,"metric":"percent"},{"benchmark":"ocrbench","model":"ovis2.6-80b-a3b","score":91.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"ovis2.6-80b-a3b","score":74.2,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"ovis2.6-80b-a3b","score":66,"metric":"percent"},{"benchmark":"chartqa-pro","model":"ovis2.6-80b-a3b","score":69,"metric":"percent"},{"benchmark":"charxiv-rq","model":"ovis2.6-80b-a3b","score":68.1,"metric":"percent"},{"benchmark":"docvqa","model":"ovis2.6-80b-a3b","score":96.5,"metric":"percent"},{"benchmark":"infovqa","model":"ovis2.6-80b-a3b","score":90.9,"metric":"percent"},{"benchmark":"textvqa","model":"ovis2.6-80b-a3b","score":91.2,"metric":"percent"},{"benchmark":"ai2d","model":"ovis2.6-80b-a3b","score":90.5,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"ovis2.6-80b-a3b","score":55.6,"metric":"percent"},{"benchmark":"v-star","model":"ovis2.6-80b-a3b","score":94.8,"metric":"percent"},{"benchmark":"v-star","model":"gpt-5-mini","score":75.4,"metric":"percent"},{"benchmark":"v-star","model":"gemini-2.5-pro","score":81.2,"metric":"percent"},{"benchmark":"hrbench4k","model":"ovis2.6-80b-a3b","score":85,"metric":"percent"},{"benchmark":"hrbench8k","model":"ovis2.6-80b-a3b","score":83.4,"metric":"percent"},{"benchmark":"hrbench4k","model":"skywork-r1v4","score":82.8,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-30b-a3b-instruct","score":78.5,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen3-vl-235b-a22b","score":83,"metric":"percent"},{"benchmark":"hrbench4k","model":"gemini-2.5-flash","score":77.5,"metric":"percent"},{"benchmark":"hrbench4k","model":"gemini-2.5-pro","score":83.9,"metric":"percent"},{"benchmark":"hrbench8k","model":"skywork-r1v4","score":79.8,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-30b-a3b-instruct","score":74.2,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen3-vl-235b-a22b","score":80.4,"metric":"percent"},{"benchmark":"hrbench8k","model":"gemini-2.5-flash","score":73.7,"metric":"percent"},{"benchmark":"hrbench8k","model":"gemini-2.5-pro","score":81.5,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"skywork-r1v4","score":71.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen3-vl-30b-a3b-instruct","score":67.7,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen3-vl-235b-a22b","score":71.6,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gemini-2.5-flash","score":60.9,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gemini-2.5-pro","score":71.3,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"skywork-r1v4","score":70.8,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"qwen3-vl-30b-a3b-instruct","score":63.7,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"qwen3-vl-235b-a22b","score":68.8,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"gemini-2.5-flash","score":61.2,"metric":"percent"},{"benchmark":"mme-realworld-cn","model":"gemini-2.5-pro","score":69.3,"metric":"percent"},{"benchmark":"v-star","model":"skywork-r1v4","score":88,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-30b-a3b-instruct","score":82.2,"metric":"percent"},{"benchmark":"v-star","model":"qwen3-vl-235b-a22b","score":80.6,"metric":"percent"},{"benchmark":"v-star","model":"gemini-2.5-flash","score":72.3,"metric":"percent"},{"benchmark":"v-star","model":"gemini-2.5-pro","score":79.1,"metric":"percent"},{"benchmark":"treebench","model":"skywork-r1v4","score":48.4,"metric":"percent"},{"benchmark":"treebench","model":"qwen3-vl-30b-a3b-instruct","score":42.7,"metric":"percent"},{"benchmark":"treebench","model":"qwen3-vl-235b-a22b","score":49.6,"metric":"percent"},{"benchmark":"treebench","model":"gemini-2.5-flash","score":45.9,"metric":"percent"},{"benchmark":"treebench","model":"gemini-2.5-pro","score":54.6,"metric":"percent"},{"benchmark":"mmsearch","model":"skywork-r1v4","score":66.1,"metric":"percent"},{"benchmark":"mmsearch","model":"qwen3-vl-30b-a3b-instruct","score":18.7,"metric":"percent"},{"benchmark":"mmsearch","model":"qwen3-vl-235b-a22b","score":48,"metric":"percent"},{"benchmark":"mmsearch","model":"gemini-2.5-flash","score":64.9,"metric":"percent"},{"benchmark":"mmsearch","model":"gemini-2.5-pro","score":71.9,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"skywork-r1v4","score":38.4,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"qwen3-vl-30b-a3b-instruct","score":30,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"qwen3-vl-235b-a22b","score":31.6,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"gemini-2.5-flash","score":40.8,"metric":"percent"},{"benchmark":"browsecomp-vl","model":"gemini-2.5-pro","score":45.4,"metric":"percent"},{"benchmark":"biology-instruction","model":"intern-s2-397b","score":55.71,"metric":"percent"},{"benchmark":"biology-instruction","model":"qwen3.5-397b-a17b","score":4.49,"metric":"percent"},{"benchmark":"biology-instruction","model":"deepseek-v4-pro","score":9.14,"metric":"percent"},{"benchmark":"biology-instruction","model":"kimi-k2.7-code","score":7.68,"metric":"percent"},{"benchmark":"biology-instruction","model":"glm-5.2","score":6.34,"metric":"percent"},{"benchmark":"biology-instruction","model":"gpt-5.5","score":10.52,"metric":"percent"},{"benchmark":"biology-instruction","model":"gemini-3.1-pro","score":13.87,"metric":"percent"},{"benchmark":"biology-instruction","model":"claude-opus-4.8","score":6.78,"metric":"percent"},{"benchmark":"mol-instructions","model":"intern-s2-397b","score":53.95,"metric":"percent"},{"benchmark":"mol-instructions","model":"qwen3.5-397b-a17b","score":11.65,"metric":"percent"},{"benchmark":"mol-instructions","model":"deepseek-v4-pro","score":12.06,"metric":"percent"},{"benchmark":"mol-instructions","model":"kimi-k2.7-code","score":24.56,"metric":"percent"},{"benchmark":"mol-instructions","model":"glm-5.2","score":19.58,"metric":"percent"},{"benchmark":"mol-instructions","model":"gpt-5.5","score":40.49,"metric":"percent"},{"benchmark":"mol-instructions","model":"gemini-3.1-pro","score":38.84,"metric":"percent"},{"benchmark":"mol-instructions","model":"claude-opus-4.8","score":38.35,"metric":"percent"},{"benchmark":"molecular-iq","model":"intern-s2-397b","score":62.35,"metric":"percent"},{"benchmark":"molecular-iq","model":"qwen3.5-397b-a17b","score":41.48,"metric":"percent"},{"benchmark":"molecular-iq","model":"deepseek-v4-pro","score":44.43,"metric":"percent"},{"benchmark":"molecular-iq","model":"kimi-k2.7-code","score":52.81,"metric":"percent"},{"benchmark":"molecular-iq","model":"glm-5.2","score":60.91,"metric":"percent"},{"benchmark":"molecular-iq","model":"gpt-5.5","score":76.41,"metric":"percent"},{"benchmark":"molecular-iq","model":"gemini-3.1-pro","score":38.94,"metric":"percent"},{"benchmark":"molecular-iq","model":"claude-opus-4.8","score":66.78,"metric":"percent"},{"benchmark":"tomg-bench","model":"intern-s2-397b","score":66.76,"metric":"percent"},{"benchmark":"tomg-bench","model":"qwen3.5-397b-a17b","score":54.06,"metric":"percent"},{"benchmark":"tomg-bench","model":"deepseek-v4-pro","score":57.63,"metric":"percent"},{"benchmark":"tomg-bench","model":"kimi-k2.7-code","score":58.28,"metric":"percent"},{"benchmark":"tomg-bench","model":"glm-5.2","score":57.89,"metric":"percent"},{"benchmark":"tomg-bench","model":"gpt-5.5","score":69.89,"metric":"percent"},{"benchmark":"tomg-bench","model":"gemini-3.1-pro","score":62.67,"metric":"percent"},{"benchmark":"tomg-bench","model":"claude-opus-4.8","score":61.38,"metric":"percent"},{"benchmark":"xlrs-bench","model":"intern-s2-397b","score":51.38,"metric":"percent"},{"benchmark":"xlrs-bench","model":"qwen3.5-397b-a17b","score":50.11,"metric":"percent"},{"benchmark":"xlrs-bench","model":"kimi-k2.7-code","score":49.9,"metric":"percent"},{"benchmark":"xlrs-bench","model":"gpt-5.5","score":50.96,"metric":"percent"},{"benchmark":"xlrs-bench","model":"gemini-3.1-pro","score":54.27,"metric":"percent"},{"benchmark":"xlrs-bench","model":"claude-opus-4.8","score":51.84,"metric":"percent"},{"benchmark":"microvqa","model":"intern-s2-397b","score":69.67,"metric":"percent"},{"benchmark":"microvqa","model":"qwen3.5-397b-a17b","score":68.71,"metric":"percent"},{"benchmark":"microvqa","model":"kimi-k2.7-code","score":61.04,"metric":"percent"},{"benchmark":"microvqa","model":"gpt-5.5","score":63.63,"metric":"percent"},{"benchmark":"microvqa","model":"gemini-3.1-pro","score":71.02,"metric":"percent"},{"benchmark":"microvqa","model":"claude-opus-4.8","score":61.8,"metric":"percent"},{"benchmark":"sfe","model":"intern-s2-397b","score":60.74,"metric":"percent"},{"benchmark":"sfe","model":"qwen3.5-397b-a17b","score":62.97,"metric":"percent"},{"benchmark":"sfe","model":"kimi-k2.7-code","score":50.76,"metric":"percent"},{"benchmark":"sfe","model":"gpt-5.5","score":52.09,"metric":"percent"},{"benchmark":"sfe","model":"gemini-3.1-pro","score":59.57,"metric":"percent"},{"benchmark":"sfe","model":"claude-opus-4.8","score":59.08,"metric":"percent"},{"benchmark":"scicode","model":"intern-s2-397b","score":47.63,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-397b-a17b","score":46.35,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-pro","score":47.53,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k2.7-code","score":43.49,"metric":"percent"},{"benchmark":"scicode","model":"glm-5.2","score":51.97,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.5","score":55.92,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3.1-pro","score":54.44,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.8","score":56.21,"metric":"percent"},{"benchmark":"sgi-bench","model":"intern-s2-397b","score":51.89,"metric":"percent"},{"benchmark":"sgi-bench","model":"qwen3.5-397b-a17b","score":44.44,"metric":"percent"},{"benchmark":"sgi-bench","model":"deepseek-v4-pro","score":45.7,"metric":"percent"},{"benchmark":"sgi-bench","model":"kimi-k2.7-code","score":50.63,"metric":"percent"},{"benchmark":"sgi-bench","model":"glm-5.2","score":52.41,"metric":"percent"},{"benchmark":"sgi-bench","model":"gpt-5.5","score":42.77,"metric":"percent"},{"benchmark":"sgi-bench","model":"gemini-3.1-pro","score":45.28,"metric":"percent"},{"benchmark":"sgi-bench","model":"claude-opus-4.8","score":49.06,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"intern-s2-397b","score":87,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"qwen3.5-397b-a17b","score":67.67,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"deepseek-v4-pro","score":65.67,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"kimi-k2.7-code","score":79.67,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"glm-5.2","score":76,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.5","score":77,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"claude-opus-4.8","score":68,"metric":"percent"},{"benchmark":"frontierscience-research","model":"intern-s2-397b","score":55,"metric":"percent"},{"benchmark":"frontierscience-research","model":"qwen3.5-397b-a17b","score":26.67,"metric":"percent"},{"benchmark":"frontierscience-research","model":"deepseek-v4-pro","score":42.22,"metric":"percent"},{"benchmark":"frontierscience-research","model":"kimi-k2.7-code","score":51.11,"metric":"percent"},{"benchmark":"frontierscience-research","model":"glm-5.2","score":57.22,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.5","score":41.67,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gemini-3.1-pro","score":25,"metric":"percent"},{"benchmark":"frontierscience-research","model":"claude-opus-4.8","score":36.67,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-s2-397b","score":89.77,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-pro","score":86.86,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2.7-code","score":87.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-5.2","score":87.22,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.5","score":88.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.8","score":90.12,"metric":"percent"},{"benchmark":"advancedif","model":"intern-s2-397b","score":71.57,"metric":"percent"},{"benchmark":"advancedif","model":"qwen3.5-397b-a17b","score":75.49,"metric":"percent"},{"benchmark":"advancedif","model":"deepseek-v4-pro","score":73.83,"metric":"percent"},{"benchmark":"advancedif","model":"kimi-k2.7-code","score":76.17,"metric":"percent"},{"benchmark":"advancedif","model":"glm-5.2","score":75.76,"metric":"percent"},{"benchmark":"advancedif","model":"gpt-5.5","score":76.2,"metric":"percent"},{"benchmark":"advancedif","model":"gemini-3.1-pro","score":79.78,"metric":"percent"},{"benchmark":"advancedif","model":"claude-opus-4.8","score":72.88,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"intern-s2-397b","score":93.56,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-397b-a17b","score":87.88,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-pro","score":91.76,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"kimi-k2.7-code","score":90.34,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.5","score":97.06,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-opus-4.8","score":95.36,"metric":"percent"},{"benchmark":"mmmu-pro","model":"intern-s2-397b","score":81.68,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-397b-a17b","score":80.29,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k2.7-code","score":77.92,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.5","score":81.68,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-pro","score":83.99,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-opus-4.8","score":76.88,"metric":"percent"},{"benchmark":"chartqa-pro","model":"intern-s2-397b","score":71.12,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3.5-397b-a17b","score":68.61,"metric":"percent"},{"benchmark":"chartqa-pro","model":"kimi-k2.7-code","score":54.86,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gpt-5.5","score":69.23,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gemini-3.1-pro","score":71.18,"metric":"percent"},{"benchmark":"chartqa-pro","model":"claude-opus-4.8","score":58.65,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"intern-s2-397b","score":64.04,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k2.7-code","score":66.29,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.5","score":79.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"intern-s2-397b","score":68.54,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-397b-a17b","score":43.55,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-pro","score":49.98,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k2.7-code","score":53.49,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"glm-5.2","score":68.54,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.8","score":62.1,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"intern-s2-397b","score":84,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-397b-a17b","score":65,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-pro","score":72.44,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"kimi-k2.7-code","score":78.56,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.2","score":82,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gpt-5.5","score":73.33,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemini-3.1-pro","score":44,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.8","score":77,"metric":"percent"},{"benchmark":"biology-instruction","model":"intern-s2-preview","score":43.95,"metric":"percent"},{"benchmark":"biology-instruction","model":"intern-s1-pro","score":52.45,"metric":"percent"},{"benchmark":"biology-instruction","model":"qwen3.6-35b-a3b","score":6.83,"metric":"percent"},{"benchmark":"biology-instruction","model":"step-3.5-flash-20260204","score":2.77,"metric":"percent"},{"benchmark":"biology-instruction","model":"gemma-4-26b-a4b-it","score":4.16,"metric":"percent"},{"benchmark":"biology-instruction","model":"claude-4.5-haiku","score":4.75,"metric":"percent"},{"benchmark":"biology-instruction","model":"gemini-3.1-flash-lite","score":9.62,"metric":"percent"},{"benchmark":"biology-instruction","model":"gpt-5.4-nano","score":7.67,"metric":"percent"},{"benchmark":"microvqa","model":"intern-s2-preview","score":66.22,"metric":"percent"},{"benchmark":"microvqa","model":"intern-s1-pro","score":63.34,"metric":"percent"},{"benchmark":"microvqa","model":"qwen3.6-35b-a3b","score":63.63,"metric":"percent"},{"benchmark":"microvqa","model":"gemma-4-26b-a4b-it","score":63.92,"metric":"percent"},{"benchmark":"microvqa","model":"claude-4.5-haiku","score":53.17,"metric":"percent"},{"benchmark":"microvqa","model":"gemini-3.1-flash-lite","score":63.34,"metric":"percent"},{"benchmark":"microvqa","model":"gpt-5.4-nano","score":51.73,"metric":"percent"},{"benchmark":"mol-instructions","model":"intern-s2-preview","score":44.58,"metric":"percent"},{"benchmark":"mol-instructions","model":"intern-s1-pro","score":48.82,"metric":"percent"},{"benchmark":"mol-instructions","model":"qwen3.6-35b-a3b","score":5.89,"metric":"percent"},{"benchmark":"mol-instructions","model":"step-3.5-flash-20260204","score":6.55,"metric":"percent"},{"benchmark":"mol-instructions","model":"gemma-4-26b-a4b-it","score":7.87,"metric":"percent"},{"benchmark":"mol-instructions","model":"claude-4.5-haiku","score":9.65,"metric":"percent"},{"benchmark":"mol-instructions","model":"gemini-3.1-flash-lite","score":16.67,"metric":"percent"},{"benchmark":"mol-instructions","model":"gpt-5.4-nano","score":13.54,"metric":"percent"},{"benchmark":"molecular-iq","model":"intern-s2-preview","score":57.26,"metric":"percent"},{"benchmark":"molecular-iq","model":"intern-s1-pro","score":25.31,"metric":"percent"},{"benchmark":"molecular-iq","model":"qwen3.6-35b-a3b","score":32.62,"metric":"percent"},{"benchmark":"molecular-iq","model":"step-3.5-flash-20260204","score":45.94,"metric":"percent"},{"benchmark":"molecular-iq","model":"gemma-4-26b-a4b-it","score":32.97,"metric":"percent"},{"benchmark":"molecular-iq","model":"claude-4.5-haiku","score":31.74,"metric":"percent"},{"benchmark":"molecular-iq","model":"gemini-3.1-flash-lite","score":46.25,"metric":"percent"},{"benchmark":"molecular-iq","model":"gpt-5.4-nano","score":45.72,"metric":"percent"},{"benchmark":"sfe","model":"intern-s2-preview","score":58.43,"metric":"percent"},{"benchmark":"sfe","model":"intern-s1-pro","score":52.66,"metric":"percent"},{"benchmark":"sfe","model":"qwen3.6-35b-a3b","score":51.31,"metric":"percent"},{"benchmark":"sfe","model":"gemma-4-26b-a4b-it","score":63.09,"metric":"percent"},{"benchmark":"sfe","model":"claude-4.5-haiku","score":48.51,"metric":"percent"},{"benchmark":"sfe","model":"gemini-3.1-flash-lite","score":52.03,"metric":"percent"},{"benchmark":"sfe","model":"gpt-5.4-nano","score":36.8,"metric":"percent"},{"benchmark":"xlrs-bench","model":"intern-s2-preview","score":50.71,"metric":"percent"},{"benchmark":"xlrs-bench","model":"intern-s1-pro","score":48.41,"metric":"percent"},{"benchmark":"xlrs-bench","model":"qwen3.6-35b-a3b","score":45.42,"metric":"percent"},{"benchmark":"xlrs-bench","model":"gemma-4-26b-a4b-it","score":46.92,"metric":"percent"},{"benchmark":"xlrs-bench","model":"claude-4.5-haiku","score":44.86,"metric":"percent"},{"benchmark":"xlrs-bench","model":"gemini-3.1-flash-lite","score":49.29,"metric":"percent"},{"benchmark":"xlrs-bench","model":"gpt-5.4-nano","score":42.71,"metric":"percent"},{"benchmark":"scireasoner","model":"intern-s2-preview","score":45.82,"metric":"percent"},{"benchmark":"scireasoner","model":"intern-s1-pro","score":54.22,"metric":"percent"},{"benchmark":"scireasoner","model":"qwen3.6-35b-a3b","score":13.72,"metric":"percent"},{"benchmark":"scireasoner","model":"step-3.5-flash-20260204","score":13.29,"metric":"percent"},{"benchmark":"scireasoner","model":"gemma-4-26b-a4b-it","score":16.28,"metric":"percent"},{"benchmark":"scireasoner","model":"claude-4.5-haiku","score":12.65,"metric":"percent"},{"benchmark":"scireasoner","model":"gemini-3.1-flash-lite","score":14.48,"metric":"percent"},{"benchmark":"scireasoner","model":"gpt-5.4-nano","score":11.91,"metric":"percent"},{"benchmark":"sgi-bench","model":"intern-s2-preview","score":52.52,"metric":"percent"},{"benchmark":"sgi-bench","model":"intern-s1-pro","score":38.36,"metric":"percent"},{"benchmark":"sgi-bench","model":"qwen3.6-35b-a3b","score":37.3,"metric":"percent"},{"benchmark":"sgi-bench","model":"step-3.5-flash-20260204","score":36.16,"metric":"percent"},{"benchmark":"sgi-bench","model":"gemma-4-26b-a4b-it","score":26.1,"metric":"percent"},{"benchmark":"sgi-bench","model":"claude-4.5-haiku","score":37.11,"metric":"percent"},{"benchmark":"sgi-bench","model":"gemini-3.1-flash-lite","score":16.35,"metric":"percent"},{"benchmark":"sgi-bench","model":"gpt-5.4-nano","score":25.73,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"intern-s2-preview","score":60.33,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"intern-s1-pro","score":53.33,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"qwen3.6-35b-a3b","score":65,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"step-3.5-flash-20260204","score":70,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gemma-4-26b-a4b-it","score":58,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"claude-4.5-haiku","score":31.67,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gemini-3.1-flash-lite","score":45.41,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.4-nano","score":20.13,"metric":"percent"},{"benchmark":"frontierscience-research","model":"intern-s2-preview","score":19.44,"metric":"percent"},{"benchmark":"frontierscience-research","model":"intern-s1-pro","score":12.22,"metric":"percent"},{"benchmark":"frontierscience-research","model":"qwen3.6-35b-a3b","score":10,"metric":"percent"},{"benchmark":"frontierscience-research","model":"step-3.5-flash-20260204","score":10,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gemma-4-26b-a4b-it","score":3.33,"metric":"percent"},{"benchmark":"frontierscience-research","model":"claude-4.5-haiku","score":17.78,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gemini-3.1-flash-lite","score":3.89,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.4-nano","score":5.56,"metric":"percent"},{"benchmark":"scicode","model":"intern-s2-preview","score":39.64,"metric":"percent"},{"benchmark":"scicode","model":"intern-s1-pro","score":42.74,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-35b-a3b","score":40.6,"metric":"percent"},{"benchmark":"scicode","model":"step-3.5-flash-20260204","score":46.15,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-26b-a4b-it","score":42.6,"metric":"percent"},{"benchmark":"scicode","model":"claude-4.5-haiku","score":40.48,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3.1-flash-lite","score":41.12,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.4-nano","score":35.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-s2-preview","score":88,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-s1-pro","score":86.59,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-35b-a3b","score":85.12,"metric":"percent"},{"benchmark":"mmlu-pro","model":"step-3.5-flash-20260204","score":83.44,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-26b-a4b-it","score":84.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-4.5-haiku","score":82.16,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3.1-flash-lite","score":87.31,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.4-nano","score":78.91,"metric":"percent"},{"benchmark":"mmmu-pro","model":"intern-s2-preview","score":76.88,"metric":"percent"},{"benchmark":"mmmu-pro","model":"intern-s1-pro","score":72.77,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.6-35b-a3b","score":74.28,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-26b-a4b-it","score":73.82,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-4.5-haiku","score":63.12,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3.1-flash-lite","score":76.07,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.4-nano","score":63.41,"metric":"percent"},{"benchmark":"hle-text-only","model":"intern-s2-preview","score":21.94,"metric":"percent"},{"benchmark":"hle-text-only","model":"intern-s1-pro","score":19.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.6-35b-a3b","score":21.42,"metric":"percent"},{"benchmark":"hle-text-only","model":"step-3.5-flash-20260204","score":23.04,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemma-4-26b-a4b-it","score":8.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-4.5-haiku","score":8.26,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemini-3.1-flash-lite","score":19.41,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.4-nano","score":19.87,"metric":"percent"},{"benchmark":"hle","model":"intern-s2-preview","score":18.07,"metric":"avg@3"},{"benchmark":"hle","model":"intern-s1-pro","score":10.63,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.6-35b-a3b","score":17.04,"metric":"avg@3"},{"benchmark":"hle","model":"gemma-4-26b-a4b-it","score":9.37,"metric":"avg@3"},{"benchmark":"hle","model":"claude-4.5-haiku","score":6.85,"metric":"avg@3"},{"benchmark":"hle","model":"gemini-3.1-flash-lite","score":14.74,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4-nano","score":15.15,"metric":"avg@3"},{"benchmark":"imo-answerbench","model":"intern-s2-preview","score":84,"metric":"percent"},{"benchmark":"imo-answerbench","model":"intern-s1-pro","score":77.25,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.6-35b-a3b","score":81,"metric":"percent"},{"benchmark":"imo-answerbench","model":"step-3.5-flash-20260204","score":79,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-26b-a4b-it","score":64.25,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-4.5-haiku","score":60.75,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemini-3.1-flash-lite","score":64.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.4-nano","score":73.5,"metric":"percent"},{"benchmark":"mathvision","model":"intern-s2-preview","score":83.36,"metric":"percent"},{"benchmark":"mathvision","model":"intern-s1-pro","score":72.43,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.6-35b-a3b","score":80.59,"metric":"percent"},{"benchmark":"mathvision","model":"claude-4.5-haiku","score":65.79,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3.1-flash-lite","score":70.43,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.4-nano","score":71.91,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"intern-s2-preview","score":87.31,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"intern-s1-pro","score":79.92,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.6-35b-a3b","score":83.24,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"step-3.5-flash-20260204","score":85.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-26b-a4b-it","score":69.79,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"claude-4.5-haiku","score":62.41,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemini-3.1-flash-lite","score":73.48,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.4-nano","score":81.25,"metric":"percent"},{"benchmark":"chartqa-pro","model":"intern-s2-preview","score":68.9,"metric":"percent"},{"benchmark":"chartqa-pro","model":"intern-s1-pro","score":64.66,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3.6-35b-a3b","score":64.54,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gemma-4-26b-a4b-it","score":44.26,"metric":"percent"},{"benchmark":"chartqa-pro","model":"claude-4.5-haiku","score":52.87,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gemini-3.1-flash-lite","score":67.77,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gpt-5.4-nano","score":57.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"intern-s2-preview","score":27.8,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"intern-s1-pro","score":41.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"qwen3.6-35b-a3b","score":20.8,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"step-3.5-flash-20260204","score":22.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemma-4-26b-a4b-it","score":9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-4.5-haiku","score":8,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gemini-3.1-flash-lite","score":42.5,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.4-nano","score":11.7,"metric":"percent"},{"benchmark":"ifbench","model":"intern-s2-preview","score":80.87,"metric":"percent"},{"benchmark":"ifbench","model":"intern-s1-pro","score":69,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":63.52,"metric":"percent"},{"benchmark":"ifbench","model":"step-3.5-flash-20260204","score":65.72,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-26b-a4b-it","score":77.74,"metric":"percent"},{"benchmark":"ifbench","model":"claude-4.5-haiku","score":49.92,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-3.1-flash-lite","score":76.15,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.4-nano","score":66.21,"metric":"percent"},{"benchmark":"pinchbench","model":"intern-s2-preview","score":88.22,"metric":"percent"},{"benchmark":"pinchbench","model":"intern-s1-pro","score":64.83,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.6-35b-a3b","score":87.05,"metric":"percent"},{"benchmark":"pinchbench","model":"step-3.5-flash-20260204","score":85,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-26b-a4b-it","score":84.13,"metric":"percent"},{"benchmark":"pinchbench","model":"claude-4.5-haiku","score":85.77,"metric":"percent"},{"benchmark":"pinchbench","model":"gemini-3.1-flash-lite","score":84.77,"metric":"percent"},{"benchmark":"pinchbench","model":"gpt-5.4-nano","score":79.37,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"intern-s2-preview","score":64,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"intern-s1-pro","score":38.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-26b-a4b-it","score":49.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemini-3.1-flash-lite","score":59.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.4-nano","score":42.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-s2-preview-397b","score":89.75,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"intern-s2-preview-397b","score":69.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"qwen3.5-397b-a17b","score":54.8,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"deepseek-v4-pro","score":46.6,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"kimi-k2.7-code","score":38.6,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"glm-5.2","score":37.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.5","score":64.3,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"claude-opus-4.8","score":43.3,"metric":"percent"},{"benchmark":"advancedif","model":"intern-s2-preview-397b","score":74.44,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"intern-s2-preview-397b","score":91.57,"metric":"percent"},{"benchmark":"mmmu-pro","model":"intern-s2-preview-397b","score":80.46,"metric":"percent"},{"benchmark":"chartqa-pro","model":"intern-s2-preview-397b","score":69.65,"metric":"percent"},{"benchmark":"skillsbench","model":"intern-s2-preview-397b","score":50.03,"metric":"percent"},{"benchmark":"skillsbench","model":"qwen3.5-397b-a17b","score":35.58,"metric":"percent"},{"benchmark":"skillsbench","model":"deepseek-v4-pro","score":49.53,"metric":"percent"},{"benchmark":"skillsbench","model":"kimi-k2.7-code","score":55.63,"metric":"percent"},{"benchmark":"skillsbench","model":"glm-5.2","score":53.19,"metric":"percent"},{"benchmark":"skillsbench","model":"gpt-5.5","score":49.59,"metric":"percent"},{"benchmark":"skillsbench","model":"gemini-3.1-pro","score":37.2,"metric":"percent"},{"benchmark":"skillsbench","model":"claude-opus-4.8","score":54.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"intern-s2-preview-397b","score":67.42,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"intern-s2-preview-397b","score":61.56,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"kimi-k2.7-code","score":57.59,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"intern-s2-preview-397b","score":81.67,"metric":"percent"},{"benchmark":"biology-instruction","model":"intern-s2-preview-397b","score":56.92,"metric":"percent"},{"benchmark":"mol-instructions","model":"intern-s2-preview-397b","score":52.37,"metric":"percent"},{"benchmark":"molecular-iq","model":"intern-s2-preview-397b","score":61.49,"metric":"percent"},{"benchmark":"scireasoner","model":"intern-s2-preview-397b","score":63.97,"metric":"percent"},{"benchmark":"scireasoner","model":"qwen3.5-397b-a17b","score":45.02,"metric":"percent"},{"benchmark":"scireasoner","model":"deepseek-v4-pro","score":51.11,"metric":"percent"},{"benchmark":"scireasoner","model":"kimi-k2.7-code","score":51.69,"metric":"percent"},{"benchmark":"scireasoner","model":"glm-5.2","score":51.45,"metric":"percent"},{"benchmark":"scireasoner","model":"gpt-5.5","score":61.15,"metric":"percent"},{"benchmark":"scireasoner","model":"gemini-3.1-pro","score":60.35,"metric":"percent"},{"benchmark":"scireasoner","model":"claude-opus-4.8","score":58,"metric":"percent"},{"benchmark":"tomg-bench","model":"intern-s2-preview-397b","score":65.66,"metric":"percent"},{"benchmark":"xlrs-bench","model":"intern-s2-preview-397b","score":51.97,"metric":"percent"},{"benchmark":"microvqa","model":"intern-s2-preview-397b","score":68.81,"metric":"percent"},{"benchmark":"sfe","model":"intern-s2-preview-397b","score":61.67,"metric":"percent"},{"benchmark":"scicode","model":"intern-s2-preview-397b","score":49.11,"metric":"percent"},{"benchmark":"sgi-bench","model":"intern-s2-preview-397b","score":49.37,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-30b-a3b-2507","score":81.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-coder-480b-a35b-instruct","score":82.4,"metric":"percent"},{"benchmark":"ifeval","model":"telechat3-coder-36b-thinking","score":84.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-dev-72b","score":60.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-32b-thinking","score":28,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-30b-a3b-2507","score":51.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-coder-480b-a35b-instruct","score":69.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"telechat3-coder-36b-thinking","score":65,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-32b-thinking","score":1.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-30b-a3b-2507","score":31.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-coder-480b-a35b-instruct","score":37.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"telechat3-coder-36b-thinking","score":34.8,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-dev-72b","score":51.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b-thinking","score":66.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-2507","score":42.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-coder-480b-a35b-instruct","score":57.5,"metric":"percent"},{"benchmark":"livecodebench","model":"telechat3-coder-36b-thinking","score":78.2,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3-32b-thinking","score":64.3,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3-30b-a3b-2507","score":73.8,"metric":"percent"},{"benchmark":"artifactsbench","model":"qwen3-coder-480b-a35b-instruct","score":78.7,"metric":"percent"},{"benchmark":"artifactsbench","model":"telechat3-coder-36b-thinking","score":82.8,"metric":"percent"},{"benchmark":"humaneval-x","model":"kimi-dev-72b","score":67.44,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen3-32b-thinking","score":84.3,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen3-30b-a3b-2507","score":88.9,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen3-coder-480b-a35b-instruct","score":91.7,"metric":"percent"},{"benchmark":"humaneval-x","model":"telechat3-coder-36b-thinking","score":88.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-32b-thinking","score":83.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-30b-a3b-2507","score":79.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-coder-480b-a35b-instruct","score":79.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"telechat3-coder-36b-thinking","score":84.2,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-32b-thinking","score":95,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-30b-a3b-2507","score":74.1,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3-coder-480b-a35b-instruct","score":75.9,"metric":"percent"},{"benchmark":"cruxeval","model":"telechat3-coder-36b-thinking","score":89.7,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-30b-a3b-2507","score":59.2,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-coder-480b-a35b-instruct","score":68.7,"metric":"percent"},{"benchmark":"bfcl-v3","model":"telechat3-coder-36b-thinking","score":70.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-v-4.6","score":82.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3.5-0.8b","score":68,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemma-4-e2b-it","score":68.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"lfm2.5-vl-1.6b","score":65.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-v-4.6","score":80.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen3.5-0.8b","score":68,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemma-4-e2b-it","score":64.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"lfm2.5-vl-1.6b","score":65,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-v-4.6","score":68,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-0.8b","score":55.9,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-e2b-it","score":55.7,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2.5-vl-1.6b","score":50.7,"metric":"percent"},{"benchmark":"ai2d","model":"minicpm-v-4.6","score":85.1,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-0.8b","score":68.7,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-4-e2b-it","score":73,"metric":"percent"},{"benchmark":"ai2d","model":"lfm2.5-vl-1.6b","score":72.5,"metric":"percent"},{"benchmark":"mmt-bench","model":"minicpm-v-4.6","score":60,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3.5-0.8b","score":50.9,"metric":"percent"},{"benchmark":"mmt-bench","model":"gemma-4-e2b-it","score":56.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"lfm2.5-vl-1.6b","score":54.1,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v-4.6","score":52.6,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-0.8b","score":47.4,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-e2b-it","score":59.6,"metric":"percent"},{"benchmark":"mmmu","model":"lfm2.5-vl-1.6b","score":40.6,"metric":"percent"},{"benchmark":"mathvista","model":"minicpm-v-4.6","score":75.5,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3.5-0.8b","score":58.6,"metric":"percent"},{"benchmark":"mathvista","model":"gemma-4-e2b-it","score":58.5,"metric":"percent"},{"benchmark":"mathvista","model":"lfm2.5-vl-1.6b","score":55.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"minicpm-v-4.6","score":35.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-e2b-it","score":33.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"lfm2.5-vl-1.6b","score":19.8,"metric":"percent"},{"benchmark":"mathverse-mini","model":"minicpm-v-4.6","score":56.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3.5-0.8b","score":49.2,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gemma-4-e2b-it","score":47,"metric":"percent"},{"benchmark":"mathverse-mini","model":"lfm2.5-vl-1.6b","score":26.3,"metric":"percent"},{"benchmark":"wemath","model":"minicpm-v-4.6","score":48.8,"metric":"percent"},{"benchmark":"wemath","model":"qwen3.5-0.8b","score":33.1,"metric":"percent"},{"benchmark":"wemath","model":"gemma-4-e2b-it","score":41.1,"metric":"percent"},{"benchmark":"wemath","model":"lfm2.5-vl-1.6b","score":12.7,"metric":"percent"},{"benchmark":"dynamath","model":"minicpm-v-4.6","score":59.1,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-0.8b","score":46.5,"metric":"percent"},{"benchmark":"dynamath","model":"gemma-4-e2b-it","score":58.3,"metric":"percent"},{"benchmark":"dynamath","model":"lfm2.5-vl-1.6b","score":30.6,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-v-4.6","score":83.8,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-0.8b","score":79.1,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-4-e2b-it","score":73.5,"metric":"percent"},{"benchmark":"ocrbench","model":"lfm2.5-vl-1.6b","score":79.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"minicpm-v-4.6","score":40.6,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-0.8b","score":39.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemma-4-e2b-it","score":44.3,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"lfm2.5-vl-1.6b","score":41.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"minicpm-v-4.6","score":47.3,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.5-0.8b","score":36.1,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gemma-4-e2b-it","score":24.6,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"lfm2.5-vl-1.6b","score":23.2,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-v-4.6","score":89.4,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3.5-0.8b","score":87.9,"metric":"percent"},{"benchmark":"docvqa","model":"gemma-4-e2b-it","score":74.5,"metric":"percent"},{"benchmark":"docvqa","model":"lfm2.5-vl-1.6b","score":87.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-v-4.6","score":45.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-0.8b","score":38.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemma-4-e2b-it","score":33.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"lfm2.5-vl-1.6b","score":25.4,"metric":"percent"},{"benchmark":"refcoco","model":"minicpm-v-4.6","score":86.7,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-0.8b","score":77.8,"metric":"percent"},{"benchmark":"refcoco","model":"gemma-4-e2b-it","score":65.5,"metric":"percent"},{"benchmark":"blink","model":"minicpm-v-4.6","score":55.5,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-0.8b","score":46.3,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-e2b-it","score":51.6,"metric":"percent"},{"benchmark":"blink","model":"lfm2.5-vl-1.6b","score":48.8,"metric":"percent"},{"benchmark":"muirbench","model":"minicpm-v-4.6","score":60.2,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3.5-0.8b","score":41.8,"metric":"percent"},{"benchmark":"muirbench","model":"gemma-4-e2b-it","score":46.6,"metric":"percent"},{"benchmark":"muirbench","model":"lfm2.5-vl-1.6b","score":29.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-v-4.6","score":58.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-0.8b","score":46.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-4-e2b-it","score":44.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"lfm2.5-vl-1.6b","score":42,"metric":"percent"},{"benchmark":"mmhal-bench","model":"minicpm-v-4.6","score":4.6,"metric":"score"},{"benchmark":"mmhal-bench","model":"qwen3.5-0.8b","score":2.5,"metric":"score"},{"benchmark":"mmhal-bench","model":"gemma-4-e2b-it","score":2.7,"metric":"score"},{"benchmark":"mmhal-bench","model":"lfm2.5-vl-1.6b","score":2.9,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"minicpm-v-4.6","score":30.6,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"qwen3.5-0.8b","score":41.7,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"gemma-4-e2b-it","score":59.4,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"lfm2.5-vl-1.6b","score":33.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"minicpm-v-4.6","score":59.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.5-0.8b","score":48.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemma-4-e2b-it","score":56.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"lfm2.5-vl-1.6b","score":40.9,"metric":"percent"},{"benchmark":"lvbench","model":"minicpm-v-4.6","score":42,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3.5-0.8b","score":35.8,"metric":"percent"},{"benchmark":"lvbench","model":"gemma-4-e2b-it","score":33.3,"metric":"percent"},{"benchmark":"lvbench","model":"lfm2.5-vl-1.6b","score":25.4,"metric":"percent"},{"benchmark":"mlvu","model":"minicpm-v-4.6","score":65.2,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-0.8b","score":54.9,"metric":"percent"},{"benchmark":"mlvu","model":"gemma-4-e2b-it","score":40.4,"metric":"percent"},{"benchmark":"mlvu","model":"lfm2.5-vl-1.6b","score":32.5,"metric":"percent"},{"benchmark":"longvideobench","model":"minicpm-v-4.6","score":53.8,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3.5-0.8b","score":47.2,"metric":"percent"},{"benchmark":"longvideobench","model":"gemma-4-e2b-it","score":46.4,"metric":"percent"},{"benchmark":"longvideobench","model":"lfm2.5-vl-1.6b","score":30.4,"metric":"percent"},{"benchmark":"motionbench","model":"minicpm-v-4.6","score":54.2,"metric":"percent"},{"benchmark":"motionbench","model":"qwen3.5-0.8b","score":51.6,"metric":"percent"},{"benchmark":"motionbench","model":"gemma-4-e2b-it","score":42.5,"metric":"percent"},{"benchmark":"motionbench","model":"lfm2.5-vl-1.6b","score":28.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-v-4.6-thinking","score":84.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3.5-0.8b-thinking","score":69.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemma-4-e2b-it","score":63.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"lfm2.5-vl-1.6b","score":70,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-v-4.6-thinking","score":81.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen3.5-0.8b-thinking","score":69.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemma-4-e2b-it","score":53.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"lfm2.5-vl-1.6b","score":65.5,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-v-4.6-thinking","score":70.2,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-0.8b-thinking","score":58.3,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-e2b-it","score":58.1,"metric":"percent"},{"benchmark":"mmstar","model":"lfm2.5-vl-1.6b","score":51,"metric":"percent"},{"benchmark":"ai2d","model":"minicpm-v-4.6-thinking","score":84.6,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-0.8b-thinking","score":69.9,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-4-e2b-it","score":72.4,"metric":"percent"},{"benchmark":"ai2d","model":"lfm2.5-vl-1.6b","score":72.4,"metric":"percent"},{"benchmark":"mmt-bench","model":"minicpm-v-4.6-thinking","score":62.5,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3.5-0.8b-thinking","score":53.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"gemma-4-e2b-it","score":57.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"lfm2.5-vl-1.6b","score":54.4,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v-4.6-thinking","score":55.3,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-0.8b-thinking","score":49,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-e2b-it","score":59.9,"metric":"percent"},{"benchmark":"mathvista","model":"minicpm-v-4.6-thinking","score":75.6,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3.5-0.8b-thinking","score":62.2,"metric":"percent"},{"benchmark":"mathvista","model":"gemma-4-e2b-it","score":58.6,"metric":"percent"},{"benchmark":"mathvista","model":"lfm2.5-vl-1.6b","score":56.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"minicpm-v-4.6-thinking","score":33.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-0.8b-thinking","score":31.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-e2b-it","score":37.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"lfm2.5-vl-1.6b","score":20.3,"metric":"percent"},{"benchmark":"mathverse-mini","model":"minicpm-v-4.6-thinking","score":58.3,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3.5-0.8b-thinking","score":48.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gemma-4-e2b-it","score":47.6,"metric":"percent"},{"benchmark":"mathverse-mini","model":"lfm2.5-vl-1.6b","score":26,"metric":"percent"},{"benchmark":"wemath","model":"minicpm-v-4.6-thinking","score":54.3,"metric":"percent"},{"benchmark":"wemath","model":"qwen3.5-0.8b-thinking","score":37.3,"metric":"percent"},{"benchmark":"wemath","model":"gemma-4-e2b-it","score":40.5,"metric":"percent"},{"benchmark":"wemath","model":"lfm2.5-vl-1.6b","score":12.3,"metric":"percent"},{"benchmark":"dynamath","model":"minicpm-v-4.6-thinking","score":61.1,"metric":"percent"},{"benchmark":"dynamath","model":"qwen3.5-0.8b-thinking","score":49.9,"metric":"percent"},{"benchmark":"dynamath","model":"gemma-4-e2b-it","score":50.1,"metric":"percent"},{"benchmark":"dynamath","model":"lfm2.5-vl-1.6b","score":31.3,"metric":"percent"},{"benchmark":"logicvista","model":"minicpm-v-4.6-thinking","score":47.7,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3.5-0.8b-thinking","score":35.4,"metric":"percent"},{"benchmark":"logicvista","model":"gemma-4-e2b-it","score":46.5,"metric":"percent"},{"benchmark":"logicvista","model":"lfm2.5-vl-1.6b","score":28.6,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-v-4.6-thinking","score":85.7,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-0.8b-thinking","score":74.5,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-4-e2b-it","score":78,"metric":"percent"},{"benchmark":"ocrbench","model":"lfm2.5-vl-1.6b","score":79.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"minicpm-v-4.6-thinking","score":36,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-0.8b-thinking","score":42.9,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemma-4-e2b-it","score":46.4,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"lfm2.5-vl-1.6b","score":41.8,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"minicpm-v-4.6-thinking","score":31.3,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.5-0.8b-thinking","score":40.9,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"gemma-4-e2b-it","score":21.7,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"lfm2.5-vl-1.6b","score":23.5,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-v-4.6-thinking","score":88.9,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3.5-0.8b-thinking","score":87.7,"metric":"percent"},{"benchmark":"docvqa","model":"gemma-4-e2b-it","score":75.2,"metric":"percent"},{"benchmark":"docvqa","model":"lfm2.5-vl-1.6b","score":87.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-v-4.6-thinking","score":47.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-0.8b-thinking","score":41.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemma-4-e2b-it","score":30.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"lfm2.5-vl-1.6b","score":25.7,"metric":"percent"},{"benchmark":"blink","model":"minicpm-v-4.6-thinking","score":60.1,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-0.8b-thinking","score":49.2,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-e2b-it","score":50.6,"metric":"percent"},{"benchmark":"blink","model":"lfm2.5-vl-1.6b","score":47.8,"metric":"percent"},{"benchmark":"muirbench","model":"minicpm-v-4.6-thinking","score":53.4,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3.5-0.8b-thinking","score":45.3,"metric":"percent"},{"benchmark":"muirbench","model":"gemma-4-e2b-it","score":39.1,"metric":"percent"},{"benchmark":"muirbench","model":"lfm2.5-vl-1.6b","score":29.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-v-4.6-thinking","score":57.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.5-0.8b-thinking","score":53.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-4-e2b-it","score":45.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"lfm2.5-vl-1.6b","score":41.6,"metric":"percent"},{"benchmark":"mmhal-bench","model":"minicpm-v-4.6-thinking","score":4.7,"metric":"score"},{"benchmark":"mmhal-bench","model":"qwen3.5-0.8b-thinking","score":2.7,"metric":"score"},{"benchmark":"mmhal-bench","model":"gemma-4-e2b-it","score":3.6,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"minicpm-v-4.6-thinking","score":28.1,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"qwen3.5-0.8b-thinking","score":41.7,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"gemma-4-e2b-it","score":50,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"lfm2.5-vl-1.6b","score":32.3,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-v-4.7-35b-a3b","score":80.67,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.6-35b-a3b","score":76,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.6-27b","score":74.4,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.8-27b","score":75.13,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-31b-it","score":76.47,"metric":"percent"},{"benchmark":"mmt-bench","model":"minicpm-v-4.7-35b-a3b","score":75.47,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3.6-35b-a3b","score":72.53,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3.6-27b","score":73.58,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3.8-27b","score":72.82,"metric":"percent"},{"benchmark":"mmt-bench","model":"gemma-4-31b-it","score":75.73,"metric":"percent"},{"benchmark":"simplevqa","model":"minicpm-v-4.7-35b-a3b","score":54.14,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.6-35b-a3b","score":54.4,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.6-27b","score":52.75,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.8-27b","score":50.81,"metric":"percent"},{"benchmark":"simplevqa","model":"gemma-4-31b-it","score":52.24,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v-4.7-35b-a3b","score":80.22,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.6-35b-a3b","score":77.44,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.6-27b","score":78.44,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.8-27b","score":76,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-31b-it","score":75.33,"metric":"percent"},{"benchmark":"mathvista","model":"minicpm-v-4.7-35b-a3b","score":88,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3.6-35b-a3b","score":84.4,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3.6-27b","score":84.4,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3.8-27b","score":84.4,"metric":"percent"},{"benchmark":"mathvista","model":"gemma-4-31b-it","score":78.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"minicpm-v-4.7-35b-a3b","score":69.71,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.6-35b-a3b","score":69.88,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.6-27b","score":69.97,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.8-27b","score":69.74,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemma-4-31b-it","score":64.02,"metric":"percent"},{"benchmark":"mathverse-mini","model":"minicpm-v-4.7-35b-a3b","score":86.45,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3.6-35b-a3b","score":82.74,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3.6-27b","score":81.88,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3.8-27b","score":84.37,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gemma-4-31b-it","score":75.58,"metric":"percent"},{"benchmark":"mathvision","model":"minicpm-v-4.7-35b-a3b","score":74.24,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.6-35b-a3b","score":74.24,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.6-27b","score":75.03,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.8-27b","score":78.22,"metric":"percent"},{"benchmark":"mathvision","model":"gemma-4-31b-it","score":69.28,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-v-4.7-35b-a3b","score":91.2,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.6-35b-a3b","score":86,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.6-27b","score":86.8,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.8-27b","score":83.9,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-4-31b-it","score":85.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-v-4.7-35b-a3b","score":75.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.6-35b-a3b","score":67.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.6-27b","score":68.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.8-27b","score":70.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemma-4-31b-it","score":65,"metric":"percent"},{"benchmark":"cc-ocr","model":"minicpm-v-4.7-35b-a3b","score":81.14,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.6-35b-a3b","score":82.33,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.6-27b","score":82.34,"metric":"percent"},{"benchmark":"cc-ocr","model":"qwen3.8-27b","score":82.49,"metric":"percent"},{"benchmark":"cc-ocr","model":"gemma-4-31b-it","score":76.91,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-v-4.7-35b-a3b","score":84.99,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.6-35b-a3b","score":83.98,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.6-27b","score":81.31,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.8-27b","score":79.6,"metric":"percent"},{"benchmark":"textvqa","model":"gemma-4-31b-it","score":81.21,"metric":"percent"},{"benchmark":"blink","model":"minicpm-v-4.7-35b-a3b","score":70.33,"metric":"percent"},{"benchmark":"blink","model":"qwen3.6-35b-a3b","score":66.91,"metric":"percent"},{"benchmark":"blink","model":"qwen3.6-27b","score":66.65,"metric":"percent"},{"benchmark":"blink","model":"qwen3.8-27b","score":67.81,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-31b-it","score":69.33,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-v-4.7-35b-a3b","score":63.83,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.6-35b-a3b","score":62.06,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.6-27b","score":62.35,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3.8-27b","score":60.98,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemma-4-31b-it","score":61.65,"metric":"percent"},{"benchmark":"mmhal-bench","model":"minicpm-v-4.7-35b-a3b","score":4.72,"metric":"score"},{"benchmark":"mmhal-bench","model":"qwen3.6-35b-a3b","score":4.96,"metric":"score"},{"benchmark":"mmhal-bench","model":"qwen3.6-27b","score":3.17,"metric":"score"},{"benchmark":"mmhal-bench","model":"qwen3.8-27b","score":5.03,"metric":"score"},{"benchmark":"mmhal-bench","model":"gemma-4-31b-it","score":4.18,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"minicpm-v-4.7-35b-a3b","score":21.88,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"qwen3.6-35b-a3b","score":25,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"qwen3.6-27b","score":21.88,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"qwen3.8-27b","score":21.88,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"gemma-4-31b-it","score":27.08,"metric":"percent"},{"benchmark":"refcoco","model":"minicpm-v-4.7-35b-a3b","score":90.93,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.6-35b-a3b","score":90.97,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.6-27b","score":90.91,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.8-27b","score":88.77,"metric":"percent"},{"benchmark":"refcoco","model":"gemma-4-31b-it","score":81.47,"metric":"percent"},{"benchmark":"screenspot","model":"minicpm-v-4.7-35b-a3b","score":86.99,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3.6-35b-a3b","score":92.94,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3.6-27b","score":90.73,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3.8-27b","score":93.31,"metric":"percent"},{"benchmark":"screenspot","model":"gemma-4-31b-it","score":83.75,"metric":"percent"},{"benchmark":"mm-ifeval","model":"minicpm-v-4.7-35b-a3b","score":65.41,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3.6-35b-a3b","score":62.85,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3.6-27b","score":65.77,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3.8-27b","score":68.03,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemma-4-31b-it","score":69.59,"metric":"percent"},{"benchmark":"videomme-nosub","model":"minicpm-v-4.7-35b-a3b","score":76.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.6-35b-a3b","score":75.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.6-27b","score":70.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3.8-27b","score":73.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemma-4-31b-it","score":74.1,"metric":"percent"},{"benchmark":"longvideobench","model":"minicpm-v-4.7-35b-a3b","score":68.9,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3.6-35b-a3b","score":63.1,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3.6-27b","score":67.7,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3.8-27b","score":60.9,"metric":"percent"},{"benchmark":"longvideobench","model":"gemma-4-31b-it","score":60.7,"metric":"percent"},{"benchmark":"motionbench","model":"minicpm-v-4.7-35b-a3b","score":68.12,"metric":"percent"},{"benchmark":"motionbench","model":"qwen3.6-35b-a3b","score":67.87,"metric":"percent"},{"benchmark":"motionbench","model":"qwen3.6-27b","score":69.11,"metric":"percent"},{"benchmark":"motionbench","model":"qwen3.8-27b","score":65.11,"metric":"percent"},{"benchmark":"motionbench","model":"gemma-4-31b-it","score":62.67,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-v-4.7-35b-a3b","score":90.21,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3.6-35b-a3b","score":89.34,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3.6-27b","score":89.52,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3.8-27b","score":87.66,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-4-31b-it","score":79.76,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minicpm-v-4.7-35b-a3b","score":83.45,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-35b-a3b","score":84.11,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-27b","score":84.52,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.8-27b","score":82.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-31b-it","score":84.43,"metric":"percent"},{"benchmark":"supergpqa","model":"minicpm-v-4.7-35b-a3b","score":61.23,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.6-35b-a3b","score":63.37,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.6-27b","score":63.71,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.8-27b","score":60.41,"metric":"percent"},{"benchmark":"supergpqa","model":"gemma-4-31b-it","score":62.23,"metric":"percent"},{"benchmark":"ifbench","model":"minicpm-v-4.7-35b-a3b","score":47.67,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":35.33,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-27b","score":44.67,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-27b","score":43.67,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-31b-it","score":54.33,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minicpm-v-4.7-35b-a3b","score":76.46,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-35b-a3b","score":74.17,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-27b","score":80.42,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.8-27b","score":76.04,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-31b-it","score":76.88,"metric":"percent"},{"benchmark":"livecodebench","model":"minicpm-v-4.7-35b-a3b","score":56.57,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.6-35b-a3b","score":54.29,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.6-27b","score":59.05,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.8-27b","score":63.62,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-31b-it","score":71.24,"metric":"percent"},{"benchmark":"bfcl-v4","model":"minicpm-v-4.7-35b-a3b","score":60.06,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.6-35b-a3b","score":60.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.6-27b","score":60.66,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.8-27b","score":63.72,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-31b-it","score":61.96,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-v-4.7-1b","score":69.53,"metric":"percent"},{"benchmark":"mmt-bench","model":"minicpm-v-4.7-1b","score":61.69,"metric":"percent"},{"benchmark":"simplevqa","model":"minicpm-v-4.7-1b","score":42.23,"metric":"percent"},{"benchmark":"simplevqa","model":"minicpm-v-4.6","score":40.87,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-0.8b","score":30.4,"metric":"percent"},{"benchmark":"simplevqa","model":"lfm2.5-vl-1.6b","score":31.51,"metric":"percent"},{"benchmark":"simplevqa","model":"gemma-4-e2b-it","score":35.45,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v-4.7-1b","score":56.89,"metric":"percent"},{"benchmark":"mathvista","model":"minicpm-v-4.7-1b","score":74.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"minicpm-v-4.7-1b","score":38.03,"metric":"percent"},{"benchmark":"mathverse-mini","model":"minicpm-v-4.7-1b","score":60.41,"metric":"percent"},{"benchmark":"mathvision","model":"minicpm-v-4.7-1b","score":31.64,"metric":"percent"},{"benchmark":"mathvision","model":"minicpm-v-4.6","score":31.64,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-0.8b","score":20.33,"metric":"percent"},{"benchmark":"mathvision","model":"lfm2.5-vl-1.6b","score":17.17,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-v-4.7-1b","score":86.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-v-4.7-1b","score":48.8,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-v-4.7-1b","score":77.4,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-v-4.6","score":77.1,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.5-0.8b","score":66.72,"metric":"percent"},{"benchmark":"textvqa","model":"lfm2.5-vl-1.6b","score":82.88,"metric":"percent"},{"benchmark":"textvqa","model":"gemma-4-e2b-it","score":67.18,"metric":"percent"},{"benchmark":"blink","model":"minicpm-v-4.7-1b","score":60.7,"metric":"percent"},{"benchmark":"muirbench","model":"minicpm-v-4.7-1b","score":65.69,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3.5-0.8b","score":54.04,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-v-4.7-1b","score":57.85,"metric":"percent"},{"benchmark":"mmhal-bench","model":"minicpm-v-4.7-1b","score":4.34,"metric":"score"},{"benchmark":"mmhal-bench","model":"qwen3.5-0.8b","score":2.62,"metric":"score"},{"benchmark":"mmhal-bench","model":"gemma-4-e2b-it","score":3.49,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"minicpm-v-4.7-1b","score":26.04,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"qwen3.5-0.8b","score":33.33,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"lfm2.5-vl-1.6b","score":22.92,"metric":"percent"},{"benchmark":"mmhal-bench-hallucination-rate","model":"gemma-4-e2b-it","score":40.62,"metric":"percent"},{"benchmark":"refcoco","model":"minicpm-v-4.7-1b","score":84.85,"metric":"percent"},{"benchmark":"refcoco","model":"lfm2.5-vl-1.6b","score":68.22,"metric":"percent"},{"benchmark":"screenspot","model":"minicpm-v-4.7-1b","score":68.05,"metric":"percent"},{"benchmark":"screenspot","model":"minicpm-v-4.6","score":56.64,"metric":"percent"},{"benchmark":"screenspot","model":"qwen3.5-0.8b","score":61.39,"metric":"percent"},{"benchmark":"screenspot","model":"gemma-4-e2b-it","score":20.26,"metric":"percent"},{"benchmark":"mm-ifeval","model":"minicpm-v-4.7-1b","score":51.68,"metric":"percent"},{"benchmark":"mm-ifeval","model":"minicpm-v-4.6","score":44.57,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3.5-0.8b","score":35.78,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemma-4-e2b-it","score":54.32,"metric":"percent"},{"benchmark":"longvideobench","model":"minicpm-v-4.7-1b","score":53.4,"metric":"percent"},{"benchmark":"longvideobench","model":"lfm2.5-vl-1.6b","score":54,"metric":"percent"},{"benchmark":"motionbench","model":"minicpm-v-4.7-1b","score":54.55,"metric":"percent"},{"benchmark":"motionbench","model":"lfm2.5-vl-1.6b","score":49.18,"metric":"percent"},{"benchmark":"mmsearch","model":"qwen2.5-vl-7b","score":7.6,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen2.5-vl-7b","score":47.88,"metric":"percent"},{"benchmark":"mmsearch","model":"qwen3-vl-8b-instruct","score":11.7,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-8b-instruct","score":42.94,"metric":"percent"},{"benchmark":"mmsearch","model":"qwen2.5-vl-32b-instruct","score":11.7,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen2.5-vl-32b-instruct","score":48.57,"metric":"percent"},{"benchmark":"mmsearch","model":"qwen3-vl-32b-instruct","score":16.96,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3-vl-32b-instruct","score":45.9,"metric":"percent"},{"benchmark":"mmsearch","model":"gpt-4o-mini","score":15.79,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-4o-mini","score":44.42,"metric":"percent"},{"benchmark":"mmsearch","model":"gemini-2.5-flash","score":21.64,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-2.5-flash","score":55.48,"metric":"percent"},{"benchmark":"mmsearch","model":"gpt-4o","score":23.39,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-4o","score":51.73,"metric":"percent"},{"benchmark":"mmsearch","model":"gpt-5","score":35.09,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5","score":61.7,"metric":"percent"},{"benchmark":"mmsearch","model":"gpt-5.2","score":43.27,"metric":"percent"},{"benchmark":"simplevqa","model":"gpt-5.2","score":59.92,"metric":"percent"},{"benchmark":"mmsearch","model":"gemini-3-flash","score":57.31,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3-flash","score":63.57,"metric":"percent"},{"benchmark":"mmsearch","model":"gemini-3-pro","score":62.57,"metric":"percent"},{"benchmark":"simplevqa","model":"gemini-3-pro","score":64.07,"metric":"percent"},{"benchmark":"mmsearch","model":"sensenova-mars-8b","score":67.84,"metric":"percent"},{"benchmark":"simplevqa","model":"sensenova-mars-8b","score":70.19,"metric":"percent"},{"benchmark":"mmsearch","model":"sensenova-mars-32b","score":74.27,"metric":"percent"},{"benchmark":"simplevqa","model":"sensenova-mars-32b","score":74.14,"metric":"percent"},{"benchmark":"v-star","model":"gemini-2.5-pro","score":83.8,"metric":"percent"},{"benchmark":"hrbench4k","model":"gemini-2.5-pro","score":87.3,"metric":"percent"},{"benchmark":"hrbench8k","model":"gemini-2.5-pro","score":85.4,"metric":"percent"},{"benchmark":"v-star","model":"gpt-4o","score":67.5,"metric":"percent"},{"benchmark":"hrbench4k","model":"gpt-4o","score":65,"metric":"percent"},{"benchmark":"hrbench8k","model":"gpt-4o","score":59.6,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gpt-4o","score":62.8,"metric":"percent"},{"benchmark":"v-star","model":"qwen2.5-vl-7b","score":75.3,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen2.5-vl-7b","score":65.5,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen2.5-vl-7b","score":62.1,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen2.5-vl-7b","score":56.8,"metric":"percent"},{"benchmark":"v-star","model":"qwen2.5-vl-32b-instruct","score":80.6,"metric":"percent"},{"benchmark":"hrbench4k","model":"qwen2.5-vl-32b-instruct","score":69.3,"metric":"percent"},{"benchmark":"hrbench8k","model":"qwen2.5-vl-32b-instruct","score":63.6,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen2.5-vl-32b-instruct","score":59.1,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen3-vl-8b-instruct","score":61.9,"metric":"percent"},{"benchmark":"v-star","model":"sensenova-mars-8b","score":92.2,"metric":"percent"},{"benchmark":"hrbench4k","model":"sensenova-mars-8b","score":83.1,"metric":"percent"},{"benchmark":"hrbench8k","model":"sensenova-mars-8b","score":78.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"sensenova-mars-8b","score":67.9,"metric":"percent"},{"benchmark":"v-star","model":"sensenova-mars-32b","score":94.2,"metric":"percent"},{"benchmark":"hrbench4k","model":"sensenova-mars-32b","score":90.2,"metric":"percent"},{"benchmark":"hrbench8k","model":"sensenova-mars-32b","score":86.6,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"sensenova-mars-32b","score":72.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.5-flash","score":86.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.5-flash","score":86,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-flash","score":75.3,"metric":"percent"},{"benchmark":"mmvet","model":"gemini-2.5-flash","score":81.4,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-flash","score":76.3,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-flash","score":75.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.5-flash","score":59.1,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-flash","score":87.7,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-flash","score":86.4,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-2.5-flash","score":74.3,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-flash","score":93,"metric":"percent"},{"benchmark":"mmt-bench","model":"gemini-2.5-flash","score":70,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemini-2.5-flash","score":75.8,"metric":"percent"},{"benchmark":"mantis","model":"gemini-2.5-flash","score":72.8,"metric":"percent"},{"benchmark":"muirbench","model":"gemini-2.5-flash","score":74.5,"metric":"percent"},{"benchmark":"mmhal-bench","model":"gemini-2.5-flash","score":4.6,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"gemini-2.5-flash","score":23.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.0-pro","score":83,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.0-pro","score":83,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.0-pro","score":71.3,"metric":"percent"},{"benchmark":"mmvet","model":"gemini-2.0-pro","score":70.4,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.0-pro","score":72.6,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.0-pro","score":68.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.0-pro","score":49.8,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.0-pro","score":84.8,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.0-pro","score":86.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o","score":86,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4o","score":86,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-4o","score":71.6,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4o","score":76.9,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4o","score":72.9,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4o","score":70.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4o","score":57,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4o","score":86.3,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4o","score":82.2,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-4o","score":77.4,"metric":"percent"},{"benchmark":"mmt-bench","model":"gpt-4o","score":66.7,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gpt-4o","score":64.6,"metric":"percent"},{"benchmark":"mantis","model":"gpt-4o","score":70.1,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-4o","score":70.5,"metric":"percent"},{"benchmark":"mmhal-bench","model":"gpt-4o","score":4.2,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"gpt-4o","score":25,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3.5-8b","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl3.5-8b","score":80,"metric":"percent"},{"benchmark":"mmvet","model":"internvl3.5-8b","score":83.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl3.5-8b","score":54.5,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl3.5-8b","score":66.7,"metric":"percent"},{"benchmark":"mm-ifeval","model":"internvl3.5-8b","score":56.3,"metric":"percent"},{"benchmark":"mantis","model":"internvl3.5-8b","score":70.5,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl3.5-8b","score":3.8,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"internvl3.5-8b","score":34.7,"metric":"percent"},{"benchmark":"mmvet","model":"qwen3-vl-8b-instruct","score":73.7,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-8b-instruct","score":82.9,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3-vl-8b-instruct","score":60.9,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3-vl-8b-instruct","score":59.4,"metric":"percent"},{"benchmark":"mantis","model":"qwen3-vl-8b-instruct","score":74.2,"metric":"percent"},{"benchmark":"mmhal-bench","model":"qwen3-vl-8b-instruct","score":4.7,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"qwen3-vl-8b-instruct","score":29.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-omni-30b-a3b-instruct","score":84.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen3-omni-30b-a3b-instruct","score":84.1,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-omni-30b-a3b-instruct","score":75.9,"metric":"percent"},{"benchmark":"mmvet","model":"qwen3-omni-30b-a3b-instruct","score":74.8,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-omni-30b-a3b-instruct","score":88,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-omni-30b-a3b-instruct","score":84.1,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-omni-30b-a3b-instruct","score":95.4,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3-omni-30b-a3b-instruct","score":70.4,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3-omni-30b-a3b-instruct","score":65.7,"metric":"percent"},{"benchmark":"mantis","model":"qwen3-omni-30b-a3b-instruct","score":78.3,"metric":"percent"},{"benchmark":"muirbench","model":"qwen3-omni-30b-a3b-instruct","score":61.9,"metric":"percent"},{"benchmark":"mmhal-bench","model":"qwen3-omni-30b-a3b-instruct","score":4.6,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"qwen3-omni-30b-a3b-instruct","score":31.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-o-4.5","score":87.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-o-4.5","score":87.2,"metric":"percent"},{"benchmark":"mathvista","model":"minicpm-o-4.5","score":80.1,"metric":"percent"},{"benchmark":"mmvet","model":"minicpm-o-4.5","score":74.4,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-o-4.5","score":67.6,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-o-4.5","score":73.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-o-4.5","score":63.2,"metric":"percent"},{"benchmark":"ai2d","model":"minicpm-o-4.5","score":87.6,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-o-4.5","score":87.6,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-o-4.5","score":83.8,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-o-4.5","score":94.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"minicpm-o-4.5","score":69.7,"metric":"percent"},{"benchmark":"mm-ifeval","model":"minicpm-o-4.5","score":66.3,"metric":"percent"},{"benchmark":"mantis","model":"minicpm-o-4.5","score":79.7,"metric":"percent"},{"benchmark":"muirbench","model":"minicpm-o-4.5","score":72,"metric":"percent"},{"benchmark":"mmhal-bench","model":"minicpm-o-4.5","score":4.7,"metric":"score"},{"benchmark":"mmhal-bench-hallucination-rate","model":"minicpm-o-4.5","score":24.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.5-flash-thinking","score":87.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.5-flash-thinking","score":87.3,"metric":"percent"},{"benchmark":"mathvista","model":"gemini-2.5-flash-thinking","score":79.4,"metric":"percent"},{"benchmark":"mmvet","model":"gemini-2.5-flash-thinking","score":81.2,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-2.5-flash-thinking","score":77.7,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-2.5-flash-thinking","score":76.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.5-flash-thinking","score":63.5,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-2.5-flash-thinking","score":88.7,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-flash-thinking","score":85.3,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-2.5-flash-thinking","score":73.8,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-2.5-flash-thinking","score":92.8,"metric":"percent"},{"benchmark":"mmt-bench","model":"gemini-2.5-flash-thinking","score":70.7,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemini-2.5-flash-thinking","score":75.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-5","score":85.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-5","score":85.6,"metric":"percent"},{"benchmark":"mathvista","model":"gpt-5","score":81.9,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-5","score":77.6,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5","score":75.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5","score":65.2,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5","score":80.7,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-5","score":77.8,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5","score":91.3,"metric":"percent"},{"benchmark":"mmt-bench","model":"gpt-5","score":72.7,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gpt-5","score":83.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-vl-8b-thinking","score":85.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen3-vl-8b-thinking","score":85.5,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-vl-8b-thinking","score":81.4,"metric":"percent"},{"benchmark":"mmvet","model":"qwen3-vl-8b-thinking","score":69.8,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-8b-thinking","score":74.1,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-8b-thinking","score":75.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-8b-thinking","score":65.4,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-8b-thinking","score":84.9,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-8b-thinking","score":81.9,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-vl-8b-thinking","score":77.8,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-8b-thinking","score":95.3,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3-vl-8b-thinking","score":68.1,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3-vl-8b-thinking","score":73.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3-omni-30b-a3b-thinking","score":88.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen3-omni-30b-a3b-thinking","score":87.7,"metric":"percent"},{"benchmark":"mathvista","model":"qwen3-omni-30b-a3b-thinking","score":80,"metric":"percent"},{"benchmark":"mmvet","model":"qwen3-omni-30b-a3b-thinking","score":74.8,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-omni-30b-a3b-thinking","score":75.6,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-omni-30b-a3b-thinking","score":74.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-omni-30b-a3b-thinking","score":62.8,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-omni-30b-a3b-thinking","score":86.1,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-omni-30b-a3b-thinking","score":85.9,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3-omni-30b-a3b-thinking","score":80.8,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-omni-30b-a3b-thinking","score":94.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen3-omni-30b-a3b-thinking","score":70.9,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen3-omni-30b-a3b-thinking","score":69.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-o-4.5-thinking","score":89,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-o-4.5-thinking","score":87.6,"metric":"percent"},{"benchmark":"mathvista","model":"minicpm-o-4.5-thinking","score":81,"metric":"percent"},{"benchmark":"mmvet","model":"minicpm-o-4.5-thinking","score":73.6,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-o-4.5-thinking","score":70.2,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-o-4.5-thinking","score":73.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-o-4.5-thinking","score":62.6,"metric":"percent"},{"benchmark":"ai2d","model":"minicpm-o-4.5-thinking","score":88.5,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-o-4.5-thinking","score":87.9,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-o-4.5-thinking","score":79.8,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-o-4.5-thinking","score":92.3,"metric":"percent"},{"benchmark":"mmt-bench","model":"minicpm-o-4.5-thinking","score":69.7,"metric":"percent"},{"benchmark":"mm-ifeval","model":"minicpm-o-4.5-thinking","score":68.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gemini-2.5-flash","score":75.6,"metric":"percent"},{"benchmark":"lvbench","model":"gemini-2.5-flash","score":62.2,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-2.5-flash","score":77.8,"metric":"percent"},{"benchmark":"motionbench","model":"internvl3.5-8b","score":62.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen3-omni-30b-a3b-instruct","score":70.5,"metric":"percent"},{"benchmark":"lvbench","model":"qwen3-omni-30b-a3b-instruct","score":50.2,"metric":"percent"},{"benchmark":"longvideobench","model":"qwen3-omni-30b-a3b-instruct","score":66.9,"metric":"percent"},{"benchmark":"motionbench","model":"qwen3-omni-30b-a3b-instruct","score":61.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"minicpm-o-4.5","score":70.4,"metric":"percent"},{"benchmark":"lvbench","model":"minicpm-o-4.5","score":50.9,"metric":"percent"},{"benchmark":"mlvu","model":"minicpm-o-4.5","score":76.5,"metric":"percent"},{"benchmark":"longvideobench","model":"minicpm-o-4.5","score":66,"metric":"percent"},{"benchmark":"motionbench","model":"minicpm-o-4.5","score":61.4,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-8b-instruct","score":69.4,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-8b-instruct","score":78.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-8b-instruct","score":81.7,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-8b-instruct","score":86.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-8b-instruct","score":75.9,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b-instruct","score":84,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-8b-instruct","score":93.4,"metric":"percent"},{"benchmark":"bbh","model":"minicpm-o-4.5","score":81.1,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-o-4.5","score":79.5,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm-o-4.5","score":77,"metric":"percent"},{"benchmark":"humaneval","model":"minicpm-o-4.5","score":86.6,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm-o-4.5","score":76.7,"metric":"percent"},{"benchmark":"math500","model":"minicpm-o-4.5","score":77,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm-o-4.5","score":94.5,"metric":"percent"},{"benchmark":"daily-omni","model":"gemini-2.5-flash","score":79.3,"metric":"percent"},{"benchmark":"videoholmes","model":"gemini-2.5-flash","score":51.3,"metric":"percent"},{"benchmark":"futureomni","model":"gemini-2.5-flash","score":55.6,"metric":"percent"},{"benchmark":"daily-omni","model":"qwen3-omni-30b-a3b-instruct","score":70.7,"metric":"percent"},{"benchmark":"videoholmes","model":"qwen3-omni-30b-a3b-instruct","score":50.4,"metric":"percent"},{"benchmark":"futureomni","model":"qwen3-omni-30b-a3b-instruct","score":62.1,"metric":"percent"},{"benchmark":"daily-omni","model":"minicpm-o-4.5","score":80.2,"metric":"percent"},{"benchmark":"videoholmes","model":"minicpm-o-4.5","score":64.3,"metric":"percent"},{"benchmark":"futureomni","model":"minicpm-o-4.5","score":56.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-4b","score":80.8,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-3-8b-instruct","score":79.8,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-12b-it","score":76.2,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-h-small","score":76.7,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2-24b-a2b","score":74.9,"metric":"percent"},{"benchmark":"mmlu","model":"marco-mini-instruct","score":83.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-4b","score":80.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"ministral-3-8b-instruct","score":79.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-3-12b-it","score":76.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"granite-4.0-h-small","score":76.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"lfm2-24b-a2b","score":74.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"marco-mini-instruct","score":83.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b","score":66.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ministral-3-8b-instruct","score":63.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-12b-it","score":55.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-h-small","score":57.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2-24b-a2b","score":57.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"marco-mini-instruct","score":70.7,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-4b","score":51.7,"metric":"percent"},{"benchmark":"agieval","model":"ministral-3-8b-instruct","score":52.4,"metric":"percent"},{"benchmark":"agieval","model":"gemma-3-12b-it","score":43.6,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.0-h-small","score":44.7,"metric":"percent"},{"benchmark":"agieval","model":"lfm2-24b-a2b","score":49,"metric":"percent"},{"benchmark":"agieval","model":"marco-mini-instruct","score":55.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b","score":50.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-8b-instruct","score":44.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-12b-it","score":35.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"granite-4.0-h-small","score":38.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2-24b-a2b","score":39.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"marco-mini-instruct","score":50.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-4b","score":88.6,"metric":"percent"},{"benchmark":"gsm8k","model":"ministral-3-8b-instruct","score":89.5,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-12b-it","score":89.7,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-h-small","score":83.9,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2-24b-a2b","score":87.2,"metric":"percent"},{"benchmark":"gsm8k","model":"marco-mini-instruct","score":93.1,"metric":"percent"},{"benchmark":"math","model":"qwen3-4b","score":93.4,"metric":"percent"},{"benchmark":"math","model":"ministral-3-8b-instruct","score":86.2,"metric":"percent"},{"benchmark":"math","model":"gemma-3-12b-it","score":83.8,"metric":"percent"},{"benchmark":"math","model":"granite-4.0-h-small","score":75.7,"metric":"percent"},{"benchmark":"math","model":"lfm2-24b-a2b","score":83.9,"metric":"percent"},{"benchmark":"math","model":"marco-mini-instruct","score":91.8,"metric":"percent"},{"benchmark":"global-mmlu","model":"qwen3-4b","score":70.2,"metric":"percent"},{"benchmark":"global-mmlu","model":"ministral-3-8b-instruct","score":55.4,"metric":"percent"},{"benchmark":"global-mmlu","model":"gemma-3-12b-it","score":69.2,"metric":"percent"},{"benchmark":"global-mmlu","model":"granite-4.0-h-small","score":67.4,"metric":"percent"},{"benchmark":"global-mmlu","model":"lfm2-24b-a2b","score":57,"metric":"percent"},{"benchmark":"global-mmlu","model":"marco-mini-instruct","score":73.3,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-4b","score":71.3,"metric":"percent"},{"benchmark":"mmmlu","model":"ministral-3-8b-instruct","score":56.4,"metric":"percent"},{"benchmark":"mmmlu","model":"gemma-3-12b-it","score":69.4,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.0-h-small","score":68.1,"metric":"percent"},{"benchmark":"mmmlu","model":"lfm2-24b-a2b","score":62.3,"metric":"percent"},{"benchmark":"mmmlu","model":"marco-mini-instruct","score":73.7,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-4b","score":84.4,"metric":"percent"},{"benchmark":"mgsm","model":"ministral-3-8b-instruct","score":68.7,"metric":"percent"},{"benchmark":"mgsm","model":"gemma-3-12b-it","score":84,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.0-h-small","score":75.7,"metric":"percent"},{"benchmark":"mgsm","model":"lfm2-24b-a2b","score":67.8,"metric":"percent"},{"benchmark":"mgsm","model":"marco-mini-instruct","score":87.4,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-4b","score":47.2,"metric":"percent"},{"benchmark":"polymath","model":"ministral-3-8b-instruct","score":26.4,"metric":"percent"},{"benchmark":"polymath","model":"gemma-3-12b-it","score":35.5,"metric":"percent"},{"benchmark":"polymath","model":"granite-4.0-h-small","score":28.9,"metric":"percent"},{"benchmark":"polymath","model":"lfm2-24b-a2b","score":29.3,"metric":"percent"},{"benchmark":"polymath","model":"marco-mini-instruct","score":44.7,"metric":"percent"},{"benchmark":"include","model":"qwen3-4b","score":63.8,"metric":"percent"},{"benchmark":"include","model":"ministral-3-8b-instruct","score":50.7,"metric":"percent"},{"benchmark":"include","model":"gemma-3-12b-it","score":65,"metric":"percent"},{"benchmark":"include","model":"granite-4.0-h-small","score":60.3,"metric":"percent"},{"benchmark":"include","model":"lfm2-24b-a2b","score":49.1,"metric":"percent"},{"benchmark":"include","model":"marco-mini-instruct","score":65.6,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-4b","score":79.6,"metric":"percent"},{"benchmark":"global-piqa","model":"ministral-3-8b-instruct","score":61.3,"metric":"percent"},{"benchmark":"global-piqa","model":"gemma-3-12b-it","score":82.2,"metric":"percent"},{"benchmark":"global-piqa","model":"granite-4.0-h-small","score":80.2,"metric":"percent"},{"benchmark":"global-piqa","model":"lfm2-24b-a2b","score":69,"metric":"percent"},{"benchmark":"global-piqa","model":"marco-mini-instruct","score":84.2,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-4b","score":78.6,"metric":"percent"},{"benchmark":"cmmlu","model":"ministral-3-8b-instruct","score":67.4,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-3-12b-it","score":60.8,"metric":"percent"},{"benchmark":"cmmlu","model":"granite-4.0-h-small","score":59.6,"metric":"percent"},{"benchmark":"cmmlu","model":"lfm2-24b-a2b","score":56.7,"metric":"percent"},{"benchmark":"cmmlu","model":"marco-mini-instruct","score":75.3,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-4b","score":80.4,"metric":"percent"},{"benchmark":"c-eval","model":"ministral-3-8b-instruct","score":68,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-3-12b-it","score":59.7,"metric":"percent"},{"benchmark":"c-eval","model":"granite-4.0-h-small","score":59.4,"metric":"percent"},{"benchmark":"c-eval","model":"lfm2-24b-a2b","score":56.7,"metric":"percent"},{"benchmark":"c-eval","model":"marco-mini-instruct","score":75.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-1.7b","score":62.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-vl-2b-instruct","score":62.1,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-3-3b-instruct","score":69.8,"metric":"percent"},{"benchmark":"mmlu","model":"lfm2-8b-a1b","score":72.1,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-h-tiny","score":50.8,"metric":"percent"},{"benchmark":"mmlu","model":"marco-nano-instruct","score":73.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-1.7b","score":62.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3-vl-2b-instruct","score":62.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"ministral-3-3b-instruct","score":69.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"lfm2-8b-a1b","score":71.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"granite-4.0-h-tiny","score":51.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"marco-nano-instruct","score":73.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b","score":35.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-vl-2b-instruct","score":38.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ministral-3-3b-instruct","score":49.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"lfm2-8b-a1b","score":49.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-4.0-h-tiny","score":25.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"marco-nano-instruct","score":54.5,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-1.7b","score":39.6,"metric":"percent"},{"benchmark":"agieval","model":"qwen3-vl-2b-instruct","score":33,"metric":"percent"},{"benchmark":"agieval","model":"ministral-3-3b-instruct","score":44.7,"metric":"percent"},{"benchmark":"agieval","model":"lfm2-8b-a1b","score":45.2,"metric":"percent"},{"benchmark":"agieval","model":"granite-4.0-h-tiny","score":30.7,"metric":"percent"},{"benchmark":"agieval","model":"marco-nano-instruct","score":49.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-1.7b","score":27.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-vl-2b-instruct","score":21,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-3b-instruct","score":31.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"lfm2-8b-a1b","score":31.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"granite-4.0-h-tiny","score":28.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"marco-nano-instruct","score":22.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-1.7b","score":77.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-vl-2b-instruct","score":79.7,"metric":"percent"},{"benchmark":"gsm8k","model":"ministral-3-3b-instruct","score":79,"metric":"percent"},{"benchmark":"gsm8k","model":"lfm2-8b-a1b","score":84.6,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-h-tiny","score":71.1,"metric":"percent"},{"benchmark":"gsm8k","model":"marco-nano-instruct","score":86.7,"metric":"percent"},{"benchmark":"math","model":"qwen3-1.7b","score":70.6,"metric":"percent"},{"benchmark":"math","model":"qwen3-vl-2b-instruct","score":73.7,"metric":"percent"},{"benchmark":"math","model":"ministral-3-3b-instruct","score":70.2,"metric":"percent"},{"benchmark":"math","model":"lfm2-8b-a1b","score":82.6,"metric":"percent"},{"benchmark":"math","model":"granite-4.0-h-tiny","score":53.4,"metric":"percent"},{"benchmark":"math","model":"marco-nano-instruct","score":79.6,"metric":"percent"},{"benchmark":"global-mmlu","model":"qwen3-1.7b","score":46.3,"metric":"percent"},{"benchmark":"global-mmlu","model":"qwen3-vl-2b-instruct","score":45.9,"metric":"percent"},{"benchmark":"global-mmlu","model":"ministral-3-3b-instruct","score":38.4,"metric":"percent"},{"benchmark":"global-mmlu","model":"lfm2-8b-a1b","score":49,"metric":"percent"},{"benchmark":"global-mmlu","model":"granite-4.0-h-tiny","score":43,"metric":"percent"},{"benchmark":"global-mmlu","model":"marco-nano-instruct","score":58.7,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-1.7b","score":49,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3-vl-2b-instruct","score":49,"metric":"percent"},{"benchmark":"mmmlu","model":"ministral-3-3b-instruct","score":39.4,"metric":"percent"},{"benchmark":"mmmlu","model":"lfm2-8b-a1b","score":56.5,"metric":"percent"},{"benchmark":"mmmlu","model":"granite-4.0-h-tiny","score":44.1,"metric":"percent"},{"benchmark":"mmmlu","model":"marco-nano-instruct","score":59.9,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-1.7b","score":63.6,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3-vl-2b-instruct","score":67.6,"metric":"percent"},{"benchmark":"mgsm","model":"ministral-3-3b-instruct","score":47,"metric":"percent"},{"benchmark":"mgsm","model":"lfm2-8b-a1b","score":56.5,"metric":"percent"},{"benchmark":"mgsm","model":"granite-4.0-h-tiny","score":55.3,"metric":"percent"},{"benchmark":"mgsm","model":"marco-nano-instruct","score":76.5,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-1.7b","score":23.4,"metric":"percent"},{"benchmark":"polymath","model":"qwen3-vl-2b-instruct","score":25.5,"metric":"percent"},{"benchmark":"polymath","model":"ministral-3-3b-instruct","score":16.3,"metric":"percent"},{"benchmark":"polymath","model":"lfm2-8b-a1b","score":26.5,"metric":"percent"},{"benchmark":"polymath","model":"granite-4.0-h-tiny","score":18.7,"metric":"percent"},{"benchmark":"polymath","model":"marco-nano-instruct","score":29.6,"metric":"percent"},{"benchmark":"include","model":"qwen3-1.7b","score":44.9,"metric":"percent"},{"benchmark":"include","model":"qwen3-vl-2b-instruct","score":44.4,"metric":"percent"},{"benchmark":"include","model":"ministral-3-3b-instruct","score":35.4,"metric":"percent"},{"benchmark":"include","model":"lfm2-8b-a1b","score":43.5,"metric":"percent"},{"benchmark":"include","model":"granite-4.0-h-tiny","score":38.6,"metric":"percent"},{"benchmark":"include","model":"marco-nano-instruct","score":54.3,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-1.7b","score":62,"metric":"percent"},{"benchmark":"global-piqa","model":"qwen3-vl-2b-instruct","score":65.8,"metric":"percent"},{"benchmark":"global-piqa","model":"ministral-3-3b-instruct","score":50.6,"metric":"percent"},{"benchmark":"global-piqa","model":"lfm2-8b-a1b","score":60.8,"metric":"percent"},{"benchmark":"global-piqa","model":"granite-4.0-h-tiny","score":63.3,"metric":"percent"},{"benchmark":"global-piqa","model":"marco-nano-instruct","score":70.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-1.7b","score":60.4,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen3-vl-2b-instruct","score":63.3,"metric":"percent"},{"benchmark":"cmmlu","model":"ministral-3-3b-instruct","score":48.9,"metric":"percent"},{"benchmark":"cmmlu","model":"lfm2-8b-a1b","score":52.7,"metric":"percent"},{"benchmark":"cmmlu","model":"granite-4.0-h-tiny","score":39.2,"metric":"percent"},{"benchmark":"cmmlu","model":"marco-nano-instruct","score":60,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-1.7b","score":58.7,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3-vl-2b-instruct","score":63.2,"metric":"percent"},{"benchmark":"c-eval","model":"ministral-3-3b-instruct","score":50.6,"metric":"percent"},{"benchmark":"c-eval","model":"lfm2-8b-a1b","score":50.8,"metric":"percent"},{"benchmark":"c-eval","model":"granite-4.0-h-tiny","score":39.4,"metric":"percent"},{"benchmark":"c-eval","model":"marco-nano-instruct","score":60.8,"metric":"percent"},{"benchmark":"gaia-text-only","model":"glm-4.7","score":61.9,"metric":"percent"},{"benchmark":"gaia-text-only","model":"minimax-m2.1","score":64.3,"metric":"percent"},{"benchmark":"hle-with-tools","model":"minimax-m2.1","score":19.1,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"deepseek-v3.2","score":75.1,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v3.2","score":60.9,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2.5","score":74.9,"metric":"percent"},{"benchmark":"deepsearchqa","model":"kimi-k2.5","score":77.1,"metric":"percent"},{"benchmark":"browsecomp","model":"claude-sonnet-4","score":12.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"claude-sonnet-4","score":29.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"claude-sonnet-4","score":68.3,"metric":"percent"},{"benchmark":"webwalker-qa","model":"claude-sonnet-4","score":61.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"claude-sonnet-4","score":64.6,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"claude-opus-4.5","score":80,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"o3","score":67,"metric":"avg@3"},{"benchmark":"browsecomp-zh","model":"gpt-5-high","score":65,"metric":"percent"},{"benchmark":"gaia-text-only","model":"gpt-5-high","score":76.4,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"gpt-5-high","score":77.8,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"gpt-5-high","score":75,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"gpt-5-high","score":79,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gemini-3-pro","score":76.9,"metric":"percent"},{"benchmark":"gaia-text-only","model":"mirothinker-1.7-mini","score":80.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"mirothinker-1.7-mini","score":67.9,"metric":"percent"},{"benchmark":"gaia-text-only","model":"mirothinker-v1.5-235b","score":80.8,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"mirothinker-v1.5-235b","score":77.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"mirothinker-v1.5-235b","score":39.2,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"mirothinker-v1.5-30b","score":72,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"mirothinker-v1.5-30b","score":73.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"mirothinker-v1.5-30b","score":31,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"mirothinker-v1.0-72b","score":81.9,"metric":"percent"},{"benchmark":"webwalker-qa","model":"mirothinker-v1.0-72b","score":62.1,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"mirothinker-v1.0-72b","score":77.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"mirothinker-v1.0-72b","score":37.7,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"tongyi-deepresearch","score":70.9,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"tongyi-deepresearch","score":75,"metric":"avg@3"},{"benchmark":"browsecomp","model":"agentcpm-explore","score":24.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"agentcpm-explore","score":29.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"agentcpm-explore","score":63.9,"metric":"percent"},{"benchmark":"webwalker-qa","model":"agentcpm-explore","score":68.1,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"agentcpm-explore","score":70,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"agentcpm-explore","score":34,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"agentcpm-explore","score":32.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"agentcpm-explore","score":19.1,"metric":"avg@3"},{"benchmark":"browsecomp","model":"marco-deepresearch-8b","score":31.4,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"marco-deepresearch-8b","score":47.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"marco-deepresearch-8b","score":69.9,"metric":"percent"},{"benchmark":"webwalker-qa","model":"marco-deepresearch-8b","score":69.6,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"marco-deepresearch-8b","score":82,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"marco-deepresearch-8b","score":42,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"marco-deepresearch-8b","score":29.9,"metric":"percent"},{"benchmark":"hle-with-tools","model":"marco-deepresearch-8b","score":22.5,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"claude-sonnet-4.5","score":71.2,"metric":"percent"},{"benchmark":"hle-with-tools","model":"claude-sonnet-4.5","score":24.5,"metric":"avg@3"},{"benchmark":"frames","model":"claude-sonnet-4.5","score":85,"metric":"percent"},{"benchmark":"seal-0","model":"claude-sonnet-4.5","score":53.4,"metric":"percent"},{"benchmark":"gaia-text-only","model":"deepseek-v3.2","score":63.5,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"deepseek-v3.2","score":71,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"minimax-m2","score":75.7,"metric":"percent"},{"benchmark":"hle-with-tools","model":"minimax-m2","score":31.8,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"gpt-5-high","score":77.8,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"glm-4.6","score":71.9,"metric":"percent"},{"benchmark":"hle-with-tools","model":"kimi-researcher","score":26.9,"metric":"avg@3"},{"benchmark":"seal-0","model":"kimi-researcher","score":36,"metric":"percent"},{"benchmark":"gaia-text-only","model":"seed1.8","score":87.4,"metric":"percent"},{"benchmark":"hle-with-tools","model":"seed1.8","score":40.9,"metric":"avg@3"},{"benchmark":"browsecomp","model":"agentcpm-explore","score":25,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"agentcpm-explore","score":29,"metric":"percent"},{"benchmark":"frames","model":"agentcpm-explore","score":82.7,"metric":"percent"},{"benchmark":"seal-0","model":"agentcpm-explore","score":40,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"agentcpm-explore","score":70,"metric":"avg@3"},{"benchmark":"deepresearchbench","model":"openai-deepresearch","score":46.45,"metric":"percent"},{"benchmark":"deepresearchbench","model":"agentcpm-report","score":50.11,"metric":"percent"},{"benchmark":"mmmu","model":"exaone-4.5-33b-thinking","score":78.7,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-5-mini-high","score":79,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3-vl-32b-thinking","score":78.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"exaone-4.5-33b-thinking","score":68.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5-mini-high","score":67.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3-vl-32b-thinking","score":68.1,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"exaone-4.5-33b-thinking","score":42.1,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gpt-5-mini-high","score":34.4,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3-vl-32b-thinking","score":41.6,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"qwen3-vl-235b-a22b-thinking","score":47.6,"metric":"percent"},{"benchmark":"mathvision","model":"exaone-4.5-33b-thinking","score":75.2,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5-mini-high","score":71.9,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-32b-thinking","score":70.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"exaone-4.5-33b-thinking","score":85,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-5-mini-high","score":79.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3-vl-32b-thinking","score":85.9,"metric":"percent"},{"benchmark":"wemath","model":"exaone-4.5-33b-thinking","score":79.1,"metric":"percent"},{"benchmark":"wemath","model":"gpt-5-mini-high","score":70.3,"metric":"percent"},{"benchmark":"wemath","model":"qwen3-vl-32b-thinking","score":71.6,"metric":"percent"},{"benchmark":"wemath","model":"qwen3-vl-235b-a22b-thinking","score":74.8,"metric":"percent"},{"benchmark":"wemath","model":"qwen3.5-27b","score":84,"metric":"percent"},{"benchmark":"logicvista","model":"exaone-4.5-33b-thinking","score":73.8,"metric":"percent"},{"benchmark":"logicvista","model":"gpt-5-mini-high","score":70.3,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3-vl-32b-thinking","score":70.9,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3-vl-235b-a22b-thinking","score":72.2,"metric":"percent"},{"benchmark":"logicvista","model":"qwen3.5-27b","score":77,"metric":"percent"},{"benchmark":"babyvision","model":"exaone-4.5-33b-thinking","score":18.8,"metric":"percent"},{"benchmark":"babyvision","model":"gpt-5-mini-high","score":20.9,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-vl-32b-thinking","score":17.4,"metric":"percent"},{"benchmark":"babyvision","model":"qwen3-vl-235b-a22b-thinking","score":22.2,"metric":"percent"},{"benchmark":"ai2d","model":"exaone-4.5-33b-thinking","score":89,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5-mini-high","score":88.2,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3-vl-32b-thinking","score":88.9,"metric":"percent"},{"benchmark":"chartqa-pro","model":"exaone-4.5-33b-thinking","score":62.2,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gpt-5-mini-high","score":60.9,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3-vl-32b-thinking","score":61.4,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3-vl-235b-a22b-thinking","score":61.2,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3.5-27b","score":66.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"exaone-4.5-33b-thinking","score":71.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5-mini-high","score":68.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3-vl-32b-thinking","score":65.2,"metric":"percent"},{"benchmark":"ocrbench","model":"exaone-4.5-33b-thinking","score":63.2,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-5-mini-high","score":55.8,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-32b-thinking","score":68.4,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3-vl-235b-a22b-thinking","score":66.8,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-27b","score":67.3,"metric":"percent"},{"benchmark":"mmstar","model":"exaone-4.5-33b-thinking","score":74.9,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-5-mini-high","score":74.1,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3-vl-32b-thinking","score":79.4,"metric":"percent"},{"benchmark":"blink","model":"exaone-4.5-33b-thinking","score":68.8,"metric":"percent"},{"benchmark":"blink","model":"gpt-5-mini-high","score":67.7,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-32b-thinking","score":68.5,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-27b","score":71.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"exaone-4.5-33b-thinking","score":63.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-5-mini-high","score":63.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen3-vl-32b-thinking","score":67.4,"metric":"percent"},{"benchmark":"aime-2025","model":"exaone-4.5-33b-thinking","score":92.9,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-mini-high","score":91.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-vl-235b-a22b-thinking","score":89.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-27b","score":93.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"exaone-4.5-33b-thinking","score":92.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5-mini-high","score":92.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"k-exaone","score":92.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-vl-235b-a22b-thinking","score":89.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-27b","score":90.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"exaone-4.5-33b-thinking","score":80.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-mini-high","score":82.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-vl-235b-a22b-thinking","score":77.1,"metric":"percent"},{"benchmark":"livecodebench","model":"exaone-4.5-33b-thinking","score":81.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini-high","score":78.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-vl-235b-a22b-thinking","score":70.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-4.5-33b-thinking","score":83.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5-mini-high","score":83.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-vl-235b-a22b-thinking","score":83.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"exaone-4.5-33b-thinking","score":77.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-5-mini-high","score":78.3,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-vl-235b-a22b-thinking","score":67,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.5-27b","score":84.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"exaone-4.5-33b-thinking","score":56.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-5-mini-high","score":60,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-vl-235b-a22b-thinking","score":62,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3.5-27b","score":67.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"exaone-4.5-33b-thinking","score":73,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3-vl-235b-a22b-thinking","score":44.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-27b","score":99.3,"metric":"percent"},{"benchmark":"ifbench","model":"exaone-4.5-33b-thinking","score":62.6,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5-mini-high","score":74,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-vl-235b-a22b-thinking","score":59.2,"metric":"percent"},{"benchmark":"ifeval","model":"exaone-4.5-33b-thinking","score":89.6,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-5-mini-high","score":92.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-vl-235b-a22b-thinking","score":88.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"exaone-4.5-33b-thinking","score":50.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-vl-235b-a22b-thinking","score":58.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-27b","score":67.3,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"exaone-4.5-33b-thinking","score":67.6,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"gpt-5-mini-high","score":72.5,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3-vl-235b-a22b-thinking","score":71.1,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3.5-27b","score":73,"metric":"percent"},{"benchmark":"kobolt","model":"exaone-4.5-33b-thinking","score":52.1,"metric":"percent"},{"benchmark":"kobolt","model":"gpt-5-mini-high","score":63.6,"metric":"percent"},{"benchmark":"kobolt","model":"qwen3-vl-235b-a22b-thinking","score":51.1,"metric":"percent"},{"benchmark":"kobolt","model":"qwen3.5-27b","score":54.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"k-exaone-2.0","score":83.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-397b-a17b","score":89.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k-exaone-2.0","score":82.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"k-exaone-2.0","score":18.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-397b-a17b","score":28.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"k-exaone-2.0","score":92.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-pro-thinking-max","score":95.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"k-exaone-2.0","score":78.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"k-exaone","score":80.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-397b-a17b","score":84.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"k-exaone-2.0","score":78.6,"metric":"percent"},{"benchmark":"scicode","model":"k-exaone-2.0","score":37.4,"metric":"percent"},{"benchmark":"scicode","model":"k-exaone","score":35.6,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-pro-thinking-max","score":50,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"k-exaone-2.0","score":68.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5.1","score":73.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"k-exaone-2.0","score":43.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"k-exaone","score":30.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"k-exaone-2.0","score":14.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"k-exaone","score":14.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.1","score":11.5,"metric":"percent"},{"benchmark":"claw-eval","model":"k-exaone-2.0","score":77.7,"metric":"percent"},{"benchmark":"claw-eval","model":"k-exaone","score":70.3,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-397b-a17b","score":79.7,"metric":"percent"},{"benchmark":"claw-eval","model":"glm-5.1","score":84.4,"metric":"percent"},{"benchmark":"claw-eval","model":"deepseek-v4-pro-thinking-max","score":82.7,"metric":"percent"},{"benchmark":"ifeval","model":"k-exaone-2.0","score":92.4,"metric":"percent"},{"benchmark":"ifeval","model":"glm-5.1","score":93.9,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v4-pro-thinking-max","score":94,"metric":"percent"},{"benchmark":"ifbench","model":"k-exaone-2.0","score":72.6,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5.1","score":76.3,"metric":"percent"},{"benchmark":"mrcr-128k","model":"k-exaone-2.0","score":94.4,"metric":"percent"},{"benchmark":"mrcr-128k","model":"qwen3.5-397b-a17b","score":93,"metric":"percent"},{"benchmark":"mrcr-128k","model":"glm-5.1","score":71.5,"metric":"percent"},{"benchmark":"mrcr-128k","model":"deepseek-v4-pro-thinking-max","score":92.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"k-exaone-2.0","score":56.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-397b-a17b","score":65.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.1","score":62.3,"metric":"percent"},{"benchmark":"ko-longbench","model":"k-exaone-2.0","score":89.6,"metric":"percent"},{"benchmark":"ko-longbench","model":"qwen3.5-397b-a17b","score":91.3,"metric":"percent"},{"benchmark":"ko-longbench","model":"glm-5.1","score":83.6,"metric":"percent"},{"benchmark":"ko-longbench","model":"deepseek-v4-pro-thinking-max","score":91.4,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"k-exaone-2.0","score":69.1,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3.5-397b-a17b","score":77.4,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"glm-5.1","score":75.8,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"deepseek-v4-pro-thinking-max","score":80.5,"metric":"percent"},{"benchmark":"click","model":"k-exaone-2.0","score":84.2,"metric":"percent"},{"benchmark":"click","model":"qwen3.5-397b-a17b","score":88.9,"metric":"percent"},{"benchmark":"click","model":"glm-5.1","score":88.7,"metric":"percent"},{"benchmark":"click","model":"deepseek-v4-pro-thinking-max","score":91.6,"metric":"percent"},{"benchmark":"mmmlu","model":"k-exaone-2.0","score":86.6,"metric":"percent"},{"benchmark":"mmmlu","model":"k-exaone","score":86.2,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen3.5-397b-a17b","score":90.6,"metric":"percent"},{"benchmark":"mmmlu","model":"glm-5.1","score":89.7,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v4-pro-thinking-max","score":89.6,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"k-exaone-2.0","score":86.6,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"k-exaone","score":86.9,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"qwen3.5-397b-a17b","score":92.1,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"glm-5.1","score":90.7,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"deepseek-v4-pro-thinking-max","score":92,"metric":"percent"},{"benchmark":"polymath","model":"k-exaone-2.0","score":71.3,"metric":"percent"},{"benchmark":"polymath","model":"k-exaone","score":57.4,"metric":"percent"},{"benchmark":"polymath","model":"glm-5.1","score":73.8,"metric":"percent"},{"benchmark":"polymath","model":"deepseek-v4-pro-thinking-max","score":80.9,"metric":"percent"},{"benchmark":"kgc-safety","model":"k-exaone-2.0","score":99.8,"metric":"percent"},{"benchmark":"kgc-safety","model":"qwen3.5-397b-a17b","score":92,"metric":"percent"},{"benchmark":"kgc-safety","model":"glm-5.1","score":69.3,"metric":"percent"},{"benchmark":"kgc-safety","model":"deepseek-v4-pro-thinking-max","score":82.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"solar-open-2-250b","score":86.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-medium-3.5","score":81.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-flash-thinking-max","score":85.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"solar-open-2-250b","score":86.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"solar-open-100b","score":66.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-medium-3.5","score":77.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash-thinking-max","score":88.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"solar-open-2-250b","score":28.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"solar-open-100b","score":11.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"mistral-medium-3.5","score":12.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-flash-thinking-max","score":32.3,"metric":"percent"},{"benchmark":"livecodebench","model":"solar-open-2-250b","score":92.4,"metric":"percent"},{"benchmark":"livecodebench","model":"solar-open-100b","score":56.5,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-medium-3.5","score":84.9,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-thinking-max","score":92.3,"metric":"percent"},{"benchmark":"artifactsbench","model":"solar-open-2-250b","score":55.9,"metric":"percent"},{"benchmark":"artifactsbench","model":"solar-open-100b","score":43.4,"metric":"percent"},{"benchmark":"artifactsbench","model":"mistral-medium-3.5","score":49.8,"metric":"percent"},{"benchmark":"artifactsbench","model":"deepseek-v4-flash-thinking-max","score":61,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"solar-open-2-250b","score":93.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"solar-open-100b","score":68.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"mistral-medium-3.5","score":62.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-flash-thinking-max","score":94.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"solar-open-2-250b","score":95.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"solar-open-100b","score":87.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"mistral-medium-3.5","score":89,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-flash-thinking-max","score":97,"metric":"percent"},{"benchmark":"multichallenge","model":"solar-open-2-250b","score":61,"metric":"percent"},{"benchmark":"multichallenge","model":"solar-open-100b","score":40.5,"metric":"percent"},{"benchmark":"multichallenge","model":"mistral-medium-3.5","score":49.8,"metric":"percent"},{"benchmark":"multichallenge","model":"deepseek-v4-flash-thinking-max","score":62,"metric":"percent"},{"benchmark":"ifbench","model":"solar-open-2-250b","score":80,"metric":"percent"},{"benchmark":"ifbench","model":"solar-open-100b","score":57.7,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-flash-thinking-max","score":80.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"solar-open-2-250b","score":62.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"solar-open-100b","score":36,"metric":"percent"},{"benchmark":"aa-lcr","model":"mistral-medium-3.5","score":61,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"solar-open-2-250b","score":70.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"solar-open-100b","score":15.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mistral-medium-3.5","score":69.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-flash-thinking-max","score":73.8,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"solar-open-2-250b","score":28.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"solar-open-100b","score":2.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"mistral-medium-3.5","score":33.3,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"deepseek-v4-flash-thinking-max","score":34.1,"metric":"percent"},{"benchmark":"apex-agents","model":"solar-open-2-250b","score":16.6,"metric":"percent"},{"benchmark":"apex-agents","model":"solar-open-100b","score":2.4,"metric":"percent"},{"benchmark":"apex-agents","model":"mistral-medium-3.5","score":6.1,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-flash-thinking-max","score":13.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"solar-open-2-250b","score":58.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"solar-open-100b","score":34.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"mistral-medium-3.5","score":30.7,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-flash-thinking-max","score":58.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"solar-open-2-250b","score":19.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"solar-open-100b","score":7.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"mistral-medium-3.5","score":5.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-flash-thinking-max","score":22.3,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"solar-open-2-250b","score":1128,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"mistral-medium-3.5","score":929,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4-flash-thinking-max","score":1187,"metric":"elo"},{"benchmark":"kmmlu-pro","model":"solar-open-2-250b","score":78.4,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"solar-open-100b","score":64,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"deepseek-v4-flash-thinking-max","score":78.9,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"claude-4.5-haiku","score":67.9,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"gpt-5.4-mini","score":78.1,"metric":"percent"},{"benchmark":"click","model":"solar-open-2-250b","score":90.7,"metric":"percent"},{"benchmark":"click","model":"solar-open-100b","score":78.9,"metric":"percent"},{"benchmark":"click","model":"deepseek-v4-flash-thinking-max","score":89.2,"metric":"percent"},{"benchmark":"click","model":"claude-4.5-haiku","score":53.5,"metric":"percent"},{"benchmark":"click","model":"gpt-5.4-mini","score":89.6,"metric":"percent"},{"benchmark":"hrm8k","model":"solar-open-2-250b","score":92.2,"metric":"percent"},{"benchmark":"hrm8k","model":"solar-open-100b","score":87.6,"metric":"percent"},{"benchmark":"hrm8k","model":"deepseek-v4-flash-thinking-max","score":93.4,"metric":"percent"},{"benchmark":"hrm8k","model":"claude-4.5-haiku","score":90.6,"metric":"percent"},{"benchmark":"hrm8k","model":"gpt-5.4-mini","score":91.3,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"hyperclovax-seed-omni-8b","score":64.9,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen2.5-omni-7b","score":31.1,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"emu3-8b","score":18.7,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"janus-pro-7b","score":16.4,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"hyperclovax-seed-omni-8b","score":75.3,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"qwen2.5-omni-7b","score":51,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"emu3-8b","score":20,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"janus-pro-7b","score":14.9,"metric":"percent"},{"benchmark":"kobolt","model":"hyperclovax-seed-omni-8b","score":27.7,"metric":"percent"},{"benchmark":"kobolt","model":"qwen2.5-omni-7b","score":17.7,"metric":"percent"},{"benchmark":"kobolt","model":"emu3-8b","score":10.3,"metric":"percent"},{"benchmark":"kobolt","model":"janus-pro-7b","score":5.9,"metric":"percent"},{"benchmark":"mmlu","model":"hyperclovax-seed-omni-8b","score":75.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-omni-7b","score":71.6,"metric":"percent"},{"benchmark":"mmlu","model":"emu3-8b","score":32.4,"metric":"percent"},{"benchmark":"mmlu","model":"janus-pro-7b","score":48.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"hyperclovax-seed-omni-8b","score":54.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-omni-7b","score":50.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"emu3-8b","score":10.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"janus-pro-7b","score":20,"metric":"percent"},{"benchmark":"gsm8k","model":"hyperclovax-seed-omni-8b","score":87.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-omni-7b","score":87,"metric":"percent"},{"benchmark":"gsm8k","model":"emu3-8b","score":3,"metric":"percent"},{"benchmark":"gsm8k","model":"janus-pro-7b","score":43.5,"metric":"percent"},{"benchmark":"textvqa","model":"hyperclovax-seed-omni-8b","score":80.3,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2.5-omni-7b","score":84.4,"metric":"percent"},{"benchmark":"textvqa","model":"emu3-8b","score":62.9,"metric":"percent"},{"benchmark":"textvqa","model":"janus-pro-7b","score":58.7,"metric":"percent"},{"benchmark":"docvqa","model":"hyperclovax-seed-omni-8b","score":90.7,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2.5-omni-7b","score":94.9,"metric":"percent"},{"benchmark":"docvqa","model":"emu3-8b","score":74.1,"metric":"percent"},{"benchmark":"docvqa","model":"janus-pro-7b","score":43.4,"metric":"percent"},{"benchmark":"videomme","model":"hyperclovax-seed-omni-8b","score":58.2,"metric":"percent"},{"benchmark":"videomme","model":"qwen2.5-omni-7b","score":64.3,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-2-3b-base","score":62.77,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-2-1.3b-base","score":56.49,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kanana-2-3b-base","score":36.54,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kanana-2-1.3b-base","score":29.87,"metric":"percent"},{"benchmark":"bbh","model":"kanana-2-3b-base","score":54.23,"metric":"percent"},{"benchmark":"bbh","model":"kanana-2-1.3b-base","score":45.58,"metric":"percent"},{"benchmark":"simpleqa","model":"kanana-2-3b-base","score":27.39,"metric":"percent"},{"benchmark":"simpleqa","model":"kanana-2-1.3b-base","score":23.76,"metric":"percent"},{"benchmark":"math","model":"kanana-2-3b-base","score":35.08,"metric":"percent"},{"benchmark":"math","model":"kanana-2-1.3b-base","score":30.82,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-2-3b-base","score":61.03,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-2-1.3b-base","score":51.93,"metric":"percent"},{"benchmark":"humaneval","model":"kanana-2-3b-base","score":55.96,"metric":"percent"},{"benchmark":"humaneval","model":"kanana-2-1.3b-base","score":51.33,"metric":"percent"},{"benchmark":"mbpp","model":"kanana-2-3b-base","score":50.95,"metric":"percent"},{"benchmark":"mbpp","model":"kanana-2-1.3b-base","score":44.86,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-2-3b-base","score":47.92,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-2-1.3b-base","score":44.17,"metric":"percent"},{"benchmark":"kosimpleqa","model":"kanana-2-3b-base","score":32.5,"metric":"percent"},{"benchmark":"kosimpleqa","model":"kanana-2-1.3b-base","score":28.5,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-2-3b-base","score":80.66,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-2-1.3b-base","score":75.34,"metric":"percent"},{"benchmark":"mbpp-ko","model":"kanana-2-3b-base","score":44.55,"metric":"percent"},{"benchmark":"mbpp-ko","model":"kanana-2-1.3b-base","score":39.38,"metric":"percent"},{"benchmark":"ruler-32k","model":"kanana-2-3b-base","score":67.5,"metric":"percent"},{"benchmark":"ruler-32k","model":"kanana-2-1.3b-base","score":55.72,"metric":"percent"},{"benchmark":"mt-bench","model":"kanana-2-3b-instruct","score":7.15,"metric":"percent"},{"benchmark":"mt-bench","model":"kanana-2-1.3b-instruct","score":6.83,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen3.5-2b","score":6.87,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen3-1.7b","score":6.98,"metric":"percent"},{"benchmark":"komt-bench","model":"kanana-2-3b-instruct","score":6.92,"metric":"score"},{"benchmark":"komt-bench","model":"kanana-2-1.3b-instruct","score":6.54,"metric":"score"},{"benchmark":"komt-bench","model":"qwen3.5-2b","score":5.21,"metric":"score"},{"benchmark":"komt-bench","model":"qwen3-1.7b","score":5.29,"metric":"score"},{"benchmark":"ifbench","model":"kanana-2-3b-instruct","score":33.33,"metric":"percent"},{"benchmark":"ifbench","model":"kanana-2-1.3b-instruct","score":34.69,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-2b","score":24.83,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-1.7b","score":18.33,"metric":"percent"},{"benchmark":"ifeval","model":"kanana-2-3b-instruct","score":80.96,"metric":"percent"},{"benchmark":"ifeval","model":"kanana-2-1.3b-instruct","score":77.63,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-2b","score":66.91,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-1.7b","score":68.39,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"kanana-2-3b-instruct","score":71.94,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"kanana-2-1.3b-instruct","score":69.64,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"qwen3.5-2b","score":66.96,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"qwen3-1.7b","score":65.48,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kanana-2-3b-instruct","score":17.12,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kanana-2-1.3b-instruct","score":5.5,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3.5-2b","score":6.27,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3-1.7b","score":4.38,"metric":"percent"},{"benchmark":"mbpp","model":"kanana-2-3b-instruct","score":70.63,"metric":"percent"},{"benchmark":"mbpp","model":"kanana-2-1.3b-instruct","score":69.05,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3.5-2b","score":55.56,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-1.7b","score":62.17,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kanana-2-3b-instruct","score":60.05,"metric":"percent"},{"benchmark":"mbpp-plus","model":"kanana-2-1.3b-instruct","score":60.85,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.5-2b","score":46.83,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3-1.7b","score":52.65,"metric":"percent"},{"benchmark":"gsm-plus","model":"kanana-2-3b-instruct","score":61.17,"metric":"percent"},{"benchmark":"gsm-plus","model":"kanana-2-1.3b-instruct","score":58.27,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3.5-2b","score":61.29,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3-1.7b","score":63.1,"metric":"percent"},{"benchmark":"math500","model":"kanana-2-3b-instruct","score":61.2,"metric":"percent"},{"benchmark":"math500","model":"kanana-2-1.3b-instruct","score":61.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-2b","score":67.8,"metric":"percent"},{"benchmark":"minerva-math","model":"kanana-2-3b-instruct","score":24.44,"metric":"percent"},{"benchmark":"minerva-math","model":"kanana-2-1.3b-instruct","score":22.43,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen3.5-2b","score":35.18,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen3-1.7b","score":27.21,"metric":"percent"},{"benchmark":"kosimpleqa","model":"kanana-2-3b-instruct","score":22.29,"metric":"percent"},{"benchmark":"kosimpleqa","model":"kanana-2-1.3b-instruct","score":17.81,"metric":"percent"},{"benchmark":"kosimpleqa","model":"qwen3.5-2b","score":3.21,"metric":"percent"},{"benchmark":"kosimpleqa","model":"qwen3-1.7b","score":2.82,"metric":"percent"},{"benchmark":"mmlu","model":"kanana-2-30b-a3b-base","score":75.44,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b-base","score":81.14,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kanana-2-30b-a3b-base","score":56.14,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-base","score":61.83,"metric":"percent"},{"benchmark":"bbh","model":"kanana-2-30b-a3b-base","score":79.76,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-30b-a3b-base","score":79.97,"metric":"percent"},{"benchmark":"simpleqa","model":"kanana-2-30b-a3b-base","score":29.7,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-30b-a3b-base","score":26.47,"metric":"percent"},{"benchmark":"math","model":"kanana-2-30b-a3b-base","score":54.4,"metric":"percent"},{"benchmark":"math","model":"qwen3-30b-a3b-base","score":62.58,"metric":"percent"},{"benchmark":"gsm8k","model":"kanana-2-30b-a3b-base","score":82.71,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-30b-a3b-base","score":88.1,"metric":"percent"},{"benchmark":"humaneval","model":"kanana-2-30b-a3b-base","score":75.29,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-30b-a3b-base","score":53.32,"metric":"percent"},{"benchmark":"mbpp","model":"kanana-2-30b-a3b-base","score":62.39,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-30b-a3b-base","score":72.58,"metric":"percent"},{"benchmark":"kmmlu","model":"kanana-2-30b-a3b-base","score":62.15,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen3-30b-a3b-base","score":62.25,"metric":"percent"},{"benchmark":"kosimpleqa","model":"kanana-2-30b-a3b-base","score":49.4,"metric":"percent"},{"benchmark":"kosimpleqa","model":"qwen3-30b-a3b-base","score":26.33,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"kanana-2-30b-a3b-base","score":88.73,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"qwen3-30b-a3b-base","score":72.04,"metric":"percent"},{"benchmark":"gsm8k-ko","model":"kanana-2-30b-a3b-base","score":77.48,"metric":"percent"},{"benchmark":"gsm8k-ko","model":"qwen3-30b-a3b-base","score":88.1,"metric":"percent"},{"benchmark":"mbpp-ko","model":"kanana-2-30b-a3b-base","score":61.55,"metric":"percent"},{"benchmark":"mbpp-ko","model":"qwen3-30b-a3b-base","score":66.84,"metric":"percent"},{"benchmark":"ruler-4k","model":"kanana-2-30b-a3b-base","score":93.09,"metric":"percent"},{"benchmark":"ruler-4k","model":"qwen3-30b-a3b-base","score":94.32,"metric":"percent"},{"benchmark":"ruler-8k","model":"kanana-2-30b-a3b-base","score":92.29,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen3-30b-a3b-base","score":92.16,"metric":"percent"},{"benchmark":"ruler-16k","model":"kanana-2-30b-a3b-base","score":90.73,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen3-30b-a3b-base","score":91.28,"metric":"percent"},{"benchmark":"ruler-32k","model":"kanana-2-30b-a3b-base","score":88.63,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen3-30b-a3b-base","score":88.32,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ax-k2","score":97.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ax-k1","score":91.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-397b-a17b","score":92.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-3-ultra","score":85.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-flash-thinking-max","score":96.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"glm-5.1","score":95.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.6-thinking","score":95.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minimax-m2.7","score":88.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"ax-k2","score":45.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"ax-k1","score":1,"metric":"percent"},{"benchmark":"matharena-apex","model":"qwen3.5-397b-a17b","score":13.5,"metric":"percent"},{"benchmark":"matharena-apex","model":"nemotron-3-ultra","score":3.1,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-flash-thinking-max","score":28.1,"metric":"percent"},{"benchmark":"matharena-apex","model":"glm-5.1","score":10.4,"metric":"percent"},{"benchmark":"matharena-apex","model":"kimi-k2.6-thinking","score":20.8,"metric":"percent"},{"benchmark":"matharena-apex","model":"minimax-m2.7","score":1,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"ax-k2","score":88.6,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"ax-k1","score":50.8,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"qwen3.5-397b-a17b","score":61.2,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"nemotron-3-ultra","score":45.5,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-flash-thinking-max","score":88,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"glm-5.1","score":72.1,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"kimi-k2.6-thinking","score":72.6,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"minimax-m2.7","score":30.3,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"ax-k2","score":80.5,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"ax-k1","score":68.9,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen3.5-397b-a17b","score":78.4,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"nemotron-3-ultra","score":69.2,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"deepseek-v4-flash-thinking-max","score":78.8,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"glm-5.1","score":76.5,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"kimi-k2.6-thinking","score":73.4,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"minimax-m2.7","score":66.6,"metric":"percent"},{"benchmark":"kobolt","model":"ax-k2","score":73,"metric":"percent"},{"benchmark":"kobolt","model":"ax-k1","score":51,"metric":"percent"},{"benchmark":"kobolt","model":"qwen3.5-397b-a17b","score":69.9,"metric":"percent"},{"benchmark":"kobolt","model":"nemotron-3-ultra","score":59.1,"metric":"percent"},{"benchmark":"kobolt","model":"deepseek-v4-flash-thinking-max","score":75.3,"metric":"percent"},{"benchmark":"kobolt","model":"glm-5.1","score":72,"metric":"percent"},{"benchmark":"kobolt","model":"kimi-k2.6-thinking","score":66,"metric":"percent"},{"benchmark":"kobolt","model":"minimax-m2.7","score":51.4,"metric":"percent"},{"benchmark":"click","model":"ax-k2","score":91.6,"metric":"percent"},{"benchmark":"click","model":"ax-k1","score":85.3,"metric":"percent"},{"benchmark":"click","model":"qwen3.5-397b-a17b","score":88.4,"metric":"percent"},{"benchmark":"click","model":"nemotron-3-ultra","score":84.1,"metric":"percent"},{"benchmark":"click","model":"deepseek-v4-flash-thinking-max","score":89.6,"metric":"percent"},{"benchmark":"click","model":"glm-5.1","score":88.8,"metric":"percent"},{"benchmark":"click","model":"kimi-k2.6-thinking","score":80.9,"metric":"percent"},{"benchmark":"click","model":"minimax-m2.7","score":76.1,"metric":"percent"},{"benchmark":"livecodebench","model":"ax-k2","score":84,"metric":"percent"},{"benchmark":"livecodebench","model":"ax-k1","score":74.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-397b-a17b","score":82.6,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-ultra","score":76.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-thinking-max","score":89.4,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-5.1","score":86.4,"metric":"percent"},{"benchmark":"livecodebench","model":"kimi-k2.6-thinking","score":86.5,"metric":"percent"},{"benchmark":"livecodebench","model":"minimax-m2.7","score":69.8,"metric":"percent"},{"benchmark":"scicode","model":"ax-k2","score":41,"metric":"percent"},{"benchmark":"scicode","model":"ax-k1","score":24.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ax-k2","score":36,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k2.6-thinking","score":65.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"ax-k2","score":27.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"ax-k1","score":8.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.1","score":28,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ax-k2","score":85.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ax-k1","score":76.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-5.1","score":86.8,"metric":"percent"},{"benchmark":"ifbench","model":"ax-k2","score":75.9,"metric":"percent"},{"benchmark":"ifbench","model":"ax-k1","score":63.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"ax-k2","score":66,"metric":"percent"},{"benchmark":"aa-lcr","model":"ax-k1","score":26,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-ultra","score":67,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2.6-thinking","score":69.7,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"ax-k2","score":1031,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"ax-k1","score":500,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.1","score":1257,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"minimax-m2.7","score":1158,"metric":"elo"},{"benchmark":"tau2-telecom","model":"ax-k2","score":98,"metric":"percent"},{"benchmark":"tau2-telecom","model":"ax-k1","score":86,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-397b-a17b","score":95.6,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-ultra","score":83.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v4-flash-thinking-max","score":95,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-5.1","score":97.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kimi-k2.6-thinking","score":95.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"ax-k2","score":13,"metric":"percent"},{"benchmark":"tau2-telecom","model":"motif-3","score":94.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"minimax-m3","score":88.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.7-max","score":94.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"deepseek-v4-pro-thinking-max","score":96.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"motif-3","score":35.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-5.1","score":13.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"kimi-k2.6-thinking","score":23.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.7-max","score":12,"metric":"percent"},{"benchmark":"tau3-banking","model":"deepseek-v4-pro-thinking-max","score":30.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"motif-3","score":76.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m3","score":75,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5.1","score":76.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k2.6-thinking","score":76.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-pro-thinking-max","score":77.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"motif-3","score":74.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minimax-m3","score":65.2,"metric":"percent"},{"benchmark":"scicode","model":"motif-3","score":40.6,"metric":"percent"},{"benchmark":"scicode","model":"minimax-m3","score":45.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"motif-3","score":83.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"kimi-k2.6-thinking","score":81.8,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"motif-3","score":75.5,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"qwen3.7-max","score":44.5,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"deepseek-v4-pro-thinking-max","score":85.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"motif-3","score":83.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m3","score":92.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"motif-3","score":37,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.1","score":30.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"kimi-k2.6-thinking","score":37.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"deepseek-v4-pro-thinking-max","score":37.5,"metric":"percent"},{"benchmark":"critpt","model":"motif-3","score":6.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"motif-3","score":72.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"minimax-m3","score":80.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.1","score":68,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2.6-thinking","score":76.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.7-max","score":75,"metric":"percent"},{"benchmark":"aa-lcr","model":"deepseek-v4-pro-thinking-max","score":70,"metric":"percent"},{"benchmark":"ifbench","model":"motif-3","score":78.2,"metric":"percent"},{"benchmark":"ifbench","model":"minimax-m3","score":82.9,"metric":"percent"},{"benchmark":"mmlu","model":"motif-3-base","score":86.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"motif-3-base","score":68.56,"metric":"percent"},{"benchmark":"arc-challenge","model":"motif-3-base","score":94.71,"metric":"percent"},{"benchmark":"winogrande","model":"motif-3-base","score":80.9,"metric":"percent"},{"benchmark":"hellaswag","model":"motif-3-base","score":88.3,"metric":"percent"},{"benchmark":"piqa","model":"motif-3-base","score":85.14,"metric":"percent"},{"benchmark":"gsm8k","model":"motif-3-base","score":93.93,"metric":"percent"},{"benchmark":"math","model":"motif-3-base","score":70.58,"metric":"percent"},{"benchmark":"humaneval","model":"motif-3-base","score":73.7,"metric":"percent"},{"benchmark":"mbpp","model":"motif-3-base","score":84.6,"metric":"percent"},{"benchmark":"math500","model":"sarvam-105b","score":98.6,"metric":"percent"},{"benchmark":"math500","model":"glm-4.5-air","score":97.2,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-120b","score":97,"metric":"percent"},{"benchmark":"math500","model":"qwen3-next-80b-a3b-thinking","score":98.2,"metric":"percent"},{"benchmark":"livecodebench","model":"sarvam-105b","score":71.7,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-air","score":59.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":72.3,"metric":"percent"},{"benchmark":"mmlu","model":"sarvam-105b","score":90.6,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.5-air","score":87.3,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-120b","score":90,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-next-80b-a3b-thinking","score":90,"metric":"percent"},{"benchmark":"mmlu-pro","model":"sarvam-105b","score":81.7,"metric":"percent"},{"benchmark":"writingbench","model":"sarvam-105b","score":80.5,"metric":"percent"},{"benchmark":"writingbench","model":"glm-4.5-air","score":83.8,"metric":"percent"},{"benchmark":"writingbench","model":"gpt-oss-120b","score":86.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"sarvam-105b","score":71,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"glm-4.5-air","score":68.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-oss-120b","score":88.5,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-next-80b-a3b-thinking","score":68.2,"metric":"percent"},{"benchmark":"ifeval","model":"sarvam-105b","score":84.8,"metric":"percent"},{"benchmark":"ifeval","model":"glm-4.5-air","score":83.5,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-120b","score":85.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"sarvam-105b","score":78.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.5-air","score":75,"metric":"percent"},{"benchmark":"aime-2025","model":"sarvam-105b","score":88.3,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.5-air","score":83.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":90,"metric":"percent"},{"benchmark":"beyondaime","model":"sarvam-105b","score":69.1,"metric":"percent"},{"benchmark":"beyondaime","model":"glm-4.5-air","score":61.5,"metric":"percent"},{"benchmark":"beyondaime","model":"gpt-oss-120b","score":51,"metric":"percent"},{"benchmark":"beyondaime","model":"qwen3-next-80b-a3b-thinking","score":68,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"sarvam-105b","score":85.8,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"glm-4.5-air","score":69.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-next-80b-a3b-thinking","score":73.9,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"sarvam-105b","score":85.8,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-4.5-air","score":75,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-next-80b-a3b-thinking","score":80,"metric":"percent"},{"benchmark":"browsecomp","model":"sarvam-105b","score":49.5,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-4.5-air","score":21.3,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3-next-80b-a3b-thinking","score":38,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"sarvam-105b","score":45,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.5-air","score":57.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-oss-120b","score":50.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3-next-80b-a3b-thinking","score":60.9,"metric":"percent"},{"benchmark":"math500","model":"sarvam-30b","score":97,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-27b-it","score":87.4,"metric":"percent"},{"benchmark":"math500","model":"mistral-small-3.2-24b-instruct","score":69.4,"metric":"percent"},{"benchmark":"math500","model":"olmo-3.1-think-32b","score":96.2,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3-nano-30b-a3b","score":98,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b-thinking-2507","score":97.6,"metric":"percent"},{"benchmark":"math500","model":"glm-4.7-flash","score":97,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-20b","score":94.2,"metric":"percent"},{"benchmark":"humaneval","model":"sarvam-30b","score":92.1,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-3-27b-it","score":88.4,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-small-3.2-24b-instruct","score":92.9,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3.1-think-32b","score":95.1,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-nano-30b-a3b","score":97.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-30b-a3b-thinking-2507","score":95.7,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4.7-flash","score":96.3,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-oss-20b","score":95.7,"metric":"percent"},{"benchmark":"mbpp","model":"sarvam-30b","score":92.7,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-27b-it","score":81.8,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-small-3.2-24b-instruct","score":78.3,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3.1-think-32b","score":58.7,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-nano-30b-a3b","score":91.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-30b-a3b-thinking-2507","score":94.3,"metric":"percent"},{"benchmark":"mbpp","model":"glm-4.7-flash","score":91.8,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-oss-20b","score":95.3,"metric":"percent"},{"benchmark":"livecodebench","model":"sarvam-30b","score":70,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-27b-it","score":28,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-small-3.2-24b-instruct","score":26,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3.1-think-32b","score":73,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-nano-30b-a3b","score":68.3,"metric":"percent"},{"benchmark":"mmlu","model":"sarvam-30b","score":85.1,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b-it","score":81.2,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3-nano-30b-a3b","score":84,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-30b-a3b-thinking-2507","score":88.4,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.7-flash","score":86.9,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-20b","score":85.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"sarvam-30b","score":80,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-27b-it","score":68.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-3.2-24b-instruct","score":69.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3.1-think-32b","score":72,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-30b-a3b","score":78.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.7-flash","score":73.6,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"sarvam-30b","score":49,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gemma-3-27b-it","score":50.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"olmo-3.1-think-32b","score":42,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"qwen3-30b-a3b-thinking-2507","score":72.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"glm-4.7-flash","score":58.1,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"gpt-oss-20b","score":62.9,"metric":"percent"},{"benchmark":"writingbench","model":"sarvam-30b","score":78.7,"metric":"percent"},{"benchmark":"writingbench","model":"gemma-3-27b-it","score":71.4,"metric":"percent"},{"benchmark":"writingbench","model":"mistral-small-3.2-24b-instruct","score":70.3,"metric":"percent"},{"benchmark":"writingbench","model":"olmo-3.1-think-32b","score":75.7,"metric":"percent"},{"benchmark":"writingbench","model":"nemotron-3-nano-30b-a3b","score":83.7,"metric":"percent"},{"benchmark":"writingbench","model":"glm-4.7-flash","score":79.2,"metric":"percent"},{"benchmark":"writingbench","model":"gpt-oss-20b","score":79.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"sarvam-30b","score":66.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3.1-think-32b","score":57.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-nano-30b-a3b","score":73,"metric":"percent"},{"benchmark":"aime-2025","model":"sarvam-30b","score":88.3,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-nano-30b-a3b","score":89.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"sarvam-30b","score":73.3,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"olmo-3.1-think-32b","score":51.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"nemotron-3-nano-30b-a3b","score":85,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-30b-a3b-thinking-2507","score":71.4,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"glm-4.7-flash","score":85,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"sarvam-30b","score":74.2,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"olmo-3.1-think-32b","score":58.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"nemotron-3-nano-30b-a3b","score":75,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"qwen3-30b-a3b-thinking-2507","score":73.3,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"glm-4.7-flash","score":81.7,"metric":"percent"},{"benchmark":"hmmt-nov-2025","model":"gpt-oss-20b","score":68.3,"metric":"percent"},{"benchmark":"beyondaime","model":"sarvam-30b","score":58.3,"metric":"percent"},{"benchmark":"beyondaime","model":"olmo-3.1-think-32b","score":48.5,"metric":"percent"},{"benchmark":"beyondaime","model":"nemotron-3-nano-30b-a3b","score":64,"metric":"percent"},{"benchmark":"beyondaime","model":"qwen3-30b-a3b-thinking-2507","score":61,"metric":"percent"},{"benchmark":"beyondaime","model":"glm-4.7-flash","score":60,"metric":"percent"},{"benchmark":"beyondaime","model":"gpt-oss-20b","score":46,"metric":"percent"},{"benchmark":"browsecomp","model":"sarvam-30b","score":35.5,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-nano-30b-a3b","score":23.8,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3-30b-a3b-thinking-2507","score":2.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"sarvam-30b","score":34,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-nano-30b-a3b","score":38.8,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-think-v2","score":90.42,"metric":"percent"},{"benchmark":"hmmt-2025","model":"k2-think-v2","score":84.79,"metric":"percent"},{"benchmark":"scicode","model":"k2-think-v2","score":33,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-think-v2","score":72.98,"metric":"percent"},{"benchmark":"hle-text-only","model":"k2-think-v2","score":9.5,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"k2-horizon-375b-a23b","score":1441,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-3-ultra","score":1162,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"inkling","score":1234,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"minimax-m3","score":1380,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.2","score":1498,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-luna","score":1569,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-terra","score":1503,"metric":"elo"},{"benchmark":"tau3-banking","model":"k2-horizon-375b-a23b","score":34,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-ultra","score":14.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"inkling","score":29.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.6-luna","score":31.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.6-terra","score":28.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-sonnet-5","score":37.3,"metric":"percent"},{"benchmark":"apex-agents","model":"k2-horizon-375b-a23b","score":24.8,"metric":"percent"},{"benchmark":"apex-agents","model":"nemotron-3-ultra","score":9,"metric":"percent"},{"benchmark":"apex-agents","model":"inkling","score":19,"metric":"percent"},{"benchmark":"apex-agents","model":"minimax-m3","score":23.8,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-5.2","score":26.9,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.6-luna","score":28.6,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.6-terra","score":25.4,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-sonnet-5","score":31.7,"metric":"percent"},{"benchmark":"mcpmark","model":"k2-horizon-375b-a23b","score":67.7,"metric":"percent"},{"benchmark":"mcpmark","model":"nemotron-3-ultra","score":45.7,"metric":"percent"},{"benchmark":"mcpmark","model":"inkling","score":51.2,"metric":"percent"},{"benchmark":"mcpmark","model":"minimax-m3","score":48.8,"metric":"percent"},{"benchmark":"mcpmark","model":"glm-5.2","score":72.4,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5.6-luna","score":66.9,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5.6-terra","score":74,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-sonnet-5","score":65.3,"metric":"percent"},{"benchmark":"browsecomp","model":"k2-horizon-375b-a23b","score":72.8,"metric":"percent"},{"benchmark":"wildclawbench","model":"k2-horizon-375b-a23b","score":50.9,"metric":"percent"},{"benchmark":"wildclawbench","model":"nemotron-3-ultra","score":34.2,"metric":"percent"},{"benchmark":"wildclawbench","model":"inkling","score":52.3,"metric":"percent"},{"benchmark":"wildclawbench","model":"minimax-m3","score":56.4,"metric":"percent"},{"benchmark":"wildclawbench","model":"glm-5.2","score":55,"metric":"percent"},{"benchmark":"wildclawbench","model":"gpt-5.6-luna","score":50.4,"metric":"percent"},{"benchmark":"wildclawbench","model":"gpt-5.6-terra","score":60,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"k2-horizon-375b-a23b","score":70.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-luna","score":80.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-5.6-terra","score":75.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-sonnet-5","score":80.5,"metric":"percent"},{"benchmark":"scicode","model":"k2-horizon-375b-a23b","score":42.7,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.6-luna","score":52.5,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.6-terra","score":50.1,"metric":"percent"},{"benchmark":"scicode","model":"claude-sonnet-5","score":53.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"k2-horizon-375b-a23b","score":32,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-ultra","score":28.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"inkling","score":31.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-5.2","score":41.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.6-luna","score":39.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-5.6-terra","score":38.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"claude-sonnet-5","score":41.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-horizon-375b-a23b","score":87.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.6-luna","score":91.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.6-terra","score":89.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-sonnet-5","score":91.1,"metric":"percent"},{"benchmark":"critpt","model":"k2-horizon-375b-a23b","score":8.6,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5.6-luna","score":21,"metric":"percent"},{"benchmark":"critpt","model":"gpt-5.6-terra","score":22.9,"metric":"percent"},{"benchmark":"critpt","model":"claude-sonnet-5","score":16.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"k2-horizon-375b-a23b","score":76,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-ultra","score":71,"metric":"percent"},{"benchmark":"aa-lcr","model":"inkling","score":73.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-5.2","score":76.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.6-luna","score":78.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-5.6-terra","score":73.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-sonnet-5","score":77,"metric":"percent"},{"benchmark":"tau3-banking","model":"k2-horizon-32b","score":24.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.8-27b","score":48,"metric":"percent"},{"benchmark":"tau3-banking","model":"granite-4.2-30b","score":14.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"k2-horizon-32b","score":62.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-27b","score":79.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"granite-4.2-30b","score":26.6,"metric":"percent"},{"benchmark":"scicode","model":"k2-horizon-32b","score":37.9,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-27b","score":44.7,"metric":"percent"},{"benchmark":"scicode","model":"granite-4.2-30b","score":36.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"k2-horizon-32b","score":25.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.8-27b","score":33.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"granite-4.2-30b","score":11.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-horizon-32b","score":82.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.8-27b","score":90.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"granite-4.2-30b","score":64.4,"metric":"percent"},{"benchmark":"critpt","model":"k2-horizon-32b","score":2.9,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.8-27b","score":5.4,"metric":"percent"},{"benchmark":"critpt","model":"muse-glimmer-30b","score":2.6,"metric":"percent"},{"benchmark":"critpt","model":"granite-4.2-30b","score":0.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"k2-horizon-32b","score":68,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.8-27b","score":77.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"granite-4.2-30b","score":46.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"k2-horizon-mova-36b-a4b","score":26.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-super-120b-a12b","score":10.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.6-35b-a3b","score":9.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-31b-it","score":14.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"k2-horizon-mova-36b-a4b","score":58.6,"metric":"percent"},{"benchmark":"scicode","model":"k2-horizon-mova-36b-a4b","score":38.9,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-super-120b-a12b","score":36,"metric":"percent"},{"benchmark":"hle-text-only","model":"k2-horizon-mova-36b-a4b","score":25.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-super-120b-a12b","score":20.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.6-35b-a3b","score":22.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-horizon-mova-36b-a4b","score":80.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-super-120b-a12b","score":80,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-35b-a3b","score":84.1,"metric":"percent"},{"benchmark":"critpt","model":"k2-horizon-mova-36b-a4b","score":2.1,"metric":"percent"},{"benchmark":"critpt","model":"nemotron-3-super-120b-a12b","score":3.1,"metric":"percent"},{"benchmark":"critpt","model":"qwen3.6-35b-a3b","score":0.3,"metric":"percent"},{"benchmark":"critpt","model":"gemma-4-31b-it","score":1.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"k2-horizon-mova-36b-a4b","score":66.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-super-120b-a12b","score":60.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.6-35b-a3b","score":66.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-4b","score":61.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"granite-4.2-3b","score":57.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"nemotron-3-nano-4b-thinking","score":34.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-4b","score":41.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"granite-4.2-3b","score":32.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-nano-4b-thinking","score":1.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-nano-4b-thinking","score":51.3,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-4b","score":9.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"granite-4.2-3b","score":6.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-nano-4b-thinking","score":4.9,"metric":"percent"},{"benchmark":"scicode","model":"granite-4.2-3b","score":24.9,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3-nano-4b-thinking","score":16.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-nano-4b-thinking","score":3.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":55.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4.2-3b","score":50.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nemotron-3-nano-4b-thinking","score":36.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"k2-horizon-3.7b","score":17.7,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-horizon-3.7b","score":89.2,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-horizon-7b","score":90.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"k2-horizon-3.7b","score":90.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"k2-horizon-7b","score":90.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"k2-horizon-3.7b","score":87.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"k2-horizon-7b","score":87.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"k2-horizon-3.7b","score":75.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"k2-horizon-7b","score":77.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-horizon-3.7b","score":68.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-horizon-7b","score":75.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"k2-horizon-3.7b","score":14,"metric":"percent"},{"benchmark":"hle-text-only","model":"k2-horizon-7b","score":19.5,"metric":"percent"},{"benchmark":"livecodebench","model":"k2-horizon-3.7b","score":64.5,"metric":"percent"},{"benchmark":"livecodebench","model":"k2-horizon-7b","score":72.7,"metric":"percent"},{"benchmark":"ojbench","model":"k2-horizon-3.7b","score":21.6,"metric":"percent"},{"benchmark":"ojbench","model":"k2-horizon-7b","score":29.4,"metric":"percent"},{"benchmark":"scicode","model":"k2-horizon-3.7b","score":25.8,"metric":"percent"},{"benchmark":"scicode","model":"k2-horizon-7b","score":33.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"k2-horizon-3.7b","score":65.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"k2-horizon-7b","score":72.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"k2-horizon-3.7b","score":39.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"k2-horizon-7b","score":44.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"k2-horizon-3.7b","score":64.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"k2-horizon-7b","score":67,"metric":"percent"},{"benchmark":"aa-lcr","model":"k2-horizon-7b","score":68,"metric":"percent"},{"benchmark":"tau3-banking","model":"k2-horizon-7b","score":25.8,"metric":"percent"},{"benchmark":"browsecomp","model":"k2-horizon-7b","score":59,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-horizon-0.9b","score":41.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-0.8b-thinking","score":1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-2b","score":34.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"k2-horizon-0.9b","score":48.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-0.8b-thinking","score":0.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-2b","score":38.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"k2-horizon-0.9b","score":25.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-0.8b-thinking","score":0.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-2b","score":22.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"k2-horizon-0.9b","score":27.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-0.8b-thinking","score":11.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-2b","score":54.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"k2-horizon-0.9b","score":79.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-0.8b-thinking","score":16.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-2b","score":75.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"k2-horizon-0.9b","score":68,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.5-0.8b-thinking","score":35.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.5-2b","score":67.7,"metric":"percent"},{"benchmark":"livecodebench","model":"k2-horizon-0.9b","score":37.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-0.8b-thinking","score":6.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-2b","score":29.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"k2-horizon-0.9b","score":28,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-0.8b-thinking","score":25.3,"metric":"percent"},{"benchmark":"belebele","model":"jais-3-375b-a23b","score":95.6,"metric":"percent"},{"benchmark":"belebele","model":"qwen3.5-397b-a17b","score":94.8,"metric":"percent"},{"benchmark":"belebele","model":"minimax-m3","score":92.3,"metric":"percent"},{"benchmark":"belebele","model":"qwen3.8-flash-next","score":95.5,"metric":"percent"},{"benchmark":"belebele","model":"nemotron-3-ultra","score":93.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"jais-3-375b-a23b","score":73.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-flash-next","score":86.1,"metric":"percent"},{"benchmark":"mcpmark","model":"jais-3-375b-a23b","score":68.5,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.5-397b-a17b","score":52.8,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.8-flash-next","score":66.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"jais-3-375b-a23b","score":70.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-397b-a17b","score":71.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"minimax-m3","score":75.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.8-flash-next","score":80.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-ultra","score":67.8,"metric":"percent"},{"benchmark":"browsecomp","model":"jais-3-375b-a23b","score":72.6,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.8-flash-next","score":79.8,"metric":"percent"},{"benchmark":"belebele","model":"jais-3-32b","score":95,"metric":"percent"},{"benchmark":"belebele","model":"falcon-h1-34b-instruct","score":86.6,"metric":"percent"},{"benchmark":"belebele","model":"gemma-4-31b-it","score":95.9,"metric":"percent"},{"benchmark":"belebele","model":"muse-glimmer-30b","score":94.3,"metric":"percent"},{"benchmark":"belebele","model":"qwen3.8-27b","score":94.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"jais-3-32b","score":63.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"falcon-h1-34b-instruct","score":1.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-31b-it","score":43.5,"metric":"percent"},{"benchmark":"mcpmark","model":"jais-3-32b","score":66.1,"metric":"percent"},{"benchmark":"mcpmark","model":"falcon-h1-34b-instruct","score":0.8,"metric":"percent"},{"benchmark":"mcpmark","model":"gemma-4-31b-it","score":48.8,"metric":"percent"},{"benchmark":"mcpmark","model":"muse-glimmer-30b","score":44.9,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.8-27b","score":49.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"jais-3-32b","score":72.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"falcon-h1-34b-instruct","score":0.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-31b-it","score":59,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"muse-glimmer-30b","score":71.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.8-27b","score":73.5,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"jais-3-32b","score":71.9,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"falcon-h1-34b-instruct","score":1.8,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gemma-4-31b-it","score":42.5,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"muse-glimmer-30b","score":41.1,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"qwen3.8-27b","score":53,"metric":"percent"},{"benchmark":"belebele","model":"jais-3-mova-36b-a4b","score":94.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"jais-3-mova-36b-a4b","score":67.3,"metric":"percent"},{"benchmark":"mcpmark","model":"jais-3-mova-36b-a4b","score":69.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"jais-3-mova-36b-a4b","score":72.8,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"jais-3-mova-36b-a4b","score":71.8,"metric":"percent"},{"benchmark":"belebele","model":"jais-3-7b","score":92.9,"metric":"percent"},{"benchmark":"belebele","model":"gemma-4-e4b-it","score":88.7,"metric":"percent"},{"benchmark":"belebele","model":"gemma-4-12b-it","score":93.6,"metric":"percent"},{"benchmark":"belebele","model":"qwen3.5-9b","score":89.2,"metric":"percent"},{"benchmark":"belebele","model":"falcon-h1-7b","score":72.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"jais-3-7b","score":46.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"falcon-h1-7b","score":0,"metric":"percent"},{"benchmark":"mcpmark","model":"jais-3-7b","score":49.6,"metric":"percent"},{"benchmark":"mcpmark","model":"gemma-4-e4b-it","score":3.2,"metric":"percent"},{"benchmark":"mcpmark","model":"gemma-4-12b-it","score":17.3,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.5-9b","score":31.5,"metric":"percent"},{"benchmark":"mcpmark","model":"falcon-h1-7b","score":0,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"jais-3-7b","score":70.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-e4b-it","score":4.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-12b-it","score":28.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-9b","score":50.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"falcon-h1-7b","score":0,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"jais-3-7b","score":67.7,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gemma-4-e4b-it","score":21.2,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gemma-4-12b-it","score":21.9,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"qwen3.5-9b","score":49.5,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"falcon-h1-7b","score":0.4,"metric":"percent"},{"benchmark":"belebele","model":"jais-3-3.7b","score":91.9,"metric":"percent"},{"benchmark":"belebele","model":"qwen3.5-4b","score":84,"metric":"percent"},{"benchmark":"belebele","model":"gemma-4-e2b-it","score":79.6,"metric":"percent"},{"benchmark":"belebele","model":"falcon-h1-3b","score":57.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"jais-3-3.7b","score":41.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"falcon-h1-3b","score":0,"metric":"percent"},{"benchmark":"mcpmark","model":"jais-3-3.7b","score":30.7,"metric":"percent"},{"benchmark":"mcpmark","model":"qwen3.5-4b","score":25.2,"metric":"percent"},{"benchmark":"mcpmark","model":"gemma-4-e2b-it","score":1.6,"metric":"percent"},{"benchmark":"mcpmark","model":"falcon-h1-3b","score":0,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"jais-3-3.7b","score":64.8,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"qwen3.5-4b","score":50.6,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gemma-4-e2b-it","score":16.4,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"falcon-h1-3b","score":0,"metric":"percent"},{"benchmark":"belebele","model":"jais-3-0.9b","score":81.6,"metric":"percent"},{"benchmark":"belebele","model":"qwen3.5-2b","score":67.6,"metric":"percent"},{"benchmark":"belebele","model":"falcon-h1-1.5b-deep","score":57.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kolibri-1","score":84.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.7-flash","score":73.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-nano-30b-a3b","score":73.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-35b-a3b","score":83.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-next-80b-a3b-thinking","score":76.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-26b-a4b-it","score":81.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b","score":76.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-small-4-thinking","score":74.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glm-4.5-air","score":73.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-super-120b-a12b","score":78,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"apertus-70b-instruct","score":29.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"kolibri-1","score":21.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-4.7-flash","score":15.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-nano-30b-a3b","score":12.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-35b-a3b","score":20.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.6-35b-a3b","score":21.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3-next-80b-a3b-thinking","score":11.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemma-4-26b-a4b-it","score":19.2,"metric":"percent"},{"benchmark":"hle-text-only","model":"gpt-oss-120b","score":19.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"mistral-small-4-thinking","score":9.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"glm-4.5-air","score":8.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3-super-120b-a12b","score":20.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.8-27b","score":35.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"apertus-70b-instruct","score":5.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kolibri-1","score":80,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.7-flash","score":76.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-35b-a3b","score":84.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-35b-a3b","score":84.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-next-80b-a3b-thinking","score":81.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-26b-a4b-it","score":84.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-4-thinking","score":80.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-air","score":80.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b","score":82.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.8-27b","score":85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-70b-instruct","score":43,"metric":"percent"},{"benchmark":"aime-2025","model":"kolibri-1","score":96.9,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.7-flash","score":89.4,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-nano-30b-a3b","score":89.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-35b-a3b","score":88.1,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.6-35b-a3b","score":84.6,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-next-80b-a3b-thinking","score":84.2,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-26b-a4b-it","score":87.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":90.6,"metric":"percent"},{"benchmark":"aime-2025","model":"mistral-small-4-thinking","score":79.8,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-4.5-air","score":81.9,"metric":"percent"},{"benchmark":"aime-2025","model":"nemotron-3-super-120b-a12b","score":91.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.8-27b","score":97.9,"metric":"percent"},{"benchmark":"aime-2025","model":"apertus-70b-instruct","score":0.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kolibri-1","score":96,"metric":"percent"},{"benchmark":"aime-2026-i","model":"glm-4.7-flash","score":88.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-3-nano-30b-a3b","score":87.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-35b-a3b","score":92.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-35b-a3b","score":91,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-next-80b-a3b-thinking","score":88.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-26b-a4b-it","score":87.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-oss-120b","score":90.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"mistral-small-4-thinking","score":83.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"glm-4.5-air","score":83.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-3-super-120b-a12b","score":90.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.8-27b","score":97.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"apertus-70b-instruct","score":0.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kolibri-1","score":27.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-4.7-flash","score":20.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-nano-30b-a3b","score":9.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-35b-a3b","score":39.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3-next-80b-a3b-thinking","score":8.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-oss-120b","score":29.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mistral-small-4-thinking","score":21,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3-super-120b-a12b","score":39.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-27b","score":76.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kolibri-1","score":94.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-4.7-flash","score":95.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-nano-30b-a3b","score":45.9,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.5-35b-a3b","score":97.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.6-35b-a3b","score":99.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gemma-4-26b-a4b-it","score":45.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-120b","score":73.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"mistral-small-4-thinking","score":41.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"glm-4.5-air","score":53.8,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3-super-120b-a12b","score":68.1,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.8-27b","score":82.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"apertus-70b-instruct","score":10.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"kolibri-1","score":69.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"glm-4.7-flash","score":57.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3-nano-30b-a3b","score":64.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.5-35b-a3b","score":70.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.6-35b-a3b","score":71.6,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3-next-80b-a3b-thinking","score":60.8,"metric":"percent"},{"benchmark":"tau2-retail","model":"gemma-4-26b-a4b-it","score":71.3,"metric":"percent"},{"benchmark":"tau2-retail","model":"gpt-oss-120b","score":60.5,"metric":"percent"},{"benchmark":"tau2-retail","model":"mistral-small-4-thinking","score":62.9,"metric":"percent"},{"benchmark":"tau2-retail","model":"glm-4.5-air","score":61.4,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3-super-120b-a12b","score":67.5,"metric":"percent"},{"benchmark":"tau2-retail","model":"qwen3.8-27b","score":68.7,"metric":"percent"},{"benchmark":"tau2-retail","model":"apertus-70b-instruct","score":9.6,"metric":"percent"},{"benchmark":"tau2-airline","model":"kolibri-1","score":76.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"glm-4.7-flash","score":68.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3-nano-30b-a3b","score":52.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3.5-35b-a3b","score":76,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3.6-35b-a3b","score":70.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3-next-80b-a3b-thinking","score":65.3,"metric":"percent"},{"benchmark":"tau2-airline","model":"gemma-4-26b-a4b-it","score":73.3,"metric":"percent"},{"benchmark":"tau2-airline","model":"gpt-oss-120b","score":72.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"mistral-small-4-thinking","score":40,"metric":"percent"},{"benchmark":"tau2-airline","model":"glm-4.5-air","score":70.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3-super-120b-a12b","score":72.7,"metric":"percent"},{"benchmark":"tau2-airline","model":"qwen3.8-27b","score":83.3,"metric":"percent"},{"benchmark":"tau2-airline","model":"apertus-70b-instruct","score":40,"metric":"percent"},{"benchmark":"tau3-banking","model":"kolibri-1","score":38.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-4.7-flash","score":7.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-nano-30b-a3b","score":5.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-35b-a3b","score":11.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.6-35b-a3b","score":10.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3-next-80b-a3b-thinking","score":5.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-26b-a4b-it","score":16,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-oss-120b","score":14.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"mistral-small-4-thinking","score":5.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"glm-4.5-air","score":6.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3-super-120b-a12b","score":15.5,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.8-27b","score":50,"metric":"percent"},{"benchmark":"tau3-banking","model":"apertus-70b-instruct","score":2.1,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kolibri-1","score":39.8,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"glm-4.7-flash","score":58.2,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"nemotron-3-nano-30b-a3b","score":47.9,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3.5-35b-a3b","score":54,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3.6-35b-a3b","score":53.5,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3-next-80b-a3b-thinking","score":51.4,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"gemma-4-26b-a4b-it","score":53.4,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"gpt-oss-120b","score":45.6,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"mistral-small-4-thinking","score":36.2,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"glm-4.5-air","score":61.6,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"nemotron-3-super-120b-a12b","score":44.6,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3.8-27b","score":42.5,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"apertus-70b-instruct","score":0.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"kolibri-1","score":61.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"glm-4.7-flash","score":65.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nemotron-3-nano-30b-a3b","score":61.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-35b-a3b","score":70.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.6-35b-a3b","score":67.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-next-80b-a3b-thinking","score":51,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-26b-a4b-it","score":68.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-oss-120b","score":57.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"mistral-small-4-thinking","score":58,"metric":"percent"},{"benchmark":"bfcl-v4","model":"glm-4.5-air","score":67.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nemotron-3-super-120b-a12b","score":61,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.8-27b","score":73.2,"metric":"percent"},{"benchmark":"browsecomp","model":"kolibri-1","score":29.4,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-nano-30b-a3b","score":14.5,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-35b-a3b","score":36.5,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.6-35b-a3b","score":26.9,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3-next-80b-a3b-thinking","score":2.8,"metric":"percent"},{"benchmark":"browsecomp","model":"gemma-4-26b-a4b-it","score":25.5,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-oss-120b","score":31.2,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3-super-120b-a12b","score":29.1,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.8-27b","score":46.4,"metric":"percent"},{"benchmark":"livecodebench","model":"kolibri-1","score":85.9,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.7-flash","score":46.5,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-nano-30b-a3b","score":71.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-35b-a3b","score":77.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.6-35b-a3b","score":82.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b-thinking","score":73.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-26b-a4b-it","score":82.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":87.5,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-small-4-thinking","score":71.2,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-super-120b-a12b","score":82,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.8-27b","score":93.8,"metric":"percent"},{"benchmark":"livecodebench","model":"apertus-70b-instruct","score":8.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kolibri-1","score":92.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"glm-4.7-flash","score":89,"metric":"percent"},{"benchmark":"humaneval-plus","model":"nemotron-3-nano-30b-a3b","score":92.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-35b-a3b","score":92.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.6-35b-a3b","score":92.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3-next-80b-a3b-thinking","score":93.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-4-26b-a4b-it","score":95.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-oss-120b","score":94.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-small-4-thinking","score":92.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"glm-4.5-air","score":91.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"nemotron-3-super-120b-a12b","score":94.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.8-27b","score":94.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"apertus-70b-instruct","score":41.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kolibri-1","score":66.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.7-flash","score":51,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-nano-30b-a3b","score":38.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-35b-a3b","score":71.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-35b-a3b","score":73.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-26b-a4b-it","score":57.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mistral-small-4-thinking","score":60.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-4.5-air","score":11.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3-super-120b-a12b","score":60.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.8-27b","score":72.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"kolibri-1","score":68.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"glm-4.7-flash","score":49.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-nano-30b-a3b","score":42.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-35b-a3b","score":66.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.6-35b-a3b","score":69.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3-next-80b-a3b-thinking","score":46.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-26b-a4b-it","score":68.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"mistral-small-4-thinking","score":52.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3-super-120b-a12b","score":67,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.8-27b","score":81.3,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3-nano-30b-a3b-base","score":79,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-35b-a3b-base","score":84.7,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4.5-air-base","score":82.8,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3-super-120b-a12b-base","score":86.8,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-7b","score":67.1,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-70b","score":69.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3-nano-30b-a3b-base","score":94.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-35b-a3b-base","score":97,"metric":"percent"},{"benchmark":"arc-challenge","model":"glm-4.5-air-base","score":96.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3-super-120b-a12b-base","score":97.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-3-7b","score":88.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-70b","score":90.7,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-3-nano-30b-a3b-base","score":89.4,"metric":"percent"},{"benchmark":"piqa","model":"qwen3.5-35b-a3b-base","score":91.9,"metric":"percent"},{"benchmark":"piqa","model":"glm-4.5-air-base","score":89.8,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-3-super-120b-a12b-base","score":95.1,"metric":"percent"},{"benchmark":"piqa","model":"olmo-3-7b","score":77.7,"metric":"percent"},{"benchmark":"piqa","model":"apertus-70b","score":80.1,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3-nano-30b-a3b-base","score":85.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3.5-35b-a3b-base","score":85.3,"metric":"percent"},{"benchmark":"hellaswag","model":"glm-4.5-air-base","score":87.2,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3-super-120b-a12b-base","score":88.8,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-7b","score":76.1,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-70b","score":84.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-30b-a3b-base","score":55.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-35b-a3b-base","score":62.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-air-base","score":55.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b-base","score":68.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3-7b","score":38,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-70b","score":40.6,"metric":"percent"},{"benchmark":"triviaqa","model":"nemotron-3-nano-30b-a3b-base","score":79.5,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3.5-35b-a3b-base","score":74.6,"metric":"percent"},{"benchmark":"triviaqa","model":"glm-4.5-air-base","score":83.8,"metric":"percent"},{"benchmark":"triviaqa","model":"nemotron-3-super-120b-a12b-base","score":86.4,"metric":"percent"},{"benchmark":"triviaqa","model":"olmo-3-7b","score":59,"metric":"percent"},{"benchmark":"triviaqa","model":"apertus-70b","score":77.4,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3-nano-30b-a3b-base","score":86.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-35b-a3b-base","score":89.5,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4.5-air-base","score":82.8,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3-super-120b-a12b-base","score":87.5,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-7b","score":75.3,"metric":"percent"},{"benchmark":"gsm8k","model":"apertus-70b","score":62.3,"metric":"percent"},{"benchmark":"minerva-math","model":"nemotron-3-nano-30b-a3b-base","score":79.8,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen3.5-35b-a3b-base","score":57.6,"metric":"percent"},{"benchmark":"minerva-math","model":"glm-4.5-air-base","score":46.5,"metric":"percent"},{"benchmark":"minerva-math","model":"nemotron-3-super-120b-a12b-base","score":77.8,"metric":"percent"},{"benchmark":"minerva-math","model":"olmo-3-7b","score":40.1,"metric":"percent"},{"benchmark":"minerva-math","model":"apertus-70b","score":16.9,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-nano-30b-a3b-base","score":73.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3.5-35b-a3b-base","score":67.2,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4.5-air-base","score":96.3,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-super-120b-a12b-base","score":83.2,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3-7b","score":46.8,"metric":"percent"},{"benchmark":"humaneval","model":"apertus-70b","score":28.3,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-nano-30b-a3b-base","score":64.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3.5-35b-a3b-base","score":63.1,"metric":"percent"},{"benchmark":"mbpp","model":"glm-4.5-air-base","score":71.9,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-super-120b-a12b-base","score":75.4,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3-7b","score":48,"metric":"percent"},{"benchmark":"mbpp","model":"apertus-70b","score":36.8,"metric":"percent"},{"benchmark":"ai2d","model":"llm-jp-4-vl-9b","score":80.1,"metric":"percent"},{"benchmark":"ai2d","model":"internvl3.5-8b","score":83.4,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-9b","score":90.8,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-4-12b-it","score":79.9,"metric":"percent"},{"benchmark":"chartqa","model":"llm-jp-4-vl-9b","score":64.9,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-8b","score":75,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3.5-9b","score":86.4,"metric":"percent"},{"benchmark":"chartqa","model":"gemma-4-12b-it","score":72.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llm-jp-4-vl-9b","score":40.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3.5-8b","score":39.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-9b","score":69.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemma-4-12b-it","score":55.8,"metric":"percent"},{"benchmark":"chartqa-pro","model":"llm-jp-4-vl-9b","score":30.8,"metric":"percent"},{"benchmark":"chartqa-pro","model":"internvl3.5-8b","score":33.5,"metric":"percent"},{"benchmark":"chartqa-pro","model":"qwen3.5-9b","score":58.9,"metric":"percent"},{"benchmark":"chartqa-pro","model":"gemma-4-12b-it","score":53.9,"metric":"percent"},{"benchmark":"docvqa","model":"llm-jp-4-vl-9b","score":89.5,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-8b","score":89.4,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3.5-9b","score":94.2,"metric":"percent"},{"benchmark":"docvqa","model":"gemma-4-12b-it","score":88.5,"metric":"percent"},{"benchmark":"infovqa","model":"llm-jp-4-vl-9b","score":67.4,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-8b","score":68.9,"metric":"percent"},{"benchmark":"infovqa","model":"qwen3.5-9b","score":88.2,"metric":"percent"},{"benchmark":"infovqa","model":"gemma-4-12b-it","score":81.5,"metric":"percent"},{"benchmark":"textvqa","model":"llm-jp-4-vl-9b","score":88.4,"metric":"percent"},{"benchmark":"textvqa","model":"internvl3.5-8b","score":83.9,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.5-9b","score":87.7,"metric":"percent"},{"benchmark":"textvqa","model":"gemma-4-12b-it","score":73.8,"metric":"percent"},{"benchmark":"mmmu","model":"llm-jp-4-vl-9b","score":50.4,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-8b","score":65.3,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-9b","score":79.1,"metric":"percent"},{"benchmark":"mmmu","model":"gemma-4-12b-it","score":72.7,"metric":"percent"},{"benchmark":"mathvision","model":"llm-jp-4-vl-9b","score":13.2,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3.5-8b","score":30.6,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3.5-9b","score":71.4,"metric":"percent"},{"benchmark":"mathvision","model":"gemma-4-12b-it","score":51.4,"metric":"percent"},{"benchmark":"blink","model":"llm-jp-4-vl-9b","score":47.3,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-8b","score":54.7,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-9b","score":71.3,"metric":"percent"},{"benchmark":"blink","model":"gemma-4-12b-it","score":58.4,"metric":"percent"},{"benchmark":"countbenchqa","model":"llm-jp-4-vl-9b","score":79.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"internvl3.5-8b","score":78.4,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3.5-9b","score":93.5,"metric":"percent"},{"benchmark":"countbenchqa","model":"gemma-4-12b-it","score":72,"metric":"percent"},{"benchmark":"realworldqa","model":"llm-jp-4-vl-9b","score":70.5,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-8b","score":64.4,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-9b","score":79,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-12b-it","score":64.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llm-jp-4-vl-9b","score":40.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"internvl3.5-8b","score":48,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-9b","score":82.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-12b-it","score":73.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llm-jp-4-vl-9b","score":84.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"internvl3.5-8b","score":80.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-9b","score":92.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-4-12b-it","score":91.2,"metric":"percent"},{"benchmark":"simpleqa","model":"llm-jp-4-vl-9b","score":6.1,"metric":"percent"},{"benchmark":"simpleqa","model":"internvl3.5-8b","score":3.3,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3.5-9b","score":8.7,"metric":"percent"},{"benchmark":"simpleqa","model":"gemma-4-12b-it","score":4.3,"metric":"percent"},{"benchmark":"math500","model":"llm-jp-4-vl-9b","score":79.7,"metric":"percent"},{"benchmark":"math500","model":"internvl3.5-8b","score":62.7,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-9b","score":96.5,"metric":"percent"},{"benchmark":"math500","model":"gemma-4-12b-it","score":95.7,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-v1.5-8b-base","score":78.1,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-7b","score":74.1,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-8b-base","score":79.3,"metric":"percent"},{"benchmark":"piqa","model":"apertus-v1.5-8b-base","score":80.3,"metric":"percent"},{"benchmark":"piqa","model":"olmo-3-7b","score":78.7,"metric":"percent"},{"benchmark":"piqa","model":"llama-3.1-8b-base","score":81.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"apertus-v1.5-8b-base","score":62.3,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-3-7b","score":58.7,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-3.1-8b-base","score":70.4,"metric":"percent"},{"benchmark":"lambada","model":"apertus-v1.5-8b-base","score":68.8,"metric":"percent"},{"benchmark":"lambada","model":"olmo-3-7b","score":65.1,"metric":"percent"},{"benchmark":"lambada","model":"llama-3.1-8b-base","score":72.3,"metric":"percent"},{"benchmark":"xnli","model":"apertus-v1.5-8b-base","score":45.3,"metric":"percent"},{"benchmark":"xnli","model":"olmo-3-7b","score":39.6,"metric":"percent"},{"benchmark":"xnli","model":"llama-3.1-8b-base","score":45.6,"metric":"percent"},{"benchmark":"xcopa","model":"apertus-v1.5-8b-base","score":64.9,"metric":"percent"},{"benchmark":"xcopa","model":"olmo-3-7b","score":55.1,"metric":"percent"},{"benchmark":"xcopa","model":"llama-3.1-8b-base","score":62.5,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-70b","score":83,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-v1.5-70b-base","score":82.2,"metric":"percent"},{"benchmark":"hellaswag","model":"k2-v2","score":83.7,"metric":"percent"},{"benchmark":"hellaswag","model":"nemotron-3.5-lightning-30b-a3b-base","score":63.7,"metric":"percent"},{"benchmark":"piqa","model":"apertus-70b","score":83,"metric":"percent"},{"benchmark":"piqa","model":"apertus-v1.5-70b-base","score":82.3,"metric":"percent"},{"benchmark":"piqa","model":"k2-v2","score":83.9,"metric":"percent"},{"benchmark":"piqa","model":"nemotron-3.5-lightning-30b-a3b-base","score":83.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"apertus-70b","score":53.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"apertus-v1.5-70b-base","score":66.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"k2-v2","score":73.3,"metric":"percent"},{"benchmark":"commonsenseqa","model":"nemotron-3.5-lightning-30b-a3b-base","score":77.7,"metric":"percent"},{"benchmark":"lambada","model":"apertus-70b","score":72.9,"metric":"percent"},{"benchmark":"lambada","model":"apertus-v1.5-70b-base","score":72.9,"metric":"percent"},{"benchmark":"lambada","model":"k2-v2","score":76.1,"metric":"percent"},{"benchmark":"lambada","model":"nemotron-3.5-lightning-30b-a3b-base","score":72.8,"metric":"percent"},{"benchmark":"xnli","model":"apertus-70b","score":45.9,"metric":"percent"},{"benchmark":"xnli","model":"apertus-v1.5-70b-base","score":46.3,"metric":"percent"},{"benchmark":"xnli","model":"k2-v2","score":44.1,"metric":"percent"},{"benchmark":"xnli","model":"nemotron-3.5-lightning-30b-a3b-base","score":43.4,"metric":"percent"},{"benchmark":"xcopa","model":"apertus-70b","score":69.9,"metric":"percent"},{"benchmark":"xcopa","model":"apertus-v1.5-70b-base","score":68,"metric":"percent"},{"benchmark":"xcopa","model":"k2-v2","score":63.8,"metric":"percent"},{"benchmark":"xcopa","model":"nemotron-3.5-lightning-30b-a3b-base","score":62.1,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-v1.5-8b","score":70.5,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-instruct-7b","score":67.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-9b","score":83.7,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-8b-instruct","score":72.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-v1.5-8b","score":48.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3-instruct-7b","score":52.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-9b","score":76,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b-instruct","score":48.4,"metric":"percent"},{"benchmark":"agieval","model":"apertus-v1.5-8b","score":45.4,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-instruct-7b","score":37.1,"metric":"percent"},{"benchmark":"agieval","model":"qwen3.5-9b","score":39,"metric":"percent"},{"benchmark":"agieval","model":"llama-3.1-8b-instruct","score":38,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-v1.5-8b","score":85,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-3-instruct-7b","score":75.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-9b","score":88.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-8b-instruct","score":81.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"apertus-v1.5-8b","score":56.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"olmo-3-instruct-7b","score":57.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen3.5-9b","score":59.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.1-8b-instruct","score":55,"metric":"percent"},{"benchmark":"ifeval","model":"apertus-v1.5-8b","score":87.1,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-instruct-7b","score":82.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-9b","score":84.3,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-8b-instruct","score":75,"metric":"percent"},{"benchmark":"multi-if","model":"apertus-v1.5-8b","score":83.7,"metric":"percent"},{"benchmark":"multi-if","model":"olmo-3-instruct-7b","score":70.5,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-9b","score":80,"metric":"percent"},{"benchmark":"multi-if","model":"llama-3.1-8b-instruct","score":66.5,"metric":"percent"},{"benchmark":"ifbench","model":"apertus-v1.5-8b","score":35.3,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-instruct-7b","score":28.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-9b","score":34.3,"metric":"percent"},{"benchmark":"ifbench","model":"llama-3.1-8b-instruct","score":25.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"apertus-v1.5-8b","score":47.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3-instruct-7b","score":57.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3.5-9b","score":71.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-8b-instruct","score":36.9,"metric":"percent"},{"benchmark":"gsm8k","model":"apertus-v1.5-8b","score":78.5,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-instruct-7b","score":83.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-9b","score":94.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b-instruct","score":84,"metric":"percent"},{"benchmark":"math","model":"apertus-v1.5-8b","score":41.2,"metric":"percent"},{"benchmark":"math","model":"olmo-3-instruct-7b","score":59.4,"metric":"percent"},{"benchmark":"math","model":"qwen3.5-9b","score":71.4,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-8b-instruct","score":36.6,"metric":"percent"},{"benchmark":"math500","model":"apertus-v1.5-8b","score":51.2,"metric":"percent"},{"benchmark":"math500","model":"olmo-3-instruct-7b","score":77.2,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-9b","score":87.2,"metric":"percent"},{"benchmark":"math500","model":"llama-3.1-8b-instruct","score":47.6,"metric":"percent"},{"benchmark":"humaneval","model":"apertus-v1.5-8b","score":68.8,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3-instruct-7b","score":81.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3.5-9b","score":88.3,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-8b-instruct","score":65.1,"metric":"percent"},{"benchmark":"mbpp","model":"apertus-v1.5-8b","score":51.8,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3-instruct-7b","score":57.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3.5-9b","score":70.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-8b-instruct","score":60.2,"metric":"percent"},{"benchmark":"bbh","model":"apertus-v1.5-8b","score":68.5,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-instruct-7b","score":58.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-9b","score":84.1,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-8b-instruct","score":72,"metric":"percent"},{"benchmark":"gpqa","model":"apertus-v1.5-8b","score":27.2,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-instruct-7b","score":31.5,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-9b","score":57.6,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.1-8b-instruct","score":26.6,"metric":"percent"},{"benchmark":"drop","model":"apertus-v1.5-8b","score":54.2,"metric":"percent"},{"benchmark":"drop","model":"olmo-3-instruct-7b","score":55.5,"metric":"percent"},{"benchmark":"drop","model":"qwen3.5-9b","score":67.9,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-8b-instruct","score":60.4,"metric":"percent"},{"benchmark":"global-mmlu","model":"apertus-v1.5-8b","score":59.4,"metric":"percent"},{"benchmark":"global-mmlu","model":"olmo-3-instruct-7b","score":46.4,"metric":"percent"},{"benchmark":"global-mmlu","model":"qwen3.5-9b","score":74.6,"metric":"percent"},{"benchmark":"global-mmlu","model":"llama-3.1-8b-instruct","score":56.9,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-70b-instruct","score":70.1,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-v1.5-70b","score":76.5,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3.1-instruct-32b","score":80.1,"metric":"percent"},{"benchmark":"mmlu","model":"eurollm-22b","score":69,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.3-70b-instruct","score":87.6,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-31b-it","score":90.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-27b","score":89.5,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-3.5-lightning-30b-a3b","score":85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-70b-instruct","score":44.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-v1.5-70b","score":56.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3.1-instruct-32b","score":66,"metric":"percent"},{"benchmark":"mmlu-pro","model":"eurollm-22b","score":49.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.3-70b-instruct","score":71.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-31b-it","score":84.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-27b","score":81.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3.5-lightning-30b-a3b","score":56.4,"metric":"percent"},{"benchmark":"agieval","model":"apertus-70b-instruct","score":40.4,"metric":"percent"},{"benchmark":"agieval","model":"apertus-v1.5-70b","score":50.6,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3.1-instruct-32b","score":50.6,"metric":"percent"},{"benchmark":"agieval","model":"eurollm-22b","score":46,"metric":"percent"},{"benchmark":"agieval","model":"llama-3.3-70b-instruct","score":54.2,"metric":"percent"},{"benchmark":"agieval","model":"gemma-4-31b-it","score":50.1,"metric":"percent"},{"benchmark":"agieval","model":"qwen3.5-27b","score":38,"metric":"percent"},{"benchmark":"agieval","model":"nemotron-3.5-lightning-30b-a3b","score":45.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-70b-instruct","score":79.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-v1.5-70b","score":87.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-3.1-instruct-32b","score":89,"metric":"percent"},{"benchmark":"arc-challenge","model":"eurollm-22b","score":80,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.3-70b-instruct","score":93.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-4-31b-it","score":96.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-27b","score":93.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3.5-lightning-30b-a3b","score":91.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"apertus-70b-instruct","score":61.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"apertus-v1.5-70b","score":67,"metric":"percent"},{"benchmark":"truthfulqa","model":"olmo-3.1-instruct-32b","score":68.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"eurollm-22b","score":56.3,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3.3-70b-instruct","score":66.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-4-31b-it","score":64.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen3.5-27b","score":64.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"nemotron-3.5-lightning-30b-a3b","score":58.3,"metric":"percent"},{"benchmark":"ifeval","model":"apertus-70b-instruct","score":65.1,"metric":"percent"},{"benchmark":"ifeval","model":"apertus-v1.5-70b","score":87.8,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3.1-instruct-32b","score":86.7,"metric":"percent"},{"benchmark":"ifeval","model":"eurollm-22b","score":71.2,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.3-70b-instruct","score":90.2,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-31b-it","score":90.9,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-27b","score":88,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-3.5-lightning-30b-a3b","score":75.6,"metric":"percent"},{"benchmark":"multi-if","model":"apertus-70b-instruct","score":65.6,"metric":"percent"},{"benchmark":"multi-if","model":"apertus-v1.5-70b","score":83.7,"metric":"percent"},{"benchmark":"multi-if","model":"olmo-3.1-instruct-32b","score":81.9,"metric":"percent"},{"benchmark":"multi-if","model":"eurollm-22b","score":67.8,"metric":"percent"},{"benchmark":"multi-if","model":"llama-3.3-70b-instruct","score":87.8,"metric":"percent"},{"benchmark":"multi-if","model":"gemma-4-31b-it","score":89.7,"metric":"percent"},{"benchmark":"multi-if","model":"qwen3.5-27b","score":86.6,"metric":"percent"},{"benchmark":"multi-if","model":"nemotron-3.5-lightning-30b-a3b","score":70.3,"metric":"percent"},{"benchmark":"ifbench","model":"apertus-70b-instruct","score":20.7,"metric":"percent"},{"benchmark":"ifbench","model":"apertus-v1.5-70b","score":25.7,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3.1-instruct-32b","score":38,"metric":"percent"},{"benchmark":"ifbench","model":"eurollm-22b","score":19,"metric":"percent"},{"benchmark":"ifbench","model":"llama-3.3-70b-instruct","score":41.3,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-31b-it","score":50.3,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-27b","score":45.3,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3.5-lightning-30b-a3b","score":31,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"apertus-70b-instruct","score":26,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"apertus-v1.5-70b","score":67.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-3.1-instruct-32b","score":57.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"eurollm-22b","score":70.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.3-70b-instruct","score":49.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"gemma-4-31b-it","score":70.1,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen3.5-27b","score":78.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"nemotron-3.5-lightning-30b-a3b","score":62.6,"metric":"percent"},{"benchmark":"gsm8k","model":"apertus-70b-instruct","score":75.1,"metric":"percent"},{"benchmark":"gsm8k","model":"apertus-v1.5-70b","score":85,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3.1-instruct-32b","score":92.9,"metric":"percent"},{"benchmark":"gsm8k","model":"eurollm-22b","score":71.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.3-70b-instruct","score":94.9,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-4-31b-it","score":96.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-27b","score":96.3,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3.5-lightning-30b-a3b","score":89.9,"metric":"percent"},{"benchmark":"math","model":"apertus-70b-instruct","score":27.8,"metric":"percent"},{"benchmark":"math","model":"apertus-v1.5-70b","score":52.9,"metric":"percent"},{"benchmark":"math","model":"olmo-3.1-instruct-32b","score":65.3,"metric":"percent"},{"benchmark":"math","model":"eurollm-22b","score":38,"metric":"percent"},{"benchmark":"math","model":"llama-3.3-70b-instruct","score":59.9,"metric":"percent"},{"benchmark":"math","model":"gemma-4-31b-it","score":78.7,"metric":"percent"},{"benchmark":"math","model":"qwen3.5-27b","score":74.9,"metric":"percent"},{"benchmark":"math","model":"nemotron-3.5-lightning-30b-a3b","score":51.2,"metric":"percent"},{"benchmark":"math500","model":"apertus-70b-instruct","score":34.4,"metric":"percent"},{"benchmark":"math500","model":"apertus-v1.5-70b","score":64,"metric":"percent"},{"benchmark":"math500","model":"olmo-3.1-instruct-32b","score":79.6,"metric":"percent"},{"benchmark":"math500","model":"eurollm-22b","score":43.2,"metric":"percent"},{"benchmark":"math500","model":"llama-3.3-70b-instruct","score":75,"metric":"percent"},{"benchmark":"math500","model":"gemma-4-31b-it","score":96.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-27b","score":89.6,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3.5-lightning-30b-a3b","score":50.4,"metric":"percent"},{"benchmark":"humaneval","model":"apertus-70b-instruct","score":46.6,"metric":"percent"},{"benchmark":"humaneval","model":"apertus-v1.5-70b","score":70.3,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3.1-instruct-32b","score":86.9,"metric":"percent"},{"benchmark":"humaneval","model":"eurollm-22b","score":51.6,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.3-70b-instruct","score":85,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-4-31b-it","score":92,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3.5-27b","score":96.2,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3.5-lightning-30b-a3b","score":55.5,"metric":"percent"},{"benchmark":"mbpp","model":"apertus-70b-instruct","score":44.8,"metric":"percent"},{"benchmark":"mbpp","model":"apertus-v1.5-70b","score":61.4,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3.1-instruct-32b","score":68.8,"metric":"percent"},{"benchmark":"mbpp","model":"eurollm-22b","score":47.4,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.3-70b-instruct","score":75.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-4-31b-it","score":69.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3.5-27b","score":80,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3.5-lightning-30b-a3b","score":74.6,"metric":"percent"},{"benchmark":"bbh","model":"apertus-70b-instruct","score":64.1,"metric":"percent"},{"benchmark":"bbh","model":"apertus-v1.5-70b","score":66,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3.1-instruct-32b","score":63.2,"metric":"percent"},{"benchmark":"bbh","model":"eurollm-22b","score":60,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.3-70b-instruct","score":87.5,"metric":"percent"},{"benchmark":"bbh","model":"gemma-4-31b-it","score":92,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-27b","score":93.3,"metric":"percent"},{"benchmark":"bbh","model":"nemotron-3.5-lightning-30b-a3b","score":83.3,"metric":"percent"},{"benchmark":"gpqa","model":"apertus-70b-instruct","score":28.1,"metric":"percent"},{"benchmark":"gpqa","model":"apertus-v1.5-70b","score":32.1,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3.1-instruct-32b","score":35.3,"metric":"percent"},{"benchmark":"gpqa","model":"eurollm-22b","score":32.1,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.3-70b-instruct","score":58.5,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-4-31b-it","score":72.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-27b","score":61.8,"metric":"percent"},{"benchmark":"gpqa","model":"nemotron-3.5-lightning-30b-a3b","score":45.1,"metric":"percent"},{"benchmark":"drop","model":"apertus-70b-instruct","score":44.3,"metric":"percent"},{"benchmark":"drop","model":"apertus-v1.5-70b","score":60.7,"metric":"percent"},{"benchmark":"drop","model":"olmo-3.1-instruct-32b","score":71.2,"metric":"percent"},{"benchmark":"drop","model":"eurollm-22b","score":52.1,"metric":"percent"},{"benchmark":"drop","model":"llama-3.3-70b-instruct","score":70.5,"metric":"percent"},{"benchmark":"drop","model":"gemma-4-31b-it","score":72.6,"metric":"percent"},{"benchmark":"drop","model":"qwen3.5-27b","score":82.4,"metric":"percent"},{"benchmark":"drop","model":"nemotron-3.5-lightning-30b-a3b","score":70.4,"metric":"percent"},{"benchmark":"global-mmlu","model":"apertus-70b-instruct","score":62.9,"metric":"percent"},{"benchmark":"global-mmlu","model":"apertus-v1.5-70b","score":66.5,"metric":"percent"},{"benchmark":"global-mmlu","model":"olmo-3.1-instruct-32b","score":65,"metric":"percent"},{"benchmark":"global-mmlu","model":"eurollm-22b","score":58.2,"metric":"percent"},{"benchmark":"global-mmlu","model":"llama-3.3-70b-instruct","score":77.7,"metric":"percent"},{"benchmark":"global-mmlu","model":"gemma-4-31b-it","score":84.7,"metric":"percent"},{"benchmark":"global-mmlu","model":"qwen3.5-27b","score":83,"metric":"percent"},{"benchmark":"global-mmlu","model":"nemotron-3.5-lightning-30b-a3b","score":69.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-v1.1-0.5b","score":44.96,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-v1.1-0.5b","score":40.42,"metric":"percent"},{"benchmark":"winogrande","model":"apertus-v1.1-0.5b","score":57.06,"metric":"percent"},{"benchmark":"xnli","model":"apertus-v1.1-0.5b","score":41.51,"metric":"percent"},{"benchmark":"xcopa","model":"apertus-v1.1-0.5b","score":55.49,"metric":"percent"},{"benchmark":"piqa","model":"apertus-v1.1-0.5b","score":71.27,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-v1.1-1.5b","score":52.66,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-v1.1-1.5b","score":48.31,"metric":"percent"},{"benchmark":"winogrande","model":"apertus-v1.1-1.5b","score":61.72,"metric":"percent"},{"benchmark":"xnli","model":"apertus-v1.1-1.5b","score":42.94,"metric":"percent"},{"benchmark":"xcopa","model":"apertus-v1.1-1.5b","score":59.76,"metric":"percent"},{"benchmark":"piqa","model":"apertus-v1.1-1.5b","score":74.54,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-v1.1-4b","score":61.15,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-v1.1-4b","score":53.51,"metric":"percent"},{"benchmark":"winogrande","model":"apertus-v1.1-4b","score":67.48,"metric":"percent"},{"benchmark":"xnli","model":"apertus-v1.1-4b","score":45.03,"metric":"percent"},{"benchmark":"xcopa","model":"apertus-v1.1-4b","score":63.82,"metric":"percent"},{"benchmark":"piqa","model":"apertus-v1.1-4b","score":78.18,"metric":"percent"},{"benchmark":"arc-challenge","model":"smollm2-1.7b-base","score":60.23,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm2-1.7b-base","score":53.38,"metric":"percent"},{"benchmark":"winogrande","model":"smollm2-1.7b-base","score":66.22,"metric":"percent"},{"benchmark":"xnli","model":"smollm2-1.7b-base","score":37.57,"metric":"percent"},{"benchmark":"xcopa","model":"smollm2-1.7b-base","score":53.51,"metric":"percent"},{"benchmark":"piqa","model":"smollm2-1.7b-base","score":77.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-0.6b-base","score":48.35,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-0.6b-base","score":41.01,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3-0.6b-base","score":59.2,"metric":"percent"},{"benchmark":"xnli","model":"qwen3-0.6b-base","score":39.55,"metric":"percent"},{"benchmark":"xcopa","model":"qwen3-0.6b-base","score":54.96,"metric":"percent"},{"benchmark":"piqa","model":"qwen3-0.6b-base","score":70.29,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-4b-base","score":64.99,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-4b-base","score":54.56,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3-4b-base","score":70.48,"metric":"percent"},{"benchmark":"xnli","model":"qwen3-4b-base","score":43,"metric":"percent"},{"benchmark":"xcopa","model":"qwen3-4b-base","score":61.82,"metric":"percent"},{"benchmark":"piqa","model":"qwen3-4b-base","score":77.97,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"gpt-oss-20b-medium","score":7.33,"metric":"score"},{"benchmark":"mt-bench","model":"gpt-oss-20b-medium","score":7.85,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"llm-jp-4-8b-thinking","score":7.54,"metric":"score"},{"benchmark":"mt-bench","model":"llm-jp-4-8b-thinking","score":7.79,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"llm-jp-4-32b-a3b-thinking","score":7.82,"metric":"score"},{"benchmark":"mt-bench","model":"llm-jp-4-32b-a3b-thinking","score":7.86,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"llm-jp-4-33b-thinking","score":8,"metric":"score"},{"benchmark":"mt-bench","model":"llm-jp-4-33b-thinking","score":8.24,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"llm-jp-4.1-8b-thinking","score":7.58,"metric":"score"},{"benchmark":"mt-bench","model":"llm-jp-4.1-8b-thinking","score":7.67,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"llm-jp-4.1-32b-a3b-thinking","score":7.69,"metric":"score"},{"benchmark":"mt-bench","model":"llm-jp-4.1-32b-a3b-thinking","score":7.85,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"llm-jp-4.1-33b-thinking","score":7.76,"metric":"score"},{"benchmark":"mt-bench","model":"llm-jp-4.1-33b-thinking","score":7.98,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"llm-jp-3.1-8x13b-32k-instruct4","score":7.48,"metric":"score"},{"benchmark":"mt-bench","model":"llm-jp-3.1-8x13b-32k-instruct4","score":7.31,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-v1.5-8b-thinking","score":74.5,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-v1.5-70b-thinking","score":77.1,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-7b","score":74,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3.1-think-32b","score":82.7,"metric":"percent"},{"benchmark":"mmlu","model":"k2-think-v2","score":88,"metric":"percent"},{"benchmark":"gpqa","model":"apertus-v1.5-8b-thinking","score":32.1,"metric":"percent"},{"benchmark":"gpqa","model":"apertus-v1.5-70b-thinking","score":30.1,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-7b","score":27.2,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3.1-think-32b","score":39.7,"metric":"percent"},{"benchmark":"gpqa","model":"k2-think-v2","score":59.6,"metric":"percent"},{"benchmark":"ifbench","model":"apertus-v1.5-8b-thinking","score":44.3,"metric":"percent"},{"benchmark":"ifbench","model":"apertus-v1.5-70b-thinking","score":32.7,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-think-7b","score":20,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3.1-think-32b","score":23,"metric":"percent"},{"benchmark":"ifbench","model":"k2-think-v2","score":36.7,"metric":"percent"},{"benchmark":"gsm8k","model":"apertus-v1.5-8b-thinking","score":85.7,"metric":"percent"},{"benchmark":"gsm8k","model":"apertus-v1.5-70b-thinking","score":86.4,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-think-7b","score":91.9,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3.1-think-32b","score":96.7,"metric":"percent"},{"benchmark":"gsm8k","model":"k2-think-v2","score":89.8,"metric":"percent"},{"benchmark":"math","model":"apertus-v1.5-8b-thinking","score":57.3,"metric":"percent"},{"benchmark":"math","model":"apertus-v1.5-70b-thinking","score":59,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-7b","score":74,"metric":"percent"},{"benchmark":"math","model":"olmo-3.1-think-32b","score":74.9,"metric":"percent"},{"benchmark":"math","model":"k2-think-v2","score":75.2,"metric":"percent"},{"benchmark":"math500","model":"apertus-v1.5-8b-thinking","score":71.4,"metric":"percent"},{"benchmark":"math500","model":"apertus-v1.5-70b-thinking","score":73.6,"metric":"percent"},{"benchmark":"math500","model":"olmo-3-think-7b","score":86.2,"metric":"percent"},{"benchmark":"math500","model":"olmo-3.1-think-32b","score":88.2,"metric":"percent"},{"benchmark":"math500","model":"k2-think-v2","score":90.2,"metric":"percent"},{"benchmark":"aime-2024","model":"apertus-v1.5-8b-thinking","score":22.9,"metric":"percent"},{"benchmark":"aime-2024","model":"apertus-v1.5-70b-thinking","score":27.9,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-7b","score":74.2,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3.1-think-32b","score":80,"metric":"percent"},{"benchmark":"aime-2024","model":"k2-think-v2","score":84.6,"metric":"percent"},{"benchmark":"aime-2025","model":"apertus-v1.5-8b-thinking","score":23.8,"metric":"percent"},{"benchmark":"aime-2025","model":"apertus-v1.5-70b-thinking","score":21.7,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-7b","score":69.1,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3.1-think-32b","score":78.8,"metric":"percent"},{"benchmark":"aime-2025","model":"k2-think-v2","score":74.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"solar-open-2-250b","score":43.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"solar-pro-4","score":57,"metric":"percent"},{"benchmark":"browsecomp","model":"solar-open-2-250b","score":37.3,"metric":"percent"},{"benchmark":"browsecomp","model":"solar-pro-4","score":49.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"solar-pro-4","score":61.4,"metric":"percent"},{"benchmark":"apex-agents","model":"solar-pro-4","score":18.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"solar-open-2-250b","score":18.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"solar-pro-4","score":23,"metric":"percent"},{"benchmark":"aa-lcr","model":"solar-open-2-250b","score":62.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"solar-pro-4","score":71,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"solar-open-2-250b","score":85.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"solar-pro-4","score":89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"solar-pro-4","score":86.3,"metric":"percent"},{"benchmark":"livecodebench","model":"solar-open-2-250b","score":87,"metric":"percent"},{"benchmark":"livecodebench","model":"solar-pro-4","score":87.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"solar-pro-4","score":95.3,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"solar-pro-4","score":79.2,"metric":"percent"},{"benchmark":"ifbench","model":"solar-pro-3","score":55.78,"metric":"percent"},{"benchmark":"arena-hard-v2","model":"solar-pro-3","score":62.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"solar-pro-3","score":10.1,"metric":"percent"},{"benchmark":"aa-lcr","model":"solar-mini-4","score":83.3,"metric":"percent"},{"benchmark":"scicode","model":"solar-mini-4","score":47.6,"metric":"percent"},{"benchmark":"hle-text-only","model":"solar-mini-4","score":25.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"solar-mini-4","score":47.2,"metric":"percent"},{"benchmark":"ifbench","model":"plamo-3.0-prime-thinking","score":70.7,"metric":"percent"},{"benchmark":"ifbench","model":"plamo-3.0-prime","score":41.7,"metric":"percent"},{"benchmark":"ifbench","model":"plamo-3.0-prime-beta","score":66,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-27b","score":65.3,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-120b","score":63.3,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.4-mini","score":62.9,"metric":"percent"},{"benchmark":"ifbench","model":"claude-4.5-haiku","score":47.3,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"plamo-3.0-prime-thinking","score":8.27,"metric":"score"},{"benchmark":"mt-bench-ja","model":"plamo-3.0-prime","score":7.18,"metric":"score"},{"benchmark":"mt-bench-ja","model":"plamo-3.0-prime-beta","score":8.38,"metric":"score"},{"benchmark":"mt-bench-ja","model":"qwen3.6-27b","score":8.35,"metric":"score"},{"benchmark":"mt-bench-ja","model":"gpt-oss-120b","score":8.46,"metric":"score"},{"benchmark":"mt-bench-ja","model":"gpt-5.4-mini","score":8.09,"metric":"score"},{"benchmark":"mt-bench-ja","model":"claude-4.5-haiku","score":8.13,"metric":"score"},{"benchmark":"mt-bench","model":"plamo-3.0-prime-thinking","score":8.56,"metric":"percent"},{"benchmark":"mt-bench","model":"plamo-3.0-prime","score":7.46,"metric":"percent"},{"benchmark":"mt-bench","model":"plamo-3.0-prime-beta","score":8.6,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen3.6-27b","score":8.73,"metric":"percent"},{"benchmark":"mt-bench","model":"gpt-oss-120b","score":8.71,"metric":"percent"},{"benchmark":"mt-bench","model":"gpt-5.4-mini","score":8.46,"metric":"percent"},{"benchmark":"mt-bench","model":"claude-4.5-haiku","score":8.62,"metric":"percent"},{"benchmark":"bfcl-v4","model":"plamo-3.0-prime-thinking","score":73.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"plamo-3.0-prime","score":58.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"plamo-3.0-prime-beta","score":71.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.6-27b","score":80.2,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-oss-120b","score":74.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.4-mini","score":72.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"claude-4.5-haiku","score":78.6,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"plamo-3.0-prime-thinking","score":9.9,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"plamo-3.0-prime","score":1.7,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"plamo-3.0-prime-beta","score":8.3,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"qwen3.6-27b","score":11.3,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gpt-oss-120b","score":14.1,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gpt-5.4-mini","score":7.7,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"claude-4.5-haiku","score":13.7,"metric":"percent"},{"benchmark":"longbench","model":"plamo-3.0-prime-thinking","score":56.9,"metric":"percent"},{"benchmark":"longbench","model":"plamo-3.0-prime","score":52.3,"metric":"percent"},{"benchmark":"longbench","model":"plamo-3.0-prime-beta","score":53.7,"metric":"percent"},{"benchmark":"longbench","model":"qwen3.6-27b","score":60.9,"metric":"percent"},{"benchmark":"longbench","model":"gpt-oss-120b","score":56,"metric":"percent"},{"benchmark":"longbench","model":"gpt-5.4-mini","score":60,"metric":"percent"},{"benchmark":"longbench","model":"claude-4.5-haiku","score":54.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"plamo-3.0-prime-thinking","score":36.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"plamo-3.0-prime","score":30,"metric":"percent"},{"benchmark":"longbench-v2","model":"plamo-3.0-prime-beta","score":34,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.6-27b","score":52.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-oss-120b","score":48.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-5.4-mini","score":55.9,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-4.5-haiku","score":50.1,"metric":"percent"},{"benchmark":"aime-2024","model":"plamo-3.0-prime-thinking","score":64.6,"metric":"percent"},{"benchmark":"aime-2024","model":"plamo-3.0-prime","score":13.2,"metric":"percent"},{"benchmark":"aime-2024","model":"plamo-3.0-prime-beta","score":53,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3.6-27b","score":92.4,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-oss-120b","score":75.9,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-5.4-mini","score":80,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-4.5-haiku","score":80,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"plamo-3.0-prime-thinking","score":59.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"plamo-3.0-prime","score":47.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"plamo-3.0-prime-beta","score":50.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-27b","score":87.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b","score":72.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4-mini","score":82.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-4.5-haiku","score":74.2,"metric":"percent"},{"benchmark":"livecodebench","model":"plamo-3.0-prime-thinking","score":56.8,"metric":"percent"},{"benchmark":"livecodebench","model":"plamo-3.0-prime","score":16.7,"metric":"percent"},{"benchmark":"livecodebench","model":"plamo-3.0-prime-beta","score":48.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.6-27b","score":55.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b","score":70.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.4-mini","score":79,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-4.5-haiku","score":57.1,"metric":"percent"},{"benchmark":"ifeval","model":"jais-2-70b-chat","score":70.78,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-72b-instruct","score":83.53,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.3-70b-instruct","score":88.2,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"gpt-4o-2024-08-06","score":7.29,"metric":"score"},{"benchmark":"mt-bench","model":"gpt-4o-2024-08-06","score":7.69,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"gpt-5.4","score":8.87,"metric":"score"},{"benchmark":"mt-bench","model":"gpt-5.4","score":8.89,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-12b-it","score":63.1,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-9b","score":65.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"granite-4.2-8b","score":66.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-12b-it","score":30.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"granite-4.2-8b","score":47.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"granite-4.2-8b","score":9.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-9b","score":14.9,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemma-4-12b-it","score":15.7,"metric":"percent"},{"benchmark":"scicode","model":"granite-4.2-8b","score":30.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"granite-4.2-8b","score":43.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"granite-4.2-8b","score":18.4,"metric":"percent"},{"benchmark":"tau3-banking","model":"granite-4.2-8b","score":7.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"muse-glimmer-30b","score":24,"metric":"percent"},{"benchmark":"hle","model":"deepseek-v4.1-flash-1017","score":42.6,"metric":"avg@3"},{"benchmark":"hle-text-only","model":"deepseek-v4.1-flash-1017","score":44,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"deepseek-v4.1-flash-1017","score":42.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4.1-flash-1017","score":77,"metric":"percent"},{"benchmark":"programbench","model":"deepseek-v4.1-flash-1017","score":29.1,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4.1-flash-1017","score":68.2,"metric":"percent"},{"benchmark":"nl2repo","model":"deepseek-v4.1-flash","score":65.4,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4.1-flash-1017","score":60.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4.1-flash-1017","score":35.4,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"deepseek-v4.1-flash-1017","score":72.1,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"deepseek-v4.1-flash","score":64.6,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"kimi-k3","score":47.8,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"glm-5.3","score":56.6,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-5.6-sol","score":54.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-opus-5","score":65.8,"metric":"percent"},{"benchmark":"chartography-with-tools","model":"deepseek-v4.1-flash-1017","score":83,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"deepseek-v4.1-flash-1017","score":92.5,"metric":"percent"},{"benchmark":"zerobench-with-tools","model":"deepseek-v4.1-flash-1017","score":51,"metric":"percent"},{"benchmark":"livecodebench","model":"mellum2.1-12b-a2.5b-thinking","score":82,"metric":"percent"},{"benchmark":"livecodebench","model":"mellum2-12b-a2.5b-thinking","score":69.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e4b-it","score":69.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-9b","score":75.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mellum2.1-12b-a2.5b-thinking","score":91.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mellum2-12b-a2.5b-thinking","score":90.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-4-e4b-it","score":89.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-9b","score":89.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mellum2.1-12b-a2.5b-thinking","score":79.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mellum2-12b-a2.5b-thinking","score":75.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-4-e4b-it","score":70.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.5-9b","score":69.8,"metric":"percent"},{"benchmark":"gsm-plus","model":"mellum2.1-12b-a2.5b-thinking","score":88.3,"metric":"percent"},{"benchmark":"gsm-plus","model":"mellum2-12b-a2.5b-thinking","score":87.1,"metric":"percent"},{"benchmark":"gsm-plus","model":"gemma-4-e4b-it","score":87.4,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3.5-9b","score":91.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mellum2.1-12b-a2.5b-thinking","score":47,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mellum2-12b-a2.5b-thinking","score":2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-e4b-it","score":23,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-9b","score":50,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mellum2.1-12b-a2.5b-thinking","score":17.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"mellum2-12b-a2.5b-thinking","score":0.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-e4b-it","score":3.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-9b","score":21.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"mellum2.1-12b-a2.5b-thinking","score":28,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"mellum2-12b-a2.5b-thinking","score":0,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-9b","score":38,"metric":"percent"},{"benchmark":"bfcl-v4","model":"mellum2.1-12b-a2.5b-thinking","score":62.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"mellum2-12b-a2.5b-thinking","score":49.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":52.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-9b","score":58.5,"metric":"percent"},{"benchmark":"workbench","model":"mellum2.1-12b-a2.5b-thinking","score":44.6,"metric":"percent"},{"benchmark":"workbench","model":"mellum2-12b-a2.5b-thinking","score":45.1,"metric":"percent"},{"benchmark":"workbench","model":"gemma-4-e4b-it","score":46.1,"metric":"percent"},{"benchmark":"workbench","model":"qwen3.5-9b","score":39.7,"metric":"percent"},{"benchmark":"toolhop","model":"mellum2.1-12b-a2.5b-thinking","score":49.1,"metric":"percent"},{"benchmark":"toolhop","model":"mellum2-12b-a2.5b-thinking","score":46.7,"metric":"percent"},{"benchmark":"toolhop","model":"gemma-4-e4b-it","score":39.9,"metric":"percent"},{"benchmark":"toolhop","model":"qwen3.5-9b","score":52,"metric":"percent"},{"benchmark":"ifeval","model":"mellum2.1-12b-a2.5b-thinking","score":90.6,"metric":"percent"},{"benchmark":"ifeval","model":"mellum2-12b-a2.5b-thinking","score":79.5,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e4b-it","score":90.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-9b","score":92.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mellum2.1-12b-a2.5b-thinking","score":64.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mellum2-12b-a2.5b-thinking","score":51,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e4b-it","score":53.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-9b","score":77.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mellum2.1-12b-a2.5b-thinking","score":87.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mellum2-12b-a2.5b-thinking","score":86,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-4-e4b-it","score":84.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-9b","score":89.5,"metric":"percent"},{"benchmark":"mixeval-hard","model":"mellum2.1-12b-a2.5b-thinking","score":46.4,"metric":"percent"},{"benchmark":"mixeval-hard","model":"mellum2-12b-a2.5b-thinking","score":41.6,"metric":"percent"},{"benchmark":"mixeval-hard","model":"gemma-4-e4b-it","score":41.4,"metric":"percent"},{"benchmark":"mixeval-hard","model":"qwen3.5-9b","score":50.3,"metric":"percent"},{"benchmark":"xstest","model":"mellum2.1-12b-a2.5b-thinking","score":88.8,"metric":"percent"},{"benchmark":"xstest","model":"mellum2-12b-a2.5b-thinking","score":91.2,"metric":"percent"},{"benchmark":"xstest","model":"gemma-4-e4b-it","score":95.2,"metric":"percent"},{"benchmark":"xstest","model":"qwen3.5-9b","score":95.6,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-labs-dory1.0-4b-1loop","score":27.3,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-labs-dory1.0-4b","score":34.94,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-labs-dory1.0-4b-4loop","score":35.11,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-4b","score":25.82,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-9b","score":28.21,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-26b-a4b-it","score":40.32,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-35b-a3b","score":37.24,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-labs-dory1.0-4b-1loop","score":50.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-labs-dory1.0-4b","score":59.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-labs-dory1.0-4b-4loop","score":61.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-4b","score":54.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-9b","score":61,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-labs-dory1.0-4b-1loop","score":12.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-labs-dory1.0-4b","score":18.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-labs-dory1.0-4b-4loop","score":22.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-4b","score":15,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-9b","score":24,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-26b-a4b-it","score":35,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":43,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-labs-dory1.0-4b-1loop","score":11.6,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-labs-dory1.0-4b","score":12.89,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-labs-dory1.0-4b-4loop","score":14.69,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-4b","score":5.03,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.5-9b","score":7.22,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemma-4-26b-a4b-it","score":13.66,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.6-35b-a3b","score":9.54,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-labs-dory1.0-4b-1loop","score":815,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-labs-dory1.0-4b","score":946,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nemotron-labs-dory1.0-4b-4loop","score":967,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.5-4b","score":424,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.5-9b","score":546,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gemma-4-26b-a4b-it","score":751.6,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.6-35b-a3b","score":987,"metric":"elo"},{"benchmark":"gpqa-diamond","model":"nemotron-labs-dory1.0-4b-1loop","score":69.19,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-labs-dory1.0-4b","score":72.41,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-labs-dory1.0-4b-4loop","score":72.16,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-4b","score":77.71,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-9b","score":80.93,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-26b-a4b-it","score":80.43,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-35b-a3b","score":85.35,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-labs-dory1.0-4b-1loop","score":8.25,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-labs-dory1.0-4b","score":10.89,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-labs-dory1.0-4b-4loop","score":10.43,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-4b","score":11.31,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-9b","score":15.43,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemma-4-26b-a4b-it","score":17.79,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.6-35b-a3b","score":19.18,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-labs-dory1.0-4b-1loop","score":74.29,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-labs-dory1.0-4b","score":77.94,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-labs-dory1.0-4b-4loop","score":79,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":53.83,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-9b","score":59,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-26b-a4b-it","score":77.89,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":57.44,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-labs-dory1.0-4b-1loop","score":63,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-labs-dory1.0-4b","score":71,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-labs-dory1.0-4b-4loop","score":73,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-4b","score":64.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-9b","score":68.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-26b-a4b-it","score":64.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.6-35b-a3b","score":68.5,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-labs-dory1.0-4b-1loop","score":10.03,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-labs-dory1.0-4b","score":10.08,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"nemotron-labs-dory1.0-4b-4loop","score":10.03,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.5-4b","score":15.02,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.5-9b","score":18.05,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gemma-4-26b-a4b-it","score":21.13,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.6-35b-a3b","score":19.95,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3.5-super-vl-120b-a12b","score":89.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"comet-60b-a12b","score":88.64,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"comet-60b-a12b-fp8","score":88.57,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":89.46,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"comet-60b-a12b-nvfp4","score":88.38,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3.5-super-vl-120b-a12b","score":28.59,"metric":"percent"},{"benchmark":"hle-text-only","model":"comet-60b-a12b","score":25.35,"metric":"percent"},{"benchmark":"hle-text-only","model":"comet-60b-a12b-fp8","score":24.51,"metric":"percent"},{"benchmark":"hle-text-only","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":27.94,"metric":"percent"},{"benchmark":"hle-text-only","model":"comet-60b-a12b-nvfp4","score":25.16,"metric":"percent"},{"benchmark":"aa-omniscience","model":"nemotron-3.5-super-vl-120b-a12b","score":5.08,"metric":"index"},{"benchmark":"aa-omniscience","model":"comet-60b-a12b","score":2.83,"metric":"index"},{"benchmark":"aa-omniscience","model":"comet-60b-a12b-fp8","score":3.19,"metric":"index"},{"benchmark":"aa-omniscience","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":5.38,"metric":"index"},{"benchmark":"aa-omniscience","model":"comet-60b-a12b-nvfp4","score":-8.29,"metric":"index"},{"benchmark":"aa-lcr","model":"nemotron-3.5-super-vl-120b-a12b","score":68.31,"metric":"percent"},{"benchmark":"aa-lcr","model":"comet-60b-a12b","score":67.38,"metric":"percent"},{"benchmark":"aa-lcr","model":"comet-60b-a12b-fp8","score":67.81,"metric":"percent"},{"benchmark":"aa-lcr","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":67.19,"metric":"percent"},{"benchmark":"aa-lcr","model":"comet-60b-a12b-nvfp4","score":67,"metric":"percent"},{"benchmark":"gdp-pdf","model":"nemotron-3.5-super-vl-120b-a12b","score":6.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"comet-60b-a12b","score":5.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"comet-60b-a12b-fp8","score":5.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":7,"metric":"percent"},{"benchmark":"gdp-pdf","model":"comet-60b-a12b-nvfp4","score":4.6,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3.5-super-vl-120b-a12b","score":45.36,"metric":"percent"},{"benchmark":"scicode","model":"comet-60b-a12b","score":46.01,"metric":"percent"},{"benchmark":"scicode","model":"comet-60b-a12b-fp8","score":46.35,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":46.22,"metric":"percent"},{"benchmark":"scicode","model":"comet-60b-a12b-nvfp4","score":46.05,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"comet-60b-a12b","score":55.76,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"comet-60b-a12b-fp8","score":57.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":59.55,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"comet-60b-a12b-nvfp4","score":55.76,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3.5-super-vl-120b-a12b","score":72.07,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"comet-60b-a12b","score":70,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"comet-60b-a12b-fp8","score":71,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":71.47,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"comet-60b-a12b-nvfp4","score":70,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3.5-super-vl-120b-a12b","score":67,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"comet-60b-a12b","score":66.56,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"comet-60b-a12b-fp8","score":69.33,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":67.11,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"comet-60b-a12b-nvfp4","score":65.22,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"nemotron-3.5-super-vl-120b-a12b","score":50.3,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"comet-60b-a12b","score":50.93,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"comet-60b-a12b-fp8","score":51.48,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":51.66,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"comet-60b-a12b-nvfp4","score":50.3,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3.5-super-vl-120b-a12b","score":77.25,"metric":"percent"},{"benchmark":"tau2-airline","model":"comet-60b-a12b","score":78,"metric":"percent"},{"benchmark":"tau2-airline","model":"comet-60b-a12b-fp8","score":77.25,"metric":"percent"},{"benchmark":"tau2-airline","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":78,"metric":"percent"},{"benchmark":"tau2-airline","model":"comet-60b-a12b-nvfp4","score":79.25,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3.5-super-vl-120b-a12b","score":82.79,"metric":"percent"},{"benchmark":"tau2-retail","model":"comet-60b-a12b","score":85.09,"metric":"percent"},{"benchmark":"tau2-retail","model":"comet-60b-a12b-fp8","score":82.68,"metric":"percent"},{"benchmark":"tau2-retail","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":81.14,"metric":"percent"},{"benchmark":"tau2-retail","model":"comet-60b-a12b-nvfp4","score":83.22,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3.5-super-vl-120b-a12b","score":76.75,"metric":"percent"},{"benchmark":"tau2-telecom","model":"comet-60b-a12b","score":79.28,"metric":"percent"},{"benchmark":"tau2-telecom","model":"comet-60b-a12b-fp8","score":83.11,"metric":"percent"},{"benchmark":"tau2-telecom","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":74.01,"metric":"percent"},{"benchmark":"tau2-telecom","model":"comet-60b-a12b-nvfp4","score":74.23,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3.5-super-vl-120b-a12b","score":21.13,"metric":"percent"},{"benchmark":"tau3-banking","model":"comet-60b-a12b","score":20.75,"metric":"percent"},{"benchmark":"tau3-banking","model":"comet-60b-a12b-fp8","score":22.68,"metric":"percent"},{"benchmark":"tau3-banking","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":18.17,"metric":"percent"},{"benchmark":"tau3-banking","model":"comet-60b-a12b-nvfp4","score":20.88,"metric":"percent"},{"benchmark":"automationbench-aa","model":"nemotron-3.5-super-vl-120b-a12b","score":31.16,"metric":"percent"},{"benchmark":"automationbench-aa","model":"comet-60b-a12b","score":33.18,"metric":"percent"},{"benchmark":"automationbench-aa","model":"comet-60b-a12b-fp8","score":33.38,"metric":"percent"},{"benchmark":"automationbench-aa","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":30.92,"metric":"percent"},{"benchmark":"automationbench-aa","model":"comet-60b-a12b-nvfp4","score":31.47,"metric":"percent"},{"benchmark":"mmmu-pro","model":"nemotron-3.5-super-vl-120b-a12b","score":70.92,"metric":"percent"},{"benchmark":"mmmu-pro","model":"comet-60b-a12b","score":67.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"comet-60b-a12b-fp8","score":66.88,"metric":"percent"},{"benchmark":"mmmu-pro","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":71.21,"metric":"percent"},{"benchmark":"mmmu-pro","model":"comet-60b-a12b-nvfp4","score":66.3,"metric":"percent"},{"benchmark":"mathvision","model":"nemotron-3.5-super-vl-120b-a12b","score":70.72,"metric":"percent"},{"benchmark":"mathvision","model":"comet-60b-a12b","score":69.14,"metric":"percent"},{"benchmark":"mathvision","model":"comet-60b-a12b-fp8","score":69.34,"metric":"percent"},{"benchmark":"mathvision","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":70.43,"metric":"percent"},{"benchmark":"mathvision","model":"comet-60b-a12b-nvfp4","score":68.72,"metric":"percent"},{"benchmark":"charxiv-rq","model":"nemotron-3.5-super-vl-120b-a12b","score":74,"metric":"percent"},{"benchmark":"charxiv-rq","model":"comet-60b-a12b","score":72.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"comet-60b-a12b-fp8","score":72.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":74.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"comet-60b-a12b-nvfp4","score":72,"metric":"percent"},{"benchmark":"blink","model":"nemotron-3.5-super-vl-120b-a12b","score":68.96,"metric":"percent"},{"benchmark":"blink","model":"comet-60b-a12b","score":68.4,"metric":"percent"},{"benchmark":"blink","model":"comet-60b-a12b-fp8","score":69,"metric":"percent"},{"benchmark":"blink","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":70.01,"metric":"percent"},{"benchmark":"blink","model":"comet-60b-a12b-nvfp4","score":68.64,"metric":"percent"},{"benchmark":"v-star","model":"nemotron-3.5-super-vl-120b-a12b","score":90.58,"metric":"percent"},{"benchmark":"v-star","model":"comet-60b-a12b","score":84.82,"metric":"percent"},{"benchmark":"v-star","model":"comet-60b-a12b-fp8","score":85.34,"metric":"percent"},{"benchmark":"v-star","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":86.39,"metric":"percent"},{"benchmark":"v-star","model":"comet-60b-a12b-nvfp4","score":83.25,"metric":"percent"},{"benchmark":"babyvision","model":"nemotron-3.5-super-vl-120b-a12b","score":26.8,"metric":"percent"},{"benchmark":"babyvision","model":"comet-60b-a12b","score":28.09,"metric":"percent"},{"benchmark":"babyvision","model":"comet-60b-a12b-fp8","score":30.93,"metric":"percent"},{"benchmark":"babyvision","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":28.87,"metric":"percent"},{"benchmark":"babyvision","model":"comet-60b-a12b-nvfp4","score":28.87,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"nemotron-3.5-super-vl-120b-a12b","score":67.43,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"comet-60b-a12b","score":66.07,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"comet-60b-a12b-fp8","score":66.28,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":67.02,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"comet-60b-a12b-nvfp4","score":66.18,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"nemotron-3.5-super-vl-120b-a12b","score":58.32,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"comet-60b-a12b","score":55.84,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"comet-60b-a12b-fp8","score":55.48,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":58.97,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"comet-60b-a12b-nvfp4","score":55.84,"metric":"percent"},{"benchmark":"ocrreasoning","model":"nemotron-3.5-super-vl-120b-a12b","score":65.2,"metric":"percent"},{"benchmark":"ocrreasoning","model":"comet-60b-a12b","score":62.49,"metric":"percent"},{"benchmark":"ocrreasoning","model":"comet-60b-a12b-fp8","score":59.03,"metric":"percent"},{"benchmark":"ocrreasoning","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":66.14,"metric":"percent"},{"benchmark":"ocrreasoning","model":"comet-60b-a12b-nvfp4","score":59.78,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"nemotron-3.5-super-vl-120b-a12b","score":60.77,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"comet-60b-a12b","score":58.61,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"comet-60b-a12b-fp8","score":58.51,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":60.26,"metric":"percent"},{"benchmark":"mmlongbench-doc","model":"comet-60b-a12b-nvfp4","score":56.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"nemotron-3.5-super-vl-120b-a12b","score":74.48,"metric":"percent"},{"benchmark":"videomme-nosub","model":"comet-60b-a12b","score":70.96,"metric":"percent"},{"benchmark":"videomme-nosub","model":"comet-60b-a12b-fp8","score":72.44,"metric":"percent"},{"benchmark":"videomme-nosub","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":74.22,"metric":"percent"},{"benchmark":"videomme-nosub","model":"comet-60b-a12b-nvfp4","score":71.96,"metric":"percent"},{"benchmark":"videomme-sub","model":"nemotron-3.5-super-vl-120b-a12b","score":75.59,"metric":"percent"},{"benchmark":"videomme-sub","model":"comet-60b-a12b","score":73.26,"metric":"percent"},{"benchmark":"videomme-sub","model":"comet-60b-a12b-fp8","score":74,"metric":"percent"},{"benchmark":"videomme-sub","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":75.96,"metric":"percent"},{"benchmark":"videomme-sub","model":"comet-60b-a12b-nvfp4","score":73.37,"metric":"percent"},{"benchmark":"videomme-v2","model":"nemotron-3.5-super-vl-120b-a12b","score":33.82,"metric":"percent"},{"benchmark":"videomme-v2","model":"comet-60b-a12b","score":31.74,"metric":"percent"},{"benchmark":"videomme-v2","model":"comet-60b-a12b-fp8","score":33.09,"metric":"percent"},{"benchmark":"videomme-v2","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":32.13,"metric":"percent"},{"benchmark":"videomme-v2","model":"comet-60b-a12b-nvfp4","score":33.33,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"youtu-parsing-omni","score":96.96,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"teleocr","score":96.91,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"ovisocr2","score":96.47,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"paddleocr-vl-1.6","score":96.34,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"hunyuanocr-1.5","score":94.74,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"interfaze-1.1-lite","score":85.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"interfaze","score":92.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3-flash","score":88.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"grok-4.3","score":73.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"interfaze-1.1-lite","score":73.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"interfaze","score":71.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.4-mini","score":40.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-sonnet-4.6","score":46.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-3-flash","score":67.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"grok-4.3","score":68.7,"metric":"percent"},{"benchmark":"olmocr-bench","model":"interfaze-1.1-lite","score":83.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"interfaze","score":85.7,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gpt-5.4-mini","score":80.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"claude-sonnet-4.6","score":73.9,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gemini-3-flash","score":75.3,"metric":"percent"},{"benchmark":"olmocr-bench","model":"grok-4.3","score":81.9,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"interfaze-1.1-lite","score":60.9,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"interfaze","score":70.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gpt-5.4-mini","score":52.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"claude-sonnet-4.6","score":54.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"gemini-3-flash","score":55.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"grok-4.3","score":54.7,"metric":"percent"},{"benchmark":"refcoco","model":"interfaze-1.1-lite","score":83.8,"metric":"percent"},{"benchmark":"refcoco","model":"interfaze","score":82.1,"metric":"percent"},{"benchmark":"sob","model":"interfaze-1.1-lite","score":81.5,"metric":"percent"},{"benchmark":"sob","model":"interfaze","score":80.5,"metric":"percent"},{"benchmark":"sob","model":"claude-sonnet-4.6","score":77.9,"metric":"percent"},{"benchmark":"sob","model":"gemini-3-flash","score":77.3,"metric":"percent"},{"benchmark":"spider-2.0-lite","model":"interfaze-1.1-lite","score":48.9,"metric":"percent"},{"benchmark":"spider-2.0-lite","model":"interfaze","score":52.9,"metric":"percent"},{"benchmark":"spider-2.0-lite","model":"gpt-5.4-mini","score":26.7,"metric":"percent"},{"benchmark":"spider-2.0-lite","model":"claude-sonnet-4.6","score":49.6,"metric":"percent"},{"benchmark":"spider-2.0-lite","model":"gemini-3-flash","score":45.2,"metric":"percent"},{"benchmark":"spider-2.0-lite","model":"grok-4.3","score":45.9,"metric":"percent"},{"benchmark":"wgo-bench","model":"glimpse","score":42.7,"metric":"percent"},{"benchmark":"wgo-bench","model":"gpt-6-astra","score":39.42,"metric":"percent"},{"benchmark":"wgo-bench","model":"gpt-6.1-sol","score":38.91,"metric":"percent"},{"benchmark":"wgo-bench","model":"claude-opus-5.5","score":12.34,"metric":"percent"},{"benchmark":"wgo-bench","model":"gemini-3.8-flash","score":33.99,"metric":"percent"},{"benchmark":"erqa","model":"glimpse","score":83.75,"metric":"percent"},{"benchmark":"erqa","model":"gpt-6-astra","score":83.75,"metric":"percent"},{"benchmark":"erqa","model":"gpt-6.1-sol","score":82.45,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-5.5","score":82.2,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3.8-flash","score":81.2,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"glimpse","score":95.36,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"gpt-6-astra","score":97.68,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"gpt-6.1-sol","score":97.16,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"gemini-3.8-flash","score":83.25,"metric":"percent"},{"benchmark":"hss","model":"glimpse","score":46.36,"metric":"percent"},{"benchmark":"hss","model":"gpt-6-astra","score":53.6,"metric":"percent"},{"benchmark":"hss","model":"gpt-6.1-sol","score":46.6,"metric":"percent"},{"benchmark":"hss","model":"claude-opus-5.5","score":49.81,"metric":"percent"},{"benchmark":"hss","model":"gemini-3.8-flash","score":41.6,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"glimpse","score":92.9,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-6-astra","score":92.1,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gpt-6.1-sol","score":92.6,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"claude-opus-5.5","score":93.4,"metric":"percent"},{"benchmark":"charxiv-rq-with-tools","model":"gemini-3.8-flash","score":91.8,"metric":"percent"},{"benchmark":"ugc-videocap","model":"glimpse","score":82.66,"metric":"percent"},{"benchmark":"ugc-videocap","model":"gpt-6-astra","score":80.32,"metric":"percent"},{"benchmark":"ugc-videocap","model":"gpt-6.1-sol","score":80.41,"metric":"percent"},{"benchmark":"ugc-videocap","model":"claude-opus-5.5","score":76.35,"metric":"percent"},{"benchmark":"ugc-videocap","model":"gemini-3.8-flash","score":78.33,"metric":"percent"},{"benchmark":"dream-1k","model":"glimpse","score":76.04,"metric":"percent"},{"benchmark":"dream-1k","model":"gpt-6-astra","score":79.05,"metric":"percent"},{"benchmark":"dream-1k","model":"gpt-6.1-sol","score":77.93,"metric":"percent"},{"benchmark":"dream-1k","model":"claude-opus-5.5","score":72.05,"metric":"percent"},{"benchmark":"dream-1k","model":"gemini-3.8-flash","score":70,"metric":"percent"},{"benchmark":"tomato","model":"glimpse","score":93.6,"metric":"percent"},{"benchmark":"tomato","model":"gpt-6-astra","score":96.02,"metric":"percent"},{"benchmark":"tomato","model":"gpt-6.1-sol","score":89.02,"metric":"percent"},{"benchmark":"tomato","model":"claude-opus-5.5","score":72.44,"metric":"percent"},{"benchmark":"tomato","model":"gemini-3.8-flash","score":83.02,"metric":"percent"},{"benchmark":"et-bench","model":"glimpse","score":63.55,"metric":"percent"},{"benchmark":"et-bench","model":"gpt-6.1-sol","score":59.79,"metric":"percent"},{"benchmark":"et-bench","model":"gemini-3.8-flash","score":63.45,"metric":"percent"},{"benchmark":"fsc-147","model":"glimpse","score":83.36,"metric":"percent"},{"benchmark":"fsc-147","model":"gpt-6-astra","score":82.02,"metric":"percent"},{"benchmark":"fsc-147","model":"gpt-6.1-sol","score":82.69,"metric":"percent"},{"benchmark":"fsc-147","model":"claude-opus-5.5","score":73.78,"metric":"percent"},{"benchmark":"fsc-147","model":"gemini-3.8-flash","score":67.06,"metric":"percent"},{"benchmark":"countqa","model":"glimpse","score":82.66,"metric":"percent"},{"benchmark":"countqa","model":"gpt-6-astra","score":86.42,"metric":"percent"},{"benchmark":"countqa","model":"gpt-6.1-sol","score":86.42,"metric":"percent"},{"benchmark":"countqa","model":"claude-opus-5.5","score":82.2,"metric":"percent"},{"benchmark":"countqa","model":"gemini-3.8-flash","score":81.09,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gpt-6-astra","score":87.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-fable-5","score":83.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-sonnet-5","score":74.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-27b","score":76.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"tev-27b","score":79.4,"metric":"percent"},{"benchmark":"olmocr-bench","model":"infinity-parser2-pro","score":87.6,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-3-4b","score":86.3,"metric":"percent"},{"benchmark":"olmocr-bench","model":"chandra-ocr-2","score":85.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-3-0.8b","score":85.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-3-1b","score":84.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"jina-ocr-v1","score":83.4,"metric":"percent"},{"benchmark":"olmocr-bench","model":"surya-ocr-2","score":83.3,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-2-1b","score":83.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mistral-ocr-4.1","score":81.9,"metric":"percent"},{"benchmark":"parsebench","model":"lightonocr-3-4b","score":75.1,"metric":"percent"},{"benchmark":"parsebench","model":"lightonocr-3-0.8b","score":74.6,"metric":"percent"},{"benchmark":"parsebench","model":"infinity-parser2-pro","score":74.3,"metric":"percent"},{"benchmark":"parsebench","model":"lightonocr-3-1b","score":71.4,"metric":"percent"},{"benchmark":"parsebench","model":"chandra-ocr-2","score":70.1,"metric":"percent"},{"benchmark":"parsebench","model":"mistral-ocr-4.1","score":68.2,"metric":"percent"},{"benchmark":"parsebench","model":"surya-ocr-2","score":64.8,"metric":"percent"},{"benchmark":"parsebench","model":"dots.mocr","score":55.8,"metric":"percent"},{"benchmark":"parsebench","model":"lightonocr-2-1b","score":48,"metric":"percent"},{"benchmark":"parsebench","model":"jina-ocr-v1","score":45.9,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"lightonocr-3-4b","score":74.1,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"lightonocr-3-0.8b","score":70.5,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"lightonocr-3-1b","score":69.6,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"chandra-ocr-2","score":69,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"infinity-parser2-pro","score":63.2,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"dots.mocr","score":59.3,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"surya-ocr-2","score":54.1,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"mistral-ocr-4.1","score":54.1,"metric":"percent"},{"benchmark":"fr-bench-pdf2md","model":"jina-ocr-v1","score":53.2,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-3-8b-reasoning","score":78.7,"metric":"percent"},{"benchmark":"aime-2024","model":"ministral-3-8b-reasoning","score":86,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-8b-reasoning","score":66.8,"metric":"percent"},{"benchmark":"livecodebench","model":"ministral-3-8b-reasoning","score":61.6,"metric":"percent"},{"benchmark":"hellaswag","model":"t5gemma-2-270m-270m","score":41.1,"metric":"percent"},{"benchmark":"hellaswag","model":"t5gemma-2-1b-1b","score":62.9,"metric":"percent"},{"benchmark":"hellaswag","model":"t5gemma-2-4b-4b","score":77.4,"metric":"percent"},{"benchmark":"boolq","model":"t5gemma-2-270m-270m","score":57.4,"metric":"percent"},{"benchmark":"boolq","model":"t5gemma-2-1b-1b","score":68.5,"metric":"percent"},{"benchmark":"boolq","model":"t5gemma-2-4b-4b","score":79.3,"metric":"percent"},{"benchmark":"piqa","model":"t5gemma-2-270m-270m","score":66.5,"metric":"percent"},{"benchmark":"piqa","model":"t5gemma-2-1b-1b","score":74.3,"metric":"percent"},{"benchmark":"piqa","model":"t5gemma-2-4b-4b","score":79.2,"metric":"percent"},{"benchmark":"socialiqa","model":"t5gemma-2-270m-270m","score":46.1,"metric":"percent"},{"benchmark":"socialiqa","model":"t5gemma-2-1b-1b","score":47.7,"metric":"percent"},{"benchmark":"socialiqa","model":"t5gemma-2-4b-4b","score":49.9,"metric":"percent"},{"benchmark":"triviaqa","model":"t5gemma-2-270m-270m","score":14.8,"metric":"percent"},{"benchmark":"triviaqa","model":"t5gemma-2-1b-1b","score":29,"metric":"percent"},{"benchmark":"triviaqa","model":"t5gemma-2-4b-4b","score":53.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"t5gemma-2-270m-270m","score":3,"metric":"percent"},{"benchmark":"naturalquestions","model":"t5gemma-2-1b-1b","score":8.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"t5gemma-2-4b-4b","score":17.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"t5gemma-2-270m-270m","score":27.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"t5gemma-2-1b-1b","score":41,"metric":"percent"},{"benchmark":"arc-challenge","model":"t5gemma-2-4b-4b","score":56.1,"metric":"percent"},{"benchmark":"arc-easy","model":"t5gemma-2-270m-270m","score":57.9,"metric":"percent"},{"benchmark":"arc-easy","model":"t5gemma-2-1b-1b","score":67.7,"metric":"percent"},{"benchmark":"arc-easy","model":"t5gemma-2-4b-4b","score":74.3,"metric":"percent"},{"benchmark":"winogrande","model":"t5gemma-2-270m-270m","score":53.9,"metric":"percent"},{"benchmark":"winogrande","model":"t5gemma-2-1b-1b","score":60.8,"metric":"percent"},{"benchmark":"winogrande","model":"t5gemma-2-4b-4b","score":71.6,"metric":"percent"},{"benchmark":"bbh","model":"t5gemma-2-270m-270m","score":22.9,"metric":"percent"},{"benchmark":"bbh","model":"t5gemma-2-1b-1b","score":28.5,"metric":"percent"},{"benchmark":"bbh","model":"t5gemma-2-4b-4b","score":43.7,"metric":"percent"},{"benchmark":"drop","model":"t5gemma-2-270m-270m","score":39.4,"metric":"percent"},{"benchmark":"drop","model":"t5gemma-2-1b-1b","score":51.2,"metric":"percent"},{"benchmark":"drop","model":"t5gemma-2-4b-4b","score":66.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"t5gemma-2-270m-270m","score":10.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"t5gemma-2-1b-1b","score":16.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"t5gemma-2-4b-4b","score":33.2,"metric":"percent"},{"benchmark":"agieval","model":"t5gemma-2-270m-270m","score":20.9,"metric":"percent"},{"benchmark":"agieval","model":"t5gemma-2-1b-1b","score":23.8,"metric":"percent"},{"benchmark":"agieval","model":"t5gemma-2-4b-4b","score":41.1,"metric":"percent"},{"benchmark":"math","model":"t5gemma-2-270m-270m","score":1.5,"metric":"percent"},{"benchmark":"math","model":"t5gemma-2-1b-1b","score":4.5,"metric":"percent"},{"benchmark":"math","model":"t5gemma-2-4b-4b","score":21.2,"metric":"percent"},{"benchmark":"gsm8k","model":"t5gemma-2-270m-270m","score":1.7,"metric":"percent"},{"benchmark":"gsm8k","model":"t5gemma-2-1b-1b","score":9.1,"metric":"percent"},{"benchmark":"gsm8k","model":"t5gemma-2-4b-4b","score":44,"metric":"percent"},{"benchmark":"gpqa","model":"t5gemma-2-270m-270m","score":9.6,"metric":"percent"},{"benchmark":"gpqa","model":"t5gemma-2-1b-1b","score":10.5,"metric":"percent"},{"benchmark":"gpqa","model":"t5gemma-2-4b-4b","score":17.6,"metric":"percent"},{"benchmark":"mbpp","model":"t5gemma-2-270m-270m","score":5.6,"metric":"percent"},{"benchmark":"mbpp","model":"t5gemma-2-1b-1b","score":25.2,"metric":"percent"},{"benchmark":"mbpp","model":"t5gemma-2-4b-4b","score":44.8,"metric":"percent"},{"benchmark":"humaneval","model":"t5gemma-2-270m-270m","score":4.3,"metric":"percent"},{"benchmark":"humaneval","model":"t5gemma-2-1b-1b","score":15.2,"metric":"percent"},{"benchmark":"humaneval","model":"t5gemma-2-4b-4b","score":30.5,"metric":"percent"},{"benchmark":"mgsm","model":"t5gemma-2-270m-270m","score":1.8,"metric":"percent"},{"benchmark":"mgsm","model":"t5gemma-2-1b-1b","score":8.9,"metric":"percent"},{"benchmark":"mgsm","model":"t5gemma-2-4b-4b","score":42.1,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"t5gemma-2-270m-270m","score":23.5,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"t5gemma-2-1b-1b","score":33.1,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"t5gemma-2-4b-4b","score":53.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"t5gemma-2-270m-270m","score":26.9,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"t5gemma-2-1b-1b","score":40.9,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"t5gemma-2-4b-4b","score":49.2,"metric":"percent"},{"benchmark":"flores","model":"t5gemma-2-270m-270m","score":23.9,"metric":"percent"},{"benchmark":"flores","model":"t5gemma-2-1b-1b","score":33.8,"metric":"percent"},{"benchmark":"flores","model":"t5gemma-2-4b-4b","score":41.8,"metric":"percent"},{"benchmark":"xquad","model":"t5gemma-2-270m-270m","score":40.8,"metric":"percent"},{"benchmark":"xquad","model":"t5gemma-2-1b-1b","score":63.1,"metric":"percent"},{"benchmark":"xquad","model":"t5gemma-2-4b-4b","score":70.6,"metric":"percent"},{"benchmark":"coco-caption","model":"t5gemma-2-270m-270m","score":69.6,"metric":"cider"},{"benchmark":"coco-caption","model":"t5gemma-2-1b-1b","score":86,"metric":"cider"},{"benchmark":"coco-caption","model":"t5gemma-2-4b-4b","score":105.4,"metric":"cider"},{"benchmark":"docvqa","model":"t5gemma-2-270m-270m","score":41.6,"metric":"percent"},{"benchmark":"docvqa","model":"t5gemma-2-1b-1b","score":66.6,"metric":"percent"},{"benchmark":"docvqa","model":"t5gemma-2-4b-4b","score":74.7,"metric":"percent"},{"benchmark":"infovqa","model":"t5gemma-2-270m-270m","score":20.2,"metric":"percent"},{"benchmark":"infovqa","model":"t5gemma-2-1b-1b","score":36.4,"metric":"percent"},{"benchmark":"infovqa","model":"t5gemma-2-4b-4b","score":46,"metric":"percent"},{"benchmark":"mmmu","model":"t5gemma-2-270m-270m","score":22.7,"metric":"percent"},{"benchmark":"mmmu","model":"t5gemma-2-1b-1b","score":28.4,"metric":"percent"},{"benchmark":"mmmu","model":"t5gemma-2-4b-4b","score":39.4,"metric":"percent"},{"benchmark":"textvqa","model":"t5gemma-2-270m-270m","score":34.1,"metric":"percent"},{"benchmark":"textvqa","model":"t5gemma-2-1b-1b","score":53.1,"metric":"percent"},{"benchmark":"textvqa","model":"t5gemma-2-4b-4b","score":58.4,"metric":"percent"},{"benchmark":"realworldqa","model":"t5gemma-2-270m-270m","score":27.2,"metric":"percent"},{"benchmark":"realworldqa","model":"t5gemma-2-1b-1b","score":42.4,"metric":"percent"},{"benchmark":"realworldqa","model":"t5gemma-2-4b-4b","score":46.1,"metric":"percent"},{"benchmark":"ai2d","model":"t5gemma-2-270m-270m","score":26.5,"metric":"percent"},{"benchmark":"ai2d","model":"t5gemma-2-1b-1b","score":44.8,"metric":"percent"},{"benchmark":"ai2d","model":"t5gemma-2-4b-4b","score":61.6,"metric":"percent"},{"benchmark":"chartqa","model":"t5gemma-2-270m-270m","score":29.2,"metric":"percent"},{"benchmark":"chartqa","model":"t5gemma-2-1b-1b","score":50.2,"metric":"percent"},{"benchmark":"chartqa","model":"t5gemma-2-4b-4b","score":66,"metric":"percent"},{"benchmark":"vqav2","model":"t5gemma-2-270m-270m","score":38.8,"metric":"percent"},{"benchmark":"vqav2","model":"t5gemma-2-1b-1b","score":57.8,"metric":"percent"},{"benchmark":"vqav2","model":"t5gemma-2-4b-4b","score":62.7,"metric":"percent"},{"benchmark":"tallyqa","model":"t5gemma-2-270m-270m","score":26.4,"metric":"percent"},{"benchmark":"tallyqa","model":"t5gemma-2-1b-1b","score":32.2,"metric":"percent"},{"benchmark":"tallyqa","model":"t5gemma-2-4b-4b","score":39.6,"metric":"percent"},{"benchmark":"spatialsense-vqa","model":"t5gemma-2-270m-270m","score":50.4,"metric":"percent"},{"benchmark":"spatialsense-vqa","model":"t5gemma-2-1b-1b","score":50.2,"metric":"percent"},{"benchmark":"spatialsense-vqa","model":"t5gemma-2-4b-4b","score":51.7,"metric":"percent"},{"benchmark":"ruler-32k","model":"t5gemma-2-270m-270m","score":57.3,"metric":"percent"},{"benchmark":"ruler-32k","model":"t5gemma-2-1b-1b","score":69.2,"metric":"percent"},{"benchmark":"ruler-32k","model":"t5gemma-2-4b-4b","score":81.7,"metric":"percent"},{"benchmark":"ruler-128k","model":"t5gemma-2-270m-270m","score":25.5,"metric":"percent"},{"benchmark":"ruler-128k","model":"t5gemma-2-1b-1b","score":35.1,"metric":"percent"},{"benchmark":"ruler-128k","model":"t5gemma-2-4b-4b","score":57.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"translategemma-27b-it","score":84.4,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"translategemma-12b-it","score":83.5,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"translategemma-4b-it","score":80.1,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gemma-3-27b-it","score":83.1,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gemma-3-12b-it","score":81.6,"metric":"percent"},{"benchmark":"wmt24-plus-plus","model":"gemma-3-4b-it","score":77.2,"metric":"percent"},{"benchmark":"mimic-cxr","model":"gemma-3-4b-it","score":81.2,"metric":"percent"},{"benchmark":"mimic-cxr","model":"medgemma-4b-it","score":88.9,"metric":"percent"},{"benchmark":"mimic-cxr","model":"medgemma-1.5-4b-it","score":89.5,"metric":"percent"},{"benchmark":"mimic-cxr","model":"medgemma-27b-it","score":90,"metric":"percent"},{"benchmark":"chexpert","model":"gemma-3-4b-it","score":32.6,"metric":"percent"},{"benchmark":"chexpert","model":"medgemma-4b-it","score":48.1,"metric":"percent"},{"benchmark":"chexpert","model":"medgemma-1.5-4b-it","score":48.2,"metric":"percent"},{"benchmark":"chexpert","model":"medgemma-27b-it","score":49.9,"metric":"percent"},{"benchmark":"cxr14","model":"gemma-3-4b-it","score":32,"metric":"percent"},{"benchmark":"cxr14","model":"medgemma-4b-it","score":50.1,"metric":"percent"},{"benchmark":"cxr14","model":"medgemma-1.5-4b-it","score":48.4,"metric":"percent"},{"benchmark":"cxr14","model":"medgemma-27b-it","score":45.3,"metric":"percent"},{"benchmark":"ms-cxr-t","model":"gemma-3-4b-it","score":59,"metric":"percent"},{"benchmark":"ms-cxr-t","model":"medgemma-4b-it","score":61.11,"metric":"percent"},{"benchmark":"ms-cxr-t","model":"medgemma-1.5-4b-it","score":65.7,"metric":"percent"},{"benchmark":"ms-cxr-t","model":"medgemma-27b-it","score":50.1,"metric":"percent"},{"benchmark":"slake","model":"gemma-3-4b-it","score":62,"metric":"percent"},{"benchmark":"slake","model":"medgemma-4b-it","score":87.6,"metric":"percent"},{"benchmark":"slake","model":"medgemma-1.5-4b-it","score":82.8,"metric":"percent"},{"benchmark":"slake","model":"medgemma-27b-it","score":85.9,"metric":"percent"},{"benchmark":"vqa-rad","model":"gemma-3-4b-it","score":42.1,"metric":"percent"},{"benchmark":"vqa-rad","model":"medgemma-4b-it","score":69.1,"metric":"percent"},{"benchmark":"vqa-rad","model":"medgemma-1.5-4b-it","score":70.2,"metric":"percent"},{"benchmark":"vqa-rad","model":"medgemma-27b-it","score":67.1,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"gemma-3-4b-it","score":16.4,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"medgemma-4b-it","score":18.8,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"medgemma-1.5-4b-it","score":20.9,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"medgemma-27b-it","score":26.8,"metric":"percent"},{"benchmark":"medqa","model":"gemma-3-4b-it","score":50.7,"metric":"percent"},{"benchmark":"medqa","model":"medgemma-4b-it","score":64.4,"metric":"percent"},{"benchmark":"medqa","model":"medgemma-1.5-4b-it","score":69.1,"metric":"percent"},{"benchmark":"medqa","model":"medgemma-27b-it","score":85.3,"metric":"percent"},{"benchmark":"medmcqa","model":"gemma-3-4b-it","score":45.4,"metric":"percent"},{"benchmark":"medmcqa","model":"medgemma-4b-it","score":55.7,"metric":"percent"},{"benchmark":"medmcqa","model":"medgemma-1.5-4b-it","score":59.8,"metric":"percent"},{"benchmark":"medmcqa","model":"medgemma-27b-it","score":70.2,"metric":"percent"},{"benchmark":"pubmedqa","model":"gemma-3-4b-it","score":68.4,"metric":"percent"},{"benchmark":"pubmedqa","model":"medgemma-4b-it","score":73.4,"metric":"percent"},{"benchmark":"pubmedqa","model":"medgemma-1.5-4b-it","score":68.2,"metric":"percent"},{"benchmark":"pubmedqa","model":"medgemma-27b-it","score":77.2,"metric":"percent"},{"benchmark":"mmlu-med","model":"gemma-3-4b-it","score":67.2,"metric":"percent"},{"benchmark":"mmlu-med","model":"medgemma-4b-it","score":70,"metric":"percent"},{"benchmark":"mmlu-med","model":"medgemma-1.5-4b-it","score":69.6,"metric":"percent"},{"benchmark":"mmlu-med","model":"medgemma-27b-it","score":86.2,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"gemma-3-4b-it","score":11.6,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"medgemma-4b-it","score":14.2,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"medgemma-1.5-4b-it","score":16.4,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"medgemma-27b-it","score":23.7,"metric":"percent"},{"benchmark":"afrimed-qa","model":"gemma-3-4b-it","score":48,"metric":"percent"},{"benchmark":"afrimed-qa","model":"medgemma-4b-it","score":52,"metric":"percent"},{"benchmark":"afrimed-qa","model":"medgemma-1.5-4b-it","score":56,"metric":"percent"},{"benchmark":"afrimed-qa","model":"medgemma-27b-it","score":72,"metric":"percent"},{"benchmark":"ehrnoteqa","model":"gemma-3-4b-it","score":78,"metric":"percent"},{"benchmark":"ehrnoteqa","model":"medgemma-4b-it","score":79.4,"metric":"percent"},{"benchmark":"ehrnoteqa","model":"medgemma-1.5-4b-it","score":80.4,"metric":"percent"},{"benchmark":"ehrnoteqa","model":"medgemma-27b-it","score":90.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo2-235b-a22b","score":70.6,"metric":"percent"},{"benchmark":"osworld-g","model":"holo2-235b-a22b","score":79,"metric":"percent"},{"benchmark":"showdown","model":"holo2-235b-a22b","score":80.4,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo2-235b-a22b","score":85.5,"metric":"percent"},{"benchmark":"webclick","model":"holo2-235b-a22b","score":94.3,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo2-235b-a22b","score":95.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo2-30b-a3b","score":66.1,"metric":"percent"},{"benchmark":"osworld-g","model":"holo2-30b-a3b","score":76.1,"metric":"percent"},{"benchmark":"showdown","model":"holo2-30b-a3b","score":77.6,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo2-30b-a3b","score":85.5,"metric":"percent"},{"benchmark":"webclick","model":"holo2-30b-a3b","score":91.3,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo2-30b-a3b","score":94.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo2-8b","score":58.9,"metric":"percent"},{"benchmark":"osworld-g","model":"holo2-8b","score":70.1,"metric":"percent"},{"benchmark":"showdown","model":"holo2-8b","score":72.5,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo2-8b","score":83.8,"metric":"percent"},{"benchmark":"webclick","model":"holo2-8b","score":89.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo2-8b","score":93.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo2-4b","score":57.2,"metric":"percent"},{"benchmark":"osworld-g","model":"holo2-4b","score":69.4,"metric":"percent"},{"benchmark":"showdown","model":"holo2-4b","score":74.7,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holo2-4b","score":83.3,"metric":"percent"},{"benchmark":"webclick","model":"holo2-4b","score":88.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holo2-4b","score":93.2,"metric":"percent"},{"benchmark":"showdown","model":"qwen3-vl-235b-a22b-thinking","score":78.4,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"qwen3-vl-235b-a22b-thinking","score":85.2,"metric":"percent"},{"benchmark":"webclick","model":"qwen3-vl-235b-a22b-thinking","score":92.1,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-235b-a22b-thinking","score":95.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-30b-a3b-thinking","score":49.9,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-30b-a3b-thinking","score":65.8,"metric":"percent"},{"benchmark":"showdown","model":"qwen3-vl-30b-a3b-thinking","score":71.2,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"qwen3-vl-30b-a3b-thinking","score":84.2,"metric":"percent"},{"benchmark":"webclick","model":"qwen3-vl-30b-a3b-thinking","score":89.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-30b-a3b-thinking","score":91.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-8b-thinking","score":38.5,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-8b-thinking","score":56,"metric":"percent"},{"benchmark":"showdown","model":"qwen3-vl-8b-thinking","score":64.2,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"qwen3-vl-8b-thinking","score":83.6,"metric":"percent"},{"benchmark":"webclick","model":"qwen3-vl-8b-thinking","score":85.9,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-8b-thinking","score":91.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3-vl-4b-thinking","score":41.4,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3-vl-4b-thinking","score":56.4,"metric":"percent"},{"benchmark":"showdown","model":"qwen3-vl-4b-thinking","score":66.6,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"qwen3-vl-4b-thinking","score":84.1,"metric":"percent"},{"benchmark":"webclick","model":"qwen3-vl-4b-thinking","score":85.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"qwen3-vl-4b-thinking","score":90,"metric":"percent"},{"benchmark":"screenspot-pro","model":"mai-ui-32b","score":67.9,"metric":"percent"},{"benchmark":"osworld-g","model":"mai-ui-32b","score":67.6,"metric":"percent"},{"benchmark":"webvoyager","model":"holotron-12b","score":80.5,"metric":"percent"},{"benchmark":"webvoyager","model":"nemotron-nano-12b-v2-vl","score":35.1,"metric":"percent"},{"benchmark":"osworld-g","model":"holotron-12b","score":49,"metric":"percent"},{"benchmark":"osworld-g","model":"nemotron-nano-12b-v2-vl","score":11,"metric":"percent"},{"benchmark":"showdown","model":"holotron-12b","score":66.1,"metric":"percent"},{"benchmark":"showdown","model":"nemotron-nano-12b-v2-vl","score":23.9,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"holotron-12b","score":82,"metric":"percent"},{"benchmark":"ground-ui-1k","model":"nemotron-nano-12b-v2-vl","score":33.5,"metric":"percent"},{"benchmark":"webclick","model":"holotron-12b","score":83.8,"metric":"percent"},{"benchmark":"webclick","model":"nemotron-nano-12b-v2-vl","score":18,"metric":"percent"},{"benchmark":"screenspot-v2","model":"holotron-12b","score":89.9,"metric":"percent"},{"benchmark":"screenspot-v2","model":"nemotron-nano-12b-v2-vl","score":36.7,"metric":"percent"},{"benchmark":"webvoyager","model":"holo2-8b","score":80.2,"metric":"percent"},{"benchmark":"webvoyager","model":"qwen3-vl-8b-instruct","score":65.4,"metric":"percent"},{"benchmark":"osworld-verified","model":"holo3-122b-a10b","score":78.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"holo3-35b-a3b","score":77.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-397b-a17b","score":62.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-122b-a10b","score":61.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3.5-35b-a3b","score":54.2,"metric":"percent"},{"benchmark":"webarena","model":"holo3-122b-a10b","score":64.9,"metric":"percent"},{"benchmark":"webarena","model":"holo3-35b-a3b","score":64.8,"metric":"percent"},{"benchmark":"webarena","model":"qwen3.5-397b-a17b","score":62.1,"metric":"percent"},{"benchmark":"webarena","model":"qwen3.5-122b-a10b","score":57.1,"metric":"percent"},{"benchmark":"webarena","model":"qwen3.5-35b-a3b","score":51.4,"metric":"percent"},{"benchmark":"webarena","model":"kimi-k2.5","score":63.4,"metric":"percent"},{"benchmark":"webarena","model":"claude-sonnet-4.6","score":65.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo3-122b-a10b","score":72.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo3-35b-a3b","score":67.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-397b-a17b","score":69.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-122b-a10b","score":65.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen3.5-35b-a3b","score":64.5,"metric":"percent"},{"benchmark":"osworld-g","model":"holo3-122b-a10b","score":79.4,"metric":"percent"},{"benchmark":"osworld-g","model":"holo3-35b-a3b","score":77.3,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3.5-397b-a17b","score":78.4,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3.5-122b-a10b","score":77.5,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3.5-35b-a3b","score":76.9,"metric":"percent"},{"benchmark":"vqav2","model":"reka-edge-2603","score":88.4,"metric":"percent"},{"benchmark":"vqav2","model":"cosmos-reason2-8b","score":79.82,"metric":"percent"},{"benchmark":"vqav2","model":"qwen3.5-9b","score":83.22,"metric":"percent"},{"benchmark":"vqav2","model":"gemini-3-pro","score":89.78,"metric":"percent"},{"benchmark":"mlvu","model":"reka-edge-2603","score":74.3,"metric":"percent"},{"benchmark":"mlvu","model":"cosmos-reason2-8b","score":37.85,"metric":"percent"},{"benchmark":"mlvu","model":"qwen3.5-9b","score":52.39,"metric":"percent"},{"benchmark":"mlvu","model":"gemini-3-pro","score":80.68,"metric":"percent"},{"benchmark":"mmvu","model":"reka-edge-2603","score":71.68,"metric":"percent"},{"benchmark":"mmvu","model":"cosmos-reason2-8b","score":51.52,"metric":"percent"},{"benchmark":"mmvu","model":"qwen3.5-9b","score":68.64,"metric":"percent"},{"benchmark":"mmvu","model":"gemini-3-pro","score":78.88,"metric":"percent"},{"benchmark":"videohallucer","model":"reka-edge-2603","score":59.57,"metric":"percent"},{"benchmark":"videohallucer","model":"cosmos-reason2-8b","score":51.65,"metric":"percent"},{"benchmark":"videohallucer","model":"qwen3.5-9b","score":56,"metric":"percent"},{"benchmark":"videohallucer","model":"gemini-3-pro","score":66.78,"metric":"percent"},{"benchmark":"mobile-actions","model":"reka-edge-2603","score":88.4,"metric":"percent"},{"benchmark":"mobile-actions","model":"cosmos-reason2-8b","score":77.94,"metric":"percent"},{"benchmark":"mobile-actions","model":"qwen3.5-9b","score":91.78,"metric":"percent"},{"benchmark":"mobile-actions","model":"gemini-3-pro","score":89.39,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mistral-ocr-3","score":79.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gemini-2.0-flash","score":59.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"qwen2.5-vl-7b","score":64.3,"metric":"percent"},{"benchmark":"olmocr-bench","model":"olmocr","score":76.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"monkeyocr-pro-3b","score":73.6,"metric":"percent"},{"benchmark":"olmocr-bench","model":"dots.ocr","score":76.9,"metric":"percent"},{"benchmark":"olmocr-bench","model":"deepseek-ocr","score":73.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"chandra-ocr-0.1.0","score":81.7,"metric":"percent"},{"benchmark":"olmocr-bench","model":"olmocr-2-7b-1025","score":80.4,"metric":"percent"},{"benchmark":"olmocr-bench","model":"monkeyocr-pro-1.2b","score":68.9,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mineru2.5","score":70.4,"metric":"percent"},{"benchmark":"olmocr-bench","model":"paddleocr-vl","score":77.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-1b-1025","score":76.1,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-2-1b-base","score":81.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-2-1b-bbox-base","score":80.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-2-1b-bbox","score":80.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-2-1b-bbox-soup","score":80.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-2-1b-ocr-soup","score":82.4,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"fanar-2-27b-instruct","score":67.4,"metric":"percent"},{"benchmark":"arabicmmlu","model":"fanar-2-27b-instruct","score":74.67,"metric":"percent"},{"benchmark":"almieyar","model":"fanar-2-27b-instruct","score":79.46,"metric":"percent"},{"benchmark":"belebele","model":"fanar-2-27b-instruct","score":86.81,"metric":"percent"},{"benchmark":"acva","model":"fanar-2-27b-instruct","score":82.7,"metric":"percent"},{"benchmark":"mmlu","model":"fanar-2-27b-instruct","score":78.89,"metric":"percent"},{"benchmark":"gsm8k","model":"fanar-2-27b-instruct","score":93.7,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"gemma-3-27b-it","score":67.65,"metric":"percent"},{"benchmark":"arabicmmlu","model":"gemma-3-27b-it","score":72.21,"metric":"percent"},{"benchmark":"almieyar","model":"gemma-3-27b-it","score":70.48,"metric":"percent"},{"benchmark":"belebele","model":"gemma-3-27b-it","score":85.54,"metric":"percent"},{"benchmark":"acva","model":"gemma-3-27b-it","score":80.23,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b-it","score":77.38,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-27b-it","score":95.8,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"acegpt-v2-32b-chat","score":61.1,"metric":"percent"},{"benchmark":"arabicmmlu","model":"acegpt-v2-32b-chat","score":69.55,"metric":"percent"},{"benchmark":"almieyar","model":"acegpt-v2-32b-chat","score":55.24,"metric":"percent"},{"benchmark":"belebele","model":"acegpt-v2-32b-chat","score":83.96,"metric":"percent"},{"benchmark":"acva","model":"acegpt-v2-32b-chat","score":79.69,"metric":"percent"},{"benchmark":"mmlu","model":"acegpt-v2-32b-chat","score":75.72,"metric":"percent"},{"benchmark":"gsm8k","model":"acegpt-v2-32b-chat","score":71.5,"metric":"percent"},{"benchmark":"mmlu-arabic","model":"qwen3-32b","score":69.32,"metric":"percent"},{"benchmark":"arabicmmlu","model":"qwen3-32b","score":73.08,"metric":"percent"},{"benchmark":"almieyar","model":"qwen3-32b","score":67.18,"metric":"percent"},{"benchmark":"belebele","model":"qwen3-32b","score":85.98,"metric":"percent"},{"benchmark":"acva","model":"qwen3-32b","score":79.72,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-32b","score":82.25,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-32b","score":95.8,"metric":"percent"},{"benchmark":"arabicmmlu","model":"fanar-1-9b-instruct","score":67.35,"metric":"percent"},{"benchmark":"belebele","model":"fanar-1-9b-instruct","score":83.26,"metric":"percent"},{"benchmark":"acva","model":"fanar-1-9b-instruct","score":79.66,"metric":"percent"},{"benchmark":"mmlu","model":"fanar-1-9b-instruct","score":71.32,"metric":"percent"},{"benchmark":"gsm8k","model":"fanar-1-9b-instruct","score":83.02,"metric":"percent"},{"benchmark":"mt-bench","model":"fanar-1-9b-instruct","score":5.58,"metric":"percent"},{"benchmark":"mt-bench","model":"fanar-2-27b-instruct","score":6.12,"metric":"percent"},{"benchmark":"ifeval","model":"fanar-1-9b-instruct","score":74.7,"metric":"percent"},{"benchmark":"ifeval","model":"fanar-2-27b-instruct","score":82.97,"metric":"percent"},{"benchmark":"vsi-bench","model":"rynnbrain-30b-a3b","score":74.5,"metric":"percent"},{"benchmark":"erqa","model":"rynnbrain-30b-a3b","score":46.3,"metric":"percent"},{"benchmark":"robospatialhome","model":"rynnbrain-30b-a3b","score":70,"metric":"percent"},{"benchmark":"mindcube","model":"rynnbrain-30b-a3b","score":63.4,"metric":"percent"},{"benchmark":"refspatialbench","model":"rynnbrain-30b-a3b","score":59.2,"metric":"percent"},{"benchmark":"ai2d","model":"rynnbrain-30b-a3b","score":87,"metric":"percent"},{"benchmark":"chartqa","model":"rynnbrain-30b-a3b","score":88.3,"metric":"percent"},{"benchmark":"docvqa","model":"rynnbrain-30b-a3b","score":96.3,"metric":"percent"},{"benchmark":"mvbench","model":"rynnbrain-30b-a3b","score":70.8,"metric":"percent"},{"benchmark":"realworldqa","model":"rynnbrain-30b-a3b","score":69.7,"metric":"percent"},{"benchmark":"infovqa","model":"rynnbrain-30b-a3b","score":84.8,"metric":"percent"},{"benchmark":"egoschema","model":"rynnbrain-30b-a3b","score":66.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"rynnbrain-30b-a3b","score":71.9,"metric":"percent"},{"benchmark":"vsi-bench","model":"robobrain-2.0","score":42.7,"metric":"percent"},{"benchmark":"erqa","model":"robobrain-2.0","score":46,"metric":"percent"},{"benchmark":"mindcube","model":"robobrain-2.0","score":29.2,"metric":"percent"},{"benchmark":"ai2d","model":"robobrain-2.0","score":67.3,"metric":"percent"},{"benchmark":"chartqa","model":"robobrain-2.0","score":82.4,"metric":"percent"},{"benchmark":"docvqa","model":"robobrain-2.0","score":90.2,"metric":"percent"},{"benchmark":"mvbench","model":"robobrain-2.0","score":57.1,"metric":"percent"},{"benchmark":"realworldqa","model":"robobrain-2.0","score":67.5,"metric":"percent"},{"benchmark":"infovqa","model":"robobrain-2.0","score":75.5,"metric":"percent"},{"benchmark":"egoschema","model":"robobrain-2.0","score":61.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"robobrain-2.0","score":55.6,"metric":"percent"},{"benchmark":"vsi-bench","model":"pelican-vl-72b","score":57.3,"metric":"percent"},{"benchmark":"erqa","model":"pelican-vl-72b","score":43,"metric":"percent"},{"benchmark":"robospatialhome","model":"pelican-vl-72b","score":55.4,"metric":"percent"},{"benchmark":"mindcube","model":"pelican-vl-72b","score":32.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"pelican-vl-72b","score":49.5,"metric":"percent"},{"benchmark":"ai2d","model":"pelican-vl-72b","score":86.7,"metric":"percent"},{"benchmark":"chartqa","model":"pelican-vl-72b","score":90.4,"metric":"percent"},{"benchmark":"docvqa","model":"pelican-vl-72b","score":95.2,"metric":"percent"},{"benchmark":"mvbench","model":"pelican-vl-72b","score":69.7,"metric":"percent"},{"benchmark":"realworldqa","model":"pelican-vl-72b","score":67.3,"metric":"percent"},{"benchmark":"infovqa","model":"pelican-vl-72b","score":89.1,"metric":"percent"},{"benchmark":"egoschema","model":"pelican-vl-72b","score":79.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"pelican-vl-72b","score":73.7,"metric":"percent"},{"benchmark":"vsi-bench","model":"gpt-5.2","score":46.6,"metric":"percent"},{"benchmark":"erqa","model":"gpt-5.2","score":45.3,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-5.2","score":54.7,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5.2","score":26.4,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-5.2","score":97.1,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-5.2","score":89.6,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-5.2","score":94.2,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-5.2","score":67.1,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-5.2","score":82.5,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-5.2","score":66.8,"metric":"percent"},{"benchmark":"egoschema","model":"gpt-5.2","score":81.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-5.2","score":84.7,"metric":"percent"},{"benchmark":"vsi-bench","model":"gemini-3-pro","score":48.8,"metric":"percent"},{"benchmark":"robospatialhome","model":"gemini-3-pro","score":56,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-3-pro","score":70.8,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-3-pro","score":71.5,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-3-pro","score":83.1,"metric":"percent"},{"benchmark":"egoschema","model":"gemini-3-pro","score":72.2,"metric":"percent"},{"benchmark":"vsi-bench","model":"claude-sonnet-4.5","score":42.5,"metric":"percent"},{"benchmark":"robospatialhome","model":"claude-sonnet-4.5","score":40.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"claude-sonnet-4.5","score":15.1,"metric":"percent"},{"benchmark":"chartqa","model":"claude-sonnet-4.5","score":88.1,"metric":"percent"},{"benchmark":"mvbench","model":"claude-sonnet-4.5","score":55.1,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-sonnet-4.5","score":68.1,"metric":"percent"},{"benchmark":"infovqa","model":"claude-sonnet-4.5","score":62.2,"metric":"percent"},{"benchmark":"egoschema","model":"claude-sonnet-4.5","score":67.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"claude-sonnet-4.5","score":68.6,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-30b-a3b-instruct","score":65.8,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-30b-a3b-instruct","score":55.4,"metric":"percent"},{"benchmark":"mindcube","model":"qwen3-vl-30b-a3b-instruct","score":39,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3-vl-30b-a3b-instruct","score":83.7,"metric":"percent"},{"benchmark":"egoschema","model":"qwen3-vl-30b-a3b-instruct","score":70.7,"metric":"percent"},{"benchmark":"vsi-bench","model":"rynnbrain-2b","score":70.5,"metric":"percent"},{"benchmark":"erqa","model":"rynnbrain-2b","score":42.3,"metric":"percent"},{"benchmark":"robospatialhome","model":"rynnbrain-2b","score":65.7,"metric":"percent"},{"benchmark":"mindcube","model":"rynnbrain-2b","score":50.1,"metric":"percent"},{"benchmark":"refspatialbench","model":"rynnbrain-2b","score":52.7,"metric":"percent"},{"benchmark":"ai2d","model":"rynnbrain-2b","score":79.4,"metric":"percent"},{"benchmark":"chartqa","model":"rynnbrain-2b","score":78.2,"metric":"percent"},{"benchmark":"docvqa","model":"rynnbrain-2b","score":93,"metric":"percent"},{"benchmark":"mvbench","model":"rynnbrain-2b","score":67.3,"metric":"percent"},{"benchmark":"realworldqa","model":"rynnbrain-2b","score":60.4,"metric":"percent"},{"benchmark":"infovqa","model":"rynnbrain-2b","score":74.7,"metric":"percent"},{"benchmark":"egoschema","model":"rynnbrain-2b","score":64,"metric":"percent"},{"benchmark":"videomme-nosub","model":"rynnbrain-2b","score":61.4,"metric":"percent"},{"benchmark":"vsi-bench","model":"rynnbrain-4b","score":73.7,"metric":"percent"},{"benchmark":"erqa","model":"rynnbrain-4b","score":46,"metric":"percent"},{"benchmark":"robospatialhome","model":"rynnbrain-4b","score":69.7,"metric":"percent"},{"benchmark":"mindcube","model":"rynnbrain-4b","score":54.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"rynnbrain-4b","score":63.9,"metric":"percent"},{"benchmark":"ai2d","model":"rynnbrain-4b","score":84.7,"metric":"percent"},{"benchmark":"chartqa","model":"rynnbrain-4b","score":85.9,"metric":"percent"},{"benchmark":"docvqa","model":"rynnbrain-4b","score":95.5,"metric":"percent"},{"benchmark":"mvbench","model":"rynnbrain-4b","score":70.9,"metric":"percent"},{"benchmark":"realworldqa","model":"rynnbrain-4b","score":69.4,"metric":"percent"},{"benchmark":"infovqa","model":"rynnbrain-4b","score":80.8,"metric":"percent"},{"benchmark":"egoschema","model":"rynnbrain-4b","score":68.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"rynnbrain-4b","score":68.5,"metric":"percent"},{"benchmark":"vsi-bench","model":"rynnbrain-8b","score":71,"metric":"percent"},{"benchmark":"erqa","model":"rynnbrain-8b","score":46.8,"metric":"percent"},{"benchmark":"robospatialhome","model":"rynnbrain-8b","score":73.1,"metric":"percent"},{"benchmark":"mindcube","model":"rynnbrain-8b","score":56.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"rynnbrain-8b","score":59.2,"metric":"percent"},{"benchmark":"ai2d","model":"rynnbrain-8b","score":86.3,"metric":"percent"},{"benchmark":"chartqa","model":"rynnbrain-8b","score":86.5,"metric":"percent"},{"benchmark":"docvqa","model":"rynnbrain-8b","score":96.2,"metric":"percent"},{"benchmark":"mvbench","model":"rynnbrain-8b","score":69.5,"metric":"percent"},{"benchmark":"realworldqa","model":"rynnbrain-8b","score":67.3,"metric":"percent"},{"benchmark":"infovqa","model":"rynnbrain-8b","score":84.6,"metric":"percent"},{"benchmark":"egoschema","model":"rynnbrain-8b","score":69.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"rynnbrain-8b","score":70.7,"metric":"percent"},{"benchmark":"mindcube","model":"mimo-embodied-7b","score":43.1,"metric":"percent"},{"benchmark":"ai2d","model":"mimo-embodied-7b","score":84.2,"metric":"percent"},{"benchmark":"chartqa","model":"mimo-embodied-7b","score":85.2,"metric":"percent"},{"benchmark":"docvqa","model":"mimo-embodied-7b","score":94.9,"metric":"percent"},{"benchmark":"mvbench","model":"mimo-embodied-7b","score":57.9,"metric":"percent"},{"benchmark":"realworldqa","model":"mimo-embodied-7b","score":66.1,"metric":"percent"},{"benchmark":"infovqa","model":"mimo-embodied-7b","score":72,"metric":"percent"},{"benchmark":"egoschema","model":"mimo-embodied-7b","score":58.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"mimo-embodied-7b","score":65,"metric":"percent"},{"benchmark":"vsi-bench","model":"robobrain-2.0-7b","score":36.1,"metric":"percent"},{"benchmark":"erqa","model":"robobrain-2.0-7b","score":36.5,"metric":"percent"},{"benchmark":"robospatialhome","model":"robobrain-2.0-7b","score":54.2,"metric":"percent"},{"benchmark":"mindcube","model":"robobrain-2.0-7b","score":38.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"robobrain-2.0-7b","score":32.5,"metric":"percent"},{"benchmark":"ai2d","model":"robobrain-2.0-7b","score":70.3,"metric":"percent"},{"benchmark":"chartqa","model":"robobrain-2.0-7b","score":82.4,"metric":"percent"},{"benchmark":"docvqa","model":"robobrain-2.0-7b","score":93.1,"metric":"percent"},{"benchmark":"mvbench","model":"robobrain-2.0-7b","score":50.6,"metric":"percent"},{"benchmark":"realworldqa","model":"robobrain-2.0-7b","score":51.2,"metric":"percent"},{"benchmark":"infovqa","model":"robobrain-2.0-7b","score":77.6,"metric":"percent"},{"benchmark":"egoschema","model":"robobrain-2.0-7b","score":54.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"robobrain-2.0-7b","score":52.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"pelican-vl-7b","score":52.8,"metric":"percent"},{"benchmark":"erqa","model":"pelican-vl-7b","score":39.8,"metric":"percent"},{"benchmark":"robospatialhome","model":"pelican-vl-7b","score":57.5,"metric":"percent"},{"benchmark":"mindcube","model":"pelican-vl-7b","score":33.7,"metric":"percent"},{"benchmark":"refspatialbench","model":"pelican-vl-7b","score":22.3,"metric":"percent"},{"benchmark":"ai2d","model":"pelican-vl-7b","score":83.8,"metric":"percent"},{"benchmark":"chartqa","model":"pelican-vl-7b","score":87.5,"metric":"percent"},{"benchmark":"docvqa","model":"pelican-vl-7b","score":94.5,"metric":"percent"},{"benchmark":"mvbench","model":"pelican-vl-7b","score":67.7,"metric":"percent"},{"benchmark":"realworldqa","model":"pelican-vl-7b","score":67.1,"metric":"percent"},{"benchmark":"infovqa","model":"pelican-vl-7b","score":81.1,"metric":"percent"},{"benchmark":"egoschema","model":"pelican-vl-7b","score":73.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"pelican-vl-7b","score":63.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"cosmos-reason2-8b","score":53.7,"metric":"percent"},{"benchmark":"erqa","model":"cosmos-reason2-8b","score":46,"metric":"percent"},{"benchmark":"robospatialhome","model":"cosmos-reason2-8b","score":59,"metric":"percent"},{"benchmark":"mindcube","model":"cosmos-reason2-8b","score":43.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"cosmos-reason2-8b","score":33.1,"metric":"percent"},{"benchmark":"ai2d","model":"cosmos-reason2-8b","score":83,"metric":"percent"},{"benchmark":"chartqa","model":"cosmos-reason2-8b","score":84.3,"metric":"percent"},{"benchmark":"docvqa","model":"cosmos-reason2-8b","score":95,"metric":"percent"},{"benchmark":"mvbench","model":"cosmos-reason2-8b","score":67,"metric":"percent"},{"benchmark":"realworldqa","model":"cosmos-reason2-8b","score":69.3,"metric":"percent"},{"benchmark":"infovqa","model":"cosmos-reason2-8b","score":78.3,"metric":"percent"},{"benchmark":"egoschema","model":"cosmos-reason2-8b","score":63.5,"metric":"percent"},{"benchmark":"videomme-nosub","model":"cosmos-reason2-8b","score":71.9,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-8b-instruct","score":60.3,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-8b-instruct","score":44.8,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-8b-instruct","score":58.2,"metric":"percent"},{"benchmark":"mindcube","model":"qwen3-vl-8b-instruct","score":36,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-8b-instruct","score":53.4,"metric":"percent"},{"benchmark":"docvqa","model":"qwen3-vl-8b-instruct","score":96.4,"metric":"percent"},{"benchmark":"egoschema","model":"qwen3-vl-8b-instruct","score":69.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"tri-21b-think","score":62.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"tri-21b-think","score":56.67,"metric":"percent"},{"benchmark":"mmlu-pro","model":"tri-21b-think","score":74.3,"metric":"percent"},{"benchmark":"hle","model":"tri-21b-think","score":5.52,"metric":"avg@3"},{"benchmark":"livecodebench","model":"tri-21b-think","score":53.7,"metric":"percent"},{"benchmark":"scicode","model":"tri-21b-think","score":21.3,"metric":"percent"},{"benchmark":"mbpp","model":"tri-21b-think","score":87.83,"metric":"percent"},{"benchmark":"humaneval","model":"tri-21b-think","score":84.14,"metric":"percent"},{"benchmark":"ifeval","model":"tri-21b-think","score":84.7,"metric":"percent"},{"benchmark":"ifbench","model":"tri-21b-think","score":56.71,"metric":"percent"},{"benchmark":"tau2-telecom","model":"tri-21b-think","score":81,"metric":"percent"},{"benchmark":"aa-lcr","model":"tri-21b-think","score":11,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"tri-21b-think","score":61.54,"metric":"percent"},{"benchmark":"click","model":"tri-21b-think","score":82.76,"metric":"percent"},{"benchmark":"kobolt","model":"tri-21b-think","score":54,"metric":"percent"},{"benchmark":"csatqa","model":"tri-21b-think","score":68.98,"metric":"percent"},{"benchmark":"kobest","model":"trida-7b","score":74.08,"metric":"percent"},{"benchmark":"kmmlu","model":"trida-7b","score":50.28,"metric":"percent"},{"benchmark":"mmlu","model":"trida-7b","score":67.23,"metric":"percent"},{"benchmark":"bbh","model":"trida-7b","score":52.45,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trida-7b","score":39.37,"metric":"percent"},{"benchmark":"humaneval","model":"trida-7b","score":35.98,"metric":"percent"},{"benchmark":"mbpp-plus","model":"trida-7b","score":50.79,"metric":"percent"},{"benchmark":"gsm8k","model":"trida-7b","score":65.13,"metric":"percent"},{"benchmark":"math500","model":"trida-7b","score":33.6,"metric":"percent"},{"benchmark":"ifeval","model":"trida-7b","score":64.98,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-next-80b-a3b-thinking","score":92.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-next-80b-a3b-thinking","score":82.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-next-80b-a3b-thinking","score":79.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3-next-80b-a3b-thinking","score":97.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b-thinking","score":67,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-oss-120b-medium","score":87.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b-medium","score":79,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b-medium","score":72.7,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-120b-medium","score":96.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b-medium","score":67,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-oss-swallow-120b-rl-v0.1","score":85.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-swallow-120b-rl-v0.1","score":73.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-swallow-120b-rl-v0.1","score":64.1,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-swallow-120b-rl-v0.1","score":98.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-swallow-120b-rl-v0.1","score":72.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-235b-a22b-thinking-2507","score":93.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-a22b-thinking-2507","score":84.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-235b-a22b-thinking-2507","score":80.3,"metric":"percent"},{"benchmark":"math500","model":"qwen3-235b-a22b-thinking-2507","score":98,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-235b-a22b-thinking-2507","score":69.2,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-5-mini","score":93.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5-mini","score":82.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-mini","score":69.2,"metric":"percent"},{"benchmark":"math500","model":"gpt-5-mini","score":97,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5-mini","score":68.6,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-next-80b-a3b-thinking","score":59.5,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-next-80b-a3b-thinking","score":23.2,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-next-80b-a3b-thinking","score":19.7,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-next-80b-a3b-thinking","score":79.7,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-next-80b-a3b-thinking","score":71,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-next-80b-a3b-thinking","score":96,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-next-80b-a3b-thinking","score":92.7,"metric":"percent"},{"benchmark":"jamc-qa","model":"gpt-oss-120b-medium","score":51.6,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"gpt-oss-120b-medium","score":26.3,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"gpt-oss-120b-medium","score":20.7,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"gpt-oss-120b-medium","score":75.6,"metric":"percent"},{"benchmark":"jgpqa","model":"gpt-oss-120b-medium","score":66.3,"metric":"percent"},{"benchmark":"math-100-ja","model":"gpt-oss-120b-medium","score":97,"metric":"percent"},{"benchmark":"jhumaneval","model":"gpt-oss-120b-medium","score":92.5,"metric":"percent"},{"benchmark":"jamc-qa","model":"gpt-oss-swallow-120b-rl-v0.1","score":63,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"gpt-oss-swallow-120b-rl-v0.1","score":26.6,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"gpt-oss-swallow-120b-rl-v0.1","score":22.1,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"gpt-oss-swallow-120b-rl-v0.1","score":77.5,"metric":"percent"},{"benchmark":"jgpqa","model":"gpt-oss-swallow-120b-rl-v0.1","score":70.5,"metric":"percent"},{"benchmark":"math-100-ja","model":"gpt-oss-swallow-120b-rl-v0.1","score":96,"metric":"percent"},{"benchmark":"jhumaneval","model":"gpt-oss-swallow-120b-rl-v0.1","score":93.5,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-235b-a22b-thinking-2507","score":65.9,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-235b-a22b-thinking-2507","score":26,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-235b-a22b-thinking-2507","score":23.4,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-235b-a22b-thinking-2507","score":81.9,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-235b-a22b-thinking-2507","score":73.9,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-235b-a22b-thinking-2507","score":97,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-235b-a22b-thinking-2507","score":93.8,"metric":"percent"},{"benchmark":"jamc-qa","model":"gpt-5-mini","score":70.1,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"gpt-5-mini","score":26.7,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"gpt-5-mini","score":23.9,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"gpt-5-mini","score":80.5,"metric":"percent"},{"benchmark":"jgpqa","model":"gpt-5-mini","score":75,"metric":"percent"},{"benchmark":"math-100-ja","model":"gpt-5-mini","score":96,"metric":"percent"},{"benchmark":"jhumaneval","model":"gpt-5-mini","score":94.5,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-oss-swallow-120b-sft-v0.1","score":87.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-swallow-120b-sft-v0.1","score":77.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-swallow-120b-sft-v0.1","score":71.2,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-swallow-120b-sft-v0.1","score":96.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-swallow-120b-sft-v0.1","score":65.5,"metric":"percent"},{"benchmark":"jamc-qa","model":"gpt-oss-swallow-120b-sft-v0.1","score":58.9,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"gpt-oss-swallow-120b-sft-v0.1","score":27,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"gpt-oss-swallow-120b-sft-v0.1","score":21.6,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"gpt-oss-swallow-120b-sft-v0.1","score":74.7,"metric":"percent"},{"benchmark":"jgpqa","model":"gpt-oss-swallow-120b-sft-v0.1","score":63.6,"metric":"percent"},{"benchmark":"math-100-ja","model":"gpt-oss-swallow-120b-sft-v0.1","score":92.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"gpt-oss-swallow-120b-sft-v0.1","score":92.2,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-27b-it","score":86.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-3-27b-it","score":47.5,"metric":"percent"},{"benchmark":"math500","model":"gemma-3-27b-it","score":88,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-3-27b-it","score":29.8,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-14b-thinking","score":89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-14b-thinking","score":77,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-14b-thinking","score":61.1,"metric":"percent"},{"benchmark":"math500","model":"qwen3-14b-thinking","score":97.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-14b-thinking","score":58.7,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-oss-20b-medium","score":84.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b-medium","score":74.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b-medium","score":63.6,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-20b-medium","score":94.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b-medium","score":63.5,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-oss-swallow-20b-rl-v0.1","score":83.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-swallow-20b-rl-v0.1","score":73.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-swallow-20b-rl-v0.1","score":64.6,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-swallow-20b-rl-v0.1","score":96.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-swallow-20b-rl-v0.1","score":69.7,"metric":"percent"},{"benchmark":"jamc-qa","model":"gemma-3-27b-it","score":48.8,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"gemma-3-27b-it","score":25,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"gemma-3-27b-it","score":23.8,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"gemma-3-27b-it","score":60.9,"metric":"percent"},{"benchmark":"jgpqa","model":"gemma-3-27b-it","score":41.7,"metric":"percent"},{"benchmark":"math-100-ja","model":"gemma-3-27b-it","score":85.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"gemma-3-27b-it","score":79.6,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-14b-thinking","score":45.5,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-14b-thinking","score":22.8,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-14b-thinking","score":22,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-14b-thinking","score":73.7,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-14b-thinking","score":55.6,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-14b-thinking","score":93.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-14b-thinking","score":91,"metric":"percent"},{"benchmark":"jamc-qa","model":"gpt-oss-20b-medium","score":40.3,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"gpt-oss-20b-medium","score":23.9,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"gpt-oss-20b-medium","score":20.8,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"gpt-oss-20b-medium","score":70.2,"metric":"percent"},{"benchmark":"jgpqa","model":"gpt-oss-20b-medium","score":57.1,"metric":"percent"},{"benchmark":"math-100-ja","model":"gpt-oss-20b-medium","score":92.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"gpt-oss-20b-medium","score":92.7,"metric":"percent"},{"benchmark":"jamc-qa","model":"gpt-oss-swallow-20b-rl-v0.1","score":53.3,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"gpt-oss-swallow-20b-rl-v0.1","score":25.1,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"gpt-oss-swallow-20b-rl-v0.1","score":21.3,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"gpt-oss-swallow-20b-rl-v0.1","score":72.2,"metric":"percent"},{"benchmark":"jgpqa","model":"gpt-oss-swallow-20b-rl-v0.1","score":62.9,"metric":"percent"},{"benchmark":"math-100-ja","model":"gpt-oss-swallow-20b-rl-v0.1","score":97,"metric":"percent"},{"benchmark":"jhumaneval","model":"gpt-oss-swallow-20b-rl-v0.1","score":92.4,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-oss-swallow-20b-sft-v0.1","score":81.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-swallow-20b-sft-v0.1","score":73.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-swallow-20b-sft-v0.1","score":63.6,"metric":"percent"},{"benchmark":"math500","model":"gpt-oss-swallow-20b-sft-v0.1","score":94.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-swallow-20b-sft-v0.1","score":61,"metric":"percent"},{"benchmark":"jamc-qa","model":"gpt-oss-swallow-20b-sft-v0.1","score":51.3,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"gpt-oss-swallow-20b-sft-v0.1","score":25.4,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"gpt-oss-swallow-20b-sft-v0.1","score":22,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"gpt-oss-swallow-20b-sft-v0.1","score":69.5,"metric":"percent"},{"benchmark":"jgpqa","model":"gpt-oss-swallow-20b-sft-v0.1","score":57.8,"metric":"percent"},{"benchmark":"math-100-ja","model":"gpt-oss-swallow-20b-sft-v0.1","score":96,"metric":"percent"},{"benchmark":"jhumaneval","model":"gpt-oss-swallow-20b-sft-v0.1","score":90.9,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-think-32b","score":85.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3-think-32b","score":75.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-think-32b","score":59.1,"metric":"percent"},{"benchmark":"math500","model":"olmo-3-think-32b","score":96.2,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-32b","score":59.7,"metric":"percent"},{"benchmark":"hellaswag","model":"qwq-bakeneko-32b","score":90.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwq-bakeneko-32b","score":77.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwq-bakeneko-32b","score":61.1,"metric":"percent"},{"benchmark":"math500","model":"qwq-bakeneko-32b","score":94.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwq-bakeneko-32b","score":51.3,"metric":"percent"},{"benchmark":"hellaswag","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":90.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":78,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":60.6,"metric":"percent"},{"benchmark":"math500","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":96.4,"metric":"percent"},{"benchmark":"livecodebench","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":56.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-30b-a3b","score":88.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b","score":78.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b","score":63.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b","score":96.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b","score":58.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":80.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":67.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":57.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":95.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":64.6,"metric":"percent"},{"benchmark":"jamc-qa","model":"olmo-3-think-32b","score":35.3,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"olmo-3-think-32b","score":17.4,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"olmo-3-think-32b","score":18.6,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"olmo-3-think-32b","score":66.9,"metric":"percent"},{"benchmark":"jgpqa","model":"olmo-3-think-32b","score":54.7,"metric":"percent"},{"benchmark":"math-100-ja","model":"olmo-3-think-32b","score":91.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"olmo-3-think-32b","score":91.5,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwq-bakeneko-32b","score":49.5,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwq-bakeneko-32b","score":23.2,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwq-bakeneko-32b","score":20.7,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwq-bakeneko-32b","score":67.7,"metric":"percent"},{"benchmark":"jgpqa","model":"qwq-bakeneko-32b","score":48.7,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwq-bakeneko-32b","score":85.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwq-bakeneko-32b","score":86.7,"metric":"percent"},{"benchmark":"jamc-qa","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":61.1,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":24.3,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":21.5,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":71.2,"metric":"percent"},{"benchmark":"jgpqa","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":52.7,"metric":"percent"},{"benchmark":"math-100-ja","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":89.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"abeja-qwq32b-reasoning-japanese-v1.0","score":86.6,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-30b-a3b","score":46,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-30b-a3b","score":17,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-30b-a3b","score":21.9,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-30b-a3b","score":73.8,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-30b-a3b","score":55.8,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-30b-a3b","score":96,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-30b-a3b","score":89.9,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":49.6,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":24.3,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":21.3,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":72.9,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":59.6,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":94.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-30b-a3b-rl-v0.2","score":90.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-30b-a3b-base","score":64.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-base","score":50.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-30b-a3b-base","score":38.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3-30b-a3b-base","score":79.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-30b-a3b-base","score":20.1,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":84.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":74.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":61.1,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":92.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":51.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":83.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":71.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":57.1,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":93.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":51.4,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-30b-a3b-base","score":43.8,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-30b-a3b-base","score":12.4,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-30b-a3b-base","score":20.6,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-30b-a3b-base","score":48.5,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-30b-a3b-base","score":34.6,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-30b-a3b-base","score":74.7,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-30b-a3b-base","score":70.2,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":52.8,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":24.8,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":22.9,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":71.3,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":54.7,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":90.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-30b-a3b-cpt-v0.2","score":89.4,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":50.4,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":24.2,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":21.9,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":71.1,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":55.8,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":89.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-30b-a3b-sft-v0.2","score":88.8,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-32b-thinking","score":90.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-32b-thinking","score":77.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-32b-thinking","score":64.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-32b-thinking","score":96.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-32b-thinking","score":60.2,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-32b-rl-v0.2","score":88.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-32b-rl-v0.2","score":77.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-32b-rl-v0.2","score":65.7,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-32b-rl-v0.2","score":97.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-32b-rl-v0.2","score":66.2,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-32b-thinking","score":47.9,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-32b-thinking","score":22.6,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-32b-thinking","score":22,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-32b-thinking","score":74.6,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-32b-thinking","score":57.1,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-32b-thinking","score":94.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-32b-thinking","score":92.3,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-32b-rl-v0.2","score":53.4,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-32b-rl-v0.2","score":25.2,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-32b-rl-v0.2","score":21.9,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-32b-rl-v0.2","score":75.4,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-32b-rl-v0.2","score":60.7,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-32b-rl-v0.2","score":97,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-32b-rl-v0.2","score":93,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-32b-cpt-v0.2","score":89.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-32b-cpt-v0.2","score":76.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-32b-cpt-v0.2","score":63.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-32b-cpt-v0.2","score":95,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-32b-cpt-v0.2","score":55.6,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-32b-sft-v0.2","score":87.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-32b-sft-v0.2","score":75.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-32b-sft-v0.2","score":63.1,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-32b-sft-v0.2","score":96,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-32b-sft-v0.2","score":56.7,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-32b-cpt-v0.2","score":55.1,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-32b-cpt-v0.2","score":25.5,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-32b-cpt-v0.2","score":23.5,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-32b-cpt-v0.2","score":73.5,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-32b-cpt-v0.2","score":57.6,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-32b-cpt-v0.2","score":93.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-32b-cpt-v0.2","score":91,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-32b-sft-v0.2","score":49.3,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-32b-sft-v0.2","score":25.1,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-32b-sft-v0.2","score":21.6,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-32b-sft-v0.2","score":72.3,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-32b-sft-v0.2","score":59.4,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-32b-sft-v0.2","score":96,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-32b-sft-v0.2","score":90.4,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-swallow-8b-instruct-v0.5","score":64.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-swallow-8b-instruct-v0.5","score":39.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-swallow-8b-instruct-v0.5","score":31.8,"metric":"percent"},{"benchmark":"math500","model":"llama-3.1-swallow-8b-instruct-v0.5","score":45.2,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-swallow-8b-instruct-v0.5","score":7.2,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-r1-distill-llama-8b","score":68.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-distill-llama-8b","score":54.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-distill-llama-8b","score":46,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1-distill-llama-8b","score":86.6,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-distill-llama-8b","score":36.4,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-think-7b","score":70.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3-think-7b","score":62.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-think-7b","score":49,"metric":"percent"},{"benchmark":"math500","model":"olmo-3-think-7b","score":93.6,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-7b","score":51,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-8b-thinking","score":85.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b-thinking","score":71.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-8b-thinking","score":56.1,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b-thinking","score":94.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b-thinking","score":52.5,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-8b-rl-v0.2","score":79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-8b-rl-v0.2","score":67.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-8b-rl-v0.2","score":54,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-8b-rl-v0.2","score":93.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-8b-rl-v0.2","score":55.5,"metric":"percent"},{"benchmark":"jamc-qa","model":"llama-3.1-swallow-8b-instruct-v0.5","score":49.6,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"llama-3.1-swallow-8b-instruct-v0.5","score":24.9,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"llama-3.1-swallow-8b-instruct-v0.5","score":22.2,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"llama-3.1-swallow-8b-instruct-v0.5","score":36.9,"metric":"percent"},{"benchmark":"jgpqa","model":"llama-3.1-swallow-8b-instruct-v0.5","score":29.5,"metric":"percent"},{"benchmark":"math-100-ja","model":"llama-3.1-swallow-8b-instruct-v0.5","score":40.4,"metric":"percent"},{"benchmark":"jhumaneval","model":"llama-3.1-swallow-8b-instruct-v0.5","score":58.4,"metric":"percent"},{"benchmark":"jamc-qa","model":"deepseek-r1-distill-llama-8b","score":27.9,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"deepseek-r1-distill-llama-8b","score":9.6,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"deepseek-r1-distill-llama-8b","score":14.4,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"deepseek-r1-distill-llama-8b","score":31.9,"metric":"percent"},{"benchmark":"jgpqa","model":"deepseek-r1-distill-llama-8b","score":31,"metric":"percent"},{"benchmark":"math-100-ja","model":"deepseek-r1-distill-llama-8b","score":55.6,"metric":"percent"},{"benchmark":"jhumaneval","model":"deepseek-r1-distill-llama-8b","score":72.1,"metric":"percent"},{"benchmark":"jamc-qa","model":"olmo-3-think-7b","score":27.6,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"olmo-3-think-7b","score":13.1,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"olmo-3-think-7b","score":14.3,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"olmo-3-think-7b","score":51.2,"metric":"percent"},{"benchmark":"jgpqa","model":"olmo-3-think-7b","score":39.3,"metric":"percent"},{"benchmark":"math-100-ja","model":"olmo-3-think-7b","score":94.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"olmo-3-think-7b","score":88.5,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-8b-thinking","score":39.8,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-8b-thinking","score":20.9,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-8b-thinking","score":20.2,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-8b-thinking","score":69.6,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-8b-thinking","score":49.1,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-8b-thinking","score":92.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-8b-thinking","score":86.9,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-8b-rl-v0.2","score":44.4,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-8b-rl-v0.2","score":23.5,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-8b-rl-v0.2","score":20.4,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-8b-rl-v0.2","score":67.5,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-8b-rl-v0.2","score":52.9,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-8b-rl-v0.2","score":92.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-8b-rl-v0.2","score":88.5,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-8b-base","score":79.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-8b-base","score":42.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-8b-base","score":33.3,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b-base","score":75.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-8b-base","score":16.8,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-8b-cpt-v0.2","score":79.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-8b-cpt-v0.2","score":62.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-8b-cpt-v0.2","score":51.5,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-8b-cpt-v0.2","score":87.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-8b-cpt-v0.2","score":34.1,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-swallow-8b-sft-v0.2","score":79.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-swallow-8b-sft-v0.2","score":66.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-swallow-8b-sft-v0.2","score":54.5,"metric":"percent"},{"benchmark":"math500","model":"qwen3-swallow-8b-sft-v0.2","score":92.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-swallow-8b-sft-v0.2","score":42.2,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-8b-base","score":36.2,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-8b-base","score":17.3,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-8b-base","score":19.3,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-8b-base","score":45.7,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-8b-base","score":32.1,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-8b-base","score":68.7,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-8b-base","score":79.8,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-8b-cpt-v0.2","score":44.9,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-8b-cpt-v0.2","score":23.8,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-8b-cpt-v0.2","score":21.5,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-8b-cpt-v0.2","score":62.8,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-8b-cpt-v0.2","score":40.4,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-8b-cpt-v0.2","score":83.8,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-8b-cpt-v0.2","score":83.3,"metric":"percent"},{"benchmark":"jamc-qa","model":"qwen3-swallow-8b-sft-v0.2","score":43.9,"metric":"percent"},{"benchmark":"wmt20-en-ja","model":"qwen3-swallow-8b-sft-v0.2","score":23.1,"metric":"bleu"},{"benchmark":"wmt20-ja-en","model":"qwen3-swallow-8b-sft-v0.2","score":20.5,"metric":"bleu"},{"benchmark":"mmlu-prox-ja","model":"qwen3-swallow-8b-sft-v0.2","score":65.3,"metric":"percent"},{"benchmark":"jgpqa","model":"qwen3-swallow-8b-sft-v0.2","score":44.6,"metric":"percent"},{"benchmark":"math-100-ja","model":"qwen3-swallow-8b-sft-v0.2","score":92.9,"metric":"percent"},{"benchmark":"jhumaneval","model":"qwen3-swallow-8b-sft-v0.2","score":83,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mistral-ocr-3","score":81.7,"metric":"percent"},{"benchmark":"olmocr-bench","model":"chandra-ocr-0.1.0","score":82,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gemini-3-pro","score":80.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"paddleocr-vl-1.5","score":79.3,"metric":"percent"},{"benchmark":"olmocr-bench","model":"paddleocr-vl","score":79.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"deepseek-ocr-2","score":78.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gemini-3-flash","score":77.5,"metric":"percent"},{"benchmark":"olmocr-bench","model":"gpt-5.2","score":69.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"falcon-ocr","score":80.3,"metric":"percent"},{"benchmark":"omnidocbench","model":"paddleocr-vl-1.5","score":94.37,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"paddleocr-vl-1.5","score":0.025,"metric":"edit_distance"},{"benchmark":"omnidocbench","model":"paddleocr-vl","score":91.76,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"paddleocr-vl","score":0.024,"metric":"edit_distance"},{"benchmark":"omnidocbench","model":"chandra-ocr-0.1.0","score":88.97,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"chandra-ocr-0.1.0","score":0.046,"metric":"edit_distance"},{"benchmark":"omnidocbench","model":"deepseek-ocr-2","score":87.66,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"deepseek-ocr-2","score":0.037,"metric":"edit_distance"},{"benchmark":"omnidocbench","model":"gpt-5.2","score":86.56,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"gpt-5.2","score":0.061,"metric":"edit_distance"},{"benchmark":"omnidocbench","model":"mistral-ocr-3","score":85.2,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"mistral-ocr-3","score":0.053,"metric":"edit_distance"},{"benchmark":"omnidocbench","model":"falcon-ocr","score":88.64,"metric":"percent"},{"benchmark":"omnidocbench-1.5","model":"falcon-ocr","score":0.055,"metric":"edit_distance"},{"benchmark":"gpqa-diamond","model":"omnicoder-9b","score":83.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"omnicoder-9b","score":23.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-9b","score":14.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-4.7","score":33.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-4.5-haiku","score":27,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-8b-thinking","score":91,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen3-vl-8b-thinking","score":86.2,"metric":"percent"},{"benchmark":"refcocog","model":"qwen3-vl-8b-thinking","score":87.8,"metric":"percent"},{"benchmark":"refcoco","model":"egm-8b","score":93.9,"metric":"percent"},{"benchmark":"refcocoplus","model":"egm-8b","score":90.5,"metric":"percent"},{"benchmark":"refcocog","model":"egm-8b","score":90.8,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-235b-a22b-instruct","score":90.4,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen3-vl-235b-a22b-instruct","score":86.4,"metric":"percent"},{"benchmark":"refcocog","model":"qwen3-vl-235b-a22b-instruct","score":90.5,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3-vl-235b-a22b-thinking","score":93.4,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen3-vl-235b-a22b-thinking","score":89.5,"metric":"percent"},{"benchmark":"refcocog","model":"qwen3-vl-235b-a22b-thinking","score":90.4,"metric":"percent"},{"benchmark":"mmmu-med","model":"lingshu-7b","score":54,"metric":"percent"},{"benchmark":"vqa-rad","model":"lingshu-7b","score":77.2,"metric":"percent"},{"benchmark":"slake","model":"lingshu-7b","score":82.4,"metric":"percent"},{"benchmark":"pathvqa","model":"lingshu-7b","score":41.9,"metric":"percent"},{"benchmark":"pmc-vqa","model":"lingshu-7b","score":54.2,"metric":"percent"},{"benchmark":"omnimedvqa","model":"lingshu-7b","score":82.9,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"lingshu-7b","score":26.9,"metric":"percent"},{"benchmark":"mmmu-med","model":"fleming-vl-8b","score":63.3,"metric":"percent"},{"benchmark":"vqa-rad","model":"fleming-vl-8b","score":78.4,"metric":"percent"},{"benchmark":"slake","model":"fleming-vl-8b","score":86.9,"metric":"percent"},{"benchmark":"pathvqa","model":"fleming-vl-8b","score":56.5,"metric":"percent"},{"benchmark":"pmc-vqa","model":"fleming-vl-8b","score":64.3,"metric":"percent"},{"benchmark":"omnimedvqa","model":"fleming-vl-8b","score":88.2,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"fleming-vl-8b","score":21.6,"metric":"percent"},{"benchmark":"mmmu-med","model":"medix-r1-8b","score":63.3,"metric":"percent"},{"benchmark":"vqa-rad","model":"medix-r1-8b","score":75.2,"metric":"percent"},{"benchmark":"slake","model":"medix-r1-8b","score":70.3,"metric":"percent"},{"benchmark":"pathvqa","model":"medix-r1-8b","score":41,"metric":"percent"},{"benchmark":"pmc-vqa","model":"medix-r1-8b","score":55.3,"metric":"percent"},{"benchmark":"omnimedvqa","model":"medix-r1-8b","score":73.8,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"medix-r1-8b","score":24.9,"metric":"percent"},{"benchmark":"mmmu-med","model":"medmo-4b","score":54.6,"metric":"percent"},{"benchmark":"vqa-rad","model":"medmo-4b","score":50.9,"metric":"percent"},{"benchmark":"slake","model":"medmo-4b","score":41,"metric":"percent"},{"benchmark":"pathvqa","model":"medmo-4b","score":42.4,"metric":"percent"},{"benchmark":"pmc-vqa","model":"medmo-4b","score":50.6,"metric":"percent"},{"benchmark":"omnimedvqa","model":"medmo-4b","score":79.7,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"medmo-4b","score":24.8,"metric":"percent"},{"benchmark":"mmmu-med","model":"medmo-8b","score":64.6,"metric":"percent"},{"benchmark":"vqa-rad","model":"medmo-8b","score":72.3,"metric":"percent"},{"benchmark":"slake","model":"medmo-8b","score":70.6,"metric":"percent"},{"benchmark":"pathvqa","model":"medmo-8b","score":56.3,"metric":"percent"},{"benchmark":"pmc-vqa","model":"medmo-8b","score":59.4,"metric":"percent"},{"benchmark":"omnimedvqa","model":"medmo-8b","score":84.8,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"medmo-8b","score":26.2,"metric":"percent"},{"benchmark":"mmmu-med","model":"medmo-4b-next","score":58.7,"metric":"percent"},{"benchmark":"vqa-rad","model":"medmo-4b-next","score":79.7,"metric":"percent"},{"benchmark":"slake","model":"medmo-4b-next","score":78,"metric":"percent"},{"benchmark":"pathvqa","model":"medmo-4b-next","score":73.3,"metric":"percent"},{"benchmark":"pmc-vqa","model":"medmo-4b-next","score":75.7,"metric":"percent"},{"benchmark":"omnimedvqa","model":"medmo-4b-next","score":90.6,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"medmo-4b-next","score":27,"metric":"percent"},{"benchmark":"mmmu-med","model":"medmo-8b-next","score":69.3,"metric":"percent"},{"benchmark":"vqa-rad","model":"medmo-8b-next","score":86.4,"metric":"percent"},{"benchmark":"slake","model":"medmo-8b-next","score":83,"metric":"percent"},{"benchmark":"pathvqa","model":"medmo-8b-next","score":56.3,"metric":"percent"},{"benchmark":"pmc-vqa","model":"medmo-8b-next","score":74.1,"metric":"percent"},{"benchmark":"omnimedvqa","model":"medmo-8b-next","score":93.3,"metric":"percent"},{"benchmark":"medxpertqa-mm","model":"medmo-8b-next","score":42.9,"metric":"percent"},{"benchmark":"mmlu-med","model":"lingshu-7b","score":69.6,"metric":"percent"},{"benchmark":"pubmedqa","model":"lingshu-7b","score":75.8,"metric":"percent"},{"benchmark":"medmcqa","model":"lingshu-7b","score":56.3,"metric":"percent"},{"benchmark":"medqa","model":"lingshu-7b","score":63.5,"metric":"percent"},{"benchmark":"medbullets-op4","model":"lingshu-7b","score":62,"metric":"percent"},{"benchmark":"medbullets-op5","model":"lingshu-7b","score":53.8,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"lingshu-7b","score":16.4,"metric":"percent"},{"benchmark":"mmlu-med","model":"fleming-vl-8b","score":71.8,"metric":"percent"},{"benchmark":"pubmedqa","model":"fleming-vl-8b","score":74,"metric":"percent"},{"benchmark":"medmcqa","model":"fleming-vl-8b","score":51.8,"metric":"percent"},{"benchmark":"medqa","model":"fleming-vl-8b","score":53.7,"metric":"percent"},{"benchmark":"medbullets-op4","model":"fleming-vl-8b","score":40.5,"metric":"percent"},{"benchmark":"medbullets-op5","model":"fleming-vl-8b","score":37.3,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"fleming-vl-8b","score":12.1,"metric":"percent"},{"benchmark":"mmlu-med","model":"medix-r1-8b","score":79,"metric":"percent"},{"benchmark":"pubmedqa","model":"medix-r1-8b","score":73.4,"metric":"percent"},{"benchmark":"medmcqa","model":"medix-r1-8b","score":60.1,"metric":"percent"},{"benchmark":"medqa","model":"medix-r1-8b","score":85.8,"metric":"percent"},{"benchmark":"medbullets-op4","model":"medix-r1-8b","score":55.1,"metric":"percent"},{"benchmark":"medbullets-op5","model":"medix-r1-8b","score":47,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"medix-r1-8b","score":14.4,"metric":"percent"},{"benchmark":"mmlu-med","model":"medmo-4b","score":75.7,"metric":"percent"},{"benchmark":"pubmedqa","model":"medmo-4b","score":78,"metric":"percent"},{"benchmark":"medmcqa","model":"medmo-4b","score":58,"metric":"percent"},{"benchmark":"medqa","model":"medmo-4b","score":78.5,"metric":"percent"},{"benchmark":"medbullets-op4","model":"medmo-4b","score":57.5,"metric":"percent"},{"benchmark":"medbullets-op5","model":"medmo-4b","score":47.7,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"medmo-4b","score":16.4,"metric":"percent"},{"benchmark":"mmlu-med","model":"medmo-8b","score":81,"metric":"percent"},{"benchmark":"pubmedqa","model":"medmo-8b","score":77.6,"metric":"percent"},{"benchmark":"medmcqa","model":"medmo-8b","score":65,"metric":"percent"},{"benchmark":"medqa","model":"medmo-8b","score":84.3,"metric":"percent"},{"benchmark":"medbullets-op4","model":"medmo-8b","score":66.5,"metric":"percent"},{"benchmark":"medbullets-op5","model":"medmo-8b","score":60.2,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"medmo-8b","score":19.9,"metric":"percent"},{"benchmark":"mmlu-med","model":"medmo-4b-next","score":74.8,"metric":"percent"},{"benchmark":"pubmedqa","model":"medmo-4b-next","score":78.2,"metric":"percent"},{"benchmark":"medmcqa","model":"medmo-4b-next","score":58.1,"metric":"percent"},{"benchmark":"medqa","model":"medmo-4b-next","score":78.3,"metric":"percent"},{"benchmark":"medbullets-op4","model":"medmo-4b-next","score":57.4,"metric":"percent"},{"benchmark":"medbullets-op5","model":"medmo-4b-next","score":47.6,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"medmo-4b-next","score":16.5,"metric":"percent"},{"benchmark":"mmlu-med","model":"medmo-8b-next","score":80.2,"metric":"percent"},{"benchmark":"pubmedqa","model":"medmo-8b-next","score":75.6,"metric":"percent"},{"benchmark":"medmcqa","model":"medmo-8b-next","score":62,"metric":"percent"},{"benchmark":"medqa","model":"medmo-8b-next","score":83.8,"metric":"percent"},{"benchmark":"medbullets-op4","model":"medmo-8b-next","score":65.2,"metric":"percent"},{"benchmark":"medbullets-op5","model":"medmo-8b-next","score":57.8,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"medmo-8b-next","score":20.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kanana-1.5-o-9.8b-instruct-2602","score":38.79,"metric":"percent"},{"benchmark":"mmmu-pro","model":"hyperclovax-seed-omni-8b","score":27.34,"metric":"percent"},{"benchmark":"mmmu-pro","model":"minicpm-o-2.6","score":23.24,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2.5-omni-7b","score":38.21,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-4o","score":48.84,"metric":"percent"},{"benchmark":"mathvista-mini","model":"kanana-1.5-o-9.8b-instruct-2602","score":70.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"hyperclovax-seed-omni-8b","score":57.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"minicpm-o-2.6","score":73.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2.5-omni-7b","score":67.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4o","score":63.8,"metric":"percent"},{"benchmark":"mathverse-mini","model":"kanana-1.5-o-9.8b-instruct-2602","score":48.83,"metric":"percent"},{"benchmark":"mathverse-mini","model":"hyperclovax-seed-omni-8b","score":20.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"minicpm-o-2.6","score":34.77,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen2.5-omni-7b","score":36.02,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gpt-4o","score":40.56,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gemini-2.5-pro","score":66.75,"metric":"percent"},{"benchmark":"wemath","model":"kanana-1.5-o-9.8b-instruct-2602","score":33.33,"metric":"percent"},{"benchmark":"wemath","model":"hyperclovax-seed-omni-8b","score":23.9,"metric":"percent"},{"benchmark":"wemath","model":"minicpm-o-2.6","score":26.19,"metric":"percent"},{"benchmark":"wemath","model":"qwen2.5-omni-7b","score":30.19,"metric":"percent"},{"benchmark":"wemath","model":"gpt-4o","score":43.9,"metric":"percent"},{"benchmark":"wemath","model":"gemini-2.5-pro","score":50.57,"metric":"percent"},{"benchmark":"logicvista","model":"kanana-1.5-o-9.8b-instruct-2602","score":47.43,"metric":"percent"},{"benchmark":"logicvista","model":"hyperclovax-seed-omni-8b","score":35.57,"metric":"percent"},{"benchmark":"logicvista","model":"minicpm-o-2.6","score":35.57,"metric":"percent"},{"benchmark":"logicvista","model":"qwen2.5-omni-7b","score":43.4,"metric":"percent"},{"benchmark":"logicvista","model":"gpt-4o","score":53.47,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"kanana-1.5-o-9.8b-instruct-2602","score":83.16,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"hyperclovax-seed-omni-8b","score":68.56,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"minicpm-o-2.6","score":80.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"qwen2.5-omni-7b","score":81.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gpt-4o","score":82.47,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemini-2.5-pro","score":89.78,"metric":"percent"},{"benchmark":"realworldqa","model":"kanana-1.5-o-9.8b-instruct-2602","score":69.41,"metric":"percent"},{"benchmark":"realworldqa","model":"hyperclovax-seed-omni-8b","score":57.25,"metric":"percent"},{"benchmark":"realworldqa","model":"minicpm-o-2.6","score":68,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2.5-omni-7b","score":70.3,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-4o","score":76.73,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-2.5-pro","score":76.99,"metric":"percent"},{"benchmark":"mmstar","model":"kanana-1.5-o-9.8b-instruct-2602","score":63.07,"metric":"percent"},{"benchmark":"mmstar","model":"hyperclovax-seed-omni-8b","score":50.33,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-o-2.6","score":63.3,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2.5-omni-7b","score":64,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4o","score":64.7,"metric":"percent"},{"benchmark":"wildvision","model":"kanana-1.5-o-9.8b-instruct-2602","score":84.4,"metric":"percent"},{"benchmark":"wildvision","model":"hyperclovax-seed-omni-8b","score":37.6,"metric":"percent"},{"benchmark":"wildvision","model":"minicpm-o-2.6","score":36,"metric":"percent"},{"benchmark":"wildvision","model":"qwen2.5-omni-7b","score":64.2,"metric":"percent"},{"benchmark":"wildvision","model":"gpt-4o","score":67.4,"metric":"percent"},{"benchmark":"wildvision","model":"gemini-2.5-pro","score":90.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"kanana-1.5-o-9.8b-instruct-2602","score":52.14,"metric":"percent"},{"benchmark":"hallusionbench","model":"hyperclovax-seed-omni-8b","score":45.87,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-o-2.6","score":51.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2.5-omni-7b","score":46.02,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4o","score":55,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-2.5-pro","score":62.56,"metric":"percent"},{"benchmark":"miabench","model":"kanana-1.5-o-9.8b-instruct-2602","score":92.27,"metric":"percent"},{"benchmark":"miabench","model":"hyperclovax-seed-omni-8b","score":85.25,"metric":"percent"},{"benchmark":"miabench","model":"minicpm-o-2.6","score":84.02,"metric":"percent"},{"benchmark":"miabench","model":"qwen2.5-omni-7b","score":88.76,"metric":"percent"},{"benchmark":"miabench","model":"gpt-4o","score":93.36,"metric":"percent"},{"benchmark":"miabench","model":"gemini-2.5-pro","score":92.25,"metric":"percent"},{"benchmark":"mm-ifeval","model":"kanana-1.5-o-9.8b-instruct-2602","score":63,"metric":"percent"},{"benchmark":"mm-ifeval","model":"hyperclovax-seed-omni-8b","score":50.74,"metric":"percent"},{"benchmark":"mm-ifeval","model":"minicpm-o-2.6","score":45.91,"metric":"percent"},{"benchmark":"mm-ifeval","model":"qwen2.5-omni-7b","score":50.45,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gpt-4o","score":61.53,"metric":"percent"},{"benchmark":"mm-ifeval","model":"gemini-2.5-pro","score":71.94,"metric":"percent"},{"benchmark":"ocrbench","model":"kanana-1.5-o-9.8b-instruct-2602","score":84.2,"metric":"percent"},{"benchmark":"ocrbench","model":"hyperclovax-seed-omni-8b","score":72.5,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-o-2.6","score":88.9,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2.5-omni-7b","score":86.3,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4o","score":81.3,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-2.5-pro","score":86.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"kanana-1.5-o-9.8b-instruct-2602","score":68.35,"metric":"percent"},{"benchmark":"charxiv-dq","model":"hyperclovax-seed-omni-8b","score":63.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"minicpm-o-2.6","score":52.98,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2.5-omni-7b","score":68.18,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4o","score":80.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-2.5-pro","score":91.38,"metric":"percent"},{"benchmark":"charxiv-rq","model":"kanana-1.5-o-9.8b-instruct-2602","score":41.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"hyperclovax-seed-omni-8b","score":26.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-o-2.6","score":32.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2.5-omni-7b","score":34.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4o","score":44.7,"metric":"percent"},{"benchmark":"konet","model":"kanana-1.5-o-9.8b-instruct-2602","score":89.44,"metric":"percent"},{"benchmark":"konet","model":"hyperclovax-seed-omni-8b","score":75.39,"metric":"percent"},{"benchmark":"konet","model":"minicpm-o-2.6","score":25.12,"metric":"percent"},{"benchmark":"konet","model":"qwen2.5-omni-7b","score":57.47,"metric":"percent"},{"benchmark":"konet","model":"gpt-4o","score":79.81,"metric":"percent"},{"benchmark":"konet","model":"gemini-2.5-pro","score":96.17,"metric":"percent"},{"benchmark":"asr-librispeech-clean","model":"kanana-1.5-o-9.8b-instruct-2602","score":1.41,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"hyperclovax-seed-omni-8b","score":1.93,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"minicpm-o-2.6","score":1.7,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"qwen2.5-omni-7b","score":1.74,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"gpt-4o-audio","score":1.39,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"gemini-2.5-pro","score":2.89,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"kanana-1.5-o-9.8b-instruct-2602","score":3.19,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"hyperclovax-seed-omni-8b","score":4.47,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"minicpm-o-2.6","score":4.4,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"qwen2.5-omni-7b","score":3.45,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"gpt-4o-audio","score":3.75,"metric":"wer"},{"benchmark":"voicebench-alpacaeval","model":"kanana-1.5-o-9.8b-instruct-2602","score":4.58,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"hyperclovax-seed-omni-8b","score":3.36,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"minicpm-o-2.6","score":4.42,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"qwen2.5-omni-7b","score":4.5,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"gpt-4o-audio","score":4.78,"metric":"percent"},{"benchmark":"voicebench-alpacaeval","model":"gemini-2.5-pro","score":4.72,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"kanana-1.5-o-9.8b-instruct-2602","score":4.09,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"hyperclovax-seed-omni-8b","score":1.89,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"minicpm-o-2.6","score":4.15,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"qwen2.5-omni-7b","score":3.84,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"gpt-4o-audio","score":4.49,"metric":"percent"},{"benchmark":"voicebench-commoneval","model":"gemini-2.5-pro","score":4.42,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"kanana-1.5-o-9.8b-instruct-2602","score":59.1,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"hyperclovax-seed-omni-8b","score":52.5,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"minicpm-o-2.6","score":60.4,"metric":"percent"},{"benchmark":"voicebench-bbh","model":"qwen2.5-omni-7b","score":66.7,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"kanana-1.5-o-9.8b-instruct-2602","score":51.5,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"hyperclovax-seed-omni-8b","score":25.34,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"minicpm-o-2.6","score":49.25,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"qwen2.5-omni-7b","score":53.5,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-32b-thinking","score":86.33,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-32b-thinking","score":70,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-32b-thinking","score":65.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-32b-thinking","score":64.44,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-32b-thinking","score":69.57,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-32b-thinking","score":32.61,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-32b-thinking","score":15.94,"metric":"percent"},{"benchmark":"aime-2024","model":"gka-primed-hqwen3-32b-reasoner","score":87.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gka-primed-hqwen3-32b-reasoner","score":81.67,"metric":"percent"},{"benchmark":"gpqa","model":"gka-primed-hqwen3-32b-reasoner","score":67.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gka-primed-hqwen3-32b-reasoner","score":70.24,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gka-primed-hqwen3-32b-reasoner","score":66.34,"metric":"percent"},{"benchmark":"ifbench","model":"gka-primed-hqwen3-32b-reasoner","score":48.22,"metric":"percent"},{"benchmark":"scicode","model":"gka-primed-hqwen3-32b-reasoner","score":12.34,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-8b-thinking","score":78.67,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b-thinking","score":71,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3-8b-thinking","score":57.77,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwen3-8b-thinking","score":57.94,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3-8b-thinking","score":66.46,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-8b-thinking","score":31.6,"metric":"percent"},{"benchmark":"scicode","model":"qwen3-8b-thinking","score":10.63,"metric":"percent"},{"benchmark":"aime-2024","model":"gka-primed-hqwen3-8b-reasoner","score":82,"metric":"percent"},{"benchmark":"aime-2025","model":"gka-primed-hqwen3-8b-reasoner","score":73.67,"metric":"percent"},{"benchmark":"gpqa","model":"gka-primed-hqwen3-8b-reasoner","score":61.81,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gka-primed-hqwen3-8b-reasoner","score":63.1,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gka-primed-hqwen3-8b-reasoner","score":62.2,"metric":"percent"},{"benchmark":"ifbench","model":"gka-primed-hqwen3-8b-reasoner","score":38.96,"metric":"percent"},{"benchmark":"scicode","model":"gka-primed-hqwen3-8b-reasoner","score":6.41,"metric":"percent"},{"benchmark":"aime-2024","model":"gdn-primed-hqwen3-8b-reasoner","score":82,"metric":"percent"},{"benchmark":"aime-2025","model":"gdn-primed-hqwen3-8b-reasoner","score":73.33,"metric":"percent"},{"benchmark":"gpqa","model":"gdn-primed-hqwen3-8b-reasoner","score":61.49,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gdn-primed-hqwen3-8b-reasoner","score":62.94,"metric":"percent"},{"benchmark":"bfcl-v3","model":"gdn-primed-hqwen3-8b-reasoner","score":57.44,"metric":"percent"},{"benchmark":"ifbench","model":"gdn-primed-hqwen3-8b-reasoner","score":37.8,"metric":"percent"},{"benchmark":"scicode","model":"gdn-primed-hqwen3-8b-reasoner","score":2.5,"metric":"percent"},{"benchmark":"gaia-text-only","model":"deepseek-v3.2-thinking","score":63.5,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v3.2-thinking","score":67.6,"metric":"percent"},{"benchmark":"seal-0","model":"deepseek-v3.2-thinking","score":38.5,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"deepseek-v3.2-thinking","score":71,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"mirothinker-v1.0-8b","score":66.4,"metric":"percent"},{"benchmark":"browsecomp","model":"mirothinker-v1.0-8b","score":31.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"mirothinker-v1.0-8b","score":40.2,"metric":"percent"},{"benchmark":"hle-with-tools","model":"mirothinker-v1.0-8b","score":21.5,"metric":"avg@3"},{"benchmark":"seal-0","model":"mirothinker-v1.0-8b","score":40.4,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"mirothinker-v1.0-8b","score":60.6,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"toolmind-web-3b","score":67,"metric":"percent"},{"benchmark":"browsecomp","model":"toolmind-web-3b","score":17.4,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"toolmind-web-3b","score":30.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"toolmind-web-3b","score":24.8,"metric":"avg@3"},{"benchmark":"seal-0","model":"toolmind-web-3b","score":47.7,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"toolmind-web-3b","score":75.1,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"toolmind-web-3b","score":37,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"toolmind-web-3b","score":45.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"lightonocr-2-1b","score":77.3,"metric":"percent"},{"benchmark":"olmocr-bench","model":"dots.ocr","score":72.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"sarashina2.2-ocr","score":68.3,"metric":"percent"},{"benchmark":"docmatix","model":"gpt-4o","score":56.8,"metric":"percent"},{"benchmark":"docmatix","model":"o3","score":45.6,"metric":"percent"},{"benchmark":"docmatix","model":"gpt-5.1","score":48.5,"metric":"percent"},{"benchmark":"docmatix","model":"gpt-5.2","score":48.4,"metric":"percent"},{"benchmark":"docmatix","model":"gemini-3.1-pro","score":35.3,"metric":"percent"},{"benchmark":"docmatix","model":"claude-opus-4.6","score":46.2,"metric":"percent"},{"benchmark":"docmatix","model":"kimi-k2.5","score":36.9,"metric":"percent"},{"benchmark":"docmatix","model":"yuan3.0-ultra","score":67.4,"metric":"percent"},{"benchmark":"doc2dial","model":"deepseek-v3","score":31.6,"metric":"percent"},{"benchmark":"quac","model":"deepseek-v3","score":28.9,"metric":"percent"},{"benchmark":"qrecc","model":"deepseek-v3","score":49.3,"metric":"percent"},{"benchmark":"coqa","model":"deepseek-v3","score":77,"metric":"percent"},{"benchmark":"doqa","model":"deepseek-v3","score":26.1,"metric":"percent"},{"benchmark":"convfinqa","model":"deepseek-v3","score":83.5,"metric":"percent"},{"benchmark":"sqa","model":"deepseek-v3","score":82.1,"metric":"percent"},{"benchmark":"topiocqa","model":"deepseek-v3","score":46.7,"metric":"percent"},{"benchmark":"hybridial","model":"deepseek-v3","score":47.4,"metric":"percent"},{"benchmark":"inscit","model":"deepseek-v3","score":32.1,"metric":"percent"},{"benchmark":"doc2dial","model":"gpt-4o","score":32.8,"metric":"percent"},{"benchmark":"quac","model":"gpt-4o","score":26.6,"metric":"percent"},{"benchmark":"qrecc","model":"gpt-4o","score":49.3,"metric":"percent"},{"benchmark":"coqa","model":"gpt-4o","score":76.1,"metric":"percent"},{"benchmark":"doqa","model":"gpt-4o","score":28.8,"metric":"percent"},{"benchmark":"convfinqa","model":"gpt-4o","score":81.9,"metric":"percent"},{"benchmark":"sqa","model":"gpt-4o","score":81.1,"metric":"percent"},{"benchmark":"topiocqa","model":"gpt-4o","score":49.8,"metric":"percent"},{"benchmark":"hybridial","model":"gpt-4o","score":41.3,"metric":"percent"},{"benchmark":"inscit","model":"gpt-4o","score":26.7,"metric":"percent"},{"benchmark":"doc2dial","model":"o3","score":23.1,"metric":"percent"},{"benchmark":"quac","model":"o3","score":20.8,"metric":"percent"},{"benchmark":"qrecc","model":"o3","score":40.4,"metric":"percent"},{"benchmark":"coqa","model":"o3","score":69.4,"metric":"percent"},{"benchmark":"doqa","model":"o3","score":18.6,"metric":"percent"},{"benchmark":"convfinqa","model":"o3","score":67.8,"metric":"percent"},{"benchmark":"sqa","model":"o3","score":86.7,"metric":"percent"},{"benchmark":"topiocqa","model":"o3","score":45.9,"metric":"percent"},{"benchmark":"hybridial","model":"o3","score":41.3,"metric":"percent"},{"benchmark":"inscit","model":"o3","score":26.7,"metric":"percent"},{"benchmark":"doc2dial","model":"deepseek-r1","score":21.5,"metric":"percent"},{"benchmark":"quac","model":"deepseek-r1","score":22.2,"metric":"percent"},{"benchmark":"qrecc","model":"deepseek-r1","score":42.4,"metric":"percent"},{"benchmark":"coqa","model":"deepseek-r1","score":62.5,"metric":"percent"},{"benchmark":"doqa","model":"deepseek-r1","score":24.7,"metric":"percent"},{"benchmark":"convfinqa","model":"deepseek-r1","score":81.5,"metric":"percent"},{"benchmark":"sqa","model":"deepseek-r1","score":82.1,"metric":"percent"},{"benchmark":"topiocqa","model":"deepseek-r1","score":30.7,"metric":"percent"},{"benchmark":"hybridial","model":"deepseek-r1","score":38,"metric":"percent"},{"benchmark":"inscit","model":"deepseek-r1","score":28.7,"metric":"percent"},{"benchmark":"doc2dial","model":"gpt-5.1","score":28.2,"metric":"percent"},{"benchmark":"quac","model":"gpt-5.1","score":23.2,"metric":"percent"},{"benchmark":"qrecc","model":"gpt-5.1","score":45.4,"metric":"percent"},{"benchmark":"coqa","model":"gpt-5.1","score":68.8,"metric":"percent"},{"benchmark":"doqa","model":"gpt-5.1","score":20.9,"metric":"percent"},{"benchmark":"convfinqa","model":"gpt-5.1","score":73.1,"metric":"percent"},{"benchmark":"sqa","model":"gpt-5.1","score":81.3,"metric":"percent"},{"benchmark":"topiocqa","model":"gpt-5.1","score":44.7,"metric":"percent"},{"benchmark":"hybridial","model":"gpt-5.1","score":45.4,"metric":"percent"},{"benchmark":"inscit","model":"gpt-5.1","score":30,"metric":"percent"},{"benchmark":"doc2dial","model":"gpt-5.2","score":30.2,"metric":"percent"},{"benchmark":"quac","model":"gpt-5.2","score":23.1,"metric":"percent"},{"benchmark":"qrecc","model":"gpt-5.2","score":47,"metric":"percent"},{"benchmark":"coqa","model":"gpt-5.2","score":64.8,"metric":"percent"},{"benchmark":"doqa","model":"gpt-5.2","score":25.3,"metric":"percent"},{"benchmark":"convfinqa","model":"gpt-5.2","score":72.3,"metric":"percent"},{"benchmark":"sqa","model":"gpt-5.2","score":79.1,"metric":"percent"},{"benchmark":"topiocqa","model":"gpt-5.2","score":38.3,"metric":"percent"},{"benchmark":"hybridial","model":"gpt-5.2","score":45.3,"metric":"percent"},{"benchmark":"inscit","model":"gpt-5.2","score":30.9,"metric":"percent"},{"benchmark":"doc2dial","model":"gemini-3.1-pro","score":33.1,"metric":"percent"},{"benchmark":"quac","model":"gemini-3.1-pro","score":27.3,"metric":"percent"},{"benchmark":"qrecc","model":"gemini-3.1-pro","score":47,"metric":"percent"},{"benchmark":"coqa","model":"gemini-3.1-pro","score":73.5,"metric":"percent"},{"benchmark":"doqa","model":"gemini-3.1-pro","score":34.2,"metric":"percent"},{"benchmark":"convfinqa","model":"gemini-3.1-pro","score":75.7,"metric":"percent"},{"benchmark":"sqa","model":"gemini-3.1-pro","score":85.5,"metric":"percent"},{"benchmark":"topiocqa","model":"gemini-3.1-pro","score":42.4,"metric":"percent"},{"benchmark":"hybridial","model":"gemini-3.1-pro","score":48.2,"metric":"percent"},{"benchmark":"inscit","model":"gemini-3.1-pro","score":30.3,"metric":"percent"},{"benchmark":"doc2dial","model":"claude-opus-4.6","score":35.3,"metric":"percent"},{"benchmark":"quac","model":"claude-opus-4.6","score":26.6,"metric":"percent"},{"benchmark":"qrecc","model":"claude-opus-4.6","score":49.4,"metric":"percent"},{"benchmark":"coqa","model":"claude-opus-4.6","score":76.4,"metric":"percent"},{"benchmark":"doqa","model":"claude-opus-4.6","score":37.3,"metric":"percent"},{"benchmark":"convfinqa","model":"claude-opus-4.6","score":86.5,"metric":"percent"},{"benchmark":"sqa","model":"claude-opus-4.6","score":85.5,"metric":"percent"},{"benchmark":"topiocqa","model":"claude-opus-4.6","score":50.2,"metric":"percent"},{"benchmark":"hybridial","model":"claude-opus-4.6","score":48.9,"metric":"percent"},{"benchmark":"inscit","model":"claude-opus-4.6","score":33.2,"metric":"percent"},{"benchmark":"doc2dial","model":"kimi-k2.5","score":34.6,"metric":"percent"},{"benchmark":"quac","model":"kimi-k2.5","score":30.9,"metric":"percent"},{"benchmark":"qrecc","model":"kimi-k2.5","score":49.9,"metric":"percent"},{"benchmark":"coqa","model":"kimi-k2.5","score":82.5,"metric":"percent"},{"benchmark":"doqa","model":"kimi-k2.5","score":35.8,"metric":"percent"},{"benchmark":"convfinqa","model":"kimi-k2.5","score":82.3,"metric":"percent"},{"benchmark":"sqa","model":"kimi-k2.5","score":83.6,"metric":"percent"},{"benchmark":"topiocqa","model":"kimi-k2.5","score":50.8,"metric":"percent"},{"benchmark":"hybridial","model":"kimi-k2.5","score":51.1,"metric":"percent"},{"benchmark":"inscit","model":"kimi-k2.5","score":34.4,"metric":"percent"},{"benchmark":"doc2dial","model":"yuan3.0-ultra","score":55.8,"metric":"percent"},{"benchmark":"quac","model":"yuan3.0-ultra","score":54.5,"metric":"percent"},{"benchmark":"qrecc","model":"yuan3.0-ultra","score":57.3,"metric":"percent"},{"benchmark":"coqa","model":"yuan3.0-ultra","score":94.6,"metric":"percent"},{"benchmark":"doqa","model":"yuan3.0-ultra","score":63.4,"metric":"percent"},{"benchmark":"convfinqa","model":"yuan3.0-ultra","score":79.8,"metric":"percent"},{"benchmark":"sqa","model":"yuan3.0-ultra","score":91,"metric":"percent"},{"benchmark":"topiocqa","model":"yuan3.0-ultra","score":72.4,"metric":"percent"},{"benchmark":"hybridial","model":"yuan3.0-ultra","score":72.9,"metric":"percent"},{"benchmark":"inscit","model":"yuan3.0-ultra","score":40,"metric":"percent"},{"benchmark":"tabmwp","model":"gpt-5.1","score":65,"metric":"percent"},{"benchmark":"wtq","model":"gpt-5.1","score":60.8,"metric":"percent"},{"benchmark":"hitab","model":"gpt-5.1","score":77.8,"metric":"percent"},{"benchmark":"tat-qa","model":"gpt-5.1","score":61.4,"metric":"percent"},{"benchmark":"fetaqa","model":"gpt-5.1","score":8.7,"metric":"percent"},{"benchmark":"tabfact","model":"gpt-5.1","score":52.8,"metric":"percent"},{"benchmark":"infotabs","model":"gpt-5.1","score":64.3,"metric":"percent"},{"benchmark":"tabmwp","model":"gpt-5.2","score":67.2,"metric":"percent"},{"benchmark":"wtq","model":"gpt-5.2","score":69.8,"metric":"percent"},{"benchmark":"hitab","model":"gpt-5.2","score":15.8,"metric":"percent"},{"benchmark":"tat-qa","model":"gpt-5.2","score":28,"metric":"percent"},{"benchmark":"fetaqa","model":"gpt-5.2","score":6.2,"metric":"percent"},{"benchmark":"tabfact","model":"gpt-5.2","score":63.5,"metric":"percent"},{"benchmark":"infotabs","model":"gpt-5.2","score":69.3,"metric":"percent"},{"benchmark":"tabmwp","model":"gemini-3.1-pro","score":80.1,"metric":"percent"},{"benchmark":"wtq","model":"gemini-3.1-pro","score":79.6,"metric":"percent"},{"benchmark":"hitab","model":"gemini-3.1-pro","score":48.3,"metric":"percent"},{"benchmark":"tat-qa","model":"gemini-3.1-pro","score":50.5,"metric":"percent"},{"benchmark":"fetaqa","model":"gemini-3.1-pro","score":9.6,"metric":"percent"},{"benchmark":"tabfact","model":"gemini-3.1-pro","score":71.1,"metric":"percent"},{"benchmark":"infotabs","model":"gemini-3.1-pro","score":74.4,"metric":"percent"},{"benchmark":"tabmwp","model":"claude-opus-4.6","score":67.6,"metric":"percent"},{"benchmark":"wtq","model":"claude-opus-4.6","score":76,"metric":"percent"},{"benchmark":"hitab","model":"claude-opus-4.6","score":44.1,"metric":"percent"},{"benchmark":"tat-qa","model":"claude-opus-4.6","score":44.5,"metric":"percent"},{"benchmark":"fetaqa","model":"claude-opus-4.6","score":12,"metric":"percent"},{"benchmark":"tabfact","model":"claude-opus-4.6","score":30.7,"metric":"percent"},{"benchmark":"infotabs","model":"claude-opus-4.6","score":59.6,"metric":"percent"},{"benchmark":"tabmwp","model":"kimi-k2.5","score":95.9,"metric":"percent"},{"benchmark":"wtq","model":"kimi-k2.5","score":79.3,"metric":"percent"},{"benchmark":"hitab","model":"kimi-k2.5","score":63.9,"metric":"percent"},{"benchmark":"tat-qa","model":"kimi-k2.5","score":62.4,"metric":"percent"},{"benchmark":"fetaqa","model":"kimi-k2.5","score":7.4,"metric":"percent"},{"benchmark":"tabfact","model":"kimi-k2.5","score":90.6,"metric":"percent"},{"benchmark":"infotabs","model":"kimi-k2.5","score":81.8,"metric":"percent"},{"benchmark":"tabmwp","model":"yuan3.0-ultra","score":91.8,"metric":"percent"},{"benchmark":"wtq","model":"yuan3.0-ultra","score":77.9,"metric":"percent"},{"benchmark":"hitab","model":"yuan3.0-ultra","score":67.6,"metric":"percent"},{"benchmark":"tat-qa","model":"yuan3.0-ultra","score":74.9,"metric":"percent"},{"benchmark":"fetaqa","model":"yuan3.0-ultra","score":39.2,"metric":"percent"},{"benchmark":"tabfact","model":"yuan3.0-ultra","score":90.4,"metric":"percent"},{"benchmark":"infotabs","model":"yuan3.0-ultra","score":89.7,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"qwen3-235b-a22b","score":77,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"qwen3-235b-a22b","score":40.1,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"claude-3.7-sonnet","score":78.4,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"claude-3.7-sonnet","score":48.4,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"gpt-5.2","score":76.2,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"gpt-5.2","score":24.6,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"gemini-3.1-pro","score":84.9,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"gemini-3.1-pro","score":60.3,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"claude-opus-4.6","score":78.9,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"claude-opus-4.6","score":59.8,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"kimi-k2.5","score":78.6,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kimi-k2.5","score":48.6,"metric":"percent"},{"benchmark":"bfcl-v3-live","model":"yuan3.0-ultra","score":74.5,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"yuan3.0-ultra","score":45.3,"metric":"percent"},{"benchmark":"spider","model":"qwen3.5-397b-a17b","score":82.4,"metric":"percent"},{"benchmark":"bird-sql","model":"qwen3.5-397b-a17b","score":39.6,"metric":"percent"},{"benchmark":"spider","model":"deepseek-v3.2","score":80.7,"metric":"percent"},{"benchmark":"bird-sql","model":"deepseek-v3.2","score":38.9,"metric":"percent"},{"benchmark":"spider","model":"kimi-k2.5","score":82.7,"metric":"percent"},{"benchmark":"bird-sql","model":"kimi-k2.5","score":43.5,"metric":"percent"},{"benchmark":"spider","model":"yuan3.0-ultra","score":83.9,"metric":"percent"},{"benchmark":"bird-sql","model":"yuan3.0-ultra","score":39.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"evocua-32b-20260105","score":56.7,"metric":"percent"},{"benchmark":"osworld-verified","model":"deepminer-mano-72b","score":53.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"ui-tars-2","score":53.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"evocua-8b-20260105","score":46.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"opencua-72b","score":45,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen3-vl-flash","score":41.6,"metric":"percent"},{"benchmark":"windows-agent-arena","model":"qwen3-vl-32b-instruct","score":30.9,"metric":"percent"},{"benchmark":"windows-agent-arena","model":"qwen3-vl-32b-thinking","score":42.9,"metric":"percent"},{"benchmark":"windows-agent-arena","model":"ui-tars-2","score":50.6,"metric":"percent"},{"benchmark":"windows-agent-arena","model":"evocua-32b-20260105","score":56.48,"metric":"percent"},{"benchmark":"screenspot-v2","model":"points-gui-g-8b","score":95.7,"metric":"percent"},{"benchmark":"screenspot-v2","model":"mai-ui-8b","score":95.2,"metric":"percent"},{"benchmark":"screenspot-v2","model":"infigui-g1-7b","score":93.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gui-g2-7b","score":93.3,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gui-owl-7b","score":92.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"mai-ui-2b","score":92.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gta1-7b","score":92.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"opencua-7b","score":92.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"points-gui-g-8b","score":59.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-owl-7b","score":54.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"infigui-g1-7b","score":51.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gta1-7b","score":50.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"opencua-7b","score":50,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-g2-7b","score":47.5,"metric":"percent"},{"benchmark":"osworld-g","model":"points-gui-g-8b","score":66,"metric":"percent"},{"benchmark":"osworld-g","model":"gui-owl-7b","score":55.9,"metric":"percent"},{"benchmark":"osworld-g","model":"gta1-7b","score":55.1,"metric":"percent"},{"benchmark":"osworld-g","model":"jedi-7b","score":54.1,"metric":"percent"},{"benchmark":"ui-vision","model":"points-gui-g-8b","score":49.9,"metric":"percent"},{"benchmark":"ui-vision","model":"phi-ground","score":27.2,"metric":"percent"},{"benchmark":"ui-vision","model":"infigui-g1-7b","score":26.1,"metric":"percent"},{"benchmark":"ui-vision","model":"ui-tars-7b","score":17.6,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"gpt-5.4","score":70.1,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"gpt-5.4","score":37.26,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"gpt-5.4","score":53.69,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"gpt-5.4","score":66.29,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"gpt-5.4","score":60,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"gpt-5.4","score":51.8,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"gpt-5.4","score":68.58,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"claude-opus-4.8","score":54.93,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"claude-opus-4.8","score":35.14,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"claude-opus-4.8","score":59.18,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"claude-opus-4.8","score":64.1,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"claude-opus-4.8","score":61.5,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"claude-opus-4.8","score":54.66,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"claude-opus-4.8","score":66.62,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"claude-opus-4.6","score":69.9,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"claude-opus-4.6","score":29.3,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"claude-opus-4.6","score":57.51,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"claude-opus-4.6","score":64.55,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"claude-opus-4.6","score":61.74,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"claude-opus-4.6","score":51.42,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"claude-opus-4.6","score":70.2,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"gemini-3.1-pro","score":59.07,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"gemini-3.1-pro","score":30.21,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"gemini-3.1-pro","score":52.47,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"gemini-3.1-pro","score":59.07,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"gemini-3.1-pro","score":61.4,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"gemini-3.1-pro","score":52.83,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"gemini-3.1-pro","score":66.92,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"claude-sonnet-4.6","score":70,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"claude-sonnet-4.6","score":28.79,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"claude-sonnet-4.6","score":56.98,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"claude-sonnet-4.6","score":64.52,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"claude-sonnet-4.6","score":58.03,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"claude-sonnet-4.6","score":50.78,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"claude-sonnet-4.6","score":63.17,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"deepseek-v4-pro","score":63.27,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"deepseek-v4-pro","score":27.61,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"deepseek-v4-pro","score":51.26,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"deepseek-v4-pro","score":59.44,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"deepseek-v4-pro","score":55.17,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"deepseek-v4-pro","score":50.32,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"deepseek-v4-pro","score":63.7,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"glm-5.1","score":67.6,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"glm-5.1","score":22.46,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"glm-5.1","score":47.32,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"glm-5.1","score":52.07,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"glm-5.1","score":59.1,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"glm-5.1","score":51.5,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"glm-5.1","score":59.13,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"kimi-k2.6","score":65.23,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"kimi-k2.6","score":27.48,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"kimi-k2.6","score":52.54,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"kimi-k2.6","score":58.77,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"kimi-k2.6","score":58.93,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"kimi-k2.6","score":50.2,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"kimi-k2.6","score":60.8,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"minimax-m2.7","score":55.82,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"minimax-m2.7","score":27.3,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"minimax-m2.7","score":41.62,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"minimax-m2.7","score":37.44,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"minimax-m2.7","score":52.4,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"minimax-m2.7","score":50.52,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"minimax-m2.7","score":57.73,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"qwen3.5-35b-a3b","score":57.87,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"qwen3.5-35b-a3b","score":25.98,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"qwen3.5-35b-a3b","score":46.13,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"qwen3.5-35b-a3b","score":47.58,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"qwen3.5-35b-a3b","score":53.18,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"qwen3.5-35b-a3b","score":47.1,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"qwen3.5-35b-a3b","score":56.27,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"qwen3.5-397b-a17b","score":68.31,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"qwen3.5-397b-a17b","score":30.81,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"qwen3.5-397b-a17b","score":55.3,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"qwen3.5-397b-a17b","score":64.44,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"qwen3.5-397b-a17b","score":54.9,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"qwen3.5-397b-a17b","score":48.55,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"qwen3.5-397b-a17b","score":60.85,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"qwen3.6-plus","score":55.28,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"qwen3.6-plus","score":21.94,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"qwen3.6-plus","score":50.58,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"qwen3.6-plus","score":59.08,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"qwen3.6-plus","score":57.65,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"qwen3.6-plus","score":50.78,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"qwen3.6-plus","score":60.33,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"qwen-agentworld-35b-a3b","score":64.79,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"qwen-agentworld-35b-a3b","score":36.69,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"qwen-agentworld-35b-a3b","score":53.96,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"qwen-agentworld-35b-a3b","score":65.63,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"qwen-agentworld-35b-a3b","score":58.17,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"qwen-agentworld-35b-a3b","score":49.55,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"qwen-agentworld-35b-a3b","score":65.92,"metric":"percent"},{"benchmark":"agentworldbench-mcp","model":"qwen-agentworld-397b-a17b","score":68.24,"metric":"percent"},{"benchmark":"agentworldbench-search","model":"qwen-agentworld-397b-a17b","score":37.82,"metric":"percent"},{"benchmark":"agentworldbench-terminal","model":"qwen-agentworld-397b-a17b","score":57.73,"metric":"percent"},{"benchmark":"agentworldbench-swe","model":"qwen-agentworld-397b-a17b","score":68.49,"metric":"percent"},{"benchmark":"agentworldbench-android","model":"qwen-agentworld-397b-a17b","score":60.2,"metric":"percent"},{"benchmark":"agentworldbench-web","model":"qwen-agentworld-397b-a17b","score":50.98,"metric":"percent"},{"benchmark":"agentworldbench-os","model":"qwen-agentworld-397b-a17b","score":67.89,"metric":"percent"},{"benchmark":"browsecomp","model":"nex-n2-mini","score":74.1,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"nex-n2-mini","score":1402,"metric":"elo"},{"benchmark":"toolathlon","model":"nex-n2-mini","score":33.3,"metric":"percent"},{"benchmark":"wildclawbench","model":"nex-n2-mini","score":47.7,"metric":"percent"},{"benchmark":"wide-search","model":"nex-n2-mini","score":62,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"nex-n2-mini","score":50.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nex-n2-mini","score":60.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"nex-n2-mini","score":8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nex-n2-mini","score":74.4,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"nex-n2-mini","score":31.5,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"nex-n2-mini","score":30,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"nex-n2-mini","score":23.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nex-n2-mini","score":82.6,"metric":"percent"},{"benchmark":"ifeval","model":"nex-n2-mini","score":89.1,"metric":"percent"},{"benchmark":"matharena-apex","model":"nex-n2-mini","score":9.4,"metric":"percent"},{"benchmark":"browsecomp","model":"nex-n2-pro","score":83.7,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"nex-n2-pro","score":1585,"metric":"elo"},{"benchmark":"toolathlon","model":"nex-n2-pro","score":51.9,"metric":"percent"},{"benchmark":"wildclawbench","model":"nex-n2-pro","score":53.5,"metric":"percent"},{"benchmark":"wide-search","model":"nex-n2-pro","score":75.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"nex-n2-pro","score":58.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nex-n2-pro","score":75.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"nex-n2-pro","score":33.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nex-n2-pro","score":80.8,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"nex-n2-pro","score":37.9,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"nex-n2-pro","score":32.9,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"nex-n2-pro","score":40,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nex-n2-pro","score":90.7,"metric":"percent"},{"benchmark":"ifeval","model":"nex-n2-pro","score":94,"metric":"percent"},{"benchmark":"matharena-apex","model":"nex-n2-pro","score":36.5,"metric":"percent"},{"benchmark":"wildclawbench","model":"gpt-5.5","score":58.2,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"gpt-5.5","score":44.8,"metric":"percent"},{"benchmark":"wildclawbench","model":"claude-opus-4.7","score":62.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.7","score":69.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-4.7","score":54,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"claude-opus-4.7","score":48.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"claude-opus-4.7","score":38.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k2.6-thinking","score":24,"metric":"percent"},{"benchmark":"wildclawbench","model":"glm-5.1","score":48.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"glm-5.1","score":58.7,"metric":"percent"},{"benchmark":"wildclawbench","model":"deepseek-v4-pro-thinking-max","score":43.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro-thinking-max","score":8,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"qwen3.5-35b-a3b","score":77,"metric":"avg@3"},{"benchmark":"gaia","model":"qwen3.5-35b-a3b","score":59.8,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-35b-a3b","score":37.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.5-35b-a3b","score":24.24,"metric":"percent"},{"benchmark":"hipho","model":"qwen3.5-35b-a3b","score":37,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"qwen3.5-35b-a3b","score":64.5,"metric":"percent"},{"benchmark":"frontierscience-research","model":"qwen3.5-35b-a3b","score":2.5,"metric":"percent"},{"benchmark":"mattools","model":"qwen3.5-35b-a3b","score":21,"metric":"percent"},{"benchmark":"molbench-bind","model":"qwen3.5-35b-a3b","score":46,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.6-35b-a3b","score":67.93,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"qwen3.6-35b-a3b","score":71,"metric":"avg@3"},{"benchmark":"seal-0","model":"qwen3.6-35b-a3b","score":38.74,"metric":"percent"},{"benchmark":"gaia","model":"qwen3.6-35b-a3b","score":78.64,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.6-35b-a3b","score":34.85,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.6-35b-a3b","score":36.2,"metric":"avg@3"},{"benchmark":"hipho","model":"qwen3.6-35b-a3b","score":37.7,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"qwen3.6-35b-a3b","score":60.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"qwen3.6-35b-a3b","score":2.9,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":64.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen3.6-35b-a3b","score":57.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.6-35b-a3b","score":91.3,"metric":"percent"},{"benchmark":"mattools","model":"qwen3.6-35b-a3b","score":15.9,"metric":"percent"},{"benchmark":"molbench-bind","model":"qwen3.6-35b-a3b","score":48.7,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"nex-n2-mini","score":82,"metric":"avg@3"},{"benchmark":"seal-0","model":"nex-n2-mini","score":49.55,"metric":"percent"},{"benchmark":"gaia","model":"nex-n2-mini","score":82.52,"metric":"percent"},{"benchmark":"scicode","model":"nex-n2-mini","score":29.9,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"nex-n2-mini","score":34.85,"metric":"percent"},{"benchmark":"hle-with-tools","model":"nex-n2-mini","score":32,"metric":"avg@3"},{"benchmark":"hipho","model":"nex-n2-mini","score":38.5,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"nex-n2-mini","score":52,"metric":"percent"},{"benchmark":"frontierscience-research","model":"nex-n2-mini","score":5,"metric":"percent"},{"benchmark":"ifbench","model":"nex-n2-mini","score":54.08,"metric":"percent"},{"benchmark":"longbench-v2","model":"nex-n2-mini","score":59.6,"metric":"percent"},{"benchmark":"ifeval","model":"nex-n2-mini","score":88.4,"metric":"percent"},{"benchmark":"vitabench","model":"nex-n2-mini","score":23,"metric":"percent"},{"benchmark":"mattools","model":"nex-n2-mini","score":34.1,"metric":"percent"},{"benchmark":"molbench-bind","model":"nex-n2-mini","score":51.4,"metric":"percent"},{"benchmark":"seal-0","model":"step-3.5-flash-20260204","score":36.94,"metric":"percent"},{"benchmark":"gaia","model":"step-3.5-flash-20260204","score":84.5,"metric":"percent"},{"benchmark":"scicode","model":"step-3.5-flash-20260204","score":40.4,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"step-3.5-flash-20260204","score":54.55,"metric":"percent"},{"benchmark":"hle-with-tools","model":"step-3.5-flash-20260204","score":23.1,"metric":"avg@3"},{"benchmark":"hipho","model":"step-3.5-flash-20260204","score":38.3,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"step-3.5-flash-20260204","score":61,"metric":"percent"},{"benchmark":"frontierscience-research","model":"step-3.5-flash-20260204","score":6.7,"metric":"percent"},{"benchmark":"ifbench","model":"step-3.5-flash-20260204","score":64.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"step-3.5-flash-20260204","score":57.5,"metric":"percent"},{"benchmark":"ifeval","model":"step-3.5-flash-20260204","score":93.53,"metric":"percent"},{"benchmark":"vitabench","model":"step-3.5-flash-20260204","score":30,"metric":"percent"},{"benchmark":"mattools","model":"step-3.5-flash-20260204","score":44.93,"metric":"percent"},{"benchmark":"molbench-bind","model":"step-3.5-flash-20260204","score":45.95,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"kimi-k2.6-thinking","score":90,"metric":"avg@3"},{"benchmark":"seal-0","model":"kimi-k2.6-thinking","score":50.45,"metric":"percent"},{"benchmark":"gaia","model":"kimi-k2.6-thinking","score":80.58,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"kimi-k2.6-thinking","score":62.12,"metric":"percent"},{"benchmark":"hipho","model":"kimi-k2.6-thinking","score":41.1,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"kimi-k2.6-thinking","score":73,"metric":"percent"},{"benchmark":"frontierscience-research","model":"kimi-k2.6-thinking","score":17.9,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.6-thinking","score":71.77,"metric":"percent"},{"benchmark":"longbench-v2","model":"kimi-k2.6-thinking","score":62,"metric":"percent"},{"benchmark":"ifeval","model":"kimi-k2.6-thinking","score":94.45,"metric":"percent"},{"benchmark":"vitabench","model":"kimi-k2.6-thinking","score":35.63,"metric":"percent"},{"benchmark":"mattools","model":"kimi-k2.6-thinking","score":63.8,"metric":"percent"},{"benchmark":"molbench-bind","model":"kimi-k2.6-thinking","score":21.6,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"deepseek-v4-pro-thinking-max","score":90,"metric":"avg@3"},{"benchmark":"seal-0","model":"deepseek-v4-pro-thinking-max","score":54.95,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-v4-pro-thinking-max","score":98.06,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"deepseek-v4-pro-thinking-max","score":63.64,"metric":"percent"},{"benchmark":"hipho","model":"deepseek-v4-pro-thinking-max","score":38.7,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"deepseek-v4-pro-thinking-max","score":76,"metric":"percent"},{"benchmark":"frontierscience-research","model":"deepseek-v4-pro-thinking-max","score":13.3,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-pro-thinking-max","score":73.47,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v4-pro-thinking-max","score":64.3,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v4-pro-thinking-max","score":93.35,"metric":"percent"},{"benchmark":"vitabench","model":"deepseek-v4-pro-thinking-max","score":49.04,"metric":"percent"},{"benchmark":"mattools","model":"deepseek-v4-pro-thinking-max","score":47.1,"metric":"percent"},{"benchmark":"molbench-bind","model":"deepseek-v4-pro-thinking-max","score":37.8,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"gpt-5.5","score":84,"metric":"avg@3"},{"benchmark":"seal-0","model":"gpt-5.5","score":42.34,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.5","score":87.38,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"gpt-5.5","score":72.73,"metric":"percent"},{"benchmark":"hipho","model":"gpt-5.5","score":43.3,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.5","score":78,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.5","score":26.7,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-5.5","score":93.35,"metric":"percent"},{"benchmark":"vitabench","model":"gpt-5.5","score":45,"metric":"percent"},{"benchmark":"mattools","model":"gpt-5.5","score":68.8,"metric":"percent"},{"benchmark":"molbench-bind","model":"gpt-5.5","score":62.2,"metric":"percent"},{"benchmark":"browsecomp","model":"agents-a1","score":75.51,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"agents-a1","score":86,"metric":"avg@3"},{"benchmark":"seal-0","model":"agents-a1","score":56.36,"metric":"percent"},{"benchmark":"gaia","model":"agents-a1","score":96.04,"metric":"percent"},{"benchmark":"scicode","model":"agents-a1","score":44.33,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"agents-a1","score":43.94,"metric":"percent"},{"benchmark":"hle-with-tools","model":"agents-a1","score":47.6,"metric":"avg@3"},{"benchmark":"hipho","model":"agents-a1","score":46.4,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"agents-a1","score":79,"metric":"percent"},{"benchmark":"frontierscience-research","model":"agents-a1","score":40,"metric":"percent"},{"benchmark":"ifbench","model":"agents-a1","score":80.61,"metric":"percent"},{"benchmark":"longbench-v2","model":"agents-a1","score":60.2,"metric":"percent"},{"benchmark":"ifeval","model":"agents-a1","score":94.82,"metric":"percent"},{"benchmark":"vitabench","model":"agents-a1","score":38.75,"metric":"percent"},{"benchmark":"mattools","model":"agents-a1","score":47.1,"metric":"percent"},{"benchmark":"molbench-bind","model":"agents-a1","score":56.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.0-9b","score":43.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.0-9b","score":40.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ornith-1.0-9b","score":69.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"ornith-1.0-9b","score":42.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ornith-1.0-9b","score":52,"metric":"percent"},{"benchmark":"nl2repo","model":"ornith-1.0-9b","score":27.2,"metric":"percent"},{"benchmark":"claw-eval","model":"ornith-1.0-9b","score":63.1,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"ornith-1.0-9b","score":17.9,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"ornith-1.0-9b","score":16.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"ornith-1.0-9b","score":15.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-9b","score":21.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-9b","score":18.9,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.5-9b","score":53.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.5-9b","score":31.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.5-9b","score":39.7,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.5-9b","score":16.2,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-9b","score":53.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"qwen3.5-9b","score":9.2,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"qwen3.5-9b","score":4.3,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"qwen3.5-9b","score":4.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-35b-a3b","score":41.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-35b-a3b","score":38.9,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"qwen3.5-35b-a3b","score":13.2,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"qwen3.5-35b-a3b","score":10.2,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"qwen3.5-35b-a3b","score":9.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-12b-it","score":21,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"gemma-4-12b-it","score":27.6,"metric":"percent"},{"benchmark":"nl2repo","model":"gemma-4-12b-it","score":10.3,"metric":"percent"},{"benchmark":"claw-eval","model":"gemma-4-12b-it","score":32.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-31b-it","score":42.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.0-35b","score":64.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.0-35b","score":62.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ornith-1.0-35b","score":75.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"ornith-1.0-35b","score":50.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ornith-1.0-35b","score":69.3,"metric":"percent"},{"benchmark":"nl2repo","model":"ornith-1.0-35b","score":34.6,"metric":"percent"},{"benchmark":"claw-eval","model":"ornith-1.0-35b","score":69.8,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"ornith-1.0-35b","score":37.1,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"ornith-1.0-35b","score":29.7,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"ornith-1.0-35b","score":27.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":52.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":49.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"qwen3.6-35b-a3b","score":15.5,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"qwen3.6-35b-a3b","score":11.4,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"qwen3.6-35b-a3b","score":13.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-397b-a17b","score":53.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-397b-a17b","score":48.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"qwen3.5-397b-a17b","score":51.6,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.5-397b-a17b","score":36.8,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"qwen3.5-397b-a17b","score":20.4,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"qwen3.5-397b-a17b","score":18.4,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"qwen3.5-397b-a17b","score":18.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.0-397b","score":77.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.0-397b","score":78.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ornith-1.0-397b","score":82.4,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"ornith-1.0-397b","score":62.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ornith-1.0-397b","score":78.9,"metric":"percent"},{"benchmark":"nl2repo","model":"ornith-1.0-397b","score":48.2,"metric":"percent"},{"benchmark":"claw-eval","model":"ornith-1.0-397b","score":77.1,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"ornith-1.0-397b","score":41.2,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"ornith-1.0-397b","score":42.6,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"ornith-1.0-397b","score":39.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.7-max","score":73.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.7-max","score":69.8,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.7-max","score":65.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"minimax-m3","score":64,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro-thinking-max","score":66.5,"metric":"percent"},{"benchmark":"claw-eval","model":"deepseek-v4-pro-thinking-max","score":75.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"claude-opus-4.7","score":70.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.7","score":80.8,"metric":"percent"},{"benchmark":"claw-eval","model":"claude-opus-4.7","score":78.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-opus-4.7","score":40.3,"metric":"percent"},{"benchmark":"swe-atlas-test-writing","model":"claude-opus-4.7","score":38.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.8","score":87.6,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-opus-4.8","score":48.8,"metric":"percent"},{"benchmark":"swe-atlas-refactoring","model":"claude-opus-4.8","score":46.7,"metric":"percent"},{"benchmark":"livecodebench","model":"mellum2-12b-a2.5b-thinking-sft","score":75.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"mellum2-12b-a2.5b-thinking-sft","score":38.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"mellum2-12b-a2.5b-thinking-sft","score":60.5,"metric":"percent"},{"benchmark":"gsm-plus","model":"mellum2-12b-a2.5b-thinking-sft","score":62.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mellum2-12b-a2.5b-thinking-sft","score":84.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mellum2-12b-a2.5b-thinking-sft","score":39.9,"metric":"percent"},{"benchmark":"ifeval","model":"mellum2-12b-a2.5b-thinking-sft","score":69.1,"metric":"percent"},{"benchmark":"mixeval","model":"mellum2-12b-a2.5b-thinking-sft","score":63.4,"metric":"percent"},{"benchmark":"xstest","model":"mellum2-12b-a2.5b-thinking-sft","score":90.8,"metric":"percent"},{"benchmark":"livecodebench","model":"mellum2-12b-a2.5b-thinking","score":69.9,"metric":"percent"},{"benchmark":"bfcl-v4","model":"mellum2-12b-a2.5b-thinking","score":45.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"mellum2-12b-a2.5b-thinking","score":69.4,"metric":"percent"},{"benchmark":"gsm-plus","model":"mellum2-12b-a2.5b-thinking","score":87,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mellum2-12b-a2.5b-thinking","score":86.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mellum2-12b-a2.5b-thinking","score":57.6,"metric":"percent"},{"benchmark":"ifeval","model":"mellum2-12b-a2.5b-thinking","score":76.5,"metric":"percent"},{"benchmark":"mixeval","model":"mellum2-12b-a2.5b-thinking","score":66.9,"metric":"percent"},{"benchmark":"xstest","model":"mellum2-12b-a2.5b-thinking","score":89.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b","score":59.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":42.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.5-4b","score":73.9,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3.5-4b","score":89.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-4b","score":88.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-4b","score":76.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-4b","score":87.1,"metric":"percent"},{"benchmark":"mixeval","model":"qwen3.5-4b","score":71.9,"metric":"percent"},{"benchmark":"xstest","model":"qwen3.5-4b","score":96.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-9b","score":68.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-9b","score":42.7,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.5-9b","score":68.5,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3.5-9b","score":90.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-9b","score":91.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-9b","score":81.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-9b","score":89.8,"metric":"percent"},{"benchmark":"mixeval","model":"qwen3.5-9b","score":76,"metric":"percent"},{"benchmark":"xstest","model":"qwen3.5-9b","score":97.6,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-7b","score":59.8,"metric":"percent"},{"benchmark":"gsm-plus","model":"olmo-3-think-7b","score":88.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"olmo-3-think-7b","score":71.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-think-7b","score":29.3,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-7b","score":84.7,"metric":"percent"},{"benchmark":"mixeval","model":"olmo-3-think-7b","score":67,"metric":"percent"},{"benchmark":"xstest","model":"olmo-3-think-7b","score":93.2,"metric":"percent"},{"benchmark":"livecodebench","model":"ministral-3-14b-reasoning","score":42.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ministral-3-14b-reasoning","score":35.9,"metric":"percent"},{"benchmark":"bfcl-v3","model":"ministral-3-14b-reasoning","score":52.2,"metric":"percent"},{"benchmark":"gsm-plus","model":"ministral-3-14b-reasoning","score":86.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"ministral-3-14b-reasoning","score":84.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-14b-reasoning","score":46,"metric":"percent"},{"benchmark":"ifeval","model":"ministral-3-14b-reasoning","score":59.7,"metric":"percent"},{"benchmark":"mixeval","model":"ministral-3-14b-reasoning","score":70.8,"metric":"percent"},{"benchmark":"xstest","model":"ministral-3-14b-reasoning","score":96.8,"metric":"percent"},{"benchmark":"livecodebench","model":"mellum2-12b-a2.5b-instruct-sft","score":30.9,"metric":"percent"},{"benchmark":"evalplus","model":"mellum2-12b-a2.5b-instruct-sft","score":76.2,"metric":"percent"},{"benchmark":"multipl-e","model":"mellum2-12b-a2.5b-instruct-sft","score":64.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"mellum2-12b-a2.5b-instruct-sft","score":31.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"mellum2-12b-a2.5b-instruct-sft","score":43.1,"metric":"percent"},{"benchmark":"gsm-plus","model":"mellum2-12b-a2.5b-instruct-sft","score":73,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mellum2-12b-a2.5b-instruct-sft","score":77.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mellum2-12b-a2.5b-instruct-sft","score":38.9,"metric":"percent"},{"benchmark":"ifeval","model":"mellum2-12b-a2.5b-instruct-sft","score":69.3,"metric":"percent"},{"benchmark":"mixeval","model":"mellum2-12b-a2.5b-instruct-sft","score":62.9,"metric":"percent"},{"benchmark":"xstest","model":"mellum2-12b-a2.5b-instruct-sft","score":78.3,"metric":"percent"},{"benchmark":"livecodebench","model":"mellum2-12b-a2.5b-instruct","score":37.2,"metric":"percent"},{"benchmark":"evalplus","model":"mellum2-12b-a2.5b-instruct","score":78.4,"metric":"percent"},{"benchmark":"multipl-e","model":"mellum2-12b-a2.5b-instruct","score":67.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"mellum2-12b-a2.5b-instruct","score":44.2,"metric":"percent"},{"benchmark":"bfcl-v3","model":"mellum2-12b-a2.5b-instruct","score":66.3,"metric":"percent"},{"benchmark":"gsm-plus","model":"mellum2-12b-a2.5b-instruct","score":80.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mellum2-12b-a2.5b-instruct","score":78.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mellum2-12b-a2.5b-instruct","score":40.9,"metric":"percent"},{"benchmark":"ifeval","model":"mellum2-12b-a2.5b-instruct","score":75.8,"metric":"percent"},{"benchmark":"mixeval","model":"mellum2-12b-a2.5b-instruct","score":62.2,"metric":"percent"},{"benchmark":"xstest","model":"mellum2-12b-a2.5b-instruct","score":81.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b","score":51,"metric":"percent"},{"benchmark":"evalplus","model":"qwen3.5-4b","score":69.4,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3.5-4b","score":51,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":52,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.5-4b","score":64.1,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3.5-4b","score":85.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.5-4b","score":87.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-4b","score":82.1,"metric":"percent"},{"benchmark":"mixeval","model":"qwen3.5-4b","score":65.9,"metric":"percent"},{"benchmark":"xstest","model":"qwen3.5-4b","score":93.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-9b","score":63.7,"metric":"percent"},{"benchmark":"evalplus","model":"qwen3.5-9b","score":71.8,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3.5-9b","score":67.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-9b","score":60.6,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.5-9b","score":70.5,"metric":"percent"},{"benchmark":"gsm-plus","model":"qwen3.5-9b","score":87.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-9b","score":79.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-9b","score":83.9,"metric":"percent"},{"benchmark":"mixeval","model":"qwen3.5-9b","score":71.1,"metric":"percent"},{"benchmark":"xstest","model":"qwen3.5-9b","score":91.2,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-instruct-7b","score":28.2,"metric":"percent"},{"benchmark":"evalplus","model":"olmo-3-instruct-7b","score":67.3,"metric":"percent"},{"benchmark":"multipl-e","model":"olmo-3-instruct-7b","score":36.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"olmo-3-instruct-7b","score":19.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"olmo-3-instruct-7b","score":41.9,"metric":"percent"},{"benchmark":"gsm-plus","model":"olmo-3-instruct-7b","score":85.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"olmo-3-instruct-7b","score":71.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-instruct-7b","score":40.9,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-instruct-7b","score":83.2,"metric":"percent"},{"benchmark":"mixeval","model":"olmo-3-instruct-7b","score":59.4,"metric":"percent"},{"benchmark":"xstest","model":"olmo-3-instruct-7b","score":91.2,"metric":"percent"},{"benchmark":"livecodebench","model":"ministral-3-14b-instruct","score":42.4,"metric":"percent"},{"benchmark":"evalplus","model":"ministral-3-14b-instruct","score":74.1,"metric":"percent"},{"benchmark":"multipl-e","model":"ministral-3-14b-instruct","score":71.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ministral-3-14b-instruct","score":38.8,"metric":"percent"},{"benchmark":"bfcl-v3","model":"ministral-3-14b-instruct","score":52.7,"metric":"percent"},{"benchmark":"gsm-plus","model":"ministral-3-14b-instruct","score":86.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"ministral-3-14b-instruct","score":85.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-14b-instruct","score":58.6,"metric":"percent"},{"benchmark":"ifeval","model":"ministral-3-14b-instruct","score":67.3,"metric":"percent"},{"benchmark":"mixeval","model":"ministral-3-14b-instruct","score":71.2,"metric":"percent"},{"benchmark":"xstest","model":"ministral-3-14b-instruct","score":96.8,"metric":"percent"},{"benchmark":"livecodebench","model":"seed-coder-8b-instruct","score":28.1,"metric":"percent"},{"benchmark":"evalplus","model":"seed-coder-8b-instruct","score":73.8,"metric":"percent"},{"benchmark":"multipl-e","model":"seed-coder-8b-instruct","score":77,"metric":"percent"},{"benchmark":"gsm-plus","model":"seed-coder-8b-instruct","score":50.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"seed-coder-8b-instruct","score":38.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"seed-coder-8b-instruct","score":20.2,"metric":"percent"},{"benchmark":"ifeval","model":"seed-coder-8b-instruct","score":56.2,"metric":"percent"},{"benchmark":"mixeval","model":"seed-coder-8b-instruct","score":37.2,"metric":"percent"},{"benchmark":"xstest","model":"seed-coder-8b-instruct","score":86.3,"metric":"percent"},{"benchmark":"aime-2025","model":"smollm3-3b","score":36.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"smollm3-3b","score":41,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"smollm3-3b","score":26,"metric":"percent"},{"benchmark":"brumo25","model":"smollm3-3b","score":49.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"smollm3-3b","score":28.7,"metric":"percent"},{"benchmark":"livecodebench","model":"smollm3-3b","score":29.1,"metric":"percent"},{"benchmark":"ojbench","model":"smollm3-3b","score":5.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"smollm3-3b","score":41.7,"metric":"percent"},{"benchmark":"ifeval","model":"smollm3-3b","score":71.2,"metric":"percent"},{"benchmark":"ifbench","model":"smollm3-3b","score":27.6,"metric":"percent"},{"benchmark":"aime-2025","model":"hunyuan-4b-instruct","score":66.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"hunyuan-4b-instruct","score":57.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"hunyuan-4b-instruct","score":35.2,"metric":"percent"},{"benchmark":"brumo25","model":"hunyuan-4b-instruct","score":62.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"hunyuan-4b-instruct","score":39.6,"metric":"percent"},{"benchmark":"livecodebench","model":"hunyuan-4b-instruct","score":46.8,"metric":"percent"},{"benchmark":"ojbench","model":"hunyuan-4b-instruct","score":12.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hunyuan-4b-instruct","score":61.1,"metric":"percent"},{"benchmark":"ifeval","model":"hunyuan-4b-instruct","score":76.6,"metric":"percent"},{"benchmark":"ifbench","model":"hunyuan-4b-instruct","score":26.5,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-4b-thinking-2507","score":81.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-4b-thinking-2507","score":79,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-4b-thinking-2507","score":55.5,"metric":"percent"},{"benchmark":"brumo25","model":"qwen3-4b-thinking-2507","score":77.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-4b-thinking-2507","score":51.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-thinking-2507","score":55.2,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3-4b-thinking-2507","score":17.9,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-4b-thinking-2507","score":52.9,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-4b","score":79.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-4b","score":84,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3.5-4b","score":73.8,"metric":"percent"},{"benchmark":"brumo25","model":"qwen3.5-4b","score":83.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-4b","score":48.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b","score":62,"metric":"percent"},{"benchmark":"ojbench","model":"qwen3.5-4b","score":23.5,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-7b","score":67.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"olmo-3-think-7b","score":69.1,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"olmo-3-think-7b","score":43.8,"metric":"percent"},{"benchmark":"brumo25","model":"olmo-3-think-7b","score":69,"metric":"percent"},{"benchmark":"imo-answerbench","model":"olmo-3-think-7b","score":49.4,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-7b","score":52.6,"metric":"percent"},{"benchmark":"ojbench","model":"olmo-3-think-7b","score":15.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3-think-7b","score":46.2,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-7b","score":77.9,"metric":"percent"},{"benchmark":"ifbench","model":"olmo-3-think-7b","score":30,"metric":"percent"},{"benchmark":"aime-2025","model":"mimo-7b-rl","score":70.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"mimo-7b-rl","score":76,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"mimo-7b-rl","score":48.5,"metric":"percent"},{"benchmark":"brumo25","model":"mimo-7b-rl","score":79.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"mimo-7b-rl","score":53.9,"metric":"percent"},{"benchmark":"livecodebench","model":"mimo-7b-rl","score":52.2,"metric":"percent"},{"benchmark":"ojbench","model":"mimo-7b-rl","score":20.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-7b-rl","score":60.6,"metric":"percent"},{"benchmark":"ifeval","model":"mimo-7b-rl","score":59.7,"metric":"percent"},{"benchmark":"ifbench","model":"mimo-7b-rl","score":31.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"openreasoning-nemotron-7b","score":80.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"openreasoning-nemotron-7b","score":63.5,"metric":"percent"},{"benchmark":"brumo25","model":"openreasoning-nemotron-7b","score":78.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"openreasoning-nemotron-7b","score":60.6,"metric":"percent"},{"benchmark":"livecodebench","model":"openreasoning-nemotron-7b","score":64.9,"metric":"percent"},{"benchmark":"ojbench","model":"openreasoning-nemotron-7b","score":25.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"openreasoning-nemotron-7b","score":61.1,"metric":"percent"},{"benchmark":"ifeval","model":"openreasoning-nemotron-7b","score":44,"metric":"percent"},{"benchmark":"ifbench","model":"openreasoning-nemotron-7b","score":31.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-12b-it","score":72.9,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemma-4-12b-it","score":63.3,"metric":"percent"},{"benchmark":"brumo25","model":"gemma-4-12b-it","score":80.4,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-12b-it","score":54.9,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-12b-it","score":88.4,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-12b-it","score":45.2,"metric":"percent"},{"benchmark":"aime-2025","model":"phi-4-reasoning-plus","score":68.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"phi-4-reasoning-plus","score":73.6,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"phi-4-reasoning-plus","score":50.3,"metric":"percent"},{"benchmark":"brumo25","model":"phi-4-reasoning-plus","score":66.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"phi-4-reasoning-plus","score":46.2,"metric":"percent"},{"benchmark":"livecodebench","model":"phi-4-reasoning-plus","score":56.8,"metric":"percent"},{"benchmark":"ojbench","model":"phi-4-reasoning-plus","score":14.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"phi-4-reasoning-plus","score":81.9,"metric":"percent"},{"benchmark":"ifeval","model":"phi-4-reasoning-plus","score":84.9,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-3-14b-reasoning","score":82.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ministral-3-14b-reasoning","score":85,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"ministral-3-14b-reasoning","score":67.1,"metric":"percent"},{"benchmark":"brumo25","model":"ministral-3-14b-reasoning","score":86.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"ministral-3-14b-reasoning","score":63.4,"metric":"percent"},{"benchmark":"livecodebench","model":"ministral-3-14b-reasoning","score":66,"metric":"percent"},{"benchmark":"ojbench","model":"ministral-3-14b-reasoning","score":15.1,"metric":"percent"},{"benchmark":"ifeval","model":"ministral-3-14b-reasoning","score":73.9,"metric":"percent"},{"benchmark":"ifbench","model":"ministral-3-14b-reasoning","score":32.3,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b-high","score":91.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-oss-20b-high","score":90.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-oss-20b-high","score":76.7,"metric":"percent"},{"benchmark":"brumo25","model":"gpt-oss-20b-high","score":86.7,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-oss-20b-high","score":61.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-20b-high","score":61,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b-high","score":71.5,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-oss-20b-high","score":92.8,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b-high","score":65,"metric":"percent"},{"benchmark":"aime-2026-i","model":"nemotron-3-nano-30b-a3b","score":90.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nemotron-3-nano-30b-a3b","score":70.4,"metric":"percent"},{"benchmark":"ifeval","model":"nemotron-3-nano-30b-a3b","score":92.8,"metric":"percent"},{"benchmark":"brumo25","model":"glm-4.5-air","score":90,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-air","score":70.7,"metric":"percent"},{"benchmark":"ifeval","model":"glm-4.5-air","score":86.3,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-235b-a22b-thinking-2507","score":83.9,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-235b-a22b-thinking-2507","score":70.5,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-235b-a22b-thinking-2507","score":51.2,"metric":"percent"},{"benchmark":"aime-2025","model":"longcat-flash-thinking","score":90.6,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"longcat-flash-thinking","score":83.7,"metric":"percent"},{"benchmark":"livecodebench","model":"longcat-flash-thinking","score":79.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"longcat-flash-thinking","score":81.5,"metric":"percent"},{"benchmark":"ifeval","model":"longcat-flash-thinking","score":86.9,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-nano-high","score":85.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-5-nano-high","score":75.6,"metric":"percent"},{"benchmark":"brumo25","model":"gpt-5-nano-high","score":80.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5-nano-high","score":71.2,"metric":"percent"},{"benchmark":"aime-2025","model":"vibethinker-3b","score":91.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"vibethinker-3b","score":94.3,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"vibethinker-3b","score":89.3,"metric":"percent"},{"benchmark":"brumo25","model":"vibethinker-3b","score":93.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"vibethinker-3b","score":76.4,"metric":"percent"},{"benchmark":"livecodebench","model":"vibethinker-3b","score":80.2,"metric":"percent"},{"benchmark":"ojbench","model":"vibethinker-3b","score":38.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vibethinker-3b","score":70.2,"metric":"percent"},{"benchmark":"ifeval","model":"vibethinker-3b","score":93.4,"metric":"percent"},{"benchmark":"ifbench","model":"vibethinker-3b","score":74.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-oss-120b-high","score":93.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gpt-oss-120b-high","score":90,"metric":"percent"},{"benchmark":"brumo25","model":"gpt-oss-120b-high","score":92.5,"metric":"percent"},{"benchmark":"ojbench","model":"gpt-oss-120b-high","score":41.5,"metric":"percent"},{"benchmark":"ifbench","model":"mimo-v2-flash","score":64.2,"metric":"percent"},{"benchmark":"ifbench","model":"minimax-m2.7","score":76,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"deepseek-r1-0528","score":79.4,"metric":"percent"},{"benchmark":"brumo25","model":"deepseek-r1-0528","score":92.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"deepseek-r1-0528","score":60.8,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-r1-0528","score":68.7,"metric":"percent"},{"benchmark":"ojbench","model":"deepseek-r1-0528","score":33.6,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-r1-0528","score":79.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v3.2-thinking","score":94.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"deepseek-v3.2-thinking","score":90.2,"metric":"percent"},{"benchmark":"brumo25","model":"deepseek-v3.2-thinking","score":96.7,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3.2-thinking","score":80.8,"metric":"percent"},{"benchmark":"ojbench","model":"deepseek-v3.2-thinking","score":48.4,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v3.2-thinking","score":60.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k2.5-thinking","score":93.3,"metric":"percent"},{"benchmark":"brumo25","model":"kimi-k2.5-thinking","score":98.3,"metric":"percent"},{"benchmark":"ifeval","model":"kimi-k2.5-thinking","score":93.9,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.5-thinking","score":70,"metric":"percent"},{"benchmark":"aime-2025","model":"glm-5","score":96.7,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"glm-5","score":97.9,"metric":"percent"},{"benchmark":"ojbench","model":"glm-5","score":55,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5","score":76.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemini-2.5-flash","score":64.2,"metric":"percent"},{"benchmark":"brumo25","model":"gemini-2.5-flash","score":83.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-flash","score":61.2,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-2.5-flash","score":23.5,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-2.5-flash","score":89.8,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-2.5-flash","score":36.1,"metric":"percent"},{"benchmark":"aime-2025","model":"o3-high","score":88.9,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"o3-high","score":77.5,"metric":"percent"},{"benchmark":"brumo25","model":"o3-high","score":95.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"o3-high","score":61.1,"metric":"percent"},{"benchmark":"ojbench","model":"o3-high","score":25.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o3-high","score":83.3,"metric":"percent"},{"benchmark":"ifeval","model":"o3-high","score":92.1,"metric":"percent"},{"benchmark":"ifbench","model":"o3-high","score":69.3,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemini-2.5-pro","score":82.5,"metric":"percent"},{"benchmark":"brumo25","model":"gemini-2.5-pro","score":90,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-2.5-pro","score":72.5,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-2.5-pro","score":38.9,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-2.5-pro","score":90.8,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"grok-4","score":90,"metric":"percent"},{"benchmark":"brumo25","model":"grok-4","score":95,"metric":"percent"},{"benchmark":"ifeval","model":"grok-4","score":88,"metric":"percent"},{"benchmark":"imo-answerbench","model":"claude-opus-4.5","score":78.5,"metric":"percent"},{"benchmark":"brumo25","model":"gpt-5-high","score":91.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.6-plus","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3-pro","score":91.7,"metric":"percent"},{"benchmark":"brumo25","model":"gemini-3-pro","score":98.3,"metric":"percent"},{"benchmark":"ojbench","model":"gemini-3-pro","score":58.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"zaya1-8b","score":89.1,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"zaya1-8b","score":71.6,"metric":"percent"},{"benchmark":"imo-answerbench","model":"zaya1-8b","score":59.3,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"zaya1-8b","score":32.2,"metric":"percent"},{"benchmark":"livecodebench","model":"zaya1-8b","score":65.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"zaya1-8b","score":71,"metric":"percent"},{"benchmark":"mmlu-pro","model":"zaya1-8b","score":74.2,"metric":"percent"},{"benchmark":"ifeval","model":"zaya1-8b","score":85.58,"metric":"percent"},{"benchmark":"ifbench","model":"zaya1-8b","score":52.56,"metric":"percent"},{"benchmark":"eqbench","model":"zaya1-8b","score":72.95,"metric":"percent"},{"benchmark":"bfcl-v4","model":"zaya1-8b","score":39.22,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-4b-thinking-2507","score":77.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3-4b-thinking-2507","score":60.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3-4b-thinking-2507","score":50.9,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"qwen3-4b-thinking-2507","score":16.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-4b-thinking-2507","score":54.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-4b-thinking-2507","score":66.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-4b-thinking-2507","score":74.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-4b-thinking-2507","score":86.8,"metric":"percent"},{"benchmark":"eqbench","model":"qwen3-4b-thinking-2507","score":79.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3-4b-thinking-2507","score":49.7,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-4b","score":84.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-4b","score":63.6,"metric":"percent"},{"benchmark":"eqbench","model":"qwen3.5-4b","score":79.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":45.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-e4b-it","score":50.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-e4b-it","score":32.1,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-e4b-it","score":27.3,"metric":"percent"},{"benchmark":"matharena-apex-shortlist","model":"gemma-4-e4b-it","score":6.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e4b-it","score":54.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e4b-it","score":57.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-e4b-it","score":70.2,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e4b-it","score":88.5,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":42.67,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-4-e4b-it","score":80.15,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":31.7,"metric":"percent"},{"benchmark":"livecodebench","model":"zaya1-8b","score":63.8,"metric":"percent"},{"benchmark":"ifeval","model":"zaya1-8b","score":85.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"trinity-mini","score":59.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"trinity-mini","score":36.9,"metric":"percent"},{"benchmark":"livecodebench","model":"trinity-mini","score":33.3,"metric":"percent"},{"benchmark":"ifeval","model":"trinity-mini","score":62,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"trinity-mini","score":46.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"trinity-mini","score":70.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"nemotron-3-nano-30b-a3b","score":75.5,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-nano-30b-a3b","score":64.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-nano-30b-a3b","score":75.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-30b-a3b","score":78.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"olmo-3.1-think-32b","score":78.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"olmo-3.1-think-32b","score":50.6,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3.1-think-32b","score":58.3,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3.1-think-32b","score":93.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"olmo-3.1-think-32b","score":59.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3.1-think-32b","score":75.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-next-80b-a3b-thinking","score":90.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3-next-80b-a3b-thinking","score":79.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3-next-80b-a3b-thinking","score":67.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3-next-80b-a3b-thinking","score":88.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-next-80b-a3b-thinking","score":76.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-next-80b-a3b-thinking","score":82.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"intellect-3","score":86.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"intellect-3","score":72.2,"metric":"percent"},{"benchmark":"livecodebench","model":"intellect-3","score":66.8,"metric":"percent"},{"benchmark":"ifeval","model":"intellect-3","score":81.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"intellect-3","score":74.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intellect-3","score":82.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"mistral-small-4-thinking","score":86.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"mistral-small-4-thinking","score":70.6,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-small-4-thinking","score":57.9,"metric":"percent"},{"benchmark":"ifeval","model":"mistral-small-4-thinking","score":84,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mistral-small-4-thinking","score":77.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-4-thinking","score":81.6,"metric":"percent"},{"benchmark":"ai2d","model":"zaya1-vl-8b","score":87.5,"metric":"percent"},{"benchmark":"chartqa","model":"zaya1-vl-8b","score":82.2,"metric":"percent"},{"benchmark":"docvqa","model":"zaya1-vl-8b","score":92.5,"metric":"percent"},{"benchmark":"infovqa","model":"zaya1-vl-8b","score":74,"metric":"percent"},{"benchmark":"textvqa","model":"zaya1-vl-8b","score":74.4,"metric":"percent"},{"benchmark":"ocrbench","model":"zaya1-vl-8b","score":79.8,"metric":"percent"},{"benchmark":"vqav2","model":"zaya1-vl-8b","score":80,"metric":"percent"},{"benchmark":"mathvista-mini","model":"zaya1-vl-8b","score":64,"metric":"percent"},{"benchmark":"mmmu","model":"zaya1-vl-8b","score":46,"metric":"percent"},{"benchmark":"seed-bench-img","model":"zaya1-vl-8b","score":72.7,"metric":"percent"},{"benchmark":"blink","model":"zaya1-vl-8b","score":45.9,"metric":"percent"},{"benchmark":"realworldqa","model":"zaya1-vl-8b","score":65,"metric":"percent"},{"benchmark":"countbenchqa","model":"zaya1-vl-8b","score":88.1,"metric":"percent"},{"benchmark":"pixmocount","model":"zaya1-vl-8b","score":83.1,"metric":"percent"},{"benchmark":"point-bench","model":"zaya1-vl-8b","score":58,"metric":"percent"},{"benchmark":"refcoco","model":"zaya1-vl-8b","score":84.3,"metric":"percent"},{"benchmark":"ai2d","model":"molmoe-1b","score":82.5,"metric":"percent"},{"benchmark":"chartqa","model":"molmoe-1b","score":77.9,"metric":"percent"},{"benchmark":"infovqa","model":"molmoe-1b","score":53.9,"metric":"percent"},{"benchmark":"textvqa","model":"molmoe-1b","score":78.1,"metric":"percent"},{"benchmark":"ocrbench","model":"molmoe-1b","score":55,"metric":"percent"},{"benchmark":"vqav2","model":"molmoe-1b","score":82.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"molmoe-1b","score":39.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"molmoe-1b","score":68.7,"metric":"percent"},{"benchmark":"countbenchqa","model":"molmoe-1b","score":77.4,"metric":"percent"},{"benchmark":"pixmocount","model":"molmoe-1b","score":45.2,"metric":"percent"},{"benchmark":"point-bench","model":"molmoe-1b","score":58,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-2b","score":86.7,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.5-2b","score":79,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-2b","score":83.1,"metric":"percent"},{"benchmark":"vqav2","model":"qwen3.5-2b","score":78.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-2b","score":52.9,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-2b","score":49.2,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-2b","score":61,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-2b","score":69,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3.5-2b","score":84.2,"metric":"percent"},{"benchmark":"pixmocount","model":"qwen3.5-2b","score":65.5,"metric":"percent"},{"benchmark":"point-bench","model":"qwen3.5-2b","score":40.6,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-2b","score":80.1,"metric":"percent"},{"benchmark":"ai2d","model":"internvl3.5-gpt-oss-20b-a4b","score":85.5,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-gpt-oss-20b-a4b","score":87,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-gpt-oss-20b-a4b","score":92.9,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-gpt-oss-20b-a4b","score":78.1,"metric":"percent"},{"benchmark":"textvqa","model":"internvl3.5-gpt-oss-20b-a4b","score":78.5,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3.5-gpt-oss-20b-a4b","score":86.7,"metric":"percent"},{"benchmark":"vqav2","model":"internvl3.5-gpt-oss-20b-a4b","score":78.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl3.5-gpt-oss-20b-a4b","score":73.5,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-gpt-oss-20b-a4b","score":72.6,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internvl3.5-gpt-oss-20b-a4b","score":76.8,"metric":"percent"},{"benchmark":"blink","model":"internvl3.5-gpt-oss-20b-a4b","score":58.9,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-gpt-oss-20b-a4b","score":71.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"internvl3.5-gpt-oss-20b-a4b","score":82.1,"metric":"percent"},{"benchmark":"pixmocount","model":"internvl3.5-gpt-oss-20b-a4b","score":47.3,"metric":"percent"},{"benchmark":"refcoco","model":"internvl3.5-gpt-oss-20b-a4b","score":89.1,"metric":"percent"},{"benchmark":"ai2d","model":"molmo2-4b","score":93.8,"metric":"percent"},{"benchmark":"infovqa","model":"molmo2-4b","score":78.6,"metric":"percent"},{"benchmark":"textvqa","model":"molmo2-4b","score":83.1,"metric":"percent"},{"benchmark":"ocrbench","model":"molmo2-4b","score":62,"metric":"percent"},{"benchmark":"vqav2","model":"molmo2-4b","score":85.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"molmo2-4b","score":56.5,"metric":"percent"},{"benchmark":"mmmu","model":"molmo2-4b","score":48.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"molmo2-4b","score":78,"metric":"percent"},{"benchmark":"blink","model":"molmo2-4b","score":63.5,"metric":"percent"},{"benchmark":"realworldqa","model":"molmo2-4b","score":73.8,"metric":"percent"},{"benchmark":"countbenchqa","model":"molmo2-4b","score":91.2,"metric":"percent"},{"benchmark":"pixmocount","model":"molmo2-4b","score":87,"metric":"percent"},{"benchmark":"point-bench","model":"molmo2-4b","score":68.5,"metric":"percent"},{"benchmark":"ai2d","model":"qwen3.5-4b","score":93.4,"metric":"percent"},{"benchmark":"chartqa","model":"qwen3.5-4b","score":82.4,"metric":"percent"},{"benchmark":"textvqa","model":"qwen3.5-4b","score":81.1,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-4b","score":85.3,"metric":"percent"},{"benchmark":"vqav2","model":"qwen3.5-4b","score":80.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen3.5-4b","score":82.3,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-4b","score":56.9,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen3.5-4b","score":76.6,"metric":"percent"},{"benchmark":"blink","model":"qwen3.5-4b","score":56.8,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-4b","score":74.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"qwen3.5-4b","score":84.8,"metric":"percent"},{"benchmark":"pixmocount","model":"qwen3.5-4b","score":84.2,"metric":"percent"},{"benchmark":"point-bench","model":"qwen3.5-4b","score":64.4,"metric":"percent"},{"benchmark":"refcoco","model":"qwen3.5-4b","score":87.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-30b-a3b-base","score":62.59,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-3-nano-30b-a3b-base","score":91.72,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-3-nano-30b-a3b-base","score":76.09,"metric":"percent"},{"benchmark":"race","model":"nemotron-3-nano-30b-a3b-base","score":88.9,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-3-nano-30b-a3b-base","score":79.27,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-3-nano-30b-a3b-base","score":74.71,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-3-nano-30b-a3b-base","score":92.49,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3-nano-30b-a3b-base","score":84.4,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"nemotron-3-nano-30b-a3b-base","score":73.97,"metric":"percent"},{"benchmark":"mgsm","model":"nemotron-3-nano-30b-a3b-base","score":80.8,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-labs-twotower-30b-a3b-base","score":78.24,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-labs-twotower-30b-a3b-base","score":60.93,"metric":"percent"},{"benchmark":"arc-challenge","model":"nemotron-labs-twotower-30b-a3b-base","score":92.66,"metric":"percent"},{"benchmark":"winogrande","model":"nemotron-labs-twotower-30b-a3b-base","score":76.09,"metric":"percent"},{"benchmark":"race","model":"nemotron-labs-twotower-30b-a3b-base","score":88.9,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-labs-twotower-30b-a3b-base","score":75.58,"metric":"percent"},{"benchmark":"mbpp","model":"nemotron-labs-twotower-30b-a3b-base","score":74.28,"metric":"percent"},{"benchmark":"gsm8k","model":"nemotron-labs-twotower-30b-a3b-base","score":90.14,"metric":"percent"},{"benchmark":"math500","model":"nemotron-labs-twotower-30b-a3b-base","score":80.6,"metric":"percent"},{"benchmark":"global-mmlu-lite","model":"nemotron-labs-twotower-30b-a3b-base","score":73.94,"metric":"percent"},{"benchmark":"mgsm","model":"nemotron-labs-twotower-30b-a3b-base","score":80.4,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"qwen3-32b","score":13.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-32b","score":7.5,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"openthinkeragent-32b","score":41.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"openthinkeragent-32b","score":26.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"openthinkeragent-32b","score":54,"metric":"percent"},{"benchmark":"aider-polyglot","model":"openthinkeragent-32b","score":32.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"minicpm4-8b","score":87.46,"metric":"percent"},{"benchmark":"arc-easy","model":"minicpm4-8b","score":95.06,"metric":"percent"},{"benchmark":"boolq","model":"minicpm4-8b","score":84.89,"metric":"percent"},{"benchmark":"piqa","model":"minicpm4-8b","score":80.52,"metric":"percent"},{"benchmark":"winogrande","model":"minicpm4-8b","score":63.3,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm4-8b","score":80.62,"metric":"percent"},{"benchmark":"c-eval","model":"minicpm4-8b","score":81.36,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm4-8b","score":75.83,"metric":"percent"},{"benchmark":"mmlu-redux","model":"minicpm4-8b","score":77.14,"metric":"percent"},{"benchmark":"bbh","model":"minicpm4-8b","score":76.72,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm4-8b","score":91.51,"metric":"percent"},{"benchmark":"arc-challenge","model":"bitcpm-cann-8b","score":86.1,"metric":"percent"},{"benchmark":"arc-easy","model":"bitcpm-cann-8b","score":93.47,"metric":"percent"},{"benchmark":"boolq","model":"bitcpm-cann-8b","score":83.39,"metric":"percent"},{"benchmark":"piqa","model":"bitcpm-cann-8b","score":78.78,"metric":"percent"},{"benchmark":"winogrande","model":"bitcpm-cann-8b","score":61.17,"metric":"percent"},{"benchmark":"cmmlu","model":"bitcpm-cann-8b","score":78.92,"metric":"percent"},{"benchmark":"c-eval","model":"bitcpm-cann-8b","score":77.5,"metric":"percent"},{"benchmark":"mmlu","model":"bitcpm-cann-8b","score":70.65,"metric":"percent"},{"benchmark":"mmlu-redux","model":"bitcpm-cann-8b","score":69.85,"metric":"percent"},{"benchmark":"bbh","model":"bitcpm-cann-8b","score":70.7,"metric":"percent"},{"benchmark":"gsm8k","model":"bitcpm-cann-8b","score":85.75,"metric":"percent"},{"benchmark":"arc-challenge","model":"bitcpm-cann-3b","score":78.98,"metric":"percent"},{"benchmark":"arc-easy","model":"bitcpm-cann-3b","score":88.36,"metric":"percent"},{"benchmark":"boolq","model":"bitcpm-cann-3b","score":77.89,"metric":"percent"},{"benchmark":"piqa","model":"bitcpm-cann-3b","score":72.69,"metric":"percent"},{"benchmark":"winogrande","model":"bitcpm-cann-3b","score":52.96,"metric":"percent"},{"benchmark":"cmmlu","model":"bitcpm-cann-3b","score":76.53,"metric":"percent"},{"benchmark":"c-eval","model":"bitcpm-cann-3b","score":75.89,"metric":"percent"},{"benchmark":"mmlu","model":"bitcpm-cann-3b","score":64.41,"metric":"percent"},{"benchmark":"mmlu-redux","model":"bitcpm-cann-3b","score":60.07,"metric":"percent"},{"benchmark":"bbh","model":"bitcpm-cann-3b","score":68.3,"metric":"percent"},{"benchmark":"gsm8k","model":"bitcpm-cann-3b","score":79.45,"metric":"percent"},{"benchmark":"arc-challenge","model":"bitcpm-cann-1b","score":67.12,"metric":"percent"},{"benchmark":"arc-easy","model":"bitcpm-cann-1b","score":79.01,"metric":"percent"},{"benchmark":"boolq","model":"bitcpm-cann-1b","score":65.5,"metric":"percent"},{"benchmark":"piqa","model":"bitcpm-cann-1b","score":65.45,"metric":"percent"},{"benchmark":"winogrande","model":"bitcpm-cann-1b","score":53.28,"metric":"percent"},{"benchmark":"cmmlu","model":"bitcpm-cann-1b","score":67.42,"metric":"percent"},{"benchmark":"c-eval","model":"bitcpm-cann-1b","score":65.96,"metric":"percent"},{"benchmark":"mmlu","model":"bitcpm-cann-1b","score":57.71,"metric":"percent"},{"benchmark":"mmlu-redux","model":"bitcpm-cann-1b","score":54.16,"metric":"percent"},{"benchmark":"bbh","model":"bitcpm-cann-1b","score":60.4,"metric":"percent"},{"benchmark":"gsm8k","model":"bitcpm-cann-1b","score":61.56,"metric":"percent"},{"benchmark":"arc-challenge","model":"minicpm4-0.5b","score":51.86,"metric":"percent"},{"benchmark":"arc-easy","model":"minicpm4-0.5b","score":71.78,"metric":"percent"},{"benchmark":"boolq","model":"minicpm4-0.5b","score":62.29,"metric":"percent"},{"benchmark":"piqa","model":"minicpm4-0.5b","score":60.99,"metric":"percent"},{"benchmark":"winogrande","model":"minicpm4-0.5b","score":51.07,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm4-0.5b","score":65.22,"metric":"percent"},{"benchmark":"c-eval","model":"minicpm4-0.5b","score":66.11,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm4-0.5b","score":55.55,"metric":"percent"},{"benchmark":"mmlu-redux","model":"minicpm4-0.5b","score":48,"metric":"percent"},{"benchmark":"bbh","model":"minicpm4-0.5b","score":49.87,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm4-0.5b","score":52.08,"metric":"percent"},{"benchmark":"arc-challenge","model":"bitcpm-cann-0.5b","score":50.51,"metric":"percent"},{"benchmark":"arc-easy","model":"bitcpm-cann-0.5b","score":65.08,"metric":"percent"},{"benchmark":"boolq","model":"bitcpm-cann-0.5b","score":43.55,"metric":"percent"},{"benchmark":"piqa","model":"bitcpm-cann-0.5b","score":58.49,"metric":"percent"},{"benchmark":"winogrande","model":"bitcpm-cann-0.5b","score":51.54,"metric":"percent"},{"benchmark":"cmmlu","model":"bitcpm-cann-0.5b","score":60.49,"metric":"percent"},{"benchmark":"c-eval","model":"bitcpm-cann-0.5b","score":60.74,"metric":"percent"},{"benchmark":"mmlu","model":"bitcpm-cann-0.5b","score":50.73,"metric":"percent"},{"benchmark":"mmlu-redux","model":"bitcpm-cann-0.5b","score":43.79,"metric":"percent"},{"benchmark":"bbh","model":"bitcpm-cann-0.5b","score":47.44,"metric":"percent"},{"benchmark":"gsm8k","model":"bitcpm-cann-0.5b","score":39.42,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"infinity-parser2-pro","score":93.95,"metric":"percent"},{"benchmark":"doclaynet","model":"infinity-parser2-pro","score":64.93,"metric":"percent"},{"benchmark":"d4la","model":"infinity-parser2-pro","score":52.41,"metric":"percent"},{"benchmark":"pubtabnet","model":"infinity-parser2-pro","score":94.76,"metric":"percent"},{"benchmark":"unimernet","model":"infinity-parser2-pro","score":97.7,"metric":"percent"},{"benchmark":"docvqa","model":"infinity-parser2-pro","score":96.43,"metric":"percent"},{"benchmark":"infovqa","model":"infinity-parser2-pro","score":86.26,"metric":"percent"},{"benchmark":"ai2d","model":"infinity-parser2-pro","score":88.89,"metric":"percent"},{"benchmark":"mathvista-mini","model":"infinity-parser2-pro","score":71.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"infinity-parser2-pro","score":87.54,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"infinity-parser2-pro","score":86.43,"metric":"percent"},{"benchmark":"mmmu","model":"infinity-parser2-pro","score":61.89,"metric":"percent"},{"benchmark":"mmstar","model":"infinity-parser2-pro","score":69.66,"metric":"percent"},{"benchmark":"ocrbench","model":"infinity-parser2-pro","score":86.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"infinity-parser2-flash","score":86,"metric":"percent"},{"benchmark":"parsebench","model":"infinity-parser2-flash","score":72.2,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"infinity-parser2-flash","score":91.98,"metric":"percent"},{"benchmark":"doclaynet","model":"infinity-parser2-flash","score":64.97,"metric":"percent"},{"benchmark":"d4la","model":"infinity-parser2-flash","score":46.05,"metric":"percent"},{"benchmark":"pubtabnet","model":"infinity-parser2-flash","score":92.41,"metric":"percent"},{"benchmark":"unimernet","model":"infinity-parser2-flash","score":96.5,"metric":"percent"},{"benchmark":"docvqa","model":"infinity-parser2-flash","score":93.16,"metric":"percent"},{"benchmark":"infovqa","model":"infinity-parser2-flash","score":75.94,"metric":"percent"},{"benchmark":"ai2d","model":"infinity-parser2-flash","score":79.53,"metric":"percent"},{"benchmark":"mathvista-mini","model":"infinity-parser2-flash","score":59.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"infinity-parser2-flash","score":77.92,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"infinity-parser2-flash","score":75.77,"metric":"percent"},{"benchmark":"mmmu","model":"infinity-parser2-flash","score":45.89,"metric":"percent"},{"benchmark":"mmstar","model":"infinity-parser2-flash","score":57.13,"metric":"percent"},{"benchmark":"ocrbench","model":"infinity-parser2-flash","score":81.6,"metric":"percent"},{"benchmark":"olmocr-bench","model":"paddleocr-vl-1.5","score":78.5,"metric":"percent"},{"benchmark":"parsebench","model":"paddleocr-vl-1.5","score":66,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"paddleocr-vl-1.5","score":94.87,"metric":"percent"},{"benchmark":"doclaynet","model":"paddleocr-vl-1.5","score":71.05,"metric":"percent"},{"benchmark":"d4la","model":"paddleocr-vl-1.5","score":50.21,"metric":"percent"},{"benchmark":"pubtabnet","model":"paddleocr-vl-1.5","score":84.6,"metric":"percent"},{"benchmark":"unimernet","model":"paddleocr-vl-1.5","score":95.8,"metric":"percent"},{"benchmark":"olmocr-bench","model":"deepseek-ocr-2","score":76.3,"metric":"percent"},{"benchmark":"parsebench","model":"deepseek-ocr-2","score":41.2,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"deepseek-ocr-2","score":90.17,"metric":"percent"},{"benchmark":"doclaynet","model":"deepseek-ocr-2","score":45.62,"metric":"percent"},{"benchmark":"d4la","model":"deepseek-ocr-2","score":33.03,"metric":"percent"},{"benchmark":"pubtabnet","model":"deepseek-ocr-2","score":89.53,"metric":"percent"},{"benchmark":"unimernet","model":"deepseek-ocr-2","score":79.8,"metric":"percent"},{"benchmark":"docvqa","model":"deepseek-ocr-2","score":43.42,"metric":"percent"},{"benchmark":"infovqa","model":"deepseek-ocr-2","score":22.07,"metric":"percent"},{"benchmark":"ai2d","model":"deepseek-ocr-2","score":37.66,"metric":"percent"},{"benchmark":"ocrbench","model":"deepseek-ocr-2","score":47.2,"metric":"percent"},{"benchmark":"olmocr-bench","model":"mineru2.5","score":75.2,"metric":"percent"},{"benchmark":"parsebench","model":"mineru2.5","score":45.9,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"mineru2.5","score":92.98,"metric":"percent"},{"benchmark":"doclaynet","model":"mineru2.5","score":67.74,"metric":"percent"},{"benchmark":"d4la","model":"mineru2.5","score":51.62,"metric":"percent"},{"benchmark":"pubtabnet","model":"mineru2.5","score":89.07,"metric":"percent"},{"benchmark":"unimernet","model":"mineru2.5","score":96.5,"metric":"percent"},{"benchmark":"parsebench","model":"gemini-3-pro","score":69.1,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"gemini-3-pro","score":92.85,"metric":"percent"},{"benchmark":"pubtabnet","model":"gemini-3-pro","score":91.4,"metric":"percent"},{"benchmark":"unimernet","model":"gemini-3-pro","score":96.4,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-3-pro","score":93.68,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-3-pro","score":85.24,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-3-pro","score":91.87,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-3-pro","score":81.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en-dev","model":"gemini-3-pro","score":90.29,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-3-pro","score":90.98,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-3-pro","score":56,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-3-pro","score":83.78,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-3-pro","score":89.3,"metric":"percent"},{"benchmark":"olmocr-bench","model":"chandra-ocr-2","score":85.9,"metric":"percent"},{"benchmark":"olmocr-bench","model":"olmocr","score":77.4,"metric":"percent"},{"benchmark":"olmocr-bench","model":"got-ocr2.0","score":48.3,"metric":"percent"},{"benchmark":"androidworld","model":"holo3.1-35b-a3b","score":79.3,"metric":"percent"},{"benchmark":"mmlu","model":"hrm-text-1b","score":60.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"hrm-text-1b","score":81.9,"metric":"percent"},{"benchmark":"hellaswag","model":"hrm-text-1b","score":63.4,"metric":"percent"},{"benchmark":"winogrande","model":"hrm-text-1b","score":72.4,"metric":"percent"},{"benchmark":"boolq","model":"hrm-text-1b","score":86.2,"metric":"percent"},{"benchmark":"drop","model":"hrm-text-1b","score":82.2,"metric":"percent"},{"benchmark":"gsm8k","model":"hrm-text-1b","score":84.5,"metric":"percent"},{"benchmark":"math","model":"hrm-text-1b","score":56.2,"metric":"percent"},{"benchmark":"mmlu","model":"huginn-3.5b","score":31.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"huginn-3.5b","score":38.2,"metric":"percent"},{"benchmark":"hellaswag","model":"huginn-3.5b","score":65.2,"metric":"percent"},{"benchmark":"winogrande","model":"huginn-3.5b","score":59.4,"metric":"percent"},{"benchmark":"boolq","model":"huginn-3.5b","score":69.8,"metric":"percent"},{"benchmark":"drop","model":"huginn-3.5b","score":17.8,"metric":"percent"},{"benchmark":"gsm8k","model":"huginn-3.5b","score":34.6,"metric":"percent"},{"benchmark":"math","model":"huginn-3.5b","score":12.6,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-7b","score":65.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-3-7b","score":81.6,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-7b","score":72.7,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-3-7b","score":64.6,"metric":"percent"},{"benchmark":"boolq","model":"olmo-3-7b","score":85.4,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-7b","score":75.5,"metric":"percent"},{"benchmark":"math","model":"olmo-3-7b","score":40,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.2-3b","score":58,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-3b","score":69.1,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.2-3b","score":47.1,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.2-3b","score":52.4,"metric":"percent"},{"benchmark":"boolq","model":"llama-3.2-3b","score":76.2,"metric":"percent"},{"benchmark":"drop","model":"llama-3.2-3b","score":45.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-3b","score":77.7,"metric":"percent"},{"benchmark":"math","model":"llama-3.2-3b","score":48,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-4b","score":59.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-3-4b","score":56.2,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-3-4b","score":77.2,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-3-4b","score":64.7,"metric":"percent"},{"benchmark":"boolq","model":"gemma-3-4b","score":72.3,"metric":"percent"},{"benchmark":"drop","model":"gemma-3-4b","score":60.1,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-4b","score":38.4,"metric":"percent"},{"benchmark":"math","model":"gemma-3-4b","score":24.2,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-2b","score":64.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-2b","score":81,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3.5-2b","score":64.6,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3.5-2b","score":56.7,"metric":"percent"},{"benchmark":"boolq","model":"qwen3.5-2b","score":80.5,"metric":"percent"},{"benchmark":"drop","model":"qwen3.5-2b","score":30.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-2b","score":53,"metric":"percent"},{"benchmark":"math","model":"qwen3.5-2b","score":34.2,"metric":"percent"},{"benchmark":"mmlu","model":"ouro-1.4b","score":67.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"ouro-1.4b","score":60.9,"metric":"percent"},{"benchmark":"hellaswag","model":"ouro-1.4b","score":74.3,"metric":"percent"},{"benchmark":"boolq","model":"ouro-1.4b","score":83.6,"metric":"percent"},{"benchmark":"drop","model":"ouro-1.4b","score":49.7,"metric":"percent"},{"benchmark":"gsm8k","model":"ouro-1.4b","score":78.9,"metric":"percent"},{"benchmark":"math","model":"ouro-1.4b","score":22.4,"metric":"percent"},{"benchmark":"fd-bench-v1.5","model":"tml-interaction-small","score":77.8,"metric":"percent"},{"benchmark":"fd-bench-v3","model":"tml-interaction-small","score":82.8,"metric":"percent"},{"benchmark":"qivd","model":"tml-interaction-small","score":54,"metric":"percent"},{"benchmark":"audio-multichallenge","model":"tml-interaction-small","score":43.4,"metric":"percent"},{"benchmark":"big-bench-audio","model":"tml-interaction-small","score":75.7,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"tml-interaction-small","score":82.1,"metric":"percent"},{"benchmark":"ifeval","model":"tml-interaction-small","score":89.7,"metric":"percent"},{"benchmark":"harmbench","model":"tml-interaction-small","score":99,"metric":"percent"},{"benchmark":"fd-bench-v1.5","model":"gpt-realtime-2.0","score":46.8,"metric":"percent"},{"benchmark":"fd-bench-v3","model":"gpt-realtime-2.0","score":80,"metric":"percent"},{"benchmark":"qivd","model":"gpt-realtime-2.0","score":57.5,"metric":"percent"},{"benchmark":"audio-multichallenge","model":"gpt-realtime-2.0","score":37.6,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-realtime-2.0","score":71.8,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"gpt-realtime-2.0","score":81.7,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-realtime-2.0","score":89.6,"metric":"percent"},{"benchmark":"harmbench","model":"gpt-realtime-2.0","score":99.5,"metric":"percent"},{"benchmark":"fd-bench-v1.5","model":"gpt-realtime-1.5","score":48.3,"metric":"percent"},{"benchmark":"fd-bench-v3","model":"gpt-realtime-1.5","score":77.9,"metric":"percent"},{"benchmark":"qivd","model":"gpt-realtime-1.5","score":41.2,"metric":"percent"},{"benchmark":"audio-multichallenge","model":"gpt-realtime-1.5","score":34.7,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-realtime-1.5","score":81.4,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"gpt-realtime-1.5","score":68.1,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-realtime-1.5","score":87.5,"metric":"percent"},{"benchmark":"harmbench","model":"gpt-realtime-1.5","score":100,"metric":"percent"},{"benchmark":"fd-bench-v1.5","model":"gemini-3.1-flash-live","score":54.3,"metric":"percent"},{"benchmark":"fd-bench-v3","model":"gemini-3.1-flash-live","score":68.5,"metric":"percent"},{"benchmark":"qivd","model":"gemini-3.1-flash-live","score":54.7,"metric":"percent"},{"benchmark":"audio-multichallenge","model":"gemini-3.1-flash-live","score":26.8,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gemini-3.1-flash-live","score":71.3,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"gemini-3.1-flash-live","score":67.6,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-3.1-flash-live","score":85.8,"metric":"percent"},{"benchmark":"harmbench","model":"gemini-3.1-flash-live","score":99,"metric":"percent"},{"benchmark":"fd-bench-v1.5","model":"qwen3.5-omni-plus-realtime","score":39,"metric":"percent"},{"benchmark":"fd-bench-v3","model":"qwen3.5-omni-plus-realtime","score":60,"metric":"percent"},{"benchmark":"qivd","model":"qwen3.5-omni-plus-realtime","score":59,"metric":"percent"},{"benchmark":"big-bench-audio","model":"qwen3.5-omni-plus-realtime","score":73,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"qwen3.5-omni-plus-realtime","score":80.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-omni-plus-realtime","score":83.4,"metric":"percent"},{"benchmark":"harmbench","model":"qwen3.5-omni-plus-realtime","score":99.5,"metric":"percent"},{"benchmark":"fd-bench-v1.5","model":"gpt-realtime-2.0-xhigh","score":47.8,"metric":"percent"},{"benchmark":"fd-bench-v3","model":"gpt-realtime-2.0-xhigh","score":81,"metric":"percent"},{"benchmark":"qivd","model":"gpt-realtime-2.0-xhigh","score":58.2,"metric":"percent"},{"benchmark":"audio-multichallenge","model":"gpt-realtime-2.0-xhigh","score":48.5,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-realtime-2.0-xhigh","score":96.6,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"gpt-realtime-2.0-xhigh","score":83.2,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-realtime-2.0-xhigh","score":95.2,"metric":"percent"},{"benchmark":"harmbench","model":"gpt-realtime-2.0-xhigh","score":100,"metric":"percent"},{"benchmark":"fd-bench-v1.5","model":"gemini-3.1-flash-live-high","score":45.5,"metric":"percent"},{"benchmark":"fd-bench-v3","model":"gemini-3.1-flash-live-high","score":71.4,"metric":"percent"},{"benchmark":"qivd","model":"gemini-3.1-flash-live-high","score":56.1,"metric":"percent"},{"benchmark":"audio-multichallenge","model":"gemini-3.1-flash-live-high","score":36.1,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gemini-3.1-flash-live-high","score":96.6,"metric":"percent"},{"benchmark":"voicebench-ifeval","model":"gemini-3.1-flash-live-high","score":82.8,"metric":"percent"},{"benchmark":"ifeval","model":"gemini-3.1-flash-live-high","score":90,"metric":"percent"},{"benchmark":"harmbench","model":"gemini-3.1-flash-live-high","score":98,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.3-instant","score":75,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.3-instant","score":69.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.3-instant","score":78.5,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.3-instant","score":65.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-5.5-instant","score":81.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-5.5-instant","score":76,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.5-instant","score":85.6,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.5-instant","score":81.2,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"fugu-ultra","score":73.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"fugu-ultra","score":82.1,"metric":"percent"},{"benchmark":"livecodebench","model":"fugu-ultra","score":93.2,"metric":"percent"},{"benchmark":"hle","model":"fugu-ultra","score":50,"metric":"avg@3"},{"benchmark":"charxiv-rq","model":"fugu-ultra","score":86.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"fugu-ultra","score":95.5,"metric":"percent"},{"benchmark":"scicode","model":"fugu-ultra","score":58.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"fugu-ultra","score":20.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"fugu-ultra","score":73.3,"metric":"percent"},{"benchmark":"mrcr-v2","model":"fugu-ultra","score":93.6,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"fugu","score":59,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"fugu","score":80.2,"metric":"percent"},{"benchmark":"livecodebench","model":"fugu","score":92.9,"metric":"percent"},{"benchmark":"hle","model":"fugu","score":47.2,"metric":"avg@3"},{"benchmark":"charxiv-rq","model":"fugu","score":85.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"fugu","score":95.5,"metric":"percent"},{"benchmark":"scicode","model":"fugu","score":60.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"fugu","score":21.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"fugu","score":74.7,"metric":"percent"},{"benchmark":"mrcr-v2","model":"fugu","score":86.6,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-opus-4.8","score":87.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-opus-4.8","score":84.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"claude-opus-4.8","score":20.6,"metric":"percent"},{"benchmark":"mrcr-v2","model":"claude-opus-4.8","score":87.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-3.1-pro","score":88.5,"metric":"percent"},{"benchmark":"tau3-banking","model":"gemini-3.1-pro","score":8.4,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gemini-3.1-pro","score":84.9,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.5","score":85.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"gpt-5.5","score":20.6,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gpt-5.5","score":94.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b","score":79.6,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":93.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-120b","score":74.6,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-120b","score":67,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-oss-120b","score":49,"metric":"percent"},{"benchmark":"tau2-telecom","model":"gpt-oss-120b","score":63.7,"metric":"percent"},{"benchmark":"scicode","model":"gpt-oss-120b","score":41.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-oss-120b","score":62.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-oss-120b","score":24.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-oss-120b","score":43.6,"metric":"percent"},{"benchmark":"hle","model":"hypernova-60b-2602","score":7.3,"metric":"avg@3"},{"benchmark":"mmlu-pro","model":"hypernova-60b-2602","score":74.3,"metric":"percent"},{"benchmark":"aime-2025","model":"hypernova-60b-2602","score":86,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hypernova-60b-2602","score":65.6,"metric":"percent"},{"benchmark":"ifbench","model":"hypernova-60b-2602","score":59.4,"metric":"percent"},{"benchmark":"aa-lcr","model":"hypernova-60b-2602","score":35.7,"metric":"percent"},{"benchmark":"tau2-telecom","model":"hypernova-60b-2602","score":60.5,"metric":"percent"},{"benchmark":"scicode","model":"hypernova-60b-2602","score":33.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"hypernova-60b-2602","score":51.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"hypernova-60b-2602","score":12.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"hypernova-60b-2602","score":26.2,"metric":"percent"},{"benchmark":"hle","model":"hypernova-60b-2605","score":15,"metric":"avg@3"},{"benchmark":"mmlu-pro","model":"hypernova-60b-2605","score":76.8,"metric":"percent"},{"benchmark":"aime-2025","model":"hypernova-60b-2605","score":90,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hypernova-60b-2605","score":71.9,"metric":"percent"},{"benchmark":"ifbench","model":"hypernova-60b-2605","score":66.6,"metric":"percent"},{"benchmark":"aa-lcr","model":"hypernova-60b-2605","score":40.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"hypernova-60b-2605","score":61.7,"metric":"percent"},{"benchmark":"scicode","model":"hypernova-60b-2605","score":36,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"hypernova-60b-2605","score":68.7,"metric":"percent"},{"benchmark":"terminal-bench","model":"hypernova-60b-2605","score":15.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"hypernova-60b-2605","score":34.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nemotron-3-nano-30b-a3b","score":74.04,"metric":"percent"},{"benchmark":"ifbench","model":"nemotron-3-nano-30b-a3b","score":72.31,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"pulsar-16b","score":71.41,"metric":"percent"},{"benchmark":"ifbench","model":"pulsar-16b","score":70.79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"pulsar-16b","score":74.78,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-oss-20b","score":68.99,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-20b","score":68.46,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b","score":76.65,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3-14b-thinking","score":63.63,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3-14b-thinking","score":39.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-14b-thinking","score":85.01,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ministral-3-14b-instruct","score":56.45,"metric":"percent"},{"benchmark":"ifbench","model":"ministral-3-14b-instruct","score":32.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ministral-3-14b-instruct","score":70.09,"metric":"percent"},{"benchmark":"hle","model":"gemma-3-270m-it","score":4,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"gemma-3-270m-it","score":21.21,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-270m-it","score":6.23,"metric":"percent"},{"benchmark":"hle","model":"qwen3-0.6b","score":5.65,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"qwen3-0.6b","score":29.59,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-0.6b","score":38.27,"metric":"percent"},{"benchmark":"hle","model":"littlelamb-0.3b","score":6.12,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"littlelamb-0.3b","score":28.18,"metric":"percent"},{"benchmark":"mmlu-pro","model":"littlelamb-0.3b","score":31.21,"metric":"percent"},{"benchmark":"hle","model":"qwen3-0.6b","score":4.54,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"qwen3-0.6b","score":27.77,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-0.6b","score":25.72,"metric":"percent"},{"benchmark":"hle","model":"littlelamb-0.3b","score":5.37,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"littlelamb-0.3b","score":24.04,"metric":"percent"},{"benchmark":"mmlu-pro","model":"littlelamb-0.3b","score":25.11,"metric":"percent"},{"benchmark":"swe-bench-pro-public","model":"hy3","score":57.9,"metric":"percent"},{"benchmark":"bigcodebench","model":"marin-8b-base","score":21.5,"metric":"pass@1"},{"benchmark":"humaneval","model":"marin-8b-base","score":31.6,"metric":"percent"},{"benchmark":"mbpp","model":"marin-8b-base","score":36.5,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"marin-8b-base","score":15.6,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"marin-8b-base","score":27.6,"metric":"percent"},{"benchmark":"mmlu-stem","model":"marin-8b-base","score":58.1,"metric":"percent"},{"benchmark":"medqa","model":"marin-8b-base","score":47.3,"metric":"percent"},{"benchmark":"sciq","model":"marin-8b-base","score":93.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"marin-8b-base","score":75.3,"metric":"percent"},{"benchmark":"piqa","model":"marin-8b-base","score":85.7,"metric":"percent"},{"benchmark":"socialiqa","model":"marin-8b-base","score":79.8,"metric":"percent"},{"benchmark":"hellaswag","model":"marin-8b-base","score":84,"metric":"percent"},{"benchmark":"winogrande","model":"marin-8b-base","score":88.6,"metric":"percent"},{"benchmark":"lambada","model":"marin-8b-base","score":73.9,"metric":"percent"},{"benchmark":"drop","model":"marin-8b-base","score":73,"metric":"percent"},{"benchmark":"naturalquestions","model":"marin-8b-base","score":42.6,"metric":"percent"},{"benchmark":"squad-v1.1","model":"marin-8b-base","score":93.4,"metric":"percent"},{"benchmark":"bbh","model":"marin-8b-base","score":55.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"marin-8b-base","score":38.8,"metric":"percent"},{"benchmark":"deepmind-math","model":"marin-8b-base","score":20.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"apertus-8b","score":20.9,"metric":"pass@1"},{"benchmark":"humaneval","model":"apertus-8b","score":21.6,"metric":"percent"},{"benchmark":"mbpp","model":"apertus-8b","score":33.5,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"apertus-8b","score":15.5,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"apertus-8b","score":29.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"apertus-8b","score":52.4,"metric":"percent"},{"benchmark":"medqa","model":"apertus-8b","score":47.6,"metric":"percent"},{"benchmark":"sciq","model":"apertus-8b","score":91.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"apertus-8b","score":72.1,"metric":"percent"},{"benchmark":"piqa","model":"apertus-8b","score":80.5,"metric":"percent"},{"benchmark":"socialiqa","model":"apertus-8b","score":76.3,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-8b","score":81,"metric":"percent"},{"benchmark":"winogrande","model":"apertus-8b","score":85.8,"metric":"percent"},{"benchmark":"lambada","model":"apertus-8b","score":70.9,"metric":"percent"},{"benchmark":"drop","model":"apertus-8b","score":37.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"apertus-8b","score":35,"metric":"percent"},{"benchmark":"squad-v1.1","model":"apertus-8b","score":89.6,"metric":"percent"},{"benchmark":"bbh","model":"apertus-8b","score":48.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-8b","score":33.9,"metric":"percent"},{"benchmark":"deepmind-math","model":"apertus-8b","score":17.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"mimo-7b-base","score":38.3,"metric":"pass@1"},{"benchmark":"humaneval","model":"mimo-7b-base","score":57,"metric":"percent"},{"benchmark":"mbpp","model":"mimo-7b-base","score":48.3,"metric":"percent"},{"benchmark":"multipl-e-humaneval","model":"mimo-7b-base","score":34.5,"metric":"percent"},{"benchmark":"multipl-e-mbpp","model":"mimo-7b-base","score":42.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"mimo-7b-base","score":63.5,"metric":"percent"},{"benchmark":"medqa","model":"mimo-7b-base","score":53,"metric":"percent"},{"benchmark":"sciq","model":"mimo-7b-base","score":93.5,"metric":"percent"},{"benchmark":"commonsenseqa","model":"mimo-7b-base","score":76.1,"metric":"percent"},{"benchmark":"piqa","model":"mimo-7b-base","score":87.2,"metric":"percent"},{"benchmark":"socialiqa","model":"mimo-7b-base","score":80.7,"metric":"percent"},{"benchmark":"hellaswag","model":"mimo-7b-base","score":80.6,"metric":"percent"},{"benchmark":"winogrande","model":"mimo-7b-base","score":86.5,"metric":"percent"},{"benchmark":"lambada","model":"mimo-7b-base","score":73.1,"metric":"percent"},{"benchmark":"drop","model":"mimo-7b-base","score":69.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"mimo-7b-base","score":33.1,"metric":"percent"},{"benchmark":"squad-v1.1","model":"mimo-7b-base","score":90.3,"metric":"percent"},{"benchmark":"bbh","model":"mimo-7b-base","score":75.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-7b-base","score":44.3,"metric":"percent"},{"benchmark":"deepmind-math","model":"mimo-7b-base","score":25.4,"metric":"percent"},{"benchmark":"math","model":"apertus-8b-instruct","score":21.9,"metric":"percent"},{"benchmark":"aime-2024","model":"apertus-8b-instruct","score":0.5,"metric":"percent"},{"benchmark":"aime-2025","model":"apertus-8b-instruct","score":0.2,"metric":"percent"},{"benchmark":"omega","model":"apertus-8b-instruct","score":5,"metric":"percent"},{"benchmark":"bbh","model":"apertus-8b-instruct","score":42.2,"metric":"percent"},{"benchmark":"zebralogic","model":"apertus-8b-instruct","score":5.3,"metric":"percent"},{"benchmark":"agieval","model":"apertus-8b-instruct","score":50.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"apertus-8b-instruct","score":34.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"apertus-8b-instruct","score":42.1,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"apertus-8b-instruct","score":7.8,"metric":"percent"},{"benchmark":"ifeval","model":"apertus-8b-instruct","score":71.4,"metric":"percent"},{"benchmark":"ifbench","model":"apertus-8b-instruct","score":22.1,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-8b-instruct","score":62.7,"metric":"percent"},{"benchmark":"popqa","model":"apertus-8b-instruct","score":25.5,"metric":"percent"},{"benchmark":"gpqa","model":"apertus-8b-instruct","score":28.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"apertus-8b-instruct","score":8.1,"metric":"percent"},{"benchmark":"math","model":"openthinker3-7b","score":94.5,"metric":"percent"},{"benchmark":"aime-2024","model":"openthinker3-7b","score":67.7,"metric":"percent"},{"benchmark":"aime-2025","model":"openthinker3-7b","score":57.2,"metric":"percent"},{"benchmark":"omega","model":"openthinker3-7b","score":38.4,"metric":"percent"},{"benchmark":"bbh","model":"openthinker3-7b","score":77.1,"metric":"percent"},{"benchmark":"zebralogic","model":"openthinker3-7b","score":34.9,"metric":"percent"},{"benchmark":"agieval","model":"openthinker3-7b","score":78.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"openthinker3-7b","score":87.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"openthinker3-7b","score":61.4,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"openthinker3-7b","score":68,"metric":"percent"},{"benchmark":"ifeval","model":"openthinker3-7b","score":51.7,"metric":"percent"},{"benchmark":"ifbench","model":"openthinker3-7b","score":23,"metric":"percent"},{"benchmark":"mmlu","model":"openthinker3-7b","score":77.4,"metric":"percent"},{"benchmark":"popqa","model":"openthinker3-7b","score":18,"metric":"percent"},{"benchmark":"gpqa","model":"openthinker3-7b","score":47.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"openthinker3-7b","score":24,"metric":"percent"},{"benchmark":"point-bench","model":"poivre-7b","score":67.5,"metric":"percent"},{"benchmark":"point-bench","model":"visionreasoner-7b","score":64.7,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gpt-03-cua","score":87.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-03-cua","score":23.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"jedi-7b","score":91.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"jedi-7b","score":50.2,"metric":"percent"},{"benchmark":"screenspot-v2","model":"groundnext-7b","score":89.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"groundnext-7b","score":50.2,"metric":"percent"},{"benchmark":"osworld-g","model":"groundnext-7b","score":67.2,"metric":"percent"},{"benchmark":"osworld-g","model":"opencua-7b","score":55.3,"metric":"percent"},{"benchmark":"osworld-g","model":"gta1-7b","score":60.1,"metric":"percent"},{"benchmark":"screenspot-v2","model":"molmo2-gui-8b","score":88.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"molmo2-gui-8b","score":52.3,"metric":"percent"},{"benchmark":"osworld-g","model":"molmo2-gui-8b","score":66.1,"metric":"percent"},{"benchmark":"nextqa","model":"llava-video-7b","score":83.2,"metric":"percent"},{"benchmark":"perceptiontest","model":"llava-video-7b","score":68.8,"metric":"percent"},{"benchmark":"mvbench","model":"llava-video-7b","score":58.6,"metric":"percent"},{"benchmark":"tomato","model":"llava-video-7b","score":24.9,"metric":"percent"},{"benchmark":"motionbench","model":"llava-video-7b","score":54.2,"metric":"percent"},{"benchmark":"tempcompass","model":"llava-video-7b","score":66.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"llava-video-7b","score":63.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"llava-video-7b","score":69.7,"metric":"percent"},{"benchmark":"longvideobench","model":"llava-video-7b","score":58.2,"metric":"percent"},{"benchmark":"mlvu","model":"llava-video-7b","score":52.8,"metric":"percent"},{"benchmark":"lvbench","model":"llava-video-7b","score":44.2,"metric":"percent"},{"benchmark":"videoevalpro","model":"llava-video-7b","score":47.8,"metric":"percent"},{"benchmark":"egoschema","model":"llava-video-7b","score":57.3,"metric":"percent"},{"benchmark":"nextqa","model":"videochat-flash-7b","score":85.5,"metric":"percent"},{"benchmark":"perceptiontest","model":"videochat-flash-7b","score":76.5,"metric":"percent"},{"benchmark":"mvbench","model":"videochat-flash-7b","score":74,"metric":"percent"},{"benchmark":"tomato","model":"videochat-flash-7b","score":32.5,"metric":"percent"},{"benchmark":"motionbench","model":"videochat-flash-7b","score":60.6,"metric":"percent"},{"benchmark":"tempcompass","model":"videochat-flash-7b","score":69.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"videochat-flash-7b","score":65.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"videochat-flash-7b","score":69.7,"metric":"percent"},{"benchmark":"longvideobench","model":"videochat-flash-7b","score":64.7,"metric":"percent"},{"benchmark":"mlvu","model":"videochat-flash-7b","score":56,"metric":"percent"},{"benchmark":"lvbench","model":"videochat-flash-7b","score":48.2,"metric":"percent"},{"benchmark":"videoevalpro","model":"videochat-flash-7b","score":51.2,"metric":"percent"},{"benchmark":"egoschema","model":"videochat-flash-7b","score":51.3,"metric":"percent"},{"benchmark":"ai2d","model":"molmopoint-o-7b","score":93.7,"metric":"percent"},{"benchmark":"chartqa","model":"molmopoint-o-7b","score":84.9,"metric":"percent"},{"benchmark":"docvqa","model":"molmopoint-o-7b","score":90.4,"metric":"percent"},{"benchmark":"infoqa","model":"molmopoint-o-7b","score":77.9,"metric":"percent"},{"benchmark":"textvqa","model":"molmopoint-o-7b","score":84.7,"metric":"percent"},{"benchmark":"vqav2","model":"molmopoint-o-7b","score":86.6,"metric":"percent"},{"benchmark":"realworldqa","model":"molmopoint-o-7b","score":73.6,"metric":"percent"},{"benchmark":"mmmu","model":"molmopoint-o-7b","score":45.8,"metric":"percent"},{"benchmark":"mathvista","model":"molmopoint-o-7b","score":54.2,"metric":"percent"},{"benchmark":"countbench","model":"molmopoint-o-7b","score":95.1,"metric":"percent"},{"benchmark":"pixmocount","model":"molmopoint-o-7b","score":88.9,"metric":"percent"},{"benchmark":"muirbench","model":"molmopoint-o-7b","score":58.4,"metric":"percent"},{"benchmark":"mmiu","model":"molmopoint-o-7b","score":51.7,"metric":"percent"},{"benchmark":"blink","model":"molmopoint-o-7b","score":50.5,"metric":"percent"},{"benchmark":"screenspot-v2","model":"uground-v1-7b","score":76.3,"metric":"percent"},{"benchmark":"screenspot-v2","model":"molmoweb-ground-8b","score":91.8,"metric":"percent"},{"benchmark":"screenspot","model":"uground-v1-7b","score":86.7,"metric":"percent"},{"benchmark":"screenspot","model":"molmoweb-ground-8b","score":88.7,"metric":"percent"},{"benchmark":"healthbench","model":"antangelmed","score":62.5,"metric":"percent"},{"benchmark":"healthbench","model":"baichuan-m2-32b","score":60.1,"metric":"percent"},{"benchmark":"healthbench","model":"medgemma-27b-text-it","score":37.4,"metric":"percent"},{"benchmark":"healthbench-hard","model":"antangelmed","score":39.6,"metric":"percent"},{"benchmark":"healthbench-hard","model":"baichuan-m2-32b","score":34.7,"metric":"percent"},{"benchmark":"healthbench-hard","model":"medgemma-27b-text-it","score":8.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"claude-3.5-sonnet-20241022","score":17.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"infigui-g1-3b","score":45.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ferret-ui-lite-3b","score":53.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-tars-7b","score":35.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"phi-ground","score":43.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-actor-7b-qwen2.5-vl","score":44.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"se-gui-7b","score":47.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"opencua-32b","score":55.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-owl-32b","score":58,"metric":"percent"},{"benchmark":"screenspot-pro","model":"uground-v1-72b","score":34.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-tars-72b","score":38.1,"metric":"percent"},{"benchmark":"ui-vision","model":"infigui-g1-3b","score":22,"metric":"percent"},{"benchmark":"ui-vision","model":"seeclick","score":5.4,"metric":"percent"},{"benchmark":"ui-vision","model":"uground-v1-7b","score":12.9,"metric":"percent"},{"benchmark":"ui-vision","model":"os-atlas-7b","score":9,"metric":"percent"},{"benchmark":"ui-vision","model":"ui-tars-72b","score":25.5,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"os-atlas-7b","score":41.4,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"aguvis-7b","score":45.7,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"uground-v1-7b","score":65.7,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"gui-actor-7b-qwen2.5-vl","score":76.5,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"se-gui-7b","score":76.6,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"gta1-7b","score":78.5,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"gui-g2-7b","score":78.8,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"gui-owl-7b","score":80.5,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"infigui-g1-7b","score":80.8,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"gui-owl-32b","score":83,"metric":"percent"},{"benchmark":"mmbench-gui-l2","model":"ui-tars-72b-dpo","score":74.3,"metric":"percent"},{"benchmark":"osworld-g","model":"gpt-03-cua","score":40.6,"metric":"percent"},{"benchmark":"osworld-g","model":"jedi-3b","score":50.9,"metric":"percent"},{"benchmark":"osworld-g","model":"os-atlas-7b","score":27.7,"metric":"percent"},{"benchmark":"osworld-g","model":"uground-v1-7b","score":36.4,"metric":"percent"},{"benchmark":"osworld-g","model":"aguvis-7b","score":38.7,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-tars-7b","score":47.5,"metric":"percent"},{"benchmark":"osworld-g","model":"opencua-32b","score":59.6,"metric":"percent"},{"benchmark":"osworld-g","model":"gui-owl-32b","score":58,"metric":"percent"},{"benchmark":"osworld-g","model":"ui-tars-72b","score":57.1,"metric":"percent"},{"benchmark":"androidworld","model":"scalecua-3b","score":23.7,"metric":"percent"},{"benchmark":"androidworld","model":"ferret-ui-lite-3b","score":28,"metric":"percent"},{"benchmark":"androidworld","model":"ui-tars-7b","score":33,"metric":"percent"},{"benchmark":"androidworld","model":"gui-owl-7b","score":66.4,"metric":"percent"},{"benchmark":"androidworld","model":"step-gui-8b","score":67.7,"metric":"percent"},{"benchmark":"androidworld","model":"ui-tars-72b-sft","score":46.6,"metric":"percent"},{"benchmark":"androidworld","model":"ui-tars-2","score":73.3,"metric":"percent"},{"benchmark":"mobileworld","model":"gui-owl-7b","score":4.5,"metric":"percent"},{"benchmark":"mobileworld","model":"gui-owl-32b","score":5.5,"metric":"percent"},{"benchmark":"mobileworld","model":"doubao-1.5-ui-tars","score":20.9,"metric":"percent"},{"benchmark":"androidworld","model":"gui-owl-1.5-8b","score":71.6,"metric":"percent"},{"benchmark":"androidworld","model":"gui-owl-1.5-32b","score":69.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"gui-owl-1.5-8b","score":52.9,"metric":"percent"},{"benchmark":"osworld-verified","model":"gui-owl-1.5-32b","score":56.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen-cua","score":86.2,"metric":"percent"},{"benchmark":"v-star","model":"llava-onevision-7b","score":75.4,"metric":"percent"},{"benchmark":"hrbench4k","model":"llava-onevision-7b","score":63,"metric":"percent"},{"benchmark":"hrbench8k","model":"llava-onevision-7b","score":59.8,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"llava-onevision-7b","score":57.4,"metric":"percent"},{"benchmark":"browsecomp","model":"mirothinker-v1.0-30b","score":41.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"mirothinker-v1.0-30b","score":47.8,"metric":"percent"},{"benchmark":"gaia-text-only","model":"mirothinker-v1.0-30b","score":73.5,"metric":"percent"},{"benchmark":"webwalker-qa","model":"mirothinker-v1.0-30b","score":61,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"mirothinker-v1.0-30b","score":70.6,"metric":"avg@3"},{"benchmark":"hle-text-only","model":"mirothinker-v1.0-30b","score":33.4,"metric":"percent"},{"benchmark":"browsecomp","model":"smtl-30b","score":48.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"smtl-30b","score":75.7,"metric":"percent"},{"benchmark":"webwalker-qa","model":"smtl-30b","score":76.5,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"smtl-30b","score":82,"metric":"avg@3"},{"benchmark":"browsecomp","model":"websailor-v2-30b-a3b","score":35.3,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"websailor-v2-30b-a3b","score":44.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"websailor-v2-30b-a3b","score":74.1,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"websailor-v2-30b-a3b","score":73.7,"metric":"avg@3"},{"benchmark":"browsecomp","model":"deepminer-32b-rl","score":33.5,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepminer-32b-rl","score":40.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"deepminer-32b-rl","score":58.7,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"deepminer-32b-rl","score":62,"metric":"avg@3"},{"benchmark":"browsecomp","model":"openseeker-v1-30b-sft","score":29.5,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"openseeker-v1-30b-sft","score":48.4,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"openseeker-v1-30b-sft","score":74,"metric":"avg@3"},{"benchmark":"browsecomp","model":"webexplorer-8b","score":15.7,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"webexplorer-8b","score":32,"metric":"percent"},{"benchmark":"gaia-text-only","model":"webexplorer-8b","score":50,"metric":"percent"},{"benchmark":"webwalker-qa","model":"webexplorer-8b","score":62.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"webexplorer-8b","score":53.7,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"webexplorer-8b","score":23,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"webexplorer-8b","score":17.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"webexplorer-8b","score":17.3,"metric":"percent"},{"benchmark":"browsecomp","model":"re-trac-4b","score":30,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"re-trac-4b","score":36.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"re-trac-4b","score":70.4,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"re-trac-4b","score":76.6,"metric":"avg@3"},{"benchmark":"hle-text-only","model":"re-trac-4b","score":22.2,"metric":"percent"},{"benchmark":"webwalker-qa","model":"mirothinker-v1.0-8b","score":60.6,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"mirothinker-v1.0-8b","score":60.6,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"mirothinker-v1.0-8b","score":34,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"mirothinker-v1.0-8b","score":36.7,"metric":"percent"},{"benchmark":"hle-text-only","model":"mirothinker-v1.0-8b","score":21.5,"metric":"percent"},{"benchmark":"frames","model":"mirothinker-v1.0-8b","score":80.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"asearcher-web-qwq-v2","score":58.7,"metric":"percent"},{"benchmark":"frames","model":"asearcher-web-qwq-v2","score":74.5,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"asearcher-web-qwq-v2","score":51.1,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"iterresearch-30b-a3b","score":72.8,"metric":"percent"},{"benchmark":"browsecomp","model":"iterresearch-30b-a3b","score":37.3,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"iterresearch-30b-a3b","score":45.2,"metric":"percent"},{"benchmark":"hle-with-tools","model":"iterresearch-30b-a3b","score":28.8,"metric":"avg@3"},{"benchmark":"frames","model":"iterresearch-30b-a3b","score":71,"metric":"percent"},{"benchmark":"seal-0","model":"iterresearch-30b-a3b","score":39.6,"metric":"percent"},{"benchmark":"hle-with-tools","model":"websailor-v2-30b-a3b","score":30.6,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"websailor-v2-30b-a3b","score":73.7,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"webleaper-30b-a3b","score":73.2,"metric":"percent"},{"benchmark":"browsecomp","model":"webleaper-30b-a3b","score":38.8,"metric":"percent"},{"benchmark":"seal-0","model":"webleaper-30b-a3b","score":48.6,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"webleaper-30b-a3b","score":72,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"webdancer-32b","score":51.5,"metric":"percent"},{"benchmark":"browsecomp","model":"webdancer-32b","score":3.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"webdancer-32b","score":18,"metric":"percent"},{"benchmark":"webwalker-qa","model":"webdancer-32b","score":47.9,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"webdancer-32b","score":38.3,"metric":"avg@3"},{"benchmark":"deepresearchbench","model":"doubao-deep-research","score":44.34,"metric":"percent"},{"benchmark":"deepresearchbench","model":"claude-research","score":45,"metric":"percent"},{"benchmark":"deepresearchbench","model":"gemini-deepresearch","score":49.71,"metric":"percent"},{"benchmark":"asr-commonvoice-8-ja","model":"distil-whisper-large-v3-ja-reazonspeech-all","score":9.2,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"distil-whisper-large-v3-ja-reazonspeech-all","score":8.4,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"distil-whisper-large-v3-ja-reazonspeech-all","score":11.6,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"distil-whisper-large-v3-ja-reazonspeech-large","score":9.4,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"distil-whisper-large-v3-ja-reazonspeech-large","score":8.5,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"distil-whisper-large-v3-ja-reazonspeech-large","score":12.2,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"distil-whisper-large-v3-ja-reazonspeech-medium","score":10.9,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"distil-whisper-large-v3-ja-reazonspeech-medium","score":11.3,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"distil-whisper-large-v3-ja-reazonspeech-medium","score":14.8,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"distil-whisper-large-v3-ja-reazonspeech-small","score":30.2,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"distil-whisper-large-v3-ja-reazonspeech-small","score":39,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"distil-whisper-large-v3-ja-reazonspeech-small","score":40.7,"metric":"cer"},{"benchmark":"asr-commonvoice-8-ja","model":"distil-whisper-large-v3-ja-reazonspeech-tiny","score":94.8,"metric":"cer"},{"benchmark":"asr-jsut-basic5000","model":"distil-whisper-large-v3-ja-reazonspeech-tiny","score":96.3,"metric":"cer"},{"benchmark":"asr-reazonspeech","model":"distil-whisper-large-v3-ja-reazonspeech-tiny","score":96.7,"metric":"cer"},{"benchmark":"putnambench","model":"aleph-prover","score":99.4,"metric":"percent"},{"benchmark":"putnambench","model":"seed-prover-1.5-high","score":86.31,"metric":"percent"},{"benchmark":"putnambench","model":"goedel-architect","score":75.6,"metric":"percent"},{"benchmark":"putnambench","model":"axproverbase","score":54.32,"metric":"percent"},{"benchmark":"putnambench","model":"seed-prover-1.5-agentic","score":53.42,"metric":"percent"},{"benchmark":"fate-h","model":"seed-prover-1.5-high","score":80,"metric":"percent"},{"benchmark":"fate-h","model":"axproverbase","score":66,"metric":"percent"},{"benchmark":"fate-h","model":"seed-prover-1.5-agentic","score":57,"metric":"percent"},{"benchmark":"fate-x","model":"seed-prover-1.5-high","score":33,"metric":"percent"},{"benchmark":"fate-x","model":"axproverbase","score":24,"metric":"percent"},{"benchmark":"fate-x","model":"seed-prover-1.5-agentic","score":10,"metric":"percent"},{"benchmark":"lingoqa","model":"internvl3.5-8b","score":46.4,"metric":"percent"},{"benchmark":"lingoqa","model":"llava-onevision-2-8b","score":41.2,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen3.5-4b","score":70.4,"metric":"percent"},{"benchmark":"lingoqa","model":"cosmos-reason2-8b","score":59.6,"metric":"percent"},{"benchmark":"lingoqa","model":"cosmos3-nano","score":65,"metric":"percent"},{"benchmark":"lingoqa","model":"mimo-embodied-7b","score":72,"metric":"percent"},{"benchmark":"lingoqa","model":"alpamayo-1.5-10b","score":64,"metric":"percent"},{"benchmark":"lingoqa","model":"qwen-drive-1.0-4b","score":77.8,"metric":"percent"},{"benchmark":"ego3d-bench","model":"internvl3.5-8b","score":23.01,"metric":"rmse"},{"benchmark":"ego3d-bench","model":"llava-onevision-2-8b","score":24.97,"metric":"rmse"},{"benchmark":"ego3d-bench","model":"qwen3.5-4b","score":13.17,"metric":"rmse"},{"benchmark":"ego3d-bench","model":"cosmos-reason2-8b","score":12.62,"metric":"rmse"},{"benchmark":"ego3d-bench","model":"cosmos3-nano","score":22.41,"metric":"rmse"},{"benchmark":"ego3d-bench","model":"mimo-embodied-7b","score":9.85,"metric":"rmse"},{"benchmark":"ego3d-bench","model":"alpamayo-1.5-10b","score":25.31,"metric":"rmse"},{"benchmark":"ego3d-bench","model":"qwen-drive-1.0-4b","score":7.78,"metric":"rmse"},{"benchmark":"vlad","model":"internvl3.5-8b","score":54.47,"metric":"percent"},{"benchmark":"vlad","model":"llava-onevision-2-8b","score":58.71,"metric":"percent"},{"benchmark":"vlad","model":"qwen3.5-4b","score":65.38,"metric":"percent"},{"benchmark":"vlad","model":"cosmos-reason2-8b","score":56.37,"metric":"percent"},{"benchmark":"vlad","model":"cosmos3-nano","score":57.73,"metric":"percent"},{"benchmark":"vlad","model":"mimo-embodied-7b","score":50.33,"metric":"percent"},{"benchmark":"vlad","model":"alpamayo-1.5-10b","score":9.13,"metric":"percent"},{"benchmark":"vlad","model":"qwen-drive-1.0-4b","score":66.52,"metric":"percent"},{"benchmark":"surds","model":"internvl3.5-8b","score":32.8,"metric":"percent"},{"benchmark":"surds","model":"llava-onevision-2-8b","score":38.6,"metric":"percent"},{"benchmark":"surds","model":"qwen3.5-4b","score":52.95,"metric":"percent"},{"benchmark":"surds","model":"cosmos-reason2-8b","score":19.54,"metric":"percent"},{"benchmark":"surds","model":"cosmos3-nano","score":39.72,"metric":"percent"},{"benchmark":"surds","model":"mimo-embodied-7b","score":43.06,"metric":"percent"},{"benchmark":"surds","model":"alpamayo-1.5-10b","score":3.1,"metric":"percent"},{"benchmark":"surds","model":"qwen-drive-1.0-4b","score":66.13,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"internvl3.5-8b","score":54.47,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"llava-onevision-2-8b","score":49.65,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"qwen3.5-4b","score":62.46,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"cosmos-reason2-8b","score":57.68,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"cosmos3-nano","score":56.93,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"mimo-embodied-7b","score":66.54,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"alpamayo-1.5-10b","score":42.61,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"qwen-drive-1.0-4b","score":70.7,"metric":"percent"},{"benchmark":"waymoqa","model":"internvl3.5-8b","score":58.09,"metric":"percent"},{"benchmark":"waymoqa","model":"llava-onevision-2-8b","score":55.23,"metric":"percent"},{"benchmark":"waymoqa","model":"qwen3.5-4b","score":67.1,"metric":"percent"},{"benchmark":"waymoqa","model":"cosmos-reason2-8b","score":57.93,"metric":"percent"},{"benchmark":"waymoqa","model":"cosmos3-nano","score":58.36,"metric":"percent"},{"benchmark":"waymoqa","model":"mimo-embodied-7b","score":69.56,"metric":"percent"},{"benchmark":"waymoqa","model":"alpamayo-1.5-10b","score":44.37,"metric":"percent"},{"benchmark":"waymoqa","model":"qwen-drive-1.0-4b","score":74.47,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3.5-8b","score":80.03,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-onevision-2-8b","score":82.66,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen3.5-4b","score":87.07,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cosmos-reason2-8b","score":82.82,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cosmos3-nano","score":79.57,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"alpamayo-1.5-10b","score":7.51,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen-drive-1.0-4b","score":85.53,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-8b","score":64.13,"metric":"percent"},{"benchmark":"mmstar","model":"llava-onevision-2-8b","score":64.93,"metric":"percent"},{"benchmark":"mmstar","model":"qwen3.5-4b","score":75.33,"metric":"percent"},{"benchmark":"mmstar","model":"cosmos-reason2-8b","score":65.27,"metric":"percent"},{"benchmark":"mmstar","model":"cosmos3-nano","score":66.67,"metric":"percent"},{"benchmark":"mmstar","model":"mimo-embodied-7b","score":22.4,"metric":"percent"},{"benchmark":"mmstar","model":"alpamayo-1.5-10b","score":26.13,"metric":"percent"},{"benchmark":"mmstar","model":"qwen-drive-1.0-4b","score":75.87,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-8b","score":62,"metric":"percent"},{"benchmark":"mmmu","model":"llava-onevision-2-8b","score":54.67,"metric":"percent"},{"benchmark":"mmmu","model":"qwen3.5-4b","score":73.44,"metric":"percent"},{"benchmark":"mmmu","model":"cosmos-reason2-8b","score":59.11,"metric":"percent"},{"benchmark":"mmmu","model":"cosmos3-nano","score":60.89,"metric":"percent"},{"benchmark":"mmmu","model":"alpamayo-1.5-10b","score":27.44,"metric":"percent"},{"benchmark":"mmmu","model":"qwen-drive-1.0-4b","score":72.67,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl3.5-8b","score":46.42,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llava-onevision-2-8b","score":36.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.5-4b","score":64.86,"metric":"percent"},{"benchmark":"mmmu-pro","model":"cosmos-reason2-8b","score":36.07,"metric":"percent"},{"benchmark":"mmmu-pro","model":"cosmos3-nano","score":46.36,"metric":"percent"},{"benchmark":"mmmu-pro","model":"mimo-embodied-7b","score":27.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"alpamayo-1.5-10b","score":15.61,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen-drive-1.0-4b","score":62.72,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl3.5-8b","score":42.25,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"llava-onevision-2-8b","score":25.95,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"qwen3.5-4b","score":61.27,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"cosmos-reason2-8b","score":43.53,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"cosmos3-nano","score":40.75,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"mimo-embodied-7b","score":28.09,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"alpamayo-1.5-10b","score":13.47,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"qwen-drive-1.0-4b","score":59.71,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3.5-8b","score":41.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llava-onevision-2-8b","score":40.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen3.5-4b","score":65.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"cosmos-reason2-8b","score":42.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"cosmos3-nano","score":42.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"mimo-embodied-7b","score":57.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"alpamayo-1.5-10b","score":1.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen-drive-1.0-4b","score":64.4,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3.5-8b","score":83.2,"metric":"percent"},{"benchmark":"ocrbench","model":"llava-onevision-2-8b","score":79.3,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-4b","score":86.9,"metric":"percent"},{"benchmark":"ocrbench","model":"cosmos-reason2-8b","score":87,"metric":"percent"},{"benchmark":"ocrbench","model":"cosmos3-nano","score":85.2,"metric":"percent"},{"benchmark":"ocrbench","model":"mimo-embodied-7b","score":78.8,"metric":"percent"},{"benchmark":"ocrbench","model":"alpamayo-1.5-10b","score":3.2,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen-drive-1.0-4b","score":86.4,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-8b","score":66.93,"metric":"percent"},{"benchmark":"realworldqa","model":"llava-onevision-2-8b","score":71.76,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen3.5-4b","score":76.34,"metric":"percent"},{"benchmark":"realworldqa","model":"cosmos-reason2-8b","score":67.45,"metric":"percent"},{"benchmark":"realworldqa","model":"cosmos3-nano","score":69.67,"metric":"percent"},{"benchmark":"realworldqa","model":"mimo-embodied-7b","score":28.5,"metric":"percent"},{"benchmark":"realworldqa","model":"alpamayo-1.5-10b","score":46.93,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen-drive-1.0-4b","score":78.95,"metric":"percent"},{"benchmark":"simplevqa","model":"internvl3.5-8b","score":40.77,"metric":"percent"},{"benchmark":"simplevqa","model":"llava-onevision-2-8b","score":36.68,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen3.5-4b","score":47.84,"metric":"percent"},{"benchmark":"simplevqa","model":"cosmos-reason2-8b","score":45.25,"metric":"percent"},{"benchmark":"simplevqa","model":"cosmos3-nano","score":44.99,"metric":"percent"},{"benchmark":"simplevqa","model":"qwen-drive-1.0-4b","score":46.12,"metric":"percent"},{"benchmark":"countqa","model":"internvl3.5-8b","score":20.94,"metric":"percent"},{"benchmark":"countqa","model":"llava-onevision-2-8b","score":22.58,"metric":"percent"},{"benchmark":"countqa","model":"qwen3.5-4b","score":35.86,"metric":"percent"},{"benchmark":"countqa","model":"cosmos-reason2-8b","score":22.32,"metric":"percent"},{"benchmark":"countqa","model":"cosmos3-nano","score":23.63,"metric":"percent"},{"benchmark":"countqa","model":"mimo-embodied-7b","score":22.64,"metric":"percent"},{"benchmark":"countqa","model":"alpamayo-1.5-10b","score":4.71,"metric":"percent"},{"benchmark":"countqa","model":"qwen-drive-1.0-4b","score":31.74,"metric":"percent"},{"benchmark":"embspatialbench","model":"internvl3.5-8b","score":74.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"llava-onevision-2-8b","score":78.43,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3.5-4b","score":75.99,"metric":"percent"},{"benchmark":"embspatialbench","model":"cosmos-reason2-8b","score":77.61,"metric":"percent"},{"benchmark":"embspatialbench","model":"cosmos3-nano","score":77.88,"metric":"percent"},{"benchmark":"embspatialbench","model":"mimo-embodied-7b","score":45.05,"metric":"percent"},{"benchmark":"embspatialbench","model":"alpamayo-1.5-10b","score":20.58,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen-drive-1.0-4b","score":78.85,"metric":"percent"},{"benchmark":"erqa","model":"internvl3.5-8b","score":42,"metric":"percent"},{"benchmark":"erqa","model":"llava-onevision-2-8b","score":42.25,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-4b","score":46.25,"metric":"percent"},{"benchmark":"erqa","model":"cosmos-reason2-8b","score":43.25,"metric":"percent"},{"benchmark":"erqa","model":"cosmos3-nano","score":41.25,"metric":"percent"},{"benchmark":"erqa","model":"mimo-embodied-7b","score":39.75,"metric":"percent"},{"benchmark":"erqa","model":"alpamayo-1.5-10b","score":27.5,"metric":"percent"},{"benchmark":"erqa","model":"qwen-drive-1.0-4b","score":48.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3.5-4b","score":54.51,"metric":"percent"},{"benchmark":"refspatialbench","model":"cosmos-reason2-8b","score":51.81,"metric":"percent"},{"benchmark":"refspatialbench","model":"mimo-embodied-7b","score":2.17,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen-drive-1.0-4b","score":50.78,"metric":"percent"},{"benchmark":"omni3d","model":"qwen3.5-4b","score":47.4,"metric":"percent"},{"benchmark":"omni3d","model":"cosmos-reason2-8b","score":32.85,"metric":"percent"},{"benchmark":"omni3d","model":"cosmos3-nano","score":32.26,"metric":"percent"},{"benchmark":"omni3d","model":"qwen-drive-1.0-4b","score":45.79,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen3.5-4b","score":40.78,"metric":"percent"},{"benchmark":"odinw-13","model":"cosmos-reason2-8b","score":40.19,"metric":"percent"},{"benchmark":"odinw-13","model":"cosmos3-nano","score":35.87,"metric":"percent"},{"benchmark":"odinw-13","model":"qwen-drive-1.0-4b","score":45.87,"metric":"percent"},{"benchmark":"lingoqa","model":"cosmos-reason1-7b","score":45.2,"metric":"percent"},{"benchmark":"ego3d-bench","model":"cosmos-reason1-7b","score":26.71,"metric":"rmse"},{"benchmark":"vlad","model":"cosmos-reason1-7b","score":33.6,"metric":"percent"},{"benchmark":"surds","model":"cosmos-reason1-7b","score":8.5,"metric":"percent"},{"benchmark":"waymoqa-safety","model":"cosmos-reason1-7b","score":39.5,"metric":"percent"},{"benchmark":"waymoqa","model":"cosmos-reason1-7b","score":43.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cosmos-reason1-7b","score":80,"metric":"percent"},{"benchmark":"mmstar","model":"cosmos-reason1-7b","score":63.5,"metric":"percent"},{"benchmark":"mmmu","model":"cosmos-reason1-7b","score":54.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"cosmos-reason1-7b","score":38.4,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"cosmos-reason1-7b","score":35.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"cosmos-reason1-7b","score":39.7,"metric":"percent"},{"benchmark":"ocrbench","model":"cosmos-reason1-7b","score":85.2,"metric":"percent"},{"benchmark":"realworldqa","model":"cosmos-reason1-7b","score":67.5,"metric":"percent"},{"benchmark":"simplevqa","model":"cosmos-reason1-7b","score":45,"metric":"percent"},{"benchmark":"countqa","model":"cosmos-reason1-7b","score":18.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"cosmos-reason1-7b","score":68.8,"metric":"percent"},{"benchmark":"erqa","model":"cosmos-reason1-7b","score":38.5,"metric":"percent"},{"benchmark":"refspatialbench","model":"cosmos-reason1-7b","score":0.4,"metric":"percent"},{"benchmark":"odinw-13","model":"cosmos-reason1-7b","score":4.8,"metric":"percent"},{"benchmark":"navsim","model":"autovla","score":89.6,"metric":"score"},{"benchmark":"navsim","model":"spanvla","score":90.3,"metric":"score"},{"benchmark":"navsim","model":"simwam-il","score":90.3,"metric":"score"},{"benchmark":"navsim","model":"qwen-drive-1.0-4b","score":88.2,"metric":"score"},{"benchmark":"navsim","model":"qwen-drive-1.0-4b-rl","score":90.7,"metric":"score"},{"benchmark":"wod-e2e","model":"autovla","score":7.56,"metric":"score"},{"benchmark":"wod-e2e","model":"mindvla-u1","score":7.87,"metric":"score"},{"benchmark":"wod-e2e","model":"qwen-drive-1.0-4b","score":7.78,"metric":"score"},{"benchmark":"wod-e2e","model":"qwen-drive-1.0-4b-rl","score":7.91,"metric":"score"},{"benchmark":"mmlu-pro","model":"command-a-plus-05-2026","score":79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-v2.5","score":84.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"command-a-plus-05-2026","score":75.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mimo-v2.5","score":83,"metric":"percent"},{"benchmark":"hle-text-only","model":"command-a-plus-05-2026","score":11.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"mimo-v2.5","score":24.3,"metric":"percent"},{"benchmark":"livecodebench","model":"command-a-plus-05-2026","score":86.1,"metric":"percent"},{"benchmark":"livecodebench","model":"mimo-v2.5","score":89.1,"metric":"percent"},{"benchmark":"artifactsbench","model":"command-a-plus-05-2026","score":42.8,"metric":"percent"},{"benchmark":"artifactsbench","model":"mimo-v2.5","score":59.3,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"command-a-plus-05-2026","score":73.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"mimo-v2.5","score":61.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"command-a-plus-05-2026","score":96,"metric":"percent"},{"benchmark":"aime-2026-i","model":"mimo-v2.5","score":92.3,"metric":"percent"},{"benchmark":"multichallenge","model":"command-a-plus-05-2026","score":45.8,"metric":"percent"},{"benchmark":"multichallenge","model":"mimo-v2.5","score":39,"metric":"percent"},{"benchmark":"ifbench","model":"command-a-plus-05-2026","score":73.9,"metric":"percent"},{"benchmark":"aa-lcr","model":"command-a-plus-05-2026","score":46,"metric":"percent"},{"benchmark":"aa-lcr","model":"mimo-v2.5","score":62.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"command-a-plus-05-2026","score":14.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"mimo-v2.5","score":73,"metric":"percent"},{"benchmark":"terminal-bench-hard","model":"mimo-v2.5","score":41.7,"metric":"percent"},{"benchmark":"apex-agents","model":"command-a-plus-05-2026","score":1.6,"metric":"percent"},{"benchmark":"apex-agents","model":"mimo-v2.5","score":13.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"command-a-plus-05-2026","score":27.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"mimo-v2.5","score":63.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"command-a-plus-05-2026","score":5.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"mimo-v2.5","score":8.7,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"command-a-plus-05-2026","score":712,"metric":"elo"},{"benchmark":"kmmlu-pro","model":"mimo-v2.5","score":69.1,"metric":"percent"},{"benchmark":"click","model":"mimo-v2.5","score":78.4,"metric":"percent"},{"benchmark":"hrm8k","model":"mimo-v2.5","score":90.7,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"x-omni","score":17.7,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"step-audio-2-mini","score":38.6,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"qwen2-audio-7b-instruct","score":23.8,"metric":"percent"},{"benchmark":"kmmlu-pro","model":"audio-flamingo-3","score":31.8,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"x-omni","score":21.3,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"step-audio-2-mini","score":59.9,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"qwen2-audio-7b-instruct","score":40.8,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"audio-flamingo-3","score":46,"metric":"percent"},{"benchmark":"kobolt","model":"x-omni","score":9.6,"metric":"percent"},{"benchmark":"kobolt","model":"step-audio-2-mini","score":17.1,"metric":"percent"},{"benchmark":"kobolt","model":"qwen2-audio-7b-instruct","score":8.9,"metric":"percent"},{"benchmark":"kobolt","model":"audio-flamingo-3","score":12.9,"metric":"percent"},{"benchmark":"mmlu","model":"x-omni","score":40,"metric":"percent"},{"benchmark":"mmlu","model":"step-audio-2-mini","score":64.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-audio-7b-instruct","score":42.9,"metric":"percent"},{"benchmark":"mmlu","model":"audio-flamingo-3","score":58.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"x-omni","score":19.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"step-audio-2-mini","score":40.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-audio-7b-instruct","score":17.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"audio-flamingo-3","score":30.8,"metric":"percent"},{"benchmark":"gsm8k","model":"x-omni","score":61.7,"metric":"percent"},{"benchmark":"gsm8k","model":"step-audio-2-mini","score":75.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-audio-7b-instruct","score":39.5,"metric":"percent"},{"benchmark":"gsm8k","model":"audio-flamingo-3","score":62.2,"metric":"percent"},{"benchmark":"textvqa","model":"x-omni","score":77.5,"metric":"percent"},{"benchmark":"docvqa","model":"x-omni","score":88.1,"metric":"percent"},{"benchmark":"videomme","model":"gpt-4v","score":59.9,"metric":"percent"},{"benchmark":"videomme","model":"llava-onevision-7b","score":57.6,"metric":"percent"},{"benchmark":"videomme","model":"llava-next-7b","score":33.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"g9v3-39a5b","score":22.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"g9v3-39a5b","score":32.6,"metric":"percent"},{"benchmark":"scicode","model":"g9v3-39a5b","score":34,"metric":"percent"},{"benchmark":"hle-text-only","model":"g9v3-39a5b","score":17.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"g9v3-39a5b","score":80.5,"metric":"percent"},{"benchmark":"critpt","model":"g9v3-39a5b","score":0.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"g9v3-39a5b","score":62,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"g9v3-3b","score":34.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"g9v3-3b","score":16.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"g9v3-3b","score":43.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"g9v3-3b","score":4.5,"metric":"percent"},{"benchmark":"scicode","model":"g9v3-3b","score":17.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"g9v3-3b","score":6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"g9v3-3b","score":47.9,"metric":"percent"},{"benchmark":"aime-2025","model":"minicpm5-1b","score":40.4,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minicpm5-1b","score":40.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"minicpm5-1b","score":23.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minicpm5-1b","score":26.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"minicpm5-1b","score":65.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"minicpm5-1b","score":60.6,"metric":"percent"},{"benchmark":"livecodebench","model":"minicpm5-1b","score":33.5,"metric":"percent"},{"benchmark":"bfcl-v4","model":"minicpm5-1b","score":25.2,"metric":"percent"},{"benchmark":"belebele","model":"fanar-2-27b-instruct","score":61.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"fanar-2-27b-instruct","score":1.1,"metric":"percent"},{"benchmark":"mcpmark","model":"fanar-2-27b-instruct","score":12.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"fanar-2-27b-instruct","score":0.4,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"fanar-2-27b-instruct","score":3.9,"metric":"percent"},{"benchmark":"belebele","model":"allam-7b-instruct-preview","score":78.8,"metric":"percent"},{"benchmark":"belebele","model":"fanar-1-9b-instruct","score":79.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"allam-7b-instruct-preview","score":0,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"fanar-1-9b-instruct","score":0,"metric":"percent"},{"benchmark":"mcpmark","model":"allam-7b-instruct-preview","score":0,"metric":"percent"},{"benchmark":"mcpmark","model":"fanar-1-9b-instruct","score":0,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"allam-7b-instruct-preview","score":0,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"fanar-1-9b-instruct","score":0,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"allam-7b-instruct-preview","score":0.1,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"fanar-1-9b-instruct","score":0.4,"metric":"percent"},{"benchmark":"belebele","model":"granite-4.0-h-3b-ar","score":61.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"granite-4.0-h-3b-ar","score":0,"metric":"percent"},{"benchmark":"mcpmark","model":"granite-4.0-h-3b-ar","score":0,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"granite-4.0-h-3b-ar","score":0.6,"metric":"percent"},{"benchmark":"belebele","model":"hala-1.2b","score":39.9,"metric":"percent"},{"benchmark":"belebele","model":"tiny-aya-global","score":62.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kolibri-origin","score":68.1,"metric":"percent"},{"benchmark":"hle-text-only","model":"kolibri-origin","score":9.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kolibri-origin","score":70.1,"metric":"percent"},{"benchmark":"aime-2025","model":"kolibri-origin","score":81.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kolibri-origin","score":81.5,"metric":"percent"},{"benchmark":"tau2-telecom","model":"kolibri-origin","score":67.5,"metric":"percent"},{"benchmark":"tau2-retail","model":"kolibri-origin","score":58.5,"metric":"percent"},{"benchmark":"tau2-airline","model":"kolibri-origin","score":58.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"kolibri-origin","score":5.7,"metric":"percent"},{"benchmark":"bfcl-v3-multi-turn","model":"kolibri-origin","score":22.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"kolibri-origin","score":36.4,"metric":"percent"},{"benchmark":"browsecomp","model":"kolibri-origin","score":4.4,"metric":"percent"},{"benchmark":"livecodebench","model":"kolibri-origin","score":59.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"kolibri-origin","score":76.8,"metric":"percent"},{"benchmark":"mmlu","model":"kolibri-1-base","score":81,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-26b-a4b","score":78.2,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-32b","score":76.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"kolibri-1-base","score":95.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-4-26b-a4b","score":95.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-3-32b","score":94.5,"metric":"percent"},{"benchmark":"piqa","model":"kolibri-1-base","score":89.5,"metric":"percent"},{"benchmark":"piqa","model":"gemma-4-26b-a4b","score":88,"metric":"percent"},{"benchmark":"piqa","model":"olmo-3-32b","score":86.8,"metric":"percent"},{"benchmark":"hellaswag","model":"kolibri-1-base","score":83.1,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-4-26b-a4b","score":84.8,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-32b","score":83.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kolibri-1-base","score":61.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-26b-a4b","score":51.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-3-32b","score":50.9,"metric":"percent"},{"benchmark":"triviaqa","model":"kolibri-1-base","score":77.2,"metric":"percent"},{"benchmark":"triviaqa","model":"gemma-4-26b-a4b","score":65.6,"metric":"percent"},{"benchmark":"triviaqa","model":"olmo-3-32b","score":74.7,"metric":"percent"},{"benchmark":"gsm8k","model":"kolibri-1-base","score":89.8,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-4-26b-a4b","score":65.7,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-32b","score":81.1,"metric":"percent"},{"benchmark":"minerva-math","model":"kolibri-1-base","score":80.1,"metric":"percent"},{"benchmark":"minerva-math","model":"gemma-4-26b-a4b","score":26.1,"metric":"percent"},{"benchmark":"minerva-math","model":"olmo-3-32b","score":45.6,"metric":"percent"},{"benchmark":"humaneval","model":"kolibri-1-base","score":86.7,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-4-26b-a4b","score":52.2,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-3-32b","score":63.9,"metric":"percent"},{"benchmark":"mbpp","model":"kolibri-1-base","score":67.3,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-4-26b-a4b","score":50,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-3-32b","score":61,"metric":"percent"},{"benchmark":"ai2d","model":"llm-jp-4-vl-9b-beta","score":76.2,"metric":"percent"},{"benchmark":"chartqa","model":"llm-jp-4-vl-9b-beta","score":70.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llm-jp-4-vl-9b-beta","score":33.2,"metric":"percent"},{"benchmark":"chartqa-pro","model":"llm-jp-4-vl-9b-beta","score":27.8,"metric":"percent"},{"benchmark":"docvqa","model":"llm-jp-4-vl-9b-beta","score":90.1,"metric":"percent"},{"benchmark":"infovqa","model":"llm-jp-4-vl-9b-beta","score":69.6,"metric":"percent"},{"benchmark":"textvqa","model":"llm-jp-4-vl-9b-beta","score":87.7,"metric":"percent"},{"benchmark":"mmmu","model":"llm-jp-4-vl-9b-beta","score":52.3,"metric":"percent"},{"benchmark":"mathvision","model":"llm-jp-4-vl-9b-beta","score":17.4,"metric":"percent"},{"benchmark":"blink","model":"llm-jp-4-vl-9b-beta","score":46.2,"metric":"percent"},{"benchmark":"countbenchqa","model":"llm-jp-4-vl-9b-beta","score":82.9,"metric":"percent"},{"benchmark":"realworldqa","model":"llm-jp-4-vl-9b-beta","score":71.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llm-jp-4-vl-9b-beta","score":29.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llm-jp-4-vl-9b-beta","score":73.5,"metric":"percent"},{"benchmark":"simpleqa","model":"llm-jp-4-vl-9b-beta","score":5.8,"metric":"percent"},{"benchmark":"math500","model":"llm-jp-4-vl-9b-beta","score":46.1,"metric":"percent"},{"benchmark":"hellaswag","model":"apertus-8b","score":78.8,"metric":"percent"},{"benchmark":"hellaswag","model":"marin-8b-base","score":82.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3.5-9b-base","score":79.3,"metric":"percent"},{"benchmark":"piqa","model":"apertus-8b","score":80.2,"metric":"percent"},{"benchmark":"piqa","model":"marin-8b-base","score":81.9,"metric":"percent"},{"benchmark":"piqa","model":"qwen3.5-9b-base","score":80.5,"metric":"percent"},{"benchmark":"commonsenseqa","model":"apertus-8b","score":62.3,"metric":"percent"},{"benchmark":"commonsenseqa","model":"marin-8b-base","score":70.3,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen3.5-9b-base","score":83.6,"metric":"percent"},{"benchmark":"lambada","model":"apertus-8b","score":70.1,"metric":"percent"},{"benchmark":"lambada","model":"marin-8b-base","score":68.8,"metric":"percent"},{"benchmark":"lambada","model":"qwen3.5-9b-base","score":70.5,"metric":"percent"},{"benchmark":"xnli","model":"apertus-8b","score":44.1,"metric":"percent"},{"benchmark":"xnli","model":"marin-8b-base","score":42.4,"metric":"percent"},{"benchmark":"xnli","model":"qwen3.5-9b-base","score":39.8,"metric":"percent"},{"benchmark":"xcopa","model":"apertus-8b","score":65.6,"metric":"percent"},{"benchmark":"xcopa","model":"marin-8b-base","score":57,"metric":"percent"},{"benchmark":"xcopa","model":"qwen3.5-9b-base","score":64.1,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-3-32b","score":81.5,"metric":"percent"},{"benchmark":"hellaswag","model":"eurollm-22b-base","score":79,"metric":"percent"},{"benchmark":"hellaswag","model":"marin-32b-base","score":85,"metric":"percent"},{"benchmark":"piqa","model":"olmo-3-32b","score":81.3,"metric":"percent"},{"benchmark":"piqa","model":"eurollm-22b-base","score":81.4,"metric":"percent"},{"benchmark":"piqa","model":"marin-32b-base","score":83.3,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-3-32b","score":71.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"eurollm-22b-base","score":60.5,"metric":"percent"},{"benchmark":"commonsenseqa","model":"marin-32b-base","score":75.5,"metric":"percent"},{"benchmark":"lambada","model":"olmo-3-32b","score":70.5,"metric":"percent"},{"benchmark":"lambada","model":"eurollm-22b-base","score":70.9,"metric":"percent"},{"benchmark":"lambada","model":"marin-32b-base","score":68.7,"metric":"percent"},{"benchmark":"xnli","model":"olmo-3-32b","score":42.4,"metric":"percent"},{"benchmark":"xnli","model":"eurollm-22b-base","score":44.1,"metric":"percent"},{"benchmark":"xnli","model":"marin-32b-base","score":42.3,"metric":"percent"},{"benchmark":"xcopa","model":"olmo-3-32b","score":59.5,"metric":"percent"},{"benchmark":"xcopa","model":"eurollm-22b-base","score":61.3,"metric":"percent"},{"benchmark":"xcopa","model":"marin-32b-base","score":58.6,"metric":"percent"},{"benchmark":"mmlu","model":"apertus-8b-instruct","score":60.6,"metric":"percent"},{"benchmark":"mmlu","model":"marin-8b-instruct","score":63.5,"metric":"percent"},{"benchmark":"mmlu","model":"eurollm-9b-instruct-2512","score":62,"metric":"percent"},{"benchmark":"mmlu-pro","model":"apertus-8b-instruct","score":35.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"marin-8b-instruct","score":41,"metric":"percent"},{"benchmark":"mmlu-pro","model":"eurollm-9b-instruct-2512","score":38.5,"metric":"percent"},{"benchmark":"agieval","model":"apertus-8b-instruct","score":38.5,"metric":"percent"},{"benchmark":"agieval","model":"marin-8b-instruct","score":36.4,"metric":"percent"},{"benchmark":"agieval","model":"eurollm-9b-instruct-2512","score":41.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"apertus-8b-instruct","score":70.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"marin-8b-instruct","score":68.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"eurollm-9b-instruct-2512","score":73.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"apertus-8b-instruct","score":56.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"marin-8b-instruct","score":55.3,"metric":"percent"},{"benchmark":"truthfulqa","model":"eurollm-9b-instruct-2512","score":47.4,"metric":"percent"},{"benchmark":"ifeval","model":"apertus-8b-instruct","score":68.4,"metric":"percent"},{"benchmark":"ifeval","model":"marin-8b-instruct","score":65.2,"metric":"percent"},{"benchmark":"ifeval","model":"eurollm-9b-instruct-2512","score":66,"metric":"percent"},{"benchmark":"multi-if","model":"apertus-8b-instruct","score":66.8,"metric":"percent"},{"benchmark":"multi-if","model":"marin-8b-instruct","score":59.6,"metric":"percent"},{"benchmark":"multi-if","model":"eurollm-9b-instruct-2512","score":56.4,"metric":"percent"},{"benchmark":"ifbench","model":"apertus-8b-instruct","score":19.7,"metric":"percent"},{"benchmark":"ifbench","model":"marin-8b-instruct","score":17.7,"metric":"percent"},{"benchmark":"ifbench","model":"eurollm-9b-instruct-2512","score":14.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"apertus-8b-instruct","score":12.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"marin-8b-instruct","score":25.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"eurollm-9b-instruct-2512","score":64.9,"metric":"percent"},{"benchmark":"gsm8k","model":"apertus-8b-instruct","score":62.7,"metric":"percent"},{"benchmark":"gsm8k","model":"marin-8b-instruct","score":81.2,"metric":"percent"},{"benchmark":"gsm8k","model":"eurollm-9b-instruct-2512","score":62.7,"metric":"percent"},{"benchmark":"math","model":"apertus-8b-instruct","score":19,"metric":"percent"},{"benchmark":"math","model":"marin-8b-instruct","score":31.5,"metric":"percent"},{"benchmark":"math","model":"eurollm-9b-instruct-2512","score":31.1,"metric":"percent"},{"benchmark":"math500","model":"apertus-8b-instruct","score":19.6,"metric":"percent"},{"benchmark":"math500","model":"marin-8b-instruct","score":38,"metric":"percent"},{"benchmark":"math500","model":"eurollm-9b-instruct-2512","score":35.4,"metric":"percent"},{"benchmark":"humaneval","model":"apertus-8b-instruct","score":41.4,"metric":"percent"},{"benchmark":"humaneval","model":"marin-8b-instruct","score":51.2,"metric":"percent"},{"benchmark":"humaneval","model":"eurollm-9b-instruct-2512","score":38.8,"metric":"percent"},{"benchmark":"mbpp","model":"apertus-8b-instruct","score":40.2,"metric":"percent"},{"benchmark":"mbpp","model":"marin-8b-instruct","score":41.2,"metric":"percent"},{"benchmark":"mbpp","model":"eurollm-9b-instruct-2512","score":41.2,"metric":"percent"},{"benchmark":"bbh","model":"apertus-8b-instruct","score":55.7,"metric":"percent"},{"benchmark":"bbh","model":"marin-8b-instruct","score":60.3,"metric":"percent"},{"benchmark":"bbh","model":"eurollm-9b-instruct-2512","score":54.5,"metric":"percent"},{"benchmark":"gpqa","model":"apertus-8b-instruct","score":27.9,"metric":"percent"},{"benchmark":"gpqa","model":"marin-8b-instruct","score":25.9,"metric":"percent"},{"benchmark":"gpqa","model":"eurollm-9b-instruct-2512","score":28.3,"metric":"percent"},{"benchmark":"drop","model":"apertus-8b-instruct","score":44.7,"metric":"percent"},{"benchmark":"drop","model":"marin-8b-instruct","score":60.1,"metric":"percent"},{"benchmark":"drop","model":"eurollm-9b-instruct-2512","score":45.8,"metric":"percent"},{"benchmark":"global-mmlu","model":"apertus-8b-instruct","score":55.5,"metric":"percent"},{"benchmark":"global-mmlu","model":"marin-8b-instruct","score":48.7,"metric":"percent"},{"benchmark":"global-mmlu","model":"eurollm-9b-instruct-2512","score":55,"metric":"percent"},{"benchmark":"ifbench","model":"plamo-2.2-prime","score":37.4,"metric":"percent"},{"benchmark":"mt-bench-ja","model":"plamo-2.2-prime","score":6.82,"metric":"score"},{"benchmark":"mt-bench","model":"plamo-2.2-prime","score":7.44,"metric":"percent"},{"benchmark":"bfcl-v4","model":"plamo-2.2-prime","score":65.2,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"plamo-2.2-prime","score":0.1,"metric":"percent"},{"benchmark":"longbench","model":"plamo-2.2-prime","score":53.5,"metric":"percent"},{"benchmark":"longbench-v2","model":"plamo-2.2-prime","score":29,"metric":"percent"},{"benchmark":"aime-2024","model":"plamo-2.2-prime","score":2.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"plamo-2.2-prime","score":32.2,"metric":"percent"},{"benchmark":"livecodebench","model":"plamo-2.2-prime","score":16.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-1.7b-base","score":62.32,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-1.7b-base","score":37.08,"metric":"percent"},{"benchmark":"bbh","model":"qwen3-1.7b-base","score":53.6,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen3-1.7b-base","score":16.83,"metric":"percent"},{"benchmark":"math","model":"qwen3-1.7b-base","score":41.74,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-1.7b-base","score":75.74,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3-1.7b-base","score":45.31,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-1.7b-base","score":53.85,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen3-1.7b-base","score":43.08,"metric":"percent"},{"benchmark":"kosimpleqa","model":"qwen3-1.7b-base","score":13.4,"metric":"percent"},{"benchmark":"hae-rae-bench","model":"qwen3-1.7b-base","score":55.54,"metric":"percent"},{"benchmark":"mbpp-ko","model":"qwen3-1.7b-base","score":47.97,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen3-1.7b-base","score":69.01,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3-1.7b-base","score":56.49,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3-1.7b-base","score":49.36,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3-1.7b-base","score":63.38,"metric":"percent"},{"benchmark":"xnli","model":"qwen3-1.7b-base","score":41.66,"metric":"percent"},{"benchmark":"xcopa","model":"qwen3-1.7b-base","score":58.35,"metric":"percent"},{"benchmark":"piqa","model":"qwen3-1.7b-base","score":75.79,"metric":"percent"},{"benchmark":"arc-challenge","model":"ling-2.5-flash-base","score":95.59,"metric":"percent"},{"benchmark":"arc-challenge","model":"step-3.5-flash-base","score":92.88,"metric":"percent"},{"benchmark":"agieval","model":"ling-2.5-flash-base","score":72.39,"metric":"percent"},{"benchmark":"agieval","model":"step-3.5-flash-base","score":74.27,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"ling-2.5-flash-base","score":15.9,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"step-3.5-flash-base","score":27.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-2.5-flash-base","score":61.36,"metric":"percent"},{"benchmark":"mmlu-pro","model":"step-3.5-flash-base","score":63.65,"metric":"percent"},{"benchmark":"c-eval","model":"ling-2.5-flash-base","score":87.86,"metric":"percent"},{"benchmark":"c-eval","model":"step-3.5-flash-base","score":89.36,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-2.5-flash-base","score":80.49,"metric":"percent"},{"benchmark":"humaneval-plus","model":"step-3.5-flash-base","score":78.05,"metric":"percent"},{"benchmark":"cruxeval","model":"ling-2.5-flash-base","score":76.5,"metric":"percent"},{"benchmark":"cruxeval","model":"step-3.5-flash-base","score":71.69,"metric":"percent"},{"benchmark":"multipl-e","model":"ling-2.5-flash-base","score":68.07,"metric":"percent"},{"benchmark":"multipl-e","model":"step-3.5-flash-base","score":63.21,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-2.5-flash-base","score":33.04,"metric":"percent"},{"benchmark":"livecodebench","model":"step-3.5-flash-base","score":35.68,"metric":"percent"},{"benchmark":"bigcodebench","model":"ling-2.5-flash-base","score":50.35,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"step-3.5-flash-base","score":49.74,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"ling-2.5-flash-base","score":48.43,"metric":"percent"},{"benchmark":"fullstackbench","model":"step-3.5-flash-base","score":50.86,"metric":"percent"},{"benchmark":"math500","model":"ling-2.5-flash-base","score":74,"metric":"percent"},{"benchmark":"math500","model":"step-3.5-flash-base","score":62.8,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-2.5-flash-base","score":39.31,"metric":"percent"},{"benchmark":"olympiadbench","model":"step-3.5-flash-base","score":34.34,"metric":"percent"},{"benchmark":"omni-math","model":"ling-2.5-flash-base","score":36.2,"metric":"percent"},{"benchmark":"omni-math","model":"step-3.5-flash-base","score":28.46,"metric":"percent"},{"benchmark":"commonsenseqa","model":"ling-2.5-flash-base","score":87.55,"metric":"percent"},{"benchmark":"commonsenseqa","model":"step-3.5-flash-base","score":88.62,"metric":"percent"},{"benchmark":"bbh","model":"ling-2.5-flash-base","score":84.72,"metric":"percent"},{"benchmark":"bbh","model":"step-3.5-flash-base","score":87.19,"metric":"percent"},{"benchmark":"longbench","model":"ling-2.5-flash-base","score":42.81,"metric":"percent"},{"benchmark":"longbench","model":"step-3.5-flash-base","score":21.47,"metric":"percent"},{"benchmark":"arc-challenge","model":"ling-2.5-mini-base","score":91.19,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-9b-base","score":94.58,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-4b-base","score":92.2,"metric":"percent"},{"benchmark":"agieval","model":"ling-2.5-mini-base","score":63.38,"metric":"percent"},{"benchmark":"agieval","model":"qwen3.5-9b-base","score":66.17,"metric":"percent"},{"benchmark":"agieval","model":"qwen3.5-4b-base","score":61.45,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"ling-2.5-mini-base","score":7.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"qwen3.5-9b-base","score":10.4,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"qwen3.5-4b-base","score":6.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-2.5-mini-base","score":49.89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-9b-base","score":57.76,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-4b-base","score":52.06,"metric":"percent"},{"benchmark":"c-eval","model":"ling-2.5-mini-base","score":80.16,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-9b-base","score":81.52,"metric":"percent"},{"benchmark":"c-eval","model":"qwen3.5-4b-base","score":76.67,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-2.5-mini-base","score":76.22,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-9b-base","score":52.44,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-4b-base","score":49.39,"metric":"percent"},{"benchmark":"cruxeval","model":"ling-2.5-mini-base","score":63.19,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3.5-9b-base","score":68.12,"metric":"percent"},{"benchmark":"cruxeval","model":"qwen3.5-4b-base","score":64.31,"metric":"percent"},{"benchmark":"multipl-e","model":"ling-2.5-mini-base","score":64.34,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3.5-9b-base","score":52.89,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen3.5-4b-base","score":45.47,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-2.5-mini-base","score":22.91,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-9b-base","score":18.06,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b-base","score":13.88,"metric":"percent"},{"benchmark":"bigcodebench","model":"ling-2.5-mini-base","score":42.54,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen3.5-9b-base","score":29.39,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen3.5-4b-base","score":24.39,"metric":"pass@1"},{"benchmark":"fullstackbench","model":"ling-2.5-mini-base","score":38.59,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3.5-9b-base","score":37.23,"metric":"percent"},{"benchmark":"fullstackbench","model":"qwen3.5-4b-base","score":33.14,"metric":"percent"},{"benchmark":"math500","model":"ling-2.5-mini-base","score":68.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-9b-base","score":55.2,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-4b-base","score":49.6,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-2.5-mini-base","score":24.1,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen3.5-9b-base","score":21.84,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen3.5-4b-base","score":17.02,"metric":"percent"},{"benchmark":"omni-math","model":"ling-2.5-mini-base","score":29.02,"metric":"percent"},{"benchmark":"omni-math","model":"qwen3.5-9b-base","score":22.99,"metric":"percent"},{"benchmark":"omni-math","model":"qwen3.5-4b-base","score":20.89,"metric":"percent"},{"benchmark":"commonsenseqa","model":"ling-2.5-mini-base","score":81.16,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen3.5-9b-base","score":83.62,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen3.5-4b-base","score":80.18,"metric":"percent"},{"benchmark":"bbh","model":"ling-2.5-mini-base","score":77.37,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-9b-base","score":84.52,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-4b-base","score":80.11,"metric":"percent"},{"benchmark":"longbench","model":"ling-2.5-mini-base","score":29.93,"metric":"percent"},{"benchmark":"longbench","model":"qwen3.5-9b-base","score":51.87,"metric":"percent"},{"benchmark":"longbench","model":"qwen3.5-4b-base","score":39.96,"metric":"percent"},{"benchmark":"browsecomp","model":"deepdive-9b-sft","score":5.6,"metric":"percent"},{"benchmark":"browsecomp","model":"deepdive-9b-rl","score":6.3,"metric":"percent"},{"benchmark":"browsecomp","model":"websailor-7b","score":6.7,"metric":"percent"},{"benchmark":"browsecomp","model":"offseeker-8b-sft","score":10.6,"metric":"percent"},{"benchmark":"browsecomp","model":"offseeker-8b-dpo","score":12.8,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepdive-9b-sft","score":15.7,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"deepdive-9b-rl","score":15.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"websailor-7b","score":14.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"offseeker-8b-sft","score":24.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"offseeker-8b-dpo","score":26.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"websailor-7b","score":37.9,"metric":"percent"},{"benchmark":"gaia-text-only","model":"offseeker-8b-sft","score":47.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"offseeker-8b-dpo","score":51.5,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.05","model":"deepdive-9b-sft","score":35,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"deepdive-9b-rl","score":38,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"websailor-7b","score":34.3,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"offseeker-8b-sft","score":48,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.05","model":"offseeker-8b-dpo","score":49,"metric":"avg@3"},{"benchmark":"mmlu","model":"ling-1t-base","score":86.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ling-1t-base","score":67.91,"metric":"percent"},{"benchmark":"gpqa","model":"ling-1t-base","score":41.92,"metric":"percent"},{"benchmark":"supergpqa","model":"ling-1t-base","score":44.06,"metric":"percent"},{"benchmark":"triviaqa","model":"ling-1t-base","score":81.62,"metric":"percent"},{"benchmark":"simpleqa","model":"ling-1t-base","score":20.87,"metric":"percent"},{"benchmark":"csimpleqa","model":"ling-1t-base","score":64.53,"metric":"percent"},{"benchmark":"mmmlu","model":"ling-1t-base","score":68.68,"metric":"percent"},{"benchmark":"gsm8k","model":"ling-1t-base","score":89.31,"metric":"percent"},{"benchmark":"cmath","model":"ling-1t-base","score":93.62,"metric":"percent"},{"benchmark":"olympiadbench","model":"ling-1t-base","score":39.56,"metric":"percent"},{"benchmark":"omni-math","model":"ling-1t-base","score":33.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ling-1t-base","score":83.54,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ling-1t-base","score":73.81,"metric":"percent"},{"benchmark":"livecodebench","model":"ling-1t-base","score":40.09,"metric":"percent"},{"benchmark":"bird-sql","model":"ling-1t-base","score":42.7,"metric":"percent"},{"benchmark":"bbh","model":"ling-1t-base","score":86.88,"metric":"percent"},{"benchmark":"bbh-zh","model":"ling-1t-base","score":85.82,"metric":"percent"},{"benchmark":"kor-bench","model":"ling-1t-base","score":49.04,"metric":"percent"},{"benchmark":"commonsenseqa","model":"ling-1t-base","score":89.76,"metric":"percent"},{"benchmark":"zebralogic","model":"ling-1t-base","score":26,"metric":"percent"},{"benchmark":"squad-v2.0","model":"ling-1t-base","score":91.29,"metric":"percent"},{"benchmark":"longbench-v2","model":"ling-1t-base","score":30.02,"metric":"percent"},{"benchmark":"screenspot-v2","model":"ui-tars-7b","score":91.6,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gui-g2-7b","score":93.8,"metric":"percent"},{"benchmark":"screenspot-v2","model":"step-gui-4b","score":93.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"step-gui-4b","score":60,"metric":"percent"},{"benchmark":"androidworld","model":"holo2-8b","score":60.4,"metric":"percent"},{"benchmark":"androidworld","model":"step-gui-4b","score":63.9,"metric":"percent"},{"benchmark":"mobileworld","model":"gui-owl-7b","score":7.7,"metric":"percent"},{"benchmark":"webvoyager","model":"step-gui-4b","score":47.8,"metric":"percent"},{"benchmark":"streamingbench","model":"video-salmonn-2-plus-7b","score":59.9,"metric":"percent"},{"benchmark":"streamingbench","model":"av-flamingo-7b","score":58.5,"metric":"percent"},{"benchmark":"streamingbench","model":"livestar-8b","score":60.2,"metric":"percent"},{"benchmark":"streamingbench","model":"mmduet2-3b","score":58.1,"metric":"percent"},{"benchmark":"streamingbench","model":"joyai-vl-interaction","score":63.3,"metric":"percent"},{"benchmark":"ovobench","model":"video-salmonn-2-plus-7b","score":46.8,"metric":"percent"},{"benchmark":"ovobench","model":"av-flamingo-7b","score":51.5,"metric":"percent"},{"benchmark":"ovobench","model":"livestar-8b","score":38,"metric":"percent"},{"benchmark":"ovobench","model":"mmduet2-3b","score":47.6,"metric":"percent"},{"benchmark":"ovobench","model":"joyai-vl-interaction","score":56.7,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"fun-audio-chat-8b","score":76.6,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"minicpm-o-2.6","score":65.2,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"baichuan-omni-1.5","score":65.6,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"kimi-audio-7b-instruct","score":68.4,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"mimo-audio-7b-instruct","score":74.9,"metric":"percent"},{"benchmark":"voicebench-mau-v05-15-25","model":"step-audio-2-mini","score":68.2,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"fun-audio-chat-8b","score":67.8,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"minicpm-o-2.6","score":56.5,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"baichuan-omni-1.5","score":50.6,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"kimi-audio-7b-instruct","score":59.3,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"mimo-audio-7b-instruct","score":61.7,"metric":"percent"},{"benchmark":"voicebench-mmsu-audio","model":"step-audio-2-mini","score":56.8,"metric":"percent"},{"benchmark":"mmstar","model":"llada-v","score":60.1,"metric":"percent"},{"benchmark":"mmstar","model":"bagel-7b-mot","score":67,"metric":"percent"},{"benchmark":"mmstar","model":"internvl-u","score":54.7,"metric":"percent"},{"benchmark":"mmstar","model":"lumina-dimoo","score":61,"metric":"percent"},{"benchmark":"mmstar","model":"llada-o","score":58,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llada-v","score":82.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bagel-7b-mot","score":85,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl-u","score":75.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"lumina-dimoo","score":84.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llada-o","score":71.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llada-v","score":70.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bagel-7b-mot","score":82.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl-u","score":73.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"lumina-dimoo","score":71.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llada-o","score":69.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"llada-v","score":39.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"bagel-7b-mot","score":52.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl-u","score":44.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"lumina-dimoo","score":32.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"llada-o","score":47.4,"metric":"percent"},{"benchmark":"realworldqa","model":"llada-v","score":63.2,"metric":"percent"},{"benchmark":"realworldqa","model":"bagel-7b-mot","score":73.9,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl-u","score":56.4,"metric":"percent"},{"benchmark":"realworldqa","model":"lumina-dimoo","score":52.4,"metric":"percent"},{"benchmark":"realworldqa","model":"llada-o","score":60.8,"metric":"percent"},{"benchmark":"simplevqa","model":"llada-v","score":26,"metric":"percent"},{"benchmark":"simplevqa","model":"bagel-7b-mot","score":41.9,"metric":"percent"},{"benchmark":"simplevqa","model":"internvl-u","score":20.7,"metric":"percent"},{"benchmark":"simplevqa","model":"lumina-dimoo","score":12.1,"metric":"percent"},{"benchmark":"simplevqa","model":"llada-o","score":29.2,"metric":"percent"},{"benchmark":"mmmu","model":"llada-v","score":48.6,"metric":"percent"},{"benchmark":"mmmu","model":"bagel-7b-mot","score":55.3,"metric":"percent"},{"benchmark":"mmmu","model":"internvl-u","score":54.7,"metric":"percent"},{"benchmark":"mmmu","model":"lumina-dimoo","score":58.6,"metric":"percent"},{"benchmark":"mmmu","model":"llada-o","score":44.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llada-v","score":35.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"bagel-7b-mot","score":37.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl-u","score":20.8,"metric":"percent"},{"benchmark":"mmmu-pro","model":"lumina-dimoo","score":20.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llada-o","score":28.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llada-v","score":59.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"bagel-7b-mot","score":73.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl-u","score":55.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"lumina-dimoo","score":10.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llada-o","score":66.1,"metric":"percent"},{"benchmark":"wemath","model":"llada-v","score":24.6,"metric":"percent"},{"benchmark":"wemath","model":"bagel-7b-mot","score":45.8,"metric":"percent"},{"benchmark":"wemath","model":"internvl-u","score":18.3,"metric":"percent"},{"benchmark":"wemath","model":"lumina-dimoo","score":6.2,"metric":"percent"},{"benchmark":"wemath","model":"llada-o","score":29.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llada-v","score":47,"metric":"percent"},{"benchmark":"charxiv-dq","model":"bagel-7b-mot","score":70.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl-u","score":53.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"lumina-dimoo","score":27.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llada-o","score":69.8,"metric":"percent"},{"benchmark":"chartqa","model":"llada-v","score":78.3,"metric":"percent"},{"benchmark":"chartqa","model":"bagel-7b-mot","score":74.3,"metric":"percent"},{"benchmark":"chartqa","model":"internvl-u","score":76.6,"metric":"percent"},{"benchmark":"chartqa","model":"lumina-dimoo","score":8.3,"metric":"percent"},{"benchmark":"chartqa","model":"llada-o","score":87.9,"metric":"percent"},{"benchmark":"ocrbench","model":"llada-v","score":63.2,"metric":"percent"},{"benchmark":"ocrbench","model":"bagel-7b-mot","score":73.3,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl-u","score":83.9,"metric":"percent"},{"benchmark":"ocrbench","model":"lumina-dimoo","score":7.6,"metric":"percent"},{"benchmark":"ocrbench","model":"llada-o","score":74.6,"metric":"percent"},{"benchmark":"docvqa","model":"llada-v","score":83.9,"metric":"percent"},{"benchmark":"docvqa","model":"bagel-7b-mot","score":94.3,"metric":"percent"},{"benchmark":"docvqa","model":"internvl-u","score":85.4,"metric":"percent"},{"benchmark":"docvqa","model":"lumina-dimoo","score":7.2,"metric":"percent"},{"benchmark":"docvqa","model":"llada-o","score":91.5,"metric":"percent"},{"benchmark":"ai2d","model":"llada-v","score":77.8,"metric":"percent"},{"benchmark":"ai2d","model":"bagel-7b-mot","score":88.9,"metric":"percent"},{"benchmark":"ai2d","model":"internvl-u","score":76.3,"metric":"percent"},{"benchmark":"ai2d","model":"lumina-dimoo","score":43.2,"metric":"percent"},{"benchmark":"ai2d","model":"llada-o","score":79.3,"metric":"percent"},{"benchmark":"infovqa","model":"llada-v","score":66.3,"metric":"percent"},{"benchmark":"infovqa","model":"bagel-7b-mot","score":60.7,"metric":"percent"},{"benchmark":"infovqa","model":"internvl-u","score":68.3,"metric":"percent"},{"benchmark":"infovqa","model":"lumina-dimoo","score":6.2,"metric":"percent"},{"benchmark":"infovqa","model":"llada-o","score":54.7,"metric":"percent"},{"benchmark":"countbench","model":"llada-v","score":75.1,"metric":"percent"},{"benchmark":"countbench","model":"bagel-7b-mot","score":93.2,"metric":"percent"},{"benchmark":"countbench","model":"internvl-u","score":62.2,"metric":"percent"},{"benchmark":"countbench","model":"lumina-dimoo","score":48.4,"metric":"percent"},{"benchmark":"countbench","model":"llada-o","score":91.7,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"llada-v","score":46,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"bagel-7b-mot","score":28.9,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"internvl-u","score":46.4,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"lumina-dimoo","score":51.7,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"llada-o","score":42.4,"metric":"percent"},{"benchmark":"v-star","model":"llada-v","score":41.8,"metric":"percent"},{"benchmark":"v-star","model":"bagel-7b-mot","score":67.5,"metric":"percent"},{"benchmark":"v-star","model":"internvl-u","score":51.3,"metric":"percent"},{"benchmark":"v-star","model":"lumina-dimoo","score":52.7,"metric":"percent"},{"benchmark":"v-star","model":"llada-o","score":57.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"opencua-72b","score":60.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"step-gui-8b","score":62.6,"metric":"percent"},{"benchmark":"screenspot-v2","model":"opencua-32b","score":93.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"opencua-72b","score":92.9,"metric":"percent"},{"benchmark":"screenspot-v2","model":"gui-owl-32b","score":93.1,"metric":"percent"},{"benchmark":"screenspot-v2","model":"step-gui-8b","score":95.1,"metric":"percent"},{"benchmark":"screenspot-v2","model":"mai-ui-32b","score":96.5,"metric":"percent"},{"benchmark":"osworld-g","model":"holo2-8b","score":63.5,"metric":"percent"},{"benchmark":"osworld-g","model":"holo2-30b-a3b","score":65.2,"metric":"percent"},{"benchmark":"osworld-g","model":"step-gui-4b","score":60.5,"metric":"percent"},{"benchmark":"androidworld","model":"ui-tars-72b","score":46.6,"metric":"percent"},{"benchmark":"androidworld","model":"holo2-30b-a3b","score":71.6,"metric":"percent"},{"benchmark":"androidworld","model":"mai-ui-32b","score":73.3,"metric":"percent"},{"benchmark":"androidworld","model":"ui-venus-2-27b","score":84,"metric":"percent"},{"benchmark":"mobileworld","model":"qwen-ui-agent-27b","score":82.1,"metric":"percent"},{"benchmark":"mobileworld","model":"ui-venus-2-27b","score":76.1,"metric":"percent"},{"benchmark":"osworld-verified","model":"qwen-ui-agent-27b","score":79.5,"metric":"percent"},{"benchmark":"osworld-verified","model":"ui-venus-2-27b","score":80.5,"metric":"percent"},{"benchmark":"osworld-2.0","model":"ui-venus-2-27b","score":13.2,"metric":"percent"},{"benchmark":"webvoyager","model":"ui-venus-2-27b","score":93.4,"metric":"percent"},{"benchmark":"online-mind2web","model":"ui-venus-2-27b","score":78.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"seed2.1-pro","score":65.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen-ui-agent-27b","score":76.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-venus-2-27b","score":74.1,"metric":"percent"},{"benchmark":"csimpleqa","model":"gpt-oss-120b-low","score":43.47,"metric":"percent"},{"benchmark":"csimpleqa","model":"gpt-5.4-mini-none","score":59.73,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-oss-120b-low","score":12.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"gpt-5.4-mini-none","score":16.5,"metric":"percent"},{"benchmark":"hle","model":"gpt-oss-120b-low","score":4.59,"metric":"avg@3"},{"benchmark":"hle","model":"gpt-5.4-mini-none","score":5.61,"metric":"avg@3"},{"benchmark":"aime-2026-i","model":"gpt-oss-120b-low","score":60.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.4-mini-none","score":35.68,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-oss-120b-low","score":35.89,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.4-mini-none","score":21.73,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-oss-120b-low","score":38.59,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gpt-5.4-mini-none","score":21.16,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-oss-120b-low","score":61.51,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-5.4-mini-none","score":55.07,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-5.4-mini-none","score":43.8,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gpt-oss-120b-low","score":52,"metric":"percent"},{"benchmark":"pinchbench-avg","model":"gpt-5.4-mini-none","score":71.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-oss-120b-low","score":43.3,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.4-mini-none","score":49.72,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-oss-120b-low","score":58.3,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-5.4-mini-none","score":38.8,"metric":"percent"},{"benchmark":"lifebench","model":"gpt-oss-120b-low","score":49.4,"metric":"percent"},{"benchmark":"lifebench","model":"gpt-5.4-mini-none","score":57.6,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-oss-120b-low","score":37.73,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-5.4-mini-none","score":34.43,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-oss-120b-low","score":68.52,"metric":"percent"},{"benchmark":"multi-if","model":"gpt-5.4-mini-none","score":71.13,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ornith-1.0-35b","score":55.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ornith-1.0-35b","score":51.67,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ornith-1.0-35b","score":34.47,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.0-35b","score":35.96,"metric":"percent"},{"benchmark":"pinchbench","model":"ornith-1.0-35b","score":91.62,"metric":"percent"},{"benchmark":"scicode","model":"ornith-1.0-35b","score":30.34,"metric":"percent"},{"benchmark":"big-bench-audio","model":"grok-voice-agent","score":92.3,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gemini-2.5-flash-native-audio-thinking","score":92.1,"metric":"percent"},{"benchmark":"big-bench-audio","model":"nova-2-sonic","score":87.1,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-realtime","score":83.3,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gemini-2.5-flash-live-preview","score":74.2,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gemini-2.5-flash-native-audio","score":71.5,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-4o-mini-realtime-preview-2024-12-17","score":68.9,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-4o-realtime-preview-2024-12-17","score":68.4,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-realtime-mini","score":67.5,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-4o-realtime-preview","score":66.2,"metric":"percent"},{"benchmark":"big-bench-audio","model":"qwen3-omni-30b-a3b-realtime","score":59.2,"metric":"percent"},{"benchmark":"big-bench-audio","model":"qwen3-omni-30b-a3b-instruct","score":58.1,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gpt-4o-audio-preview","score":54.3,"metric":"percent"},{"benchmark":"big-bench-audio","model":"gemini-2.0-flash-exp","score":35.6,"metric":"percent"},{"benchmark":"matholympiadbench","model":"kimina-prover-8b","score":8.6,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"kimina-prover-8b","score":78.3,"metric":"percent"},{"benchmark":"proofnet-test","model":"kimina-prover-8b","score":11.8,"metric":"percent"},{"benchmark":"proverbench","model":"kimina-prover-8b","score":37.8,"metric":"percent"},{"benchmark":"putnambench","model":"kimina-prover-8b","score":4.8,"metric":"percent"},{"benchmark":"matholympiadbench","model":"kimina-prover-72b","score":13.1,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"kimina-prover-72b","score":84,"metric":"percent"},{"benchmark":"proofnet-test","model":"kimina-prover-72b","score":18.3,"metric":"percent"},{"benchmark":"proverbench","model":"kimina-prover-72b","score":44.6,"metric":"percent"},{"benchmark":"putnambench","model":"kimina-prover-72b","score":3.9,"metric":"percent"},{"benchmark":"matholympiadbench","model":"deepseek-prover-v2-7b","score":11.1,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"deepseek-prover-v2-7b","score":75.6,"metric":"percent"},{"benchmark":"proofnet-test","model":"deepseek-prover-v2-7b","score":23,"metric":"percent"},{"benchmark":"proverbench","model":"deepseek-prover-v2-7b","score":49,"metric":"percent"},{"benchmark":"putnambench","model":"deepseek-prover-v2-7b","score":1.4,"metric":"percent"},{"benchmark":"matholympiadbench","model":"deepseek-prover-v2-671b","score":13.9,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"deepseek-prover-v2-671b","score":82.4,"metric":"percent"},{"benchmark":"proofnet-test","model":"deepseek-prover-v2-671b","score":30.5,"metric":"percent"},{"benchmark":"proverbench","model":"deepseek-prover-v2-671b","score":52.9,"metric":"percent"},{"benchmark":"putnambench","model":"deepseek-prover-v2-671b","score":3.3,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"leanabell-prover-v2-km","score":68.4,"metric":"percent"},{"benchmark":"proofnet-test","model":"leanabell-prover-v2-km","score":13.4,"metric":"percent"},{"benchmark":"proverbench","model":"leanabell-prover-v2-km","score":39.8,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"leanabell-prover-v2-ds","score":76.6,"metric":"percent"},{"benchmark":"proofnet-test","model":"leanabell-prover-v2-ds","score":23.7,"metric":"percent"},{"benchmark":"proverbench","model":"leanabell-prover-v2-ds","score":47.8,"metric":"percent"},{"benchmark":"matholympiadbench","model":"goedel-prover-v2-8b","score":11.1,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"goedel-prover-v2-8b","score":84.6,"metric":"percent"},{"benchmark":"proofnet-test","model":"goedel-prover-v2-8b","score":16.7,"metric":"percent"},{"benchmark":"proverbench","model":"goedel-prover-v2-8b","score":49.5,"metric":"percent"},{"benchmark":"putnambench","model":"goedel-prover-v2-8b","score":3.8,"metric":"percent"},{"benchmark":"matholympiadbench","model":"goedel-prover-v2-32b","score":16.7,"metric":"percent"},{"benchmark":"minif2f-pass32","model":"goedel-prover-v2-32b","score":88.1,"metric":"percent"},{"benchmark":"proofnet-test","model":"goedel-prover-v2-32b","score":22,"metric":"percent"},{"benchmark":"proverbench","model":"goedel-prover-v2-32b","score":53.2,"metric":"percent"},{"benchmark":"putnambench","model":"goedel-prover-v2-32b","score":6.7,"metric":"percent"},{"benchmark":"minif2f-test","model":"delta-prover","score":95.9,"metric":"percent"},{"benchmark":"minif2f-test","model":"seed-prover","score":99.6,"metric":"percent"},{"benchmark":"putnambench","model":"seed-prover","score":50.4,"metric":"percent"},{"benchmark":"putnambench","model":"seed-prover-1.5-high","score":87.9,"metric":"percent"},{"benchmark":"mmmu","model":"internvl3.5-30b-a3b-flash","score":75.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl3.5-30b-a3b-flash","score":80.9,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3.5-30b-a3b-flash","score":55.7,"metric":"percent"},{"benchmark":"visulogic","model":"internvl3.5-30b-a3b-flash","score":28.4,"metric":"percent"},{"benchmark":"babyvision","model":"internvl3.5-30b-a3b-flash","score":11.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3.5-30b-a3b-flash","score":81.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3.5-30b-a3b-flash","score":48,"metric":"percent"},{"benchmark":"chartqa","model":"internvl3.5-30b-a3b-flash","score":87.4,"metric":"percent"},{"benchmark":"infovqa","model":"internvl3.5-30b-a3b-flash","score":81.4,"metric":"percent"},{"benchmark":"docvqa","model":"internvl3.5-30b-a3b-flash","score":94.2,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl3.5-30b-a3b-flash","score":88,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"internvl3.5-30b-a3b-flash","score":47,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"internvl3.5-30b-a3b-flash","score":48.2,"metric":"percent"},{"benchmark":"osworld-g","model":"internvl3.5-30b-a3b-flash","score":42.4,"metric":"percent"},{"benchmark":"screenspot-v2","model":"internvl3.5-30b-a3b-flash","score":87.3,"metric":"percent"},{"benchmark":"mmstar","model":"internvl3.5-30b-a3b-flash","score":72,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl3.5-30b-a3b-flash","score":72.3,"metric":"percent"},{"benchmark":"countbench","model":"internvl3.5-30b-a3b-flash","score":84.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"skyrl-agent-8b-v0","score":9.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"internlm3-8b-nex-n1","score":20.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"sa-swe-32b","score":39.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"swe-swiss-32b","score":45,"metric":"percent"},{"benchmark":"mhpp","model":"codellama-7b-instruct","score":6.7,"metric":"percent"},{"benchmark":"mhpp","model":"deepseek-coder-6.7b-instruct","score":20,"metric":"percent"},{"benchmark":"mhpp","model":"codeqwen1.5-7b-chat","score":17.6,"metric":"percent"},{"benchmark":"mhpp","model":"yi-coder-9b-chat","score":26.7,"metric":"percent"},{"benchmark":"mhpp","model":"llama-3.1-8b-instruct","score":17.1,"metric":"percent"},{"benchmark":"mhpp","model":"opencoder-8b-instruct","score":30.5,"metric":"percent"},{"benchmark":"mhpp","model":"qwen2.5-coder-7b-instruct","score":26.7,"metric":"percent"},{"benchmark":"mhpp","model":"qwen3-8b","score":32.8,"metric":"percent"},{"benchmark":"mhpp","model":"seed-coder-8b-instruct","score":36.2,"metric":"percent"},{"benchmark":"mhpp","model":"stable-diffcoder-8b-instruct","score":42.4,"metric":"percent"},{"benchmark":"humaneval","model":"llada-moe-7b-a1b-instruct","score":61.6,"metric":"percent"},{"benchmark":"mbpp","model":"llada-moe-7b-a1b-instruct","score":70,"metric":"percent"},{"benchmark":"bigcodebench","model":"llada-moe-7b-a1b-instruct","score":20.4,"metric":"pass@1"},{"benchmark":"humaneval","model":"diffucoder-7b-instruct","score":72,"metric":"percent"},{"benchmark":"humaneval-plus","model":"diffucoder-7b-instruct","score":65.2,"metric":"percent"},{"benchmark":"mbpp","model":"diffucoder-7b-instruct","score":75.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"diffucoder-7b-instruct","score":61.9,"metric":"percent"},{"benchmark":"bigcodebench","model":"diffucoder-7b-instruct","score":35.7,"metric":"pass@1"},{"benchmark":"humaneval","model":"dream-coder-7b-instruct","score":82.9,"metric":"percent"},{"benchmark":"mbpp","model":"dream-coder-7b-instruct","score":79.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"dream-coder-7b-instruct","score":37.1,"metric":"pass@1"},{"benchmark":"humaneval","model":"opencoder-8b-base","score":66.5,"metric":"percent"},{"benchmark":"mbpp","model":"opencoder-8b-base","score":79.9,"metric":"percent"},{"benchmark":"multipl-e","model":"opencoder-8b-base","score":61,"metric":"percent"},{"benchmark":"crux-o","model":"opencoder-8b-base","score":43.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-7b","score":72,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-7b","score":79.4,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-coder-7b","score":58.8,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-7b","score":56,"metric":"percent"},{"benchmark":"ifbench","model":"xing4.0-29b-a4b","score":69.67,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-26b-a4b-it","score":72.67,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":65.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"xing4.0-29b-a4b","score":90,"metric":"percent"},{"benchmark":"aa-lcr","model":"xing4.0-29b-a4b","score":61,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-26b-a4b-it","score":66,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.6-35b-a3b","score":62,"metric":"percent"},{"benchmark":"claw-eval","model":"xing4.0-29b-a4b","score":76.55,"metric":"percent"},{"benchmark":"claw-eval","model":"gemma-4-26b-a4b-it","score":71.49,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.6-35b-a3b","score":74.54,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"xing4.0-29b-a4b","score":75,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-26b-a4b-it","score":53,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-35b-a3b","score":76,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"xing4.0-29b-a4b","score":57.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"gemma-4-26b-a4b-it","score":30,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":51.5,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"xing4.0-29b-a4b","score":66,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"gemma-4-26b-a4b-it","score":51,"metric":"percent"},{"benchmark":"deepresearch-bench-ii","model":"xing4.0-29b-a4b","score":60.8,"metric":"percent"},{"benchmark":"deepresearch-bench-ii","model":"gemma-4-26b-a4b-it","score":39.3,"metric":"percent"},{"benchmark":"deepresearch-bench-ii","model":"qwen3.6-35b-a3b","score":59.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nex-n2.5-mini","score":73.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nex-n2.5-pro","score":82.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nex-n2.5-max","score":86.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"nex-n2.5-mini","score":43.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"nex-n2.5-pro","score":61.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"nex-n2.5-max","score":65.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-pro-0813","score":55.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.8-max","score":67.7,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"nex-n2.5-mini","score":36.1,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"nex-n2.5-pro","score":55.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"nex-n2.5-max","score":65.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro-0813","score":62.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-max","score":69.3,"metric":"percent"},{"benchmark":"automationbench","model":"nex-n2.5-mini","score":32.3,"metric":"percent"},{"benchmark":"automationbench","model":"nex-n2.5-pro","score":44.2,"metric":"percent"},{"benchmark":"automationbench","model":"nex-n2.5-max","score":50.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"nex-n2.5-mini","score":54.6,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"nex-n2.5-pro","score":68.5,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"nex-n2.5-max","score":74.7,"metric":"percent"},{"benchmark":"gdpval-aa-v2-elo","model":"nex-n2.5-mini","score":1446,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nex-n2.5-pro","score":1628,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nex-n2.5-max","score":1713,"metric":"elo"},{"benchmark":"jobbench","model":"nex-n2.5-mini","score":28.5,"metric":"percent"},{"benchmark":"jobbench","model":"nex-n2.5-pro","score":41.4,"metric":"percent"},{"benchmark":"jobbench","model":"nex-n2.5-max","score":53.6,"metric":"percent"},{"benchmark":"jobbench","model":"kimi-k3","score":52.9,"metric":"percent"},{"benchmark":"jobbench","model":"qwen3.8-max","score":53.4,"metric":"percent"},{"benchmark":"browsecomp","model":"nex-n2.5-mini","score":83.4,"metric":"percent"},{"benchmark":"browsecomp","model":"nex-n2.5-pro","score":89.7,"metric":"percent"},{"benchmark":"browsecomp","model":"nex-n2.5-max","score":92.6,"metric":"percent"},{"benchmark":"osworld-verified","model":"nex-n2.5-mini","score":71.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"nex-n2.5-pro","score":82.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"glm-5.3-flash","score":62.3,"metric":"percent"},{"benchmark":"osworld-verified","model":"deepseek-v4-flash-vision-exp","score":76.7,"metric":"percent"},{"benchmark":"osworld-2.0","model":"nex-n2.5-mini","score":30.5,"metric":"percent"},{"benchmark":"osworld-2.0","model":"nex-n2.5-pro","score":56.4,"metric":"percent"},{"benchmark":"osworld-2.0","model":"minimax-m3","score":22.3,"metric":"percent"},{"benchmark":"webtestbench","model":"nex-n2.5-mini","score":48.6,"metric":"percent"},{"benchmark":"webtestbench","model":"nex-n2.5-pro","score":52.8,"metric":"percent"},{"benchmark":"webtestbench","model":"gpt-5.6-sol","score":54,"metric":"percent"},{"benchmark":"webtestbench","model":"qwen3.8-max","score":52.3,"metric":"percent"},{"benchmark":"webarena-verified","model":"nex-n2.5-mini","score":63.4,"metric":"percent"},{"benchmark":"webarena-verified","model":"nex-n2.5-pro","score":67.6,"metric":"percent"},{"benchmark":"webarena-verified","model":"kimi-k3","score":71.6,"metric":"percent"},{"benchmark":"webarena-verified","model":"deepseek-v4-flash-vision-exp","score":62.3,"metric":"percent"},{"benchmark":"osworld-g","model":"nex-n2.5-mini","score":82.9,"metric":"percent"},{"benchmark":"osworld-g","model":"nex-n2.5-pro","score":87.4,"metric":"percent"},{"benchmark":"osworld-g","model":"claude-opus-5","score":76.8,"metric":"percent"},{"benchmark":"osworld-g","model":"gpt-5.6-sol","score":77.7,"metric":"percent"},{"benchmark":"osworld-g","model":"kimi-k3","score":79.6,"metric":"percent"},{"benchmark":"osworld-g","model":"glm-5.3-flash","score":83.3,"metric":"percent"},{"benchmark":"osworld-g","model":"deepseek-v4-flash-vision-exp","score":59.4,"metric":"percent"},{"benchmark":"osworld-g","model":"qwen3.8-max","score":84.9,"metric":"percent"},{"benchmark":"vision2web","model":"nex-n2.5-mini","score":52.9,"metric":"percent"},{"benchmark":"vision2web","model":"nex-n2.5-pro","score":68.2,"metric":"percent"},{"benchmark":"vision2web","model":"minimax-m3","score":59,"metric":"percent"},{"benchmark":"vision2web","model":"gpt-5.6-sol","score":79.8,"metric":"percent"},{"benchmark":"vision2web","model":"qwen3.8-max","score":75.1,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"nex-n2.5-mini","score":25.5,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"nex-n2.5-pro","score":38.2,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"gpt-5.6-sol","score":40.2,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"kimi-k3","score":37.3,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"glm-5.3-flash","score":20.6,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"deepseek-v4-flash-vision-exp","score":39.2,"metric":"percent"},{"benchmark":"swe-bench-multimodal","model":"qwen3.8-max","score":39.2,"metric":"percent"},{"benchmark":"omnidocbench","model":"nex-n2.5-mini","score":89.7,"metric":"percent"},{"benchmark":"omnidocbench","model":"nex-n2.5-pro","score":92.2,"metric":"percent"},{"benchmark":"omnidocbench","model":"gpt-5.6-sol","score":92.9,"metric":"percent"},{"benchmark":"omnidocbench","model":"qwen3.8-max","score":92.1,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"nanbeige4.2-3b","score":74.3,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"qwen3.5-9b","score":61.9,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"qwen3.5-4b","score":46.7,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"gemma-4-12b-it","score":68.5,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"gemma-4-e4b-it","score":31.5,"metric":"percent"},{"benchmark":"agentif-oneday","model":"nanbeige4.2-3b","score":67.5,"metric":"percent"},{"benchmark":"agentif-oneday","model":"qwen3.5-9b","score":60.4,"metric":"percent"},{"benchmark":"agentif-oneday","model":"qwen3.5-4b","score":56.9,"metric":"percent"},{"benchmark":"officeqa-pro","model":"nanbeige4.2-3b","score":21.1,"metric":"percent"},{"benchmark":"officeqa-pro","model":"qwen3.5-9b","score":15.8,"metric":"percent"},{"benchmark":"officeqa-pro","model":"qwen3.5-4b","score":8.3,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gemma-4-12b-it","score":15.3,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gemma-4-e4b-it","score":3.1,"metric":"percent"},{"benchmark":"pinchbench","model":"nanbeige4.2-3b","score":74.7,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-9b","score":68.2,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-4b","score":63.9,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-12b-it","score":53.8,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-e4b-it","score":33.3,"metric":"percent"},{"benchmark":"claw-gym","model":"nanbeige4.2-3b","score":65,"metric":"percent"},{"benchmark":"claw-gym","model":"qwen3.5-9b","score":56.1,"metric":"percent"},{"benchmark":"claw-gym","model":"qwen3.5-4b","score":53,"metric":"percent"},{"benchmark":"claw-gym","model":"gemma-4-12b-it","score":40.8,"metric":"percent"},{"benchmark":"claw-gym","model":"gemma-4-e4b-it","score":16.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"nanbeige4.2-3b","score":52.2,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.5-9b","score":47.1,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.5-4b","score":36.9,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gemma-4-12b-it","score":25.5,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gemma-4-e4b-it","score":15.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"nanbeige4.2-3b","score":57.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nanbeige4.2-3b","score":63.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"nanbeige4.2-3b","score":46.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"nanbeige4.2-3b","score":44.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-9b","score":29.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-4b","score":25.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemma-4-12b-it","score":21.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemma-4-e4b-it","score":12.4,"metric":"percent"},{"benchmark":"hle-text-only","model":"nanbeige4.2-3b","score":17.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-9b","score":12.5,"metric":"percent"},{"benchmark":"hle-text-only","model":"qwen3.5-4b","score":6.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemma-4-12b-it","score":14.8,"metric":"percent"},{"benchmark":"hle-text-only","model":"gemma-4-e4b-it","score":4,"metric":"percent"},{"benchmark":"scicode","model":"nanbeige4.2-3b","score":35.6,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-4b","score":22.7,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-e4b-it","score":24.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"nanbeige4.2-3b","score":87.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-4b","score":78.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-e4b-it","score":60.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"nanbeige4.2-3b","score":82.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-9b","score":69.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-4b","score":60.6,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-12b-it","score":51.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-e4b-it","score":24.2,"metric":"percent"},{"benchmark":"imo-answerbench","model":"nanbeige4.2-3b","score":67.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-9b","score":56.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"qwen3.5-4b","score":46.8,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-12b-it","score":54.5,"metric":"percent"},{"benchmark":"imo-answerbench","model":"gemma-4-e4b-it","score":24,"metric":"percent"},{"benchmark":"livecodebench","model":"nanbeige4.2-3b","score":72.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e4b-it","score":55.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"nanbeige4.2-3b","score":58.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-9b","score":58,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-4b","score":52,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-e4b-it","score":30.7,"metric":"percent"},{"benchmark":"ifbench","model":"nanbeige4.2-3b","score":54.6,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-9b","score":54.1,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":41.4,"metric":"percent"},{"benchmark":"recruit-bench","model":"nanbeige4.2-3b","score":63.3,"metric":"percent"},{"benchmark":"recruit-bench","model":"qwen3.5-9b","score":59,"metric":"percent"},{"benchmark":"recruit-bench","model":"qwen3.5-4b","score":40.7,"metric":"percent"},{"benchmark":"recruit-bench","model":"gemma-4-12b-it","score":69.4,"metric":"percent"},{"benchmark":"recruit-bench","model":"gemma-4-e4b-it","score":57.9,"metric":"percent"},{"benchmark":"gdpval","model":"nanbeige4.2-3b","score":68.8,"metric":"percent"},{"benchmark":"gdpval","model":"qwen3.5-9b","score":38,"metric":"percent"},{"benchmark":"gdpval","model":"qwen3.5-4b","score":37,"metric":"percent"},{"benchmark":"agentif-oneday","model":"nanbeige4.2-3b","score":58.9,"metric":"percent"},{"benchmark":"agentif-oneday","model":"qwen3.5-9b","score":32.1,"metric":"percent"},{"benchmark":"agentif-oneday","model":"qwen3.5-4b","score":27,"metric":"percent"},{"benchmark":"deepresearch-bench-ii","model":"nanbeige4.2-3b","score":33.4,"metric":"percent"},{"benchmark":"deepresearch-bench-ii","model":"qwen3.5-9b","score":28.3,"metric":"percent"},{"benchmark":"deepresearch-bench-ii","model":"qwen3.5-4b","score":26,"metric":"percent"},{"benchmark":"researchrubrics","model":"nanbeige4.2-3b","score":44.8,"metric":"percent"},{"benchmark":"researchrubrics","model":"qwen3.5-9b","score":37.2,"metric":"percent"},{"benchmark":"researchrubrics","model":"qwen3.5-4b","score":35.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.5-397b","score":86.1,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.5-397b","score":85.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash-0731","score":81.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ornith-1.5-397b","score":86,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v4-flash-0731","score":81.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"glm-5.2","score":83,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-opus-4.8","score":85.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k3","score":86.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ornith-1.5-397b","score":65.1,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"deepseek-v4-flash-0731","score":64.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"claude-opus-4.8","score":68,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ornith-1.0-397b","score":62.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ornith-1.5-397b","score":79.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"deepseek-v4-flash-0731","score":77.9,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"glm-5.2","score":78.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"claude-opus-4.8","score":75.7,"metric":"percent"},{"benchmark":"deepswe","model":"ornith-1.5-397b","score":56,"metric":"percent"},{"benchmark":"deepswe","model":"deepseek-v4-flash-0731","score":54.4,"metric":"percent"},{"benchmark":"deepswe","model":"glm-5.2","score":46.2,"metric":"percent"},{"benchmark":"deepswe","model":"claude-opus-4.8","score":59,"metric":"percent"},{"benchmark":"deepswe","model":"ornith-1.0-397b","score":8,"metric":"percent"},{"benchmark":"frontierbench","model":"ornith-1.5-397b","score":13.5,"metric":"percent"},{"benchmark":"frontierbench","model":"deepseek-v4-flash-0731","score":6.1,"metric":"percent"},{"benchmark":"frontierbench","model":"glm-5.2","score":5.1,"metric":"percent"},{"benchmark":"frontierbench","model":"kimi-k3","score":23,"metric":"percent"},{"benchmark":"frontierbench","model":"ornith-1.0-397b","score":2.7,"metric":"percent"},{"benchmark":"nl2repo","model":"ornith-1.5-397b","score":59.5,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"ornith-1.5-397b","score":55.6,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"deepseek-v4-flash-0731","score":51.6,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"glm-5.2","score":50,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-opus-4.8","score":59.7,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"kimi-k3","score":59.7,"metric":"percent"},{"benchmark":"hle","model":"ornith-1.5-397b","score":44.6,"metric":"avg@3"},{"benchmark":"hle","model":"deepseek-v4-flash-0731","score":35,"metric":"avg@3"},{"benchmark":"hle","model":"ornith-1.0-397b","score":30.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"ornith-1.5-397b","score":56.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"deepseek-v4-flash-0731","score":50.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"ornith-1.0-397b","score":47.5,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"ornith-1.5-397b","score":92.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash-0731","score":91.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ornith-1.0-397b","score":88.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ornith-1.5-397b","score":80,"metric":"percent"},{"benchmark":"mcp-atlas","model":"deepseek-v4-flash-0731","score":74.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ornith-1.0-397b","score":76.4,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"ornith-1.5-397b","score":71.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"glm-5.2","score":48.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"kimi-k3","score":73.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"ornith-1.0-397b","score":43.2,"metric":"percent"},{"benchmark":"wide-search","model":"ornith-1.5-397b","score":80.8,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-flash-0731","score":77.3,"metric":"percent"},{"benchmark":"wide-search","model":"glm-5.2","score":79,"metric":"percent"},{"benchmark":"wide-search","model":"ornith-1.0-397b","score":75.2,"metric":"percent"},{"benchmark":"browsecomp","model":"ornith-1.5-397b","score":86.6,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-flash-0731","score":84.8,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5.2","score":85.6,"metric":"percent"},{"benchmark":"browsecomp","model":"ornith-1.0-397b","score":79.7,"metric":"percent"},{"benchmark":"claw-eval","model":"ornith-1.5-397b","score":81.4,"metric":"percent"},{"benchmark":"claw-eval","model":"deepseek-v4-flash-0731","score":77.6,"metric":"percent"},{"benchmark":"claw-eval","model":"glm-5.2","score":78.8,"metric":"percent"},{"benchmark":"claw-eval","model":"claude-opus-4.8","score":80.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.5-35b-a3b","score":67.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.5-35b-a3b","score":68.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ornith-1.5-35b-a3b","score":79,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ornith-1.5-35b-a3b","score":59.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ornith-1.0-35b","score":50.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.6-35b-a3b","score":49.5,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gemma-4-31b-it","score":35.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-397b-a17b","score":51.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ornith-1.5-35b-a3b","score":71.4,"metric":"percent"},{"benchmark":"deepswe","model":"ornith-1.5-35b-a3b","score":22,"metric":"percent"},{"benchmark":"deepswe","model":"ornith-1.0-35b","score":0,"metric":"percent"},{"benchmark":"deepswe","model":"qwen3.6-35b-a3b","score":0,"metric":"percent"},{"benchmark":"deepswe","model":"qwen3.5-397b-a17b","score":1,"metric":"percent"},{"benchmark":"frontierbench","model":"ornith-1.5-35b-a3b","score":5.1,"metric":"percent"},{"benchmark":"frontierbench","model":"ornith-1.0-35b","score":1.4,"metric":"percent"},{"benchmark":"frontierbench","model":"qwen3.6-35b-a3b","score":1.4,"metric":"percent"},{"benchmark":"frontierbench","model":"qwen3.5-397b-a17b","score":1.4,"metric":"percent"},{"benchmark":"nl2repo","model":"ornith-1.5-35b-a3b","score":46.2,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"ornith-1.5-35b-a3b","score":39.8,"metric":"percent"},{"benchmark":"hle","model":"ornith-1.5-35b-a3b","score":25.6,"metric":"avg@3"},{"benchmark":"hle","model":"ornith-1.0-35b","score":20.8,"metric":"avg@3"},{"benchmark":"hle","model":"muse-glimmer-30b","score":22,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"ornith-1.5-35b-a3b","score":33.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"ornith-1.0-35b","score":30.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"qwen3.6-35b-a3b","score":28.9,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"ornith-1.5-35b-a3b","score":89.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ornith-1.0-35b","score":86.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ornith-1.5-35b-a3b","score":70.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ornith-1.0-35b","score":64.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"gemma-4-31b-it","score":55,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.5-397b-a17b","score":72.3,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"ornith-1.5-35b-a3b","score":48.7,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"ornith-1.0-35b","score":42.4,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.6-35b-a3b","score":41.7,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gemma-4-31b-it","score":40.8,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.5-397b-a17b","score":38.3,"metric":"percent"},{"benchmark":"wide-search","model":"ornith-1.5-35b-a3b","score":67.8,"metric":"percent"},{"benchmark":"wide-search","model":"ornith-1.0-35b","score":63.4,"metric":"percent"},{"benchmark":"wide-search","model":"gemma-4-31b-it","score":54.2,"metric":"percent"},{"benchmark":"browsecomp","model":"ornith-1.5-35b-a3b","score":67.6,"metric":"percent"},{"benchmark":"browsecomp","model":"ornith-1.0-35b","score":63.5,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.6-35b-a3b","score":62,"metric":"percent"},{"benchmark":"claw-eval","model":"ornith-1.5-35b-a3b","score":72.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.5-9b","score":46.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.5-9b","score":47,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ornith-1.5-9b","score":70.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ornith-1.5-9b","score":47.5,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ornith-1.0-9b","score":42.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.5-9b","score":31.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ornith-1.5-9b","score":54.4,"metric":"percent"},{"benchmark":"nl2repo","model":"ornith-1.5-9b","score":32.4,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"ornith-1.5-9b","score":20.6,"metric":"percent"},{"benchmark":"hle","model":"ornith-1.5-9b","score":20.2,"metric":"avg@3"},{"benchmark":"hle","model":"ornith-1.0-9b","score":16.8,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.5-9b","score":14.7,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"ornith-1.5-9b","score":30.5,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"ornith-1.0-9b","score":26.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"qwen3.5-9b","score":24.5,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"ornith-1.5-9b","score":86.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"ornith-1.0-9b","score":82.5,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ornith-1.5-9b","score":54.2,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ornith-1.0-9b","score":49.4,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.5-9b","score":46.8,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"ornith-1.5-9b","score":41.2,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"ornith-1.0-9b","score":33.4,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.5-9b","score":29.6,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"gemma-4-31b-it","score":52.8,"metric":"percent"},{"benchmark":"wide-search","model":"ornith-1.5-9b","score":59.5,"metric":"percent"},{"benchmark":"wide-search","model":"ornith-1.0-9b","score":55.8,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.5-9b","score":53.6,"metric":"percent"},{"benchmark":"browsecomp","model":"ornith-1.5-9b","score":56.4,"metric":"percent"},{"benchmark":"browsecomp","model":"ornith-1.0-9b","score":44.8,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-9b","score":41.5,"metric":"percent"},{"benchmark":"claw-eval","model":"ornith-1.5-9b","score":66.5,"metric":"percent"},{"benchmark":"wikiwebfacts","model":"aliceai-foundation-80b-a3b-base","score":86.5,"metric":"percent"},{"benchmark":"wikiwebfacts","model":"qwen3.5-35b-a3b-base","score":62.4,"metric":"percent"},{"benchmark":"wikiwebfacts","model":"glm-4.5-air-base","score":70.2,"metric":"percent"},{"benchmark":"wikiwebfacts","model":"nemotron-3-super-120b-a12b-base","score":72.8,"metric":"percent"},{"benchmark":"wikiwebfacts","model":"deepseek-v4-flash-base","score":83.2,"metric":"percent"},{"benchmark":"hardmultiqa","model":"aliceai-foundation-80b-a3b-base","score":67.9,"metric":"percent"},{"benchmark":"hardmultiqa","model":"qwen3.5-35b-a3b-base","score":47.2,"metric":"percent"},{"benchmark":"hardmultiqa","model":"glm-4.5-air-base","score":48.6,"metric":"percent"},{"benchmark":"hardmultiqa","model":"nemotron-3-super-120b-a12b-base","score":54.5,"metric":"percent"},{"benchmark":"hardmultiqa","model":"deepseek-v4-flash-base","score":65.4,"metric":"percent"},{"benchmark":"cultcat","model":"aliceai-foundation-80b-a3b-base","score":86.5,"metric":"percent"},{"benchmark":"cultcat","model":"qwen3.5-35b-a3b-base","score":59.2,"metric":"percent"},{"benchmark":"cultcat","model":"glm-4.5-air-base","score":59.1,"metric":"percent"},{"benchmark":"cultcat","model":"nemotron-3-super-120b-a12b-base","score":66.3,"metric":"percent"},{"benchmark":"cultcat","model":"deepseek-v4-flash-base","score":80.7,"metric":"percent"},{"benchmark":"triviaqa","model":"aliceai-foundation-80b-a3b-base","score":79,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen3.5-35b-a3b-base","score":71.4,"metric":"percent"},{"benchmark":"triviaqa","model":"glm-4.5-air-base","score":83.5,"metric":"percent"},{"benchmark":"triviaqa","model":"nemotron-3-super-120b-a12b-base","score":89.8,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v4-flash-base","score":89.4,"metric":"percent"},{"benchmark":"edubench-russian","model":"aliceai-foundation-80b-a3b-base","score":74.2,"metric":"percent"},{"benchmark":"edubench-russian","model":"qwen3.5-35b-a3b-base","score":42.9,"metric":"percent"},{"benchmark":"edubench-russian","model":"glm-4.5-air-base","score":39,"metric":"percent"},{"benchmark":"edubench-russian","model":"nemotron-3-super-120b-a12b-base","score":44,"metric":"percent"},{"benchmark":"edubench-russian","model":"deepseek-v4-flash-base","score":67.7,"metric":"percent"},{"benchmark":"edubench-literature","model":"aliceai-foundation-80b-a3b-base","score":73.8,"metric":"percent"},{"benchmark":"edubench-literature","model":"qwen3.5-35b-a3b-base","score":51.8,"metric":"percent"},{"benchmark":"edubench-literature","model":"glm-4.5-air-base","score":51.4,"metric":"percent"},{"benchmark":"edubench-literature","model":"nemotron-3-super-120b-a12b-base","score":55.8,"metric":"percent"},{"benchmark":"edubench-literature","model":"deepseek-v4-flash-base","score":69.1,"metric":"percent"},{"benchmark":"edubench-history","model":"aliceai-foundation-80b-a3b-base","score":82,"metric":"percent"},{"benchmark":"edubench-history","model":"qwen3.5-35b-a3b-base","score":65.9,"metric":"percent"},{"benchmark":"edubench-history","model":"glm-4.5-air-base","score":62.8,"metric":"percent"},{"benchmark":"edubench-history","model":"nemotron-3-super-120b-a12b-base","score":70.2,"metric":"percent"},{"benchmark":"edubench-history","model":"deepseek-v4-flash-base","score":76.9,"metric":"percent"},{"benchmark":"edubench-english","model":"aliceai-foundation-80b-a3b-base","score":76.1,"metric":"percent"},{"benchmark":"edubench-english","model":"qwen3.5-35b-a3b-base","score":71.7,"metric":"percent"},{"benchmark":"edubench-english","model":"glm-4.5-air-base","score":67.2,"metric":"percent"},{"benchmark":"edubench-english","model":"nemotron-3-super-120b-a12b-base","score":71.3,"metric":"percent"},{"benchmark":"edubench-english","model":"deepseek-v4-flash-base","score":82.9,"metric":"percent"},{"benchmark":"expertfactsqa-medicine","model":"aliceai-foundation-80b-a3b-base","score":63.6,"metric":"percent"},{"benchmark":"expertfactsqa-medicine","model":"qwen3.5-35b-a3b-base","score":59,"metric":"percent"},{"benchmark":"expertfactsqa-medicine","model":"glm-4.5-air-base","score":50.6,"metric":"percent"},{"benchmark":"expertfactsqa-medicine","model":"nemotron-3-super-120b-a12b-base","score":42.3,"metric":"percent"},{"benchmark":"expertfactsqa-medicine","model":"deepseek-v4-flash-base","score":60.7,"metric":"percent"},{"benchmark":"expertfactsqa-law","model":"aliceai-foundation-80b-a3b-base","score":49.6,"metric":"percent"},{"benchmark":"expertfactsqa-law","model":"qwen3.5-35b-a3b-base","score":27.9,"metric":"percent"},{"benchmark":"expertfactsqa-law","model":"glm-4.5-air-base","score":22.5,"metric":"percent"},{"benchmark":"expertfactsqa-law","model":"nemotron-3-super-120b-a12b-base","score":24.3,"metric":"percent"},{"benchmark":"expertfactsqa-law","model":"deepseek-v4-flash-base","score":40.5,"metric":"percent"},{"benchmark":"ege","model":"aliceai-foundation-80b-a3b-base","score":90.5,"metric":"percent"},{"benchmark":"ege","model":"qwen3.5-35b-a3b-base","score":84.7,"metric":"percent"},{"benchmark":"ege","model":"glm-4.5-air-base","score":77.8,"metric":"percent"},{"benchmark":"ege","model":"nemotron-3-super-120b-a12b-base","score":84.3,"metric":"percent"},{"benchmark":"ege","model":"deepseek-v4-flash-base","score":90.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"aliceai-foundation-80b-a3b-base","score":66.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-35b-a3b-base","score":63.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5-air-base","score":58.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-super-120b-a12b-base","score":69.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-flash-base","score":66.5,"metric":"percent"},{"benchmark":"supergpqa","model":"aliceai-foundation-80b-a3b-base","score":44.3,"metric":"percent"},{"benchmark":"supergpqa","model":"qwen3.5-35b-a3b-base","score":43.6,"metric":"percent"},{"benchmark":"supergpqa","model":"glm-4.5-air-base","score":35.4,"metric":"percent"},{"benchmark":"supergpqa","model":"nemotron-3-super-120b-a12b-base","score":46.6,"metric":"percent"},{"benchmark":"supergpqa","model":"deepseek-v4-flash-base","score":46.1,"metric":"percent"},{"benchmark":"math500","model":"aliceai-foundation-80b-a3b-base","score":91.1,"metric":"percent"},{"benchmark":"math500","model":"qwen3.5-35b-a3b-base","score":81.9,"metric":"percent"},{"benchmark":"math500","model":"glm-4.5-air-base","score":60.2,"metric":"percent"},{"benchmark":"math500","model":"nemotron-3-super-120b-a12b-base","score":84.8,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v4-flash-base","score":80.7,"metric":"percent"},{"benchmark":"edubench-math","model":"aliceai-foundation-80b-a3b-base","score":79.3,"metric":"percent"},{"benchmark":"edubench-math","model":"qwen3.5-35b-a3b-base","score":80,"metric":"percent"},{"benchmark":"edubench-math","model":"glm-4.5-air-base","score":56.9,"metric":"percent"},{"benchmark":"edubench-math","model":"nemotron-3-super-120b-a12b-base","score":69.7,"metric":"percent"},{"benchmark":"edubench-math","model":"deepseek-v4-flash-base","score":76.3,"metric":"percent"},{"benchmark":"edubench-math-university","model":"aliceai-foundation-80b-a3b-base","score":70.1,"metric":"percent"},{"benchmark":"edubench-math-university","model":"qwen3.5-35b-a3b-base","score":69.9,"metric":"percent"},{"benchmark":"edubench-math-university","model":"glm-4.5-air-base","score":51.4,"metric":"percent"},{"benchmark":"edubench-math-university","model":"nemotron-3-super-120b-a12b-base","score":67.4,"metric":"percent"},{"benchmark":"edubench-math-university","model":"deepseek-v4-flash-base","score":68.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"aliceai-foundation-80b-a3b-base","score":48.3,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen3.5-35b-a3b-base","score":43.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"glm-4.5-air-base","score":44.5,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"nemotron-3-super-120b-a12b-base","score":48.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v4-flash-base","score":49.1,"metric":"pass@1"},{"benchmark":"livecodebench","model":"aliceai-foundation-80b-a3b-base","score":50.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-35b-a3b-base","score":50.4,"metric":"percent"},{"benchmark":"livecodebench","model":"glm-4.5-air-base","score":22.6,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-super-120b-a12b-base","score":50.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v4-flash-base","score":38.1,"metric":"percent"},{"benchmark":"finqa-128k","model":"aliceai-foundation-80b-a3b-base","score":74.1,"metric":"percent"},{"benchmark":"finqa-128k","model":"qwen3.5-35b-a3b-base","score":73.5,"metric":"percent"},{"benchmark":"finqa-128k","model":"glm-4.5-air-base","score":35.5,"metric":"percent"},{"benchmark":"finqa-128k","model":"nemotron-3-super-120b-a12b-base","score":71.7,"metric":"percent"},{"benchmark":"finqa-128k","model":"deepseek-v4-flash-base","score":74.1,"metric":"percent"},{"benchmark":"longmemeval","model":"aliceai-foundation-80b-a3b-base","score":64.6,"metric":"percent"},{"benchmark":"longmemeval","model":"qwen3.5-35b-a3b-base","score":55.6,"metric":"percent"},{"benchmark":"longmemeval","model":"glm-4.5-air-base","score":50.6,"metric":"percent"},{"benchmark":"longmemeval","model":"nemotron-3-super-120b-a12b-base","score":64.8,"metric":"percent"},{"benchmark":"longmemeval","model":"deepseek-v4-flash-base","score":68,"metric":"percent"},{"benchmark":"livecodebench","model":"aliceai-foundation-80b-a3b-base","score":60.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-35b-a3b-base","score":51.9,"metric":"percent"},{"benchmark":"livecodebench","model":"nemotron-3-super-120b-a12b-base","score":34.7,"metric":"percent"},{"benchmark":"browsecomp","model":"xyz-aquila-mini","score":78.8,"metric":"percent"},{"benchmark":"browsecomp","model":"agents-a1","score":75.5,"metric":"percent"},{"benchmark":"browsecomp","model":"apodex-1.0-mini","score":71.5,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"xyz-aquila-mini","score":82.9,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"nex-n2-mini","score":79.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"apodex-1.0-mini","score":80.6,"metric":"percent"},{"benchmark":"deepsearchqa","model":"xyz-aquila-mini","score":89.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"nex-n2-mini","score":87.2,"metric":"percent"},{"benchmark":"deepsearchqa","model":"apodex-1.0-mini","score":82.2,"metric":"percent"},{"benchmark":"gaia-text-only","model":"xyz-aquila-mini","score":97.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"agents-a1","score":96,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"xyz-aquila-mini","score":48.7,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"agents-a1","score":29.6,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"nex-n2-mini","score":41.4,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"apodex-1.0-mini","score":32.8,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"mirothinker-1.7-mini","score":34.9,"metric":"percent"},{"benchmark":"hle-with-tools","model":"xyz-aquila-mini","score":51.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"nex-n2-mini","score":37.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"apodex-1.0-mini","score":46.8,"metric":"avg@3"},{"benchmark":"wide-search","model":"xyz-aquila-mini","score":80.8,"metric":"percent"},{"benchmark":"wide-search","model":"mirothinker-1.7-mini","score":73.3,"metric":"percent"},{"benchmark":"browsecomp","model":"xyz-aquila-pro","score":84.8,"metric":"percent"},{"benchmark":"browsecomp","model":"apodex-1.0","score":75.5,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"xyz-aquila-pro","score":85.1,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"nex-n2-pro","score":79.6,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"apodex-1.0","score":82.6,"metric":"percent"},{"benchmark":"deepsearchqa","model":"xyz-aquila-pro","score":92.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"nex-n2-pro","score":92.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"apodex-1.0","score":84.6,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"xyz-aquila-pro","score":53.7,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"nex-n2-pro","score":50.4,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"mirothinker-1.7","score":34.1,"metric":"percent"},{"benchmark":"hle-with-tools","model":"xyz-aquila-pro","score":53.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"nex-n2-pro","score":50,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"apodex-1.0","score":49,"metric":"avg@3"},{"benchmark":"wide-search","model":"xyz-aquila-pro","score":81.2,"metric":"percent"},{"benchmark":"browsecomp","model":"apodex-h1","score":90.3,"metric":"percent"},{"benchmark":"browsecomp","model":"kimi-k2.6","score":83.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"apodex-h1","score":84.1,"metric":"percent"},{"benchmark":"deepsearchqa","model":"apodex-h1","score":94.4,"metric":"percent"},{"benchmark":"deepsearchqa","model":"kimi-k2.6","score":92.5,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"deepseek-v4-pro-thinking-max","score":38.3,"metric":"percent"},{"benchmark":"livebrowsecomp","model":"kimi-k2.6","score":31.7,"metric":"percent"},{"benchmark":"hle-with-tools","model":"apodex-h1","score":60.8,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"kimi-k2.6","score":55.5,"metric":"avg@3"},{"benchmark":"wide-search","model":"kimi-k2.6","score":80.8,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.5-4b","score":47.2,"metric":"percent"},{"benchmark":"browsecomp","model":"agents-a1-4b","score":66.8,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.6-35b-a3b","score":67.9,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"qwen3.5-4b","score":73,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"agents-a1-4b","score":90,"metric":"avg@3"},{"benchmark":"seal-0","model":"qwen3.5-4b","score":31.5,"metric":"percent"},{"benchmark":"seal-0","model":"agents-a1-4b","score":45.8,"metric":"percent"},{"benchmark":"seal-0","model":"qwen3.6-35b-a3b","score":38.7,"metric":"percent"},{"benchmark":"seal-0","model":"nex-n2-mini","score":49.6,"metric":"percent"},{"benchmark":"seal-0","model":"agents-a1","score":56.4,"metric":"percent"},{"benchmark":"gaia-text-only","model":"qwen3.5-4b","score":58.3,"metric":"percent"},{"benchmark":"gaia-text-only","model":"agents-a1-4b","score":95.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"qwen3.5-35b-a3b","score":59.8,"metric":"percent"},{"benchmark":"gaia-text-only","model":"qwen3.6-35b-a3b","score":78.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"nex-n2-mini","score":82.5,"metric":"percent"},{"benchmark":"scicode","model":"agents-a1-4b","score":29.6,"metric":"percent"},{"benchmark":"scicode","model":"agents-a1","score":44.3,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.5-4b","score":7.6,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"agents-a1-4b","score":22.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.5-35b-a3b","score":24.2,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.6-35b-a3b","score":34.9,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"nex-n2-mini","score":34.9,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"agents-a1","score":43.9,"metric":"percent"},{"benchmark":"livecodebench","model":"agents-a1-4b","score":59.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-35b-a3b","score":76.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.6-35b-a3b","score":78.1,"metric":"percent"},{"benchmark":"livecodebench","model":"nex-n2-mini","score":59.1,"metric":"percent"},{"benchmark":"livecodebench","model":"agents-a1","score":76.2,"metric":"percent"},{"benchmark":"frontierscience-research","model":"qwen3.5-4b","score":1.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"agents-a1-4b","score":33.3,"metric":"percent"},{"benchmark":"ifbench","model":"agents-a1-4b","score":69.1,"metric":"percent"},{"benchmark":"ifbench","model":"nex-n2-mini","score":54.1,"metric":"percent"},{"benchmark":"ifbench","model":"agents-a1","score":80.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"agents-a1-4b","score":52.1,"metric":"percent"},{"benchmark":"ifeval","model":"agents-a1-4b","score":94.8,"metric":"percent"},{"benchmark":"ifeval","model":"agents-a1","score":94.8,"metric":"percent"},{"benchmark":"vitabench","model":"agents-a1-4b","score":40.3,"metric":"percent"},{"benchmark":"vitabench","model":"agents-a1","score":38.8,"metric":"percent"},{"benchmark":"mattools","model":"qwen3.5-4b","score":10.9,"metric":"percent"},{"benchmark":"mattools","model":"agents-a1-4b","score":49.3,"metric":"percent"},{"benchmark":"apex-agents","model":"apodex-1.1","score":38.5,"metric":"percent"},{"benchmark":"apex-agents","model":"apodex-1.1","score":34.4,"metric":"percent"},{"benchmark":"apex-agents","model":"apodex-1.0","score":16.5,"metric":"percent"},{"benchmark":"apex-agents","model":"claude-opus-5","score":42.3,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-flash-0731","score":34.4,"metric":"percent"},{"benchmark":"gdpval","model":"apodex-1.1","score":78.8,"metric":"percent"},{"benchmark":"gdpval","model":"apodex-1.1","score":69.5,"metric":"percent"},{"benchmark":"gdpval","model":"apodex-1.0","score":59.3,"metric":"percent"},{"benchmark":"gdpval","model":"claude-opus-5","score":89.4,"metric":"percent"},{"benchmark":"gdpval","model":"kimi-k3","score":80,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.6-sol","score":79.3,"metric":"percent"},{"benchmark":"gdpval","model":"deepseek-v4-flash-0731","score":72.7,"metric":"percent"},{"benchmark":"gdpval","model":"deepseek-v4-pro","score":71.2,"metric":"percent"},{"benchmark":"frontierfinance","model":"apodex-1.1","score":54.3,"metric":"percent"},{"benchmark":"frontierfinance","model":"apodex-1.1","score":48.7,"metric":"percent"},{"benchmark":"frontierfinance","model":"apodex-1.0","score":40.3,"metric":"percent"},{"benchmark":"frontierfinance","model":"claude-fable-5","score":49.2,"metric":"percent"},{"benchmark":"frontierfinance","model":"kimi-k3","score":48.8,"metric":"percent"},{"benchmark":"frontierfinance","model":"gpt-5.6-sol","score":46.8,"metric":"percent"},{"benchmark":"frontierfinance","model":"gemini-3.6-flash","score":46.3,"metric":"percent"},{"benchmark":"frontierfinance","model":"deepseek-v4-pro","score":45.5,"metric":"percent"},{"benchmark":"frontierscience-research","model":"apodex-1.1","score":63.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"apodex-1.1","score":55,"metric":"percent"},{"benchmark":"frontierscience-research","model":"apodex-1.0","score":28.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"deepseek-v4-flash-0731","score":55,"metric":"percent"},{"benchmark":"frontierscience-research","model":"seed2.1-deep-think","score":40.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"muse-spark","score":38,"metric":"percent"},{"benchmark":"biomysterybench","model":"apodex-1.1","score":35.3,"metric":"percent"},{"benchmark":"biomysterybench","model":"apodex-1.1","score":23.5,"metric":"percent"},{"benchmark":"biomysterybench","model":"apodex-1.0","score":17.6,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-opus-5","score":49.4,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-mythos-preview","score":29.6,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-opus-4.7","score":27,"metric":"percent"},{"benchmark":"biomysterybench","model":"claude-opus-4.6","score":23.5,"metric":"percent"},{"benchmark":"hle-with-tools","model":"apodex-1.1","score":56.1,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"apodex-1.1","score":53.2,"metric":"avg@3"},{"benchmark":"apex-agents","model":"apodex-1.1-mini","score":27.7,"metric":"percent"},{"benchmark":"apex-agents","model":"apodex-1.1-mini","score":24.2,"metric":"percent"},{"benchmark":"apex-agents","model":"kimi-k2.6","score":27.9,"metric":"percent"},{"benchmark":"apex-agents","model":"qwen3.7-plus","score":22.4,"metric":"percent"},{"benchmark":"frontierfinance","model":"apodex-1.1-mini","score":50.2,"metric":"percent"},{"benchmark":"frontierfinance","model":"apodex-1.1-mini","score":40,"metric":"percent"},{"benchmark":"frontierfinance","model":"deepseek-v4-flash-0731","score":44.2,"metric":"percent"},{"benchmark":"frontierfinance","model":"glm-5.2","score":42.8,"metric":"percent"},{"benchmark":"frontierscience-research","model":"apodex-1.1-mini","score":51.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"apodex-1.1-mini","score":45,"metric":"percent"},{"benchmark":"agieval","model":"gemma-4-e2b-it","score":74.99,"metric":"percent"},{"benchmark":"agieval","model":"gemma-4-e4b-it","score":83.53,"metric":"percent"},{"benchmark":"agieval","model":"qwen3.5-2b","score":74.25,"metric":"percent"},{"benchmark":"agieval","model":"qwen3.5-4b","score":90.2,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v2-lite-chat","score":54.29,"metric":"percent"},{"benchmark":"agieval","model":"moonlight-instruct","score":64.66,"metric":"percent"},{"benchmark":"agieval","model":"olmoe-1b-7b","score":44.06,"metric":"percent"},{"benchmark":"agieval","model":"smollm3-3b","score":68.4,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-think-7b-sft","score":78.26,"metric":"percent"},{"benchmark":"agieval","model":"olmo-3-think-7b-dpo","score":81.62,"metric":"percent"},{"benchmark":"agieval","model":"instella-moe-16b-a3b-sft","score":81.33,"metric":"percent"},{"benchmark":"agieval","model":"instella-moe-16b-a3b-dpo","score":81.51,"metric":"percent"},{"benchmark":"agieval","model":"instella-moe-16b-a3b-think","score":82.5,"metric":"percent"},{"benchmark":"aime-2024","model":"gemma-4-e2b-it","score":48.33,"metric":"percent"},{"benchmark":"aime-2024","model":"gemma-4-e4b-it","score":60.31,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3.5-2b","score":6.87,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3.5-4b","score":58.44,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v2-lite-chat","score":0.21,"metric":"percent"},{"benchmark":"aime-2024","model":"moonlight-instruct","score":5.62,"metric":"percent"},{"benchmark":"aime-2024","model":"olmoe-1b-7b","score":0.83,"metric":"percent"},{"benchmark":"aime-2024","model":"smollm3-3b","score":47.81,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-7b-sft","score":75.21,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-7b-dpo","score":75.31,"metric":"percent"},{"benchmark":"aime-2024","model":"olmo-3-think-7b","score":75,"metric":"percent"},{"benchmark":"aime-2024","model":"instella-moe-16b-a3b-sft","score":77.5,"metric":"percent"},{"benchmark":"aime-2024","model":"instella-moe-16b-a3b-dpo","score":77.4,"metric":"percent"},{"benchmark":"aime-2024","model":"instella-moe-16b-a3b-think","score":76.9,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e2b-it","score":32.08,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e4b-it","score":42.92,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-2b","score":11.46,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-4b","score":51.88,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v2-lite-chat","score":0.31,"metric":"percent"},{"benchmark":"aime-2025","model":"moonlight-instruct","score":3.23,"metric":"percent"},{"benchmark":"aime-2025","model":"olmoe-1b-7b","score":0,"metric":"percent"},{"benchmark":"aime-2025","model":"smollm3-3b","score":38.75,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-7b-sft","score":64.27,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-7b-dpo","score":66.46,"metric":"percent"},{"benchmark":"aime-2025","model":"olmo-3-think-7b","score":69.17,"metric":"percent"},{"benchmark":"aime-2025","model":"instella-moe-16b-a3b-sft","score":71.35,"metric":"percent"},{"benchmark":"aime-2025","model":"instella-moe-16b-a3b-dpo","score":73.23,"metric":"percent"},{"benchmark":"aime-2025","model":"instella-moe-16b-a3b-think","score":73.4,"metric":"percent"},{"benchmark":"bbh","model":"gemma-4-e2b-it","score":72.8,"metric":"percent"},{"benchmark":"bbh","model":"gemma-4-e4b-it","score":76.79,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-2b","score":70.47,"metric":"percent"},{"benchmark":"bbh","model":"qwen3.5-4b","score":77.21,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2-lite-chat","score":39.86,"metric":"percent"},{"benchmark":"bbh","model":"moonlight-instruct","score":53.77,"metric":"percent"},{"benchmark":"bbh","model":"olmoe-1b-7b","score":33.27,"metric":"percent"},{"benchmark":"bbh","model":"smollm3-3b","score":65.7,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-7b-sft","score":74.8,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-7b-dpo","score":72.09,"metric":"percent"},{"benchmark":"bbh","model":"olmo-3-think-7b","score":69.67,"metric":"percent"},{"benchmark":"bbh","model":"instella-moe-16b-a3b-sft","score":74.34,"metric":"percent"},{"benchmark":"bbh","model":"instella-moe-16b-a3b-dpo","score":74.77,"metric":"percent"},{"benchmark":"bbh","model":"instella-moe-16b-a3b-think","score":74.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-4-e2b-it","score":62.32,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-4-e4b-it","score":89.63,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-2b","score":48.35,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-4b","score":85.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v2-lite-chat","score":44.76,"metric":"percent"},{"benchmark":"humaneval-plus","model":"moonlight-instruct","score":66.77,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmoe-1b-7b","score":20.98,"metric":"percent"},{"benchmark":"humaneval-plus","model":"smollm3-3b","score":78.84,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-7b-sft","score":88.17,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-7b-dpo","score":90,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-think-7b","score":89.88,"metric":"percent"},{"benchmark":"humaneval-plus","model":"instella-moe-16b-a3b-sft","score":86.77,"metric":"percent"},{"benchmark":"humaneval-plus","model":"instella-moe-16b-a3b-dpo","score":86.52,"metric":"percent"},{"benchmark":"humaneval-plus","model":"instella-moe-16b-a3b-think","score":87.9,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-4-e2b-it","score":46.21,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-4-e4b-it","score":50.22,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-2b","score":50.22,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-4b","score":69.64,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v2-lite-chat","score":28.12,"metric":"percent"},{"benchmark":"gpqa","model":"moonlight-instruct","score":33.26,"metric":"percent"},{"benchmark":"gpqa","model":"olmoe-1b-7b","score":26.56,"metric":"percent"},{"benchmark":"gpqa","model":"smollm3-3b","score":39.51,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-7b-sft","score":44.42,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-7b-dpo","score":44.87,"metric":"percent"},{"benchmark":"gpqa","model":"olmo-3-think-7b","score":45.54,"metric":"percent"},{"benchmark":"gpqa","model":"instella-moe-16b-a3b-sft","score":59.38,"metric":"percent"},{"benchmark":"gpqa","model":"instella-moe-16b-a3b-dpo","score":62.72,"metric":"percent"},{"benchmark":"gpqa","model":"instella-moe-16b-a3b-think","score":61.2,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e2b-it","score":86.88,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e4b-it","score":87.8,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-2b","score":37.52,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-4b","score":64.51,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v2-lite-chat","score":46.77,"metric":"percent"},{"benchmark":"ifeval","model":"moonlight-instruct","score":46.21,"metric":"percent"},{"benchmark":"ifeval","model":"olmoe-1b-7b","score":67.1,"metric":"percent"},{"benchmark":"ifeval","model":"smollm3-3b","score":70.43,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-7b-sft","score":81.89,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-7b-dpo","score":77.26,"metric":"percent"},{"benchmark":"ifeval","model":"olmo-3-think-7b","score":90.39,"metric":"percent"},{"benchmark":"ifeval","model":"instella-moe-16b-a3b-sft","score":81.51,"metric":"percent"},{"benchmark":"ifeval","model":"instella-moe-16b-a3b-dpo","score":77.08,"metric":"percent"},{"benchmark":"ifeval","model":"instella-moe-16b-a3b-think","score":83.7,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e2b-it","score":46.74,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-e4b-it","score":57.58,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-2b","score":8.19,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b","score":40.22,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2-lite-chat","score":6.15,"metric":"percent"},{"benchmark":"livecodebench","model":"moonlight-instruct","score":14.52,"metric":"percent"},{"benchmark":"livecodebench","model":"olmoe-1b-7b","score":2.89,"metric":"percent"},{"benchmark":"livecodebench","model":"smollm3-3b","score":29.78,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-7b-sft","score":42.99,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-7b-dpo","score":45.93,"metric":"percent"},{"benchmark":"livecodebench","model":"olmo-3-think-7b","score":51.94,"metric":"percent"},{"benchmark":"livecodebench","model":"instella-moe-16b-a3b-sft","score":48.74,"metric":"percent"},{"benchmark":"livecodebench","model":"instella-moe-16b-a3b-dpo","score":53.39,"metric":"percent"},{"benchmark":"livecodebench","model":"instella-moe-16b-a3b-think","score":54.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-4-e2b-it","score":63.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-4-e4b-it","score":65.82,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.5-2b","score":30.21,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.5-4b","score":60.13,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v2-lite-chat","score":41.48,"metric":"percent"},{"benchmark":"mbpp-plus","model":"moonlight-instruct","score":49.07,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmoe-1b-7b","score":34.58,"metric":"percent"},{"benchmark":"mbpp-plus","model":"smollm3-3b","score":60.05,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-7b-sft","score":63.47,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-7b-dpo","score":64.47,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-think-7b","score":64.84,"metric":"percent"},{"benchmark":"mbpp-plus","model":"instella-moe-16b-a3b-sft","score":61.64,"metric":"percent"},{"benchmark":"mbpp-plus","model":"instella-moe-16b-a3b-dpo","score":61.98,"metric":"percent"},{"benchmark":"mbpp-plus","model":"instella-moe-16b-a3b-think","score":62,"metric":"percent"},{"benchmark":"math","model":"gemma-4-e2b-it","score":86.65,"metric":"percent"},{"benchmark":"math","model":"gemma-4-e4b-it","score":92.52,"metric":"percent"},{"benchmark":"math","model":"qwen3.5-2b","score":48.09,"metric":"percent"},{"benchmark":"math","model":"qwen3.5-4b","score":85.67,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2-lite-chat","score":24.35,"metric":"percent"},{"benchmark":"math","model":"moonlight-instruct","score":63.13,"metric":"percent"},{"benchmark":"math","model":"olmoe-1b-7b","score":19.05,"metric":"percent"},{"benchmark":"math","model":"smollm3-3b","score":90.19,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-7b-sft","score":94.67,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-7b-dpo","score":95.48,"metric":"percent"},{"benchmark":"math","model":"olmo-3-think-7b","score":95.24,"metric":"percent"},{"benchmark":"math","model":"instella-moe-16b-a3b-sft","score":94.67,"metric":"percent"},{"benchmark":"math","model":"instella-moe-16b-a3b-dpo","score":94.92,"metric":"percent"},{"benchmark":"math","model":"instella-moe-16b-a3b-think","score":94.8,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-e2b-it","score":76.49,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-e4b-it","score":83.59,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-2b","score":76.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-4b","score":87.09,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2-lite-chat","score":58.53,"metric":"percent"},{"benchmark":"mmlu","model":"moonlight-instruct","score":70.06,"metric":"percent"},{"benchmark":"mmlu","model":"olmoe-1b-7b","score":47.56,"metric":"percent"},{"benchmark":"mmlu","model":"smollm3-3b","score":74.18,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-7b-sft","score":76.91,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-7b-dpo","score":79.09,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-think-7b","score":79.07,"metric":"percent"},{"benchmark":"mmlu","model":"instella-moe-16b-a3b-sft","score":80.82,"metric":"percent"},{"benchmark":"mmlu","model":"instella-moe-16b-a3b-dpo","score":81.74,"metric":"percent"},{"benchmark":"mmlu","model":"instella-moe-16b-a3b-think","score":81.3,"metric":"percent"},{"benchmark":"alpacaeval","model":"gemma-4-e2b-it","score":40.28,"metric":"percent"},{"benchmark":"alpacaeval","model":"gemma-4-e4b-it","score":54.9,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen3.5-2b","score":29.35,"metric":"percent"},{"benchmark":"alpacaeval","model":"qwen3.5-4b","score":66.49,"metric":"percent"},{"benchmark":"alpacaeval","model":"deepseek-v2-lite-chat","score":8.9,"metric":"percent"},{"benchmark":"alpacaeval","model":"moonlight-instruct","score":21.39,"metric":"percent"},{"benchmark":"alpacaeval","model":"olmoe-1b-7b","score":9.7,"metric":"percent"},{"benchmark":"alpacaeval","model":"smollm3-3b","score":33.39,"metric":"percent"},{"benchmark":"alpacaeval","model":"olmo-3-think-7b-sft","score":46.66,"metric":"percent"},{"benchmark":"alpacaeval","model":"olmo-3-think-7b-dpo","score":45.19,"metric":"percent"},{"benchmark":"alpacaeval","model":"olmo-3-think-7b","score":51.39,"metric":"percent"},{"benchmark":"alpacaeval","model":"instella-moe-16b-a3b-sft","score":40.92,"metric":"percent"},{"benchmark":"alpacaeval","model":"instella-moe-16b-a3b-dpo","score":46.8,"metric":"percent"},{"benchmark":"alpacaeval","model":"instella-moe-16b-a3b-think","score":45.81,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-3.2-3b","score":85.3,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-4-e2b","score":53.2,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-4-e4b","score":48.8,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen3.5-2b-base","score":93.7,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen3.5-4b-base","score":97.5,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-v2-lite","score":87.6,"metric":"percent"},{"benchmark":"arc-easy","model":"moonlight-base","score":95.3,"metric":"percent"},{"benchmark":"arc-easy","model":"olmoe-1b-7b-base","score":84.4,"metric":"percent"},{"benchmark":"arc-easy","model":"smollm3-3b-base","score":90.9,"metric":"percent"},{"benchmark":"arc-easy","model":"olmo-3-7b","score":93.6,"metric":"percent"},{"benchmark":"arc-easy","model":"instella-moe-16b-a3b-base","score":93.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.2-3b","score":71.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-4-e2b","score":41.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-4-e4b","score":37.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-2b-base","score":84.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen3.5-4b-base","score":93.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2-lite","score":74.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"moonlight-base","score":85.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmoe-1b-7b-base","score":69.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"smollm3-3b-base","score":79.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-3-7b","score":84.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"instella-moe-16b-a3b-base","score":83.8,"metric":"percent"},{"benchmark":"boolq","model":"llama-3.2-3b","score":74.2,"metric":"percent"},{"benchmark":"boolq","model":"gemma-4-e2b","score":78.9,"metric":"percent"},{"benchmark":"boolq","model":"gemma-4-e4b","score":87.2,"metric":"percent"},{"benchmark":"boolq","model":"qwen3.5-2b-base","score":85.8,"metric":"percent"},{"benchmark":"boolq","model":"qwen3.5-4b-base","score":89.8,"metric":"percent"},{"benchmark":"boolq","model":"deepseek-v2-lite","score":81.7,"metric":"percent"},{"benchmark":"boolq","model":"moonlight-base","score":85.9,"metric":"percent"},{"benchmark":"boolq","model":"olmoe-1b-7b-base","score":83.9,"metric":"percent"},{"benchmark":"boolq","model":"smollm3-3b-base","score":83.8,"metric":"percent"},{"benchmark":"boolq","model":"olmo-3-7b","score":63.9,"metric":"percent"},{"benchmark":"boolq","model":"instella-moe-16b-a3b-base","score":84.7,"metric":"percent"},{"benchmark":"sciq","model":"llama-3.2-3b","score":87.1,"metric":"percent"},{"benchmark":"sciq","model":"gemma-4-e2b","score":39.6,"metric":"percent"},{"benchmark":"sciq","model":"gemma-4-e4b","score":43.5,"metric":"percent"},{"benchmark":"sciq","model":"qwen3.5-2b-base","score":91.9,"metric":"percent"},{"benchmark":"sciq","model":"qwen3.5-4b-base","score":95.4,"metric":"percent"},{"benchmark":"sciq","model":"deepseek-v2-lite","score":88.3,"metric":"percent"},{"benchmark":"sciq","model":"moonlight-base","score":94.2,"metric":"percent"},{"benchmark":"sciq","model":"olmoe-1b-7b-base","score":87,"metric":"percent"},{"benchmark":"sciq","model":"smollm3-3b-base","score":90.1,"metric":"percent"},{"benchmark":"sciq","model":"instella-moe-16b-a3b-base","score":93.6,"metric":"percent"},{"benchmark":"piqa","model":"llama-3.2-3b","score":74.1,"metric":"percent"},{"benchmark":"piqa","model":"gemma-4-e2b","score":53.4,"metric":"percent"},{"benchmark":"piqa","model":"gemma-4-e4b","score":50.2,"metric":"percent"},{"benchmark":"piqa","model":"qwen3.5-2b-base","score":76.7,"metric":"percent"},{"benchmark":"piqa","model":"qwen3.5-4b-base","score":87.1,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-v2-lite","score":71.4,"metric":"percent"},{"benchmark":"piqa","model":"moonlight-base","score":81.8,"metric":"percent"},{"benchmark":"piqa","model":"olmoe-1b-7b-base","score":73.5,"metric":"percent"},{"benchmark":"piqa","model":"smollm3-3b-base","score":73.9,"metric":"percent"},{"benchmark":"piqa","model":"instella-moe-16b-a3b-base","score":83.8,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.2-3b","score":77,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-4-e2b","score":47.5,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-4-e4b","score":52.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3.5-2b-base","score":68.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen3.5-4b-base","score":77.1,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v2-lite","score":80.8,"metric":"percent"},{"benchmark":"hellaswag","model":"moonlight-base","score":82.5,"metric":"percent"},{"benchmark":"hellaswag","model":"olmoe-1b-7b-base","score":79.9,"metric":"percent"},{"benchmark":"hellaswag","model":"smollm3-3b-base","score":77.8,"metric":"percent"},{"benchmark":"hellaswag","model":"instella-moe-16b-a3b-base","score":79.2,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.2-3b","score":83,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-4-e2b","score":61.2,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-4-e4b","score":63.4,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3.5-2b-base","score":78.3,"metric":"percent"},{"benchmark":"winogrande","model":"qwen3.5-4b-base","score":84.6,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v2-lite","score":84.8,"metric":"percent"},{"benchmark":"winogrande","model":"moonlight-base","score":85.6,"metric":"percent"},{"benchmark":"winogrande","model":"olmoe-1b-7b-base","score":84.1,"metric":"percent"},{"benchmark":"winogrande","model":"smollm3-3b-base","score":84.4,"metric":"percent"},{"benchmark":"winogrande","model":"instella-moe-16b-a3b-base","score":86.5,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-3.2-3b","score":67,"metric":"percent"},{"benchmark":"openbookqa","model":"gemma-4-e2b","score":74.8,"metric":"percent"},{"benchmark":"openbookqa","model":"gemma-4-e4b","score":85.2,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen3.5-2b-base","score":77.4,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen3.5-4b-base","score":89.4,"metric":"percent"},{"benchmark":"openbookqa","model":"deepseek-v2-lite","score":72.4,"metric":"percent"},{"benchmark":"openbookqa","model":"moonlight-base","score":82.2,"metric":"percent"},{"benchmark":"openbookqa","model":"olmoe-1b-7b-base","score":79,"metric":"percent"},{"benchmark":"openbookqa","model":"smollm3-3b-base","score":77.4,"metric":"percent"},{"benchmark":"openbookqa","model":"olmo-3-7b","score":69.6,"metric":"percent"},{"benchmark":"openbookqa","model":"instella-moe-16b-a3b-base","score":81.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.2-3b","score":57.5,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-e2b","score":59.2,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-e4b","score":70.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-2b-base","score":65.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3.5-4b-base","score":77.3,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2-lite","score":58.8,"metric":"percent"},{"benchmark":"mmlu","model":"moonlight-base","score":71.3,"metric":"percent"},{"benchmark":"mmlu","model":"olmoe-1b-7b-base","score":62.5,"metric":"percent"},{"benchmark":"mmlu","model":"smollm3-3b-base","score":62.6,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-3-7b","score":56.4,"metric":"percent"},{"benchmark":"mmlu","model":"instella-moe-16b-a3b-base","score":67.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-3b","score":30.2,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-4-e2b","score":24,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-4-e4b","score":56.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-2b-base","score":67.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.5-4b-base","score":84.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2-lite","score":38.9,"metric":"percent"},{"benchmark":"gsm8k","model":"moonlight-base","score":85.6,"metric":"percent"},{"benchmark":"gsm8k","model":"olmoe-1b-7b-base","score":51,"metric":"percent"},{"benchmark":"gsm8k","model":"smollm3-3b-base","score":69.7,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-3-7b","score":74.6,"metric":"percent"},{"benchmark":"gsm8k","model":"instella-moe-16b-a3b-base","score":81.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.2-3b","score":31,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-4-e2b","score":22,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-4-e4b","score":44.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-2b-base","score":34.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.5-4b-base","score":55.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v2-lite","score":32.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"moonlight-base","score":52.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmoe-1b-7b-base","score":14.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"smollm3-3b-base","score":37.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-3-7b","score":48,"metric":"percent"},{"benchmark":"humaneval-plus","model":"instella-moe-16b-a3b-base","score":65.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.2-3b","score":32.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-4-e2b","score":31,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-4-e4b","score":42.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.5-2b-base","score":37.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.5-4b-base","score":53,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-v2-lite","score":32.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"moonlight-base","score":45.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmoe-1b-7b-base","score":20.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"smollm3-3b-base","score":49.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-3-7b","score":43.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"instella-moe-16b-a3b-base","score":52.5,"metric":"percent"},{"benchmark":"minerva-math","model":"llama-3.2-3b","score":8.7,"metric":"percent"},{"benchmark":"minerva-math","model":"gemma-4-e2b","score":9.4,"metric":"percent"},{"benchmark":"minerva-math","model":"gemma-4-e4b","score":20.6,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen3.5-2b-base","score":32.5,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen3.5-4b-base","score":48.3,"metric":"percent"},{"benchmark":"minerva-math","model":"deepseek-v2-lite","score":15.6,"metric":"percent"},{"benchmark":"minerva-math","model":"moonlight-base","score":43,"metric":"percent"},{"benchmark":"minerva-math","model":"olmoe-1b-7b-base","score":15.2,"metric":"percent"},{"benchmark":"minerva-math","model":"smollm3-3b-base","score":39.6,"metric":"percent"},{"benchmark":"minerva-math","model":"olmo-3-7b","score":40.2,"metric":"percent"},{"benchmark":"minerva-math","model":"instella-moe-16b-a3b-base","score":43,"metric":"percent"},{"benchmark":"ruler-8k","model":"llama-3.2-3b","score":0,"metric":"percent"},{"benchmark":"ruler-8k","model":"gemma-4-e2b","score":87.4,"metric":"percent"},{"benchmark":"ruler-8k","model":"gemma-4-e4b","score":91.3,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen3.5-2b-base","score":90.9,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen3.5-4b-base","score":88.1,"metric":"percent"},{"benchmark":"ruler-8k","model":"deepseek-v2-lite","score":76.8,"metric":"percent"},{"benchmark":"ruler-8k","model":"moonlight-base","score":89.5,"metric":"percent"},{"benchmark":"ruler-8k","model":"olmoe-1b-7b-base","score":0.2,"metric":"percent"},{"benchmark":"ruler-8k","model":"smollm3-3b-base","score":84.8,"metric":"percent"},{"benchmark":"ruler-8k","model":"olmo-3-7b","score":90.6,"metric":"percent"},{"benchmark":"ruler-8k","model":"instella-moe-16b-a3b-base","score":86.2,"metric":"percent"},{"benchmark":"ruler-16k","model":"llama-3.2-3b","score":0,"metric":"percent"},{"benchmark":"ruler-16k","model":"gemma-4-e2b","score":85,"metric":"percent"},{"benchmark":"ruler-16k","model":"gemma-4-e4b","score":92.2,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen3.5-2b-base","score":87.7,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen3.5-4b-base","score":90.4,"metric":"percent"},{"benchmark":"ruler-16k","model":"deepseek-v2-lite","score":72,"metric":"percent"},{"benchmark":"ruler-16k","model":"moonlight-base","score":0,"metric":"percent"},{"benchmark":"ruler-16k","model":"olmoe-1b-7b-base","score":0,"metric":"percent"},{"benchmark":"ruler-16k","model":"smollm3-3b-base","score":82.1,"metric":"percent"},{"benchmark":"ruler-16k","model":"olmo-3-7b","score":84.2,"metric":"percent"},{"benchmark":"ruler-16k","model":"instella-moe-16b-a3b-base","score":82.8,"metric":"percent"},{"benchmark":"ruler-32k","model":"llama-3.2-3b","score":0,"metric":"percent"},{"benchmark":"ruler-32k","model":"gemma-4-e2b","score":82,"metric":"percent"},{"benchmark":"ruler-32k","model":"gemma-4-e4b","score":89.6,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen3.5-2b-base","score":83,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen3.5-4b-base","score":90.8,"metric":"percent"},{"benchmark":"ruler-32k","model":"deepseek-v2-lite","score":58.7,"metric":"percent"},{"benchmark":"ruler-32k","model":"moonlight-base","score":0.1,"metric":"percent"},{"benchmark":"ruler-32k","model":"olmoe-1b-7b-base","score":0,"metric":"percent"},{"benchmark":"ruler-32k","model":"smollm3-3b-base","score":76.4,"metric":"percent"},{"benchmark":"ruler-32k","model":"olmo-3-7b","score":78.1,"metric":"percent"},{"benchmark":"ruler-32k","model":"instella-moe-16b-a3b-base","score":77.9,"metric":"percent"},{"benchmark":"ruler-64k","model":"llama-3.2-3b","score":0,"metric":"percent"},{"benchmark":"ruler-64k","model":"gemma-4-e2b","score":78,"metric":"percent"},{"benchmark":"ruler-64k","model":"gemma-4-e4b","score":84.7,"metric":"percent"},{"benchmark":"ruler-64k","model":"qwen3.5-2b-base","score":83,"metric":"percent"},{"benchmark":"ruler-64k","model":"qwen3.5-4b-base","score":87.1,"metric":"percent"},{"benchmark":"ruler-64k","model":"deepseek-v2-lite","score":51.1,"metric":"percent"},{"benchmark":"ruler-64k","model":"moonlight-base","score":0,"metric":"percent"},{"benchmark":"ruler-64k","model":"olmoe-1b-7b-base","score":0,"metric":"percent"},{"benchmark":"ruler-64k","model":"smollm3-3b-base","score":71,"metric":"percent"},{"benchmark":"ruler-64k","model":"olmo-3-7b","score":67.8,"metric":"percent"},{"benchmark":"ruler-64k","model":"instella-moe-16b-a3b-base","score":70.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-5.5","score":74.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-5","score":73.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"naive-n0.5-flash","score":67.8,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5.5","score":34.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"muse-spark-1.3","score":33.3,"metric":"percent"},{"benchmark":"agents-last-exam","model":"naive-n0.5-flash","score":32.4,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5","score":29.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"naive-n0.5-flash","score":86.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"naive-n0.5-flash","score":73.6,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"claude-opus-5","score":37,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"deepseek-v4.1-flash","score":20.3,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"naive-n0.5-flash","score":17.5,"metric":"percent"},{"benchmark":"programbench-almost-solved","model":"hy4-preview","score":17.5,"metric":"percent"},{"benchmark":"nl2repo","model":"naive-n0.5-flash","score":71.9,"metric":"percent"},{"benchmark":"frontierswe","model":"naive-n0.5-flash","score":78.2,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.6-sol","score":41.8,"metric":"percent"},{"benchmark":"posttrainbench","model":"naive-n0.5-flash","score":37.5,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-fable-5","score":36.2,"metric":"percent"},{"benchmark":"mle-bench-30","model":"naive-n0.5-flash","score":73.7,"metric":"percent"},{"benchmark":"mle-bench-30","model":"claude-sonnet-5","score":66.9,"metric":"percent"},{"benchmark":"mle-bench-30","model":"gemini-3.6-flash","score":63.9,"metric":"percent"},{"benchmark":"mle-bench-30","model":"gemini-3.5-flash","score":49.7,"metric":"percent"},{"benchmark":"mle-bench-30","model":"gpt-5.6-luna","score":47.6,"metric":"percent"},{"benchmark":"mle-bench-30","model":"grok-4.5","score":43.2,"metric":"percent"},{"benchmark":"paperbench","model":"naive-n0.5-flash","score":63.2,"metric":"percent"},{"benchmark":"sol-execbench","model":"naive-n0.5-flash","score":72.81,"metric":"score"},{"benchmark":"nanochat-autoresearch","model":"naive-n0.5-flash","score":0.9051,"metric":"bpb"},{"benchmark":"nanogpt-speedrun","model":"naive-n0.5-flash","score":73.8,"metric":"seconds"},{"benchmark":"cv-bench","model":"zdtaichu5.0-9b","score":86.82,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3.5-9b","score":87.19,"metric":"percent"},{"benchmark":"cv-bench","model":"step3-vl-10b","score":83.49,"metric":"percent"},{"benchmark":"cv-bench","model":"gemma-4-e4b-it","score":68.1,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-5.2","score":86.84,"metric":"percent"},{"benchmark":"3dsrbench","model":"zdtaichu5.0-9b","score":60.96,"metric":"percent"},{"benchmark":"3dsrbench","model":"qwen3.5-9b","score":56.78,"metric":"percent"},{"benchmark":"3dsrbench","model":"step3-vl-10b","score":55.01,"metric":"percent"},{"benchmark":"3dsrbench","model":"gemma-4-e4b-it","score":53.62,"metric":"percent"},{"benchmark":"3dsrbench","model":"gemini-3-pro","score":68.92,"metric":"percent"},{"benchmark":"3dsrbench","model":"grok-4","score":54.93,"metric":"percent"},{"benchmark":"3dsrbench","model":"gpt-5.2","score":60.2,"metric":"percent"},{"benchmark":"sparbench","model":"zdtaichu5.0-9b","score":51.82,"metric":"percent"},{"benchmark":"sparbench","model":"qwen3.5-9b","score":50.79,"metric":"percent"},{"benchmark":"sparbench","model":"step3-vl-10b","score":45.68,"metric":"percent"},{"benchmark":"sparbench","model":"gemma-4-e4b-it","score":28.5,"metric":"percent"},{"benchmark":"sparbench","model":"gemini-3-pro","score":48.74,"metric":"percent"},{"benchmark":"sparbench","model":"grok-4","score":44.76,"metric":"percent"},{"benchmark":"sparbench","model":"gpt-5.2","score":55.07,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"zdtaichu5.0-9b","score":62.5,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"qwen3.5-9b","score":48.2,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"step3-vl-10b","score":46.14,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"gemma-4-e4b-it","score":41.68,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"gemini-3-pro","score":50.36,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"grok-4","score":43.23,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"gpt-5.2","score":47.3,"metric":"percent"},{"benchmark":"mmsi-bench","model":"zdtaichu5.0-9b","score":47.2,"metric":"percent"},{"benchmark":"mmsi-bench","model":"qwen3.5-9b","score":38.7,"metric":"percent"},{"benchmark":"mmsi-bench","model":"step3-vl-10b","score":32.18,"metric":"percent"},{"benchmark":"mmsi-bench","model":"gemma-4-e4b-it","score":29.2,"metric":"percent"},{"benchmark":"mmsi-bench","model":"gemini-3-pro","score":45.2,"metric":"percent"},{"benchmark":"mmsi-bench","model":"grok-4","score":37.8,"metric":"percent"},{"benchmark":"mmsi-bench","model":"gpt-5.2","score":41.3,"metric":"percent"},{"benchmark":"mindcube-tiny","model":"zdtaichu5.0-9b","score":78.27,"metric":"percent"},{"benchmark":"mindcube-tiny","model":"qwen3.5-9b","score":57.6,"metric":"percent"},{"benchmark":"mindcube-tiny","model":"step3-vl-10b","score":62.81,"metric":"percent"},{"benchmark":"mindcube-tiny","model":"gemma-4-e4b-it","score":48.85,"metric":"percent"},{"benchmark":"mindcube-tiny","model":"gemini-3-pro","score":70.87,"metric":"percent"},{"benchmark":"mindcube-tiny","model":"grok-4","score":63.56,"metric":"percent"},{"benchmark":"mindcube-tiny","model":"gpt-5.2","score":60.38,"metric":"percent"},{"benchmark":"erqa","model":"zdtaichu5.0-9b","score":48,"metric":"percent"},{"benchmark":"erqa","model":"qwen3.5-9b","score":41.5,"metric":"percent"},{"benchmark":"erqa","model":"step3-vl-10b","score":47.75,"metric":"percent"},{"benchmark":"erqa","model":"gemma-4-e4b-it","score":30.2,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3-pro","score":66,"metric":"percent"},{"benchmark":"robospatialhome","model":"zdtaichu5.0-9b","score":56,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3.5-9b","score":54.1,"metric":"percent"},{"benchmark":"robospatialhome","model":"step3-vl-10b","score":52.86,"metric":"percent"},{"benchmark":"robospatialhome","model":"gemma-4-e4b-it","score":49.43,"metric":"percent"},{"benchmark":"robospatialhome","model":"gemini-3-pro","score":57.4,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-5.2","score":43.78,"metric":"percent"},{"benchmark":"vsi-bench","model":"zdtaichu5.0-9b","score":59.69,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3.5-9b","score":55.68,"metric":"percent"},{"benchmark":"vsi-bench","model":"step3-vl-10b","score":42.42,"metric":"percent"},{"benchmark":"vsi-bench","model":"gemma-4-e4b-it","score":32.91,"metric":"percent"},{"benchmark":"vsi-bench","model":"gemini-3-pro","score":52.51,"metric":"percent"},{"benchmark":"vsi-bench","model":"grok-4","score":47.92,"metric":"percent"},{"benchmark":"vsi-bench","model":"gpt-5.2","score":54.49,"metric":"percent"},{"benchmark":"mathvista-mini","model":"zdtaichu5.0-9b","score":84.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"step3-vl-10b","score":83.97,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemma-4-e4b-it","score":65.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"grok-4","score":72.5,"metric":"percent"},{"benchmark":"wemath","model":"zdtaichu5.0-9b","score":75.9,"metric":"percent"},{"benchmark":"wemath","model":"step3-vl-10b","score":73.03,"metric":"percent"},{"benchmark":"wemath","model":"gemma-4-e4b-it","score":50.19,"metric":"percent"},{"benchmark":"mathverse-mini","model":"zdtaichu5.0-9b","score":76.4,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen3.5-9b","score":84.14,"metric":"percent"},{"benchmark":"mathverse-mini","model":"step3-vl-10b","score":74.6,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gemma-4-e4b-it","score":53.55,"metric":"percent"},{"benchmark":"mmstar","model":"zdtaichu5.0-9b","score":76.8,"metric":"percent"},{"benchmark":"mmstar","model":"gemma-4-e4b-it","score":62,"metric":"percent"},{"benchmark":"mmstar","model":"grok-4","score":69.6,"metric":"percent"},{"benchmark":"ai2d","model":"zdtaichu5.0-9b","score":91.48,"metric":"percent"},{"benchmark":"ai2d","model":"gemma-4-e4b-it","score":79.15,"metric":"percent"},{"benchmark":"realworldqa","model":"zdtaichu5.0-9b","score":76.99,"metric":"percent"},{"benchmark":"realworldqa","model":"step3-vl-10b","score":74.44,"metric":"percent"},{"benchmark":"realworldqa","model":"gemma-4-e4b-it","score":59.08,"metric":"percent"},{"benchmark":"ocrbench","model":"zdtaichu5.0-9b","score":85.5,"metric":"percent"},{"benchmark":"ocrbench","model":"gemma-4-e4b-it","score":76.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"zdtaichu5.0-9b","score":77.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"step3-vl-10b","score":76.02,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-4","score":85.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"zdtaichu5.0-9b","score":88.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"step3-vl-10b","score":86.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-4-e4b-it","score":85.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"grok-4","score":86.22,"metric":"percent"},{"benchmark":"ifeval","model":"zdtaichu5.0-9b","score":93.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-9b","score":88.72,"metric":"percent"},{"benchmark":"ifeval","model":"step3-vl-10b","score":82.16,"metric":"percent"},{"benchmark":"ifeval","model":"grok-4","score":92.8,"metric":"percent"},{"benchmark":"ifbench","model":"zdtaichu5.0-9b","score":69,"metric":"percent"},{"benchmark":"ifbench","model":"step3-vl-10b","score":41.49,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":34.7,"metric":"percent"},{"benchmark":"aime-2025","model":"zdtaichu5.0-9b","score":86.7,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.5-9b","score":83.75,"metric":"percent"},{"benchmark":"aime-2025","model":"step3-vl-10b","score":87.66,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-e4b-it","score":41.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"zdtaichu5.0-9b","score":89.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-9b","score":87.92,"metric":"percent"},{"benchmark":"aime-2026-i","model":"step3-vl-10b","score":88.75,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"zdtaichu5.0-9b","score":84.2,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"step3-vl-10b","score":78.18,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"gemma-4-e4b-it","score":26.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"zdtaichu5.0-9b","score":72.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.5-9b","score":73.48,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"step3-vl-10b","score":63.64,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-e4b-it","score":33.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemini-3-pro","score":86.36,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gpt-5.2","score":96.97,"metric":"percent"},{"benchmark":"livecodebench","model":"zdtaichu5.0-9b","score":73.4,"metric":"percent"},{"benchmark":"livecodebench","model":"step3-vl-10b","score":58.86,"metric":"percent"},{"benchmark":"ifbench","model":"agnes-3.0-flash-preview","score":74.2,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k2.5","score":43.7,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-27b","score":75.6,"metric":"percent"},{"benchmark":"ifbench","model":"deepseek-v4-flash-0731","score":75.8,"metric":"percent"},{"benchmark":"ifbench","model":"gemini-3.5-flash","score":76.3,"metric":"percent"},{"benchmark":"scicode","model":"agnes-3.0-flash-preview","score":38.08,"metric":"percent"},{"benchmark":"scicode","model":"kimi-k2.5","score":39.6,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.5-27b","score":39.5,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-flash-0731","score":50.3,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-27b","score":46.6,"metric":"percent"},{"benchmark":"scicode","model":"gemini-3.5-flash","score":53.1,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-flash-next","score":50.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"agnes-3.0-flash-preview","score":85.05,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.5","score":78.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.5-27b","score":85.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemini-3.5-flash","score":92.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.8-flash-next","score":92.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"agnes-3.0-flash-preview","score":68.33,"metric":"percent"},{"benchmark":"aa-lcr","model":"kimi-k2.5","score":59,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-27b","score":72.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.8-27b","score":82,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemini-3.5-flash","score":81,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.8-flash-next","score":79.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"minimax-m3","score":74,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"agnes-3.0-flash-preview","score":23,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.6-35b-a3b","score":18.8,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"kimi-k2.5","score":22.9,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"muse-glimmer-30b","score":27,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.5-27b","score":20.7,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"deepseek-v4-flash-0731","score":40.4,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.8-27b","score":18.4,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"gemini-3.5-flash","score":51.4,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"qwen3.8-flash-next","score":24.5,"metric":"percent"},{"benchmark":"aa-omniscience-accuracy","model":"minimax-m3","score":16.7,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5.2","score":68.7,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-flash","score":73.2,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-pro","score":83.4,"metric":"percent"},{"benchmark":"browsecomp","model":"agents-a1","score":48.5,"metric":"percent"},{"benchmark":"browsecomp","model":"apodex-1.0-mini","score":73.9,"metric":"percent"},{"benchmark":"browsecomp","model":"bigbang-v1","score":76.5,"metric":"percent"},{"benchmark":"xbench-deepsearch","model":"claude-opus-4.8","score":61.4,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"gpt-5.5","score":72.4,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"glm-5.2","score":65.8,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"deepseek-v4-flash","score":62.2,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"deepseek-v4-pro","score":64.8,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"step-3.7-flash","score":50.8,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"qwen3.6-35b-a3b","score":32.6,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"nex-n2-mini","score":57.2,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"agents-a1","score":52.4,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"apodex-1.0-mini","score":61.8,"metric":"avg@3"},{"benchmark":"xbench-deepsearch","model":"bigbang-v1","score":58.4,"metric":"avg@3"},{"benchmark":"swe-bench-pro","model":"qwen3.6-35b-a3b","score":43.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"nex-n2-mini","score":50.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"agents-a1","score":42.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"apodex-1.0-mini","score":38.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"bigbang-v1","score":54.2,"metric":"percent"},{"benchmark":"scicode","model":"claude-opus-4.8","score":92.3,"metric":"percent"},{"benchmark":"scicode","model":"gpt-5.5","score":95.1,"metric":"percent"},{"benchmark":"scicode","model":"glm-5.2","score":84.3,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-flash","score":83.7,"metric":"percent"},{"benchmark":"scicode","model":"deepseek-v4-pro","score":90.2,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-35b-a3b","score":56.5,"metric":"percent"},{"benchmark":"scicode","model":"nex-n2-mini","score":39,"metric":"percent"},{"benchmark":"scicode","model":"agents-a1","score":64.1,"metric":"percent"},{"benchmark":"scicode","model":"bigbang-v1","score":68.6,"metric":"percent"},{"benchmark":"scicode-main","model":"claude-opus-4.8","score":78.1,"metric":"percent"},{"benchmark":"scicode-main","model":"gpt-5.5","score":90.6,"metric":"percent"},{"benchmark":"scicode-main","model":"glm-5.2","score":70.3,"metric":"percent"},{"benchmark":"scicode-main","model":"deepseek-v4-flash","score":68.6,"metric":"percent"},{"benchmark":"scicode-main","model":"deepseek-v4-pro","score":78.1,"metric":"percent"},{"benchmark":"scicode-main","model":"qwen3.6-35b-a3b","score":26.6,"metric":"percent"},{"benchmark":"scicode-main","model":"nex-n2-mini","score":15.6,"metric":"percent"},{"benchmark":"scicode-main","model":"agents-a1","score":50,"metric":"percent"},{"benchmark":"scicode-main","model":"bigbang-v1","score":50,"metric":"percent"},{"benchmark":"frontierscience-research","model":"claude-opus-4.8","score":45.2,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gemini-3.1-pro","score":24.8,"metric":"percent"},{"benchmark":"frontierscience-research","model":"gpt-5.5","score":58.3,"metric":"percent"},{"benchmark":"frontierscience-research","model":"glm-5.2","score":52.4,"metric":"percent"},{"benchmark":"frontierscience-research","model":"deepseek-v4-flash","score":37.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"deepseek-v4-pro","score":40.7,"metric":"percent"},{"benchmark":"frontierscience-research","model":"step-3.7-flash","score":37.2,"metric":"percent"},{"benchmark":"frontierscience-research","model":"qwen3.6-35b-a3b","score":11.9,"metric":"percent"},{"benchmark":"frontierscience-research","model":"nex-n2-mini","score":36.8,"metric":"percent"},{"benchmark":"frontierscience-research","model":"agents-a1","score":38.4,"metric":"percent"},{"benchmark":"frontierscience-research","model":"apodex-1.0-mini","score":29.6,"metric":"percent"},{"benchmark":"frontierscience-research","model":"bigbang-v1","score":46.2,"metric":"percent"},{"benchmark":"hle-with-tools","model":"nex-n2-mini","score":38.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"agents-a1","score":46.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"apodex-1.0-mini","score":45.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"bigbang-v1","score":50.3,"metric":"avg@3"},{"benchmark":"biomysterybench","model":"gpt-5.5","score":76.7,"metric":"percent"},{"benchmark":"biomysterybench","model":"glm-5.2","score":75.3,"metric":"percent"},{"benchmark":"biomysterybench","model":"deepseek-v4-flash","score":68,"metric":"percent"},{"benchmark":"biomysterybench","model":"deepseek-v4-pro","score":64.4,"metric":"percent"},{"benchmark":"biomysterybench","model":"step-3.7-flash","score":57.5,"metric":"percent"},{"benchmark":"biomysterybench","model":"qwen3.6-35b-a3b","score":44.8,"metric":"percent"},{"benchmark":"biomysterybench","model":"nex-n2-mini","score":42.9,"metric":"percent"},{"benchmark":"biomysterybench","model":"agents-a1","score":48.9,"metric":"percent"},{"benchmark":"biomysterybench","model":"apodex-1.0-mini","score":50.2,"metric":"percent"},{"benchmark":"biomysterybench","model":"bigbang-v1","score":57.5,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"gpt-5.5","score":23.5,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"glm-5.2","score":21.6,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"deepseek-v4-flash","score":23.5,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"deepseek-v4-pro","score":13.7,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"step-3.7-flash","score":11.8,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"qwen3.6-35b-a3b","score":2,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"nex-n2-mini","score":5.9,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"agents-a1","score":2,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"apodex-1.0-mini","score":5.9,"metric":"percent"},{"benchmark":"biomysterybench-hard","model":"bigbang-v1","score":15.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"claude-opus-4.8","score":63.6,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"gpt-5.5","score":59.1,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"glm-5.2","score":72.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"deepseek-v4-flash","score":40.9,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"deepseek-v4-pro","score":59.1,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"step-3.7-flash","score":40.9,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.6-35b-a3b","score":31.8,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"nex-n2-mini","score":18.2,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"agents-a1","score":27.3,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"apodex-1.0-mini","score":27.3,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"bigbang-v1","score":59.1,"metric":"percent"},{"benchmark":"paperbench","model":"gpt-5.5","score":64.2,"metric":"percent"},{"benchmark":"paperbench","model":"glm-5.2","score":63.6,"metric":"percent"},{"benchmark":"paperbench","model":"deepseek-v4-flash","score":40.4,"metric":"percent"},{"benchmark":"paperbench","model":"deepseek-v4-pro","score":50.4,"metric":"percent"},{"benchmark":"paperbench","model":"step-3.7-flash","score":36.7,"metric":"percent"},{"benchmark":"paperbench","model":"qwen3.6-35b-a3b","score":30.7,"metric":"percent"},{"benchmark":"paperbench","model":"nex-n2-mini","score":14.8,"metric":"percent"},{"benchmark":"paperbench","model":"agents-a1","score":17.3,"metric":"percent"},{"benchmark":"paperbench","model":"apodex-1.0-mini","score":20.5,"metric":"percent"},{"benchmark":"paperbench","model":"bigbang-v1","score":53.6,"metric":"percent"},{"benchmark":"claw-eval","model":"occamy-1.0","score":82.2,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.6-35b-a3b","score":69.5,"metric":"percent"},{"benchmark":"claw-eval","model":"agents-a1","score":69.9,"metric":"percent"},{"benchmark":"claw-eval","model":"nex-n2-mini","score":66.6,"metric":"percent"},{"benchmark":"claw-eval","model":"bigbang-v1","score":63.5,"metric":"percent"},{"benchmark":"claw-eval","model":"ornith-1.5-35b-a3b","score":64.4,"metric":"percent"},{"benchmark":"claw-eval","model":"gpt-5.6-sol","score":81.8,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.8-max","score":83.92,"metric":"percent"},{"benchmark":"claw-eval","model":"deepseek-v4-pro-0813","score":81.7,"metric":"percent"},{"benchmark":"claw-eval","model":"glm-5.2","score":81.6,"metric":"percent"},{"benchmark":"claweval-pass3","model":"occamy-1.0","score":71.4,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.6-35b-a3b","score":54.8,"metric":"percent"},{"benchmark":"claweval-pass3","model":"agents-a1","score":41.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"nex-n2-mini","score":37,"metric":"percent"},{"benchmark":"claweval-pass3","model":"bigbang-v1","score":40.2,"metric":"percent"},{"benchmark":"claweval-pass3","model":"ornith-1.5-35b-a3b","score":48.7,"metric":"percent"},{"benchmark":"claweval-pass3","model":"gpt-5.6-sol","score":68.9,"metric":"percent"},{"benchmark":"claweval-pass3","model":"qwen3.8-max","score":73.68,"metric":"percent"},{"benchmark":"claweval-pass3","model":"deepseek-v4-pro-0813","score":74.5,"metric":"percent"},{"benchmark":"claweval-pass3","model":"glm-5.2","score":68.3,"metric":"percent"},{"benchmark":"wildclawbench","model":"occamy-1.0","score":49.16,"metric":"percent"},{"benchmark":"wildclawbench","model":"qwen3.6-35b-a3b","score":40.4,"metric":"percent"},{"benchmark":"wildclawbench","model":"agents-a1","score":30.73,"metric":"percent"},{"benchmark":"wildclawbench","model":"nex-n2-mini","score":30.31,"metric":"percent"},{"benchmark":"wildclawbench","model":"bigbang-v1","score":32.87,"metric":"percent"},{"benchmark":"wildclawbench","model":"ornith-1.5-35b-a3b","score":45.91,"metric":"percent"},{"benchmark":"wildclawbench","model":"gpt-5.6-sol","score":67.2,"metric":"percent"},{"benchmark":"wildclawbench","model":"qwen3.8-max","score":54.42,"metric":"percent"},{"benchmark":"wildclawbench","model":"deepseek-v4-pro-0813","score":37.3,"metric":"percent"},{"benchmark":"wildclawbench","model":"glm-5.2","score":52.14,"metric":"percent"},{"benchmark":"commerceagentbench","model":"occamy-1.0","score":37.38,"metric":"percent"},{"benchmark":"commerceagentbench","model":"qwen3.6-35b-a3b","score":19.6,"metric":"percent"},{"benchmark":"commerceagentbench","model":"agents-a1","score":9.3,"metric":"percent"},{"benchmark":"commerceagentbench","model":"nex-n2-mini","score":16.8,"metric":"percent"},{"benchmark":"commerceagentbench","model":"bigbang-v1","score":30.8,"metric":"percent"},{"benchmark":"commerceagentbench","model":"ornith-1.5-35b-a3b","score":37.4,"metric":"percent"},{"benchmark":"commerceagentbench","model":"gpt-5.6-sol","score":49.5,"metric":"percent"},{"benchmark":"commerceagentbench","model":"qwen3.8-max","score":46.3,"metric":"percent"},{"benchmark":"commerceagentbench","model":"deepseek-v4-pro-0813","score":43.3,"metric":"percent"},{"benchmark":"commerceagentbench","model":"glm-5.2","score":39.3,"metric":"percent"},{"benchmark":"business-arena","model":"occamy-1.0","score":79868,"metric":"usd"},{"benchmark":"business-arena","model":"qwen3.6-35b-a3b","score":44751,"metric":"usd"},{"benchmark":"business-arena","model":"agents-a1","score":33626,"metric":"usd"},{"benchmark":"business-arena","model":"nex-n2-mini","score":13325,"metric":"usd"},{"benchmark":"business-arena","model":"bigbang-v1","score":56477,"metric":"usd"},{"benchmark":"business-arena","model":"ornith-1.5-35b-a3b","score":66292,"metric":"usd"},{"benchmark":"business-arena","model":"gpt-5.6-sol","score":168867,"metric":"usd"},{"benchmark":"business-arena","model":"qwen3.8-max","score":89423,"metric":"usd"},{"benchmark":"business-arena","model":"deepseek-v4-pro-0813","score":40804,"metric":"usd"},{"benchmark":"business-arena","model":"glm-5.2","score":55742,"metric":"usd"},{"benchmark":"gdpval-aa-v2-elo","model":"occamy-1.0","score":1128,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.6-35b-a3b","score":1004,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"agents-a1","score":869,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"nex-n2-mini","score":999,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"bigbang-v1","score":951,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"ornith-1.5-35b-a3b","score":855,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"gpt-5.6-sol","score":1741,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"qwen3.8-max","score":1640,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"deepseek-v4-pro-0813","score":1500,"metric":"elo"},{"benchmark":"gdpval-aa-v2-elo","model":"glm-5.2","score":1452,"metric":"elo"},{"benchmark":"officeqa-pro","model":"occamy-1.0","score":48.1,"metric":"percent"},{"benchmark":"officeqa-pro","model":"qwen3.6-35b-a3b","score":39.1,"metric":"percent"},{"benchmark":"officeqa-pro","model":"agents-a1","score":23.3,"metric":"percent"},{"benchmark":"officeqa-pro","model":"nex-n2-mini","score":46.6,"metric":"percent"},{"benchmark":"officeqa-pro","model":"bigbang-v1","score":43.6,"metric":"percent"},{"benchmark":"officeqa-pro","model":"ornith-1.5-35b-a3b","score":59.4,"metric":"percent"},{"benchmark":"officeqa-pro","model":"gpt-5.6-sol","score":74.4,"metric":"percent"},{"benchmark":"officeqa-pro","model":"qwen3.8-max","score":69.2,"metric":"percent"},{"benchmark":"officeqa-pro","model":"deepseek-v4-pro-0813","score":51.2,"metric":"percent"},{"benchmark":"officeqa-pro","model":"glm-5.2","score":66.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"occamy-1.0","score":37.1,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.6-35b-a3b","score":11.9,"metric":"percent"},{"benchmark":"tau3-banking","model":"agents-a1","score":7.2,"metric":"percent"},{"benchmark":"tau3-banking","model":"nex-n2-mini","score":25.8,"metric":"percent"},{"benchmark":"tau3-banking","model":"bigbang-v1","score":10.3,"metric":"percent"},{"benchmark":"tau3-banking","model":"ornith-1.5-35b-a3b","score":21.7,"metric":"percent"},{"benchmark":"tau3-banking","model":"qwen3.8-max","score":54.6,"metric":"percent"},{"benchmark":"automationbench","model":"occamy-1.0","score":27.6,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.6-35b-a3b","score":7.5,"metric":"percent"},{"benchmark":"automationbench","model":"agents-a1","score":2.2,"metric":"percent"},{"benchmark":"automationbench","model":"nex-n2-mini","score":5.7,"metric":"percent"},{"benchmark":"automationbench","model":"bigbang-v1","score":14.8,"metric":"percent"},{"benchmark":"automationbench","model":"ornith-1.5-35b-a3b","score":18.5,"metric":"percent"},{"benchmark":"automationbench","model":"gpt-5.6-sol","score":45.5,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.8-max","score":43.5,"metric":"percent"},{"benchmark":"automationbench","model":"deepseek-v4-pro-0813","score":32,"metric":"percent"},{"benchmark":"automationbench","model":"glm-5.2","score":28,"metric":"percent"},{"benchmark":"automationbench-partial","model":"occamy-1.0","score":69.1,"metric":"percent"},{"benchmark":"automationbench-partial","model":"qwen3.6-35b-a3b","score":39.4,"metric":"percent"},{"benchmark":"automationbench-partial","model":"agents-a1","score":14.7,"metric":"percent"},{"benchmark":"automationbench-partial","model":"nex-n2-mini","score":27.9,"metric":"percent"},{"benchmark":"automationbench-partial","model":"bigbang-v1","score":47.4,"metric":"percent"},{"benchmark":"automationbench-partial","model":"ornith-1.5-35b-a3b","score":58,"metric":"percent"},{"benchmark":"automationbench-partial","model":"gpt-5.6-sol","score":81.2,"metric":"percent"},{"benchmark":"automationbench-partial","model":"qwen3.8-max","score":81.2,"metric":"percent"},{"benchmark":"automationbench-partial","model":"deepseek-v4-pro-0813","score":59.7,"metric":"percent"},{"benchmark":"automationbench-partial","model":"glm-5.2","score":70,"metric":"percent"},{"benchmark":"bfcl-v4","model":"occamy-1.0","score":65.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.6-35b-a3b","score":63.19,"metric":"percent"},{"benchmark":"bfcl-v4","model":"agents-a1","score":57.23,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nex-n2-mini","score":62.81,"metric":"percent"},{"benchmark":"bfcl-v4","model":"bigbang-v1","score":57.86,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ornith-1.5-35b-a3b","score":68.51,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gpt-5.6-sol","score":64.33,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.8-max","score":73.65,"metric":"percent"},{"benchmark":"bfcl-v4","model":"deepseek-v4-pro-0813","score":67.1,"metric":"percent"},{"benchmark":"bfcl-v4","model":"glm-5.2","score":70.33,"metric":"percent"},{"benchmark":"vitabench","model":"occamy-1.0","score":41.75,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.6-35b-a3b","score":34.25,"metric":"percent"},{"benchmark":"vitabench","model":"agents-a1","score":37,"metric":"percent"},{"benchmark":"vitabench","model":"nex-n2-mini","score":26.25,"metric":"percent"},{"benchmark":"vitabench","model":"bigbang-v1","score":46,"metric":"percent"},{"benchmark":"vitabench","model":"ornith-1.5-35b-a3b","score":40.25,"metric":"percent"},{"benchmark":"vitabench","model":"gpt-5.6-sol","score":46.75,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.8-max","score":52.25,"metric":"percent"},{"benchmark":"vitabench","model":"deepseek-v4-pro-0813","score":53.5,"metric":"percent"},{"benchmark":"vitabench","model":"glm-5.2","score":43.75,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"occamy-1.0","score":59,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":49.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"agents-a1","score":41.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"bigbang-v1","score":33.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-max","score":81.3,"metric":"percent"},{"benchmark":"ifeval","model":"occamy-1.0","score":91.53,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.6-35b-a3b","score":86.9,"metric":"percent"},{"benchmark":"ifeval","model":"agents-a1","score":91.6,"metric":"percent"},{"benchmark":"ifeval","model":"nex-n2-mini","score":91.6,"metric":"percent"},{"benchmark":"ifeval","model":"bigbang-v1","score":90.5,"metric":"percent"},{"benchmark":"ifeval","model":"ornith-1.5-35b-a3b","score":81.8,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-5.6-sol","score":95,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.8-max","score":95.02,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v4-pro-0813","score":93.74,"metric":"percent"},{"benchmark":"ifeval","model":"glm-5.2","score":93.89,"metric":"percent"},{"benchmark":"osworld-verified","model":"holo4-27b","score":85.2,"metric":"percent"},{"benchmark":"osworld-verified","model":"holo4-35b-a3b","score":80.8,"metric":"percent"},{"benchmark":"osworld-2.0","model":"holo4-27b","score":61.7,"metric":"percent"},{"benchmark":"osworld-2.0","model":"holo4-35b-a3b","score":30.9,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"holo4-27b","score":41.5,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"holo4-35b-a3b","score":12.3,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"holo4-27b","score":44.1,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"holo4-35b-a3b","score":30.9,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"qwen3.8-27b","score":43.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"holo4-27b","score":19.4,"metric":"percent"},{"benchmark":"agents-last-exam","model":"holo4-35b-a3b","score":13.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.8-27b","score":19,"metric":"percent"},{"benchmark":"automationbench","model":"holo4-27b","score":45.4,"metric":"percent"},{"benchmark":"automationbench","model":"holo4-35b-a3b","score":34.5,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.8-27b","score":40.3,"metric":"percent"},{"benchmark":"androidworld","model":"holo4-27b","score":85.1,"metric":"percent"},{"benchmark":"androidworld","model":"holo4-35b-a3b","score":77.6,"metric":"percent"},{"benchmark":"osworld-2.0","model":"claude-opus-5.5","score":81.8,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-6-astra","score":73.5,"metric":"percent"},{"benchmark":"osworld-2.0-strict","model":"claude-opus-5.5","score":48.7,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-5.5","score":63.7,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-astra","score":61.4,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"muse-spark-1.3","score":57.5,"metric":"percent"},{"benchmark":"legalbench","model":"thomson-1.0-small","score":79.9,"metric":"percent"},{"benchmark":"legalbench","model":"snowdon-1.1-small","score":80.9,"metric":"percent"},{"benchmark":"legalbench","model":"qwen3.6-35b-a3b","score":80.3,"metric":"percent"},{"benchmark":"legalbench","model":"gemma-4-31b-it","score":83.1,"metric":"percent"},{"benchmark":"legalbench","model":"claude-4.5-haiku","score":80.7,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"thomson-1.0-small","score":73.4,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"snowdon-1.1-small","score":71.5,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"qwen3.6-35b-a3b","score":69.5,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"gemma-4-31b-it","score":34.2,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"claude-4.5-haiku","score":60.5,"metric":"percent"},{"benchmark":"prbench-legal","model":"thomson-1.0-small","score":31.4,"metric":"percent"},{"benchmark":"prbench-legal","model":"snowdon-1.1-small","score":25.9,"metric":"percent"},{"benchmark":"prbench-legal","model":"qwen3.6-35b-a3b","score":26.9,"metric":"percent"},{"benchmark":"prbench-legal","model":"gemma-4-31b-it","score":25.2,"metric":"percent"},{"benchmark":"prbench-legal","model":"claude-4.5-haiku","score":19.3,"metric":"percent"},{"benchmark":"lexam-mcq4-en","model":"thomson-1.0-small","score":72.2,"metric":"percent"},{"benchmark":"lexam-mcq4-en","model":"snowdon-1.1-small","score":75.6,"metric":"percent"},{"benchmark":"lexam-mcq4-en","model":"qwen3.6-35b-a3b","score":75.8,"metric":"percent"},{"benchmark":"lexam-mcq4-en","model":"gemma-4-31b-it","score":87.4,"metric":"percent"},{"benchmark":"lexam-mcq4-en","model":"claude-4.5-haiku","score":72.2,"metric":"percent"},{"benchmark":"mbe-bar-exam","model":"thomson-1.0-small","score":83.4,"metric":"percent"},{"benchmark":"mbe-bar-exam","model":"snowdon-1.1-small","score":83.1,"metric":"percent"},{"benchmark":"mbe-bar-exam","model":"qwen3.6-35b-a3b","score":80.1,"metric":"percent"},{"benchmark":"mbe-bar-exam","model":"gemma-4-31b-it","score":88.8,"metric":"percent"},{"benchmark":"mbe-bar-exam","model":"claude-4.5-haiku","score":77.3,"metric":"percent"},{"benchmark":"contract-scrub","model":"thomson-1.0-small","score":44.6,"metric":"percent"},{"benchmark":"contract-scrub","model":"snowdon-1.1-small","score":38.5,"metric":"percent"},{"benchmark":"contract-scrub","model":"qwen3.6-35b-a3b","score":39.6,"metric":"percent"},{"benchmark":"contract-scrub","model":"gemma-4-31b-it","score":54.8,"metric":"percent"},{"benchmark":"contract-scrub","model":"claude-4.5-haiku","score":36.5,"metric":"percent"},{"benchmark":"query-sufficiency","model":"thomson-1.0-small","score":59.4,"metric":"percent"},{"benchmark":"query-sufficiency","model":"snowdon-1.1-small","score":54.8,"metric":"percent"},{"benchmark":"query-sufficiency","model":"qwen3.6-35b-a3b","score":55.7,"metric":"percent"},{"benchmark":"query-sufficiency","model":"gemma-4-31b-it","score":51.7,"metric":"percent"},{"benchmark":"query-sufficiency","model":"claude-4.5-haiku","score":47.4,"metric":"percent"},{"benchmark":"harvey-lab-aa","model":"gemma-4-31b-it","score":30.2,"metric":"percent"},{"benchmark":"aime-2026-i","model":"thomson-1.0-small","score":90,"metric":"percent"},{"benchmark":"aime-2026-i","model":"snowdon-1.1-small","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-35b-a3b","score":86.7,"metric":"percent"},{"benchmark":"faitheval-inconsistent","model":"thomson-1.0-small","score":97.7,"metric":"percent"},{"benchmark":"faitheval-inconsistent","model":"snowdon-1.1-small","score":96.7,"metric":"percent"},{"benchmark":"faitheval-inconsistent","model":"qwen3.6-35b-a3b","score":96.9,"metric":"percent"},{"benchmark":"perspective-bench","model":"snowdon-1.1-small","score":93,"metric":"percent"},{"benchmark":"perspective-bench","model":"qwen3.6-35b-a3b","score":16,"metric":"percent"},{"benchmark":"gdpval","model":"snowdon-1.1-small","score":75.8,"metric":"percent"},{"benchmark":"gdpval","model":"qwen3.6-35b-a3b","score":73.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"snowdon-1.1-small","score":85.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-35b-a3b","score":85.2,"metric":"percent"},{"benchmark":"hle","model":"snowdon-1.1-small","score":13.3,"metric":"avg@3"},{"benchmark":"hle","model":"qwen3.6-35b-a3b","score":14.1,"metric":"avg@3"},{"benchmark":"ifeval","model":"snowdon-1.1-small","score":90,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.6-35b-a3b","score":91.1,"metric":"percent"},{"benchmark":"mgsm","model":"snowdon-1.1-small","score":87.4,"metric":"percent"},{"benchmark":"mgsm","model":"qwen3.6-35b-a3b","score":88.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"snowdon-1.1-small","score":85.2,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"snowdon-1.1-small","score":22.1,"metric":"percent"},{"benchmark":"simpleqa-verified","model":"qwen3.6-35b-a3b","score":21.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"snowdon-1.1-small","score":32.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.6-35b-a3b","score":34.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"snowdon-1.1-small","score":98.3,"metric":"percent"},{"benchmark":"tau2-telecom","model":"qwen3.6-35b-a3b","score":100,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"snowdon-1.1-small","score":38.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-35b-a3b","score":45.2,"metric":"percent"},{"benchmark":"writingbench","model":"snowdon-1.1-small","score":79.3,"metric":"percent"},{"benchmark":"writingbench","model":"qwen3.6-35b-a3b","score":79.5,"metric":"percent"},{"benchmark":"frontier-cs","model":"gpt-5.6-sol","score":76.4,"metric":"percent"},{"benchmark":"frontier-cs","model":"claude-opus-4.8","score":74.5,"metric":"percent"},{"benchmark":"frontier-cs","model":"gpt-5.5","score":72.1,"metric":"percent"},{"benchmark":"frontier-cs","model":"gemini-3.1-pro","score":68.9,"metric":"percent"},{"benchmark":"frontier-cs","model":"qwen3.7-max","score":61.9,"metric":"percent"},{"benchmark":"frontier-cs","model":"deepseek-v4-pro","score":44.7,"metric":"percent"},{"benchmark":"frontier-cs","model":"deepseek-v4-flash","score":39.1,"metric":"percent"},{"benchmark":"frontier-cs","model":"kimi-k2.7-code","score":54.7,"metric":"percent"},{"benchmark":"frontier-cs","model":"glm-5.3-flash","score":50.4,"metric":"percent"},{"benchmark":"frontier-cs","model":"kimi-k2.6","score":46.9,"metric":"percent"},{"benchmark":"frontier-cs","model":"qwen3.6-35b-a3b","score":23.4,"metric":"percent"},{"benchmark":"frontier-cs","model":"arex-2","score":70.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"gpt-5.6-sol","score":72.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"gpt-5.5","score":68.2,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"kimi-k3","score":72.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"naive-n0.5-flash","score":73.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"deepseek-v4-pro","score":54.5,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"deepseek-v4-flash","score":51.5,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"kimi-k2.6","score":66.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"frontis-ma1-35b","score":71.2,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.6-35b-a3b","score":39.4,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"arex-2","score":81.8,"metric":"percent"},{"benchmark":"browsecomp","model":"iris-pro","score":88.6,"metric":"percent"},{"benchmark":"browsecomp","model":"arex-base","score":82.5,"metric":"percent"},{"benchmark":"browsecomp","model":"quest-35b","score":64.6,"metric":"percent"},{"benchmark":"browsecomp","model":"iris-mini","score":82.2,"metric":"percent"},{"benchmark":"browsecomp","model":"arex-turbo","score":70.7,"metric":"percent"},{"benchmark":"browsecomp","model":"arex-2","score":84,"metric":"percent"},{"benchmark":"hle-with-tools","model":"kimi-k2.6","score":54,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"iris-pro","score":56.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"arex-base","score":52.4,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"quest-35b","score":37.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"iris-mini","score":52.3,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"arex-turbo","score":40.6,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"arex-2","score":52.6,"metric":"avg@3"},{"benchmark":"gaia-text-only","model":"gpt-5.5","score":87.4,"metric":"percent"},{"benchmark":"gaia-text-only","model":"gemini-3.1-pro","score":80.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"glm-5","score":70,"metric":"percent"},{"benchmark":"gaia-text-only","model":"kimi-k2.6","score":80.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"glm-5.3-flash","score":78.8,"metric":"percent"},{"benchmark":"gaia-text-only","model":"deepseek-v4-flash","score":57.5,"metric":"percent"},{"benchmark":"gaia-text-only","model":"deepseek-v4-pro","score":71.1,"metric":"percent"},{"benchmark":"gaia-text-only","model":"mirothinker-1.7","score":82.7,"metric":"percent"},{"benchmark":"gaia-text-only","model":"arex-base","score":85.4,"metric":"percent"},{"benchmark":"gaia-text-only","model":"qwen3.5-35b-a3b","score":80,"metric":"percent"},{"benchmark":"gaia-text-only","model":"quest-35b","score":80.8,"metric":"percent"},{"benchmark":"gaia-text-only","model":"arex-turbo","score":81.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"arex-2","score":92.2,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-fable-5","score":94.2,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gemini-3.1-pro","score":93.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v4-flash","score":90.6,"metric":"percent"},{"benchmark":"deepsearchqa","model":"deepseek-v4-pro","score":88.7,"metric":"percent"},{"benchmark":"deepsearchqa","model":"mirothinker-1.7","score":72.1,"metric":"percent"},{"benchmark":"deepsearchqa","model":"iris-pro","score":92.9,"metric":"percent"},{"benchmark":"deepsearchqa","model":"arex-base","score":89.9,"metric":"percent"},{"benchmark":"deepsearchqa","model":"qwen3.5-35b-a3b","score":68.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"iris-mini","score":86.9,"metric":"percent"},{"benchmark":"deepsearchqa","model":"arex-turbo","score":78.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"arex-2","score":93.8,"metric":"percent"},{"benchmark":"gaia-text-only","model":"qwen3.5-122b-a10b","score":81.6,"metric":"percent"},{"benchmark":"gaia-text-only","model":"qwen3.5-397b-a17b","score":83.5,"metric":"percent"},{"benchmark":"gaia-text-only","model":"mirothinker-h1","score":88.5,"metric":"percent"},{"benchmark":"xbench-deepsearch-2025.10","model":"gemini-3.1-pro","score":53,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"kimi-k2.6","score":90,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"deepseek-v4-flash","score":69,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"deepseek-v4-pro","score":80,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"qwen3.5-35b-a3b","score":50.3,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"qwen3.5-397b-a17b","score":61,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"arex-turbo","score":57,"metric":"avg@3"},{"benchmark":"xbench-deepsearch-2025.10","model":"arex-base","score":71,"metric":"avg@3"},{"benchmark":"deepsearchqa","model":"gpt-5.4","score":88.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-opus-4.6","score":91.3,"metric":"percent"},{"benchmark":"deepsearchqa","model":"qwen3.5-397b-a17b","score":82.1,"metric":"percent"},{"benchmark":"deepsearchqa","model":"mirothinker-h1","score":80.6,"metric":"percent"},{"benchmark":"wide-search","model":"gpt-5.4","score":77.5,"metric":"percent"},{"benchmark":"wide-search","model":"claude-opus-4.6","score":77.5,"metric":"percent"},{"benchmark":"wide-search","model":"gemini-3.1-pro","score":66.4,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-flash","score":76.4,"metric":"percent"},{"benchmark":"wide-search","model":"deepseek-v4-pro","score":78,"metric":"percent"},{"benchmark":"wide-search","model":"quest-35b","score":60.6,"metric":"percent"},{"benchmark":"wide-search","model":"arex-turbo","score":68.5,"metric":"percent"},{"benchmark":"wide-search","model":"arex-base","score":82,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"iris-pro","score":85.1,"metric":"percent"},{"benchmark":"browsecomp","model":"fort-searcher","score":72.2,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"fort-searcher","score":75,"metric":"percent"},{"benchmark":"browsecomp-zh","model":"iris-mini","score":84.8,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3.6-35b-a3b","score":39.39,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"frontis-ma1-35b","score":60.61,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"frontis-ma1-35b","score":71.21,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"kimi-k2.6","score":66.67,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"qwen3-30b-a3b-thinking-2507","score":34.85,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"frontis-ma1-30b","score":53.03,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"frontis-ma1-30b","score":66.67,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"glm-5.2","score":62.12,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"minimax-m3","score":59.09,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k3","score":76.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k3","score":77.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"kimi-k3","score":80.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ember-1","score":82,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k3","score":80.4,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k3","score":86,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"kimi-k3","score":93.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ember-1","score":92.2,"metric":"percent"},{"benchmark":"swe-interact","model":"kimi-k3","score":6.7,"metric":"percent"},{"benchmark":"swe-interact","model":"kimi-k3","score":13.3,"metric":"percent"},{"benchmark":"swe-interact","model":"kimi-k3","score":21.3,"metric":"percent"},{"benchmark":"swe-interact","model":"ember-1","score":20,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k3","score":55.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k3","score":62.8,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k3","score":66.4,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"ember-1","score":75.2,"metric":"percent"},{"benchmark":"tau2-airline","model":"kimi-k3","score":64,"metric":"percent"},{"benchmark":"tau2-airline","model":"ember-1","score":66,"metric":"percent"},{"benchmark":"fairpoliticsqa","model":"kimi-k2.6","score":34.1,"metric":"percent"},{"benchmark":"fairpoliticsqa","model":"sakana-namazu","score":56.3,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-max-0902","score":69.3,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.8-max-0902","score":64.9,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.8-max-0902","score":50.8,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.8-max-0902","score":73.3,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"qwen3.8-max","score":91.53,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"kimi-k3","score":91.64,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"gpt-5.5","score":90.5,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"glm-5.2","score":90.34,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"deepseek-v4-pro","score":87.17,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"deepseek-v4-flash","score":86.49,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"nex-n2-mini","score":69.96,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"agents-a1","score":74.31,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"apodex-1.0-mini","score":78.36,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"occamy-1.0","score":79.5,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"qwen3.6-27b","score":85.1,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"qwen3.6-35b-a3b","score":82.61,"metric":"percent"},{"benchmark":"gdpval-rubrics","model":"fx-work","score":86.66,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"qwen3.8-max","score":1739,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"kimi-k3","score":1687,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"gpt-5.5","score":1491,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"glm-5.2","score":1510,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"deepseek-v4-pro","score":1304,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"deepseek-v4-flash","score":1189,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"nex-n2-mini","score":1065,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"agents-a1","score":877,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"apodex-1.0-mini","score":973,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"occamy-1.0","score":1200,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"qwen3.6-27b","score":1138,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"qwen3.6-35b-a3b","score":1053,"metric":"elo"},{"benchmark":"gdpval-aa-elo","model":"fx-work","score":1352,"metric":"elo"},{"benchmark":"apex-agents","model":"qwen3.8-max","score":38.9,"metric":"percent"},{"benchmark":"apex-agents","model":"kimi-k3","score":35.5,"metric":"percent"},{"benchmark":"apex-agents","model":"gpt-5.5","score":29.9,"metric":"percent"},{"benchmark":"apex-agents","model":"glm-5.2","score":29.7,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-pro","score":19.2,"metric":"percent"},{"benchmark":"apex-agents","model":"deepseek-v4-flash","score":15.2,"metric":"percent"},{"benchmark":"apex-agents","model":"nex-n2-mini","score":15.6,"metric":"percent"},{"benchmark":"apex-agents","model":"agents-a1","score":11.7,"metric":"percent"},{"benchmark":"apex-agents","model":"apodex-1.0-mini","score":14.6,"metric":"percent"},{"benchmark":"apex-agents","model":"occamy-1.0","score":20.5,"metric":"percent"},{"benchmark":"apex-agents","model":"qwen3.6-27b","score":16.6,"metric":"percent"},{"benchmark":"apex-agents","model":"qwen3.6-35b-a3b","score":13.4,"metric":"percent"},{"benchmark":"apex-agents","model":"fx-work","score":25.2,"metric":"percent"},{"benchmark":"jobbench","model":"qwen3.8-max","score":52.57,"metric":"percent"},{"benchmark":"jobbench","model":"kimi-k3","score":43.81,"metric":"percent"},{"benchmark":"jobbench","model":"gpt-5.5","score":30.1,"metric":"percent"},{"benchmark":"jobbench","model":"glm-5.2","score":33.79,"metric":"percent"},{"benchmark":"jobbench","model":"deepseek-v4-pro","score":18.9,"metric":"percent"},{"benchmark":"jobbench","model":"deepseek-v4-flash","score":18.62,"metric":"percent"},{"benchmark":"jobbench","model":"nex-n2-mini","score":9.39,"metric":"percent"},{"benchmark":"jobbench","model":"agents-a1","score":7.19,"metric":"percent"},{"benchmark":"jobbench","model":"apodex-1.0-mini","score":7.97,"metric":"percent"},{"benchmark":"jobbench","model":"occamy-1.0","score":18.88,"metric":"percent"},{"benchmark":"jobbench","model":"qwen3.6-27b","score":19.18,"metric":"percent"},{"benchmark":"jobbench","model":"qwen3.6-35b-a3b","score":14.99,"metric":"percent"},{"benchmark":"jobbench","model":"fx-work","score":25.19,"metric":"percent"},{"benchmark":"jobbench-easy","model":"qwen3.8-max","score":82.81,"metric":"percent"},{"benchmark":"jobbench-easy","model":"kimi-k3","score":80.72,"metric":"percent"},{"benchmark":"jobbench-easy","model":"gpt-5.5","score":78.22,"metric":"percent"},{"benchmark":"jobbench-easy","model":"glm-5.2","score":75.49,"metric":"percent"},{"benchmark":"jobbench-easy","model":"deepseek-v4-pro","score":64.08,"metric":"percent"},{"benchmark":"jobbench-easy","model":"deepseek-v4-flash","score":63.13,"metric":"percent"},{"benchmark":"jobbench-easy","model":"nex-n2-mini","score":52.93,"metric":"percent"},{"benchmark":"jobbench-easy","model":"agents-a1","score":41.74,"metric":"percent"},{"benchmark":"jobbench-easy","model":"apodex-1.0-mini","score":44.38,"metric":"percent"},{"benchmark":"jobbench-easy","model":"occamy-1.0","score":65.49,"metric":"percent"},{"benchmark":"jobbench-easy","model":"qwen3.6-27b","score":64.59,"metric":"percent"},{"benchmark":"jobbench-easy","model":"qwen3.6-35b-a3b","score":56.02,"metric":"percent"},{"benchmark":"jobbench-easy","model":"fx-work","score":70.06,"metric":"percent"},{"benchmark":"math500","model":"zgcm-1-7b","score":97.13,"metric":"percent"},{"benchmark":"math500","model":"deepseek-r1-0528-qwen3-8b","score":96.32,"metric":"percent"},{"benchmark":"math500","model":"minicpm4.1-8b","score":95.6,"metric":"percent"},{"benchmark":"math500","model":"qwen3-8b","score":96.2,"metric":"percent"},{"benchmark":"math500","model":"olmo-3-think-7b","score":95.1,"metric":"percent"},{"benchmark":"aime-2024","model":"zgcm-1-7b","score":80.62,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-0528-qwen3-8b","score":83.33,"metric":"percent"},{"benchmark":"aime-2024","model":"minicpm4.1-8b","score":83.33,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen3-8b","score":80,"metric":"percent"},{"benchmark":"aime-2025","model":"zgcm-1-7b","score":73.33,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0528-qwen3-8b","score":75.21,"metric":"percent"},{"benchmark":"aime-2025","model":"minicpm4.1-8b","score":73.33,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-8b","score":63.33,"metric":"percent"},{"benchmark":"aime-2026-i","model":"zgcm-1-7b","score":75,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-r1-0528-qwen3-8b","score":69.17,"metric":"percent"},{"benchmark":"aime-2026-i","model":"minicpm4.1-8b","score":71.67,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3-8b","score":66.67,"metric":"percent"},{"benchmark":"aime-2026-i","model":"olmo-3-think-7b","score":66.16,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"zgcm-1-7b","score":70.42,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"deepseek-r1-0528-qwen3-8b","score":61.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"minicpm4.1-8b","score":52.5,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"qwen3-8b","score":43.33,"metric":"percent"},{"benchmark":"hmmt-feb-2025","model":"olmo-3-think-7b","score":43.89,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"zgcm-1-7b","score":59.48,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-r1-0528-qwen3-8b","score":51.52,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"minicpm4.1-8b","score":46.21,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3-8b","score":45.45,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"olmo-3-think-7b","score":43.94,"metric":"percent"},{"benchmark":"webwalker-qa","model":"zgcm-1-7b","score":63.09,"metric":"avg@3"},{"benchmark":"browsecomp","model":"zgcm-1-7b","score":19.43,"metric":"percent"},{"benchmark":"gaia-text-only","model":"zgcm-1-7b","score":42.52,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-opus-5","score":53,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-fable-5","score":41,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"gpt-5.6-sol","score":41,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"grok-4.6","score":30,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-opus-4.8","score":19,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"grok-4.5","score":26,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"claude-sonnet-5","score":16,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"glm-5.2","score":4,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"glm-5.3-flash","score":20,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"tev-320b","score":27,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-opus-5","score":52,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-fable-5","score":46,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-5.6-sol","score":39,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"grok-4.6","score":31,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-opus-4.8","score":27,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"grok-4.5","score":20,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-sonnet-5","score":19,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"glm-5.2","score":3,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"glm-5.3-flash","score":29,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"tev-320b","score":37,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"oxcoder-9b","score":49.6,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"oxcoder-9b","score":50.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"oxcoder-9b","score":73.5,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"oxcoder-9b","score":49.1,"metric":"percent"},{"benchmark":"nl2repo","model":"oxcoder-9b","score":36.2,"metric":"percent"},{"benchmark":"hle","model":"oxcoder-9b","score":21.2,"metric":"avg@3"},{"benchmark":"hle-with-tools","model":"oxcoder-9b","score":32.8,"metric":"avg@3"},{"benchmark":"gpqa-diamond","model":"oxcoder-9b","score":86.9,"metric":"percent"},{"benchmark":"mcp-atlas","model":"oxcoder-9b","score":56.7,"metric":"percent"},{"benchmark":"browsecomp","model":"oxcoder-9b","score":57.4,"metric":"percent"},{"benchmark":"claw-eval","model":"oxcoder-9b","score":67.8,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"veriloop-e2","score":76.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"veriloop-e2","score":88.8,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-pro","score":87.9,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"veriloop-e2","score":64.6,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro","score":62.7,"metric":"percent"},{"benchmark":"terminal-bench-3.0","model":"veriloop-e2","score":29.7,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"veriloop-e2","score":37.9,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-6-astra","score":59.6,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-fable-5.1","score":55.1,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"glm-5.3","score":41.8,"metric":"percent"},{"benchmark":"swe-marathon-v1.1","model":"veriloop-e2","score":45,"metric":"percent"},{"benchmark":"aime-2026-i","model":"veriloop-e2","score":98.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gpt-5.5","score":100,"metric":"percent"},{"benchmark":"aime-2026-i","model":"claude-opus-4.8","score":100,"metric":"percent"},{"benchmark":"aime-2026-i","model":"kimi-k3","score":97,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-pro","score":97,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemini-3.1-pro","score":98,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"veriloop-e2","score":93.9,"metric":"percent"},{"benchmark":"matharena-apex","model":"veriloop-e2","score":89.6,"metric":"percent"},{"benchmark":"matharena-apex","model":"gpt-5.5","score":80,"metric":"percent"},{"benchmark":"matharena-apex","model":"claude-opus-4.8","score":81,"metric":"percent"},{"benchmark":"matharena-apex","model":"kimi-k3","score":66,"metric":"percent"},{"benchmark":"matharena-apex","model":"deepseek-v4-pro","score":28,"metric":"percent"},{"benchmark":"matharena-apex","model":"gemini-3.1-pro","score":61,"metric":"percent"},{"benchmark":"milu","model":"gnani-evon-v3.3-30b-a3b","score":78.74,"metric":"percent"},{"benchmark":"milu","model":"sarvam-30b","score":67.15,"metric":"percent"},{"benchmark":"milu","model":"sarvam-105b","score":75.71,"metric":"percent"},{"benchmark":"milu","model":"gemma-4-26b-a4b-it","score":82.65,"metric":"percent"},{"benchmark":"milu","model":"gemma-4-31b-it","score":85.29,"metric":"percent"},{"benchmark":"indicmmlu-pro","model":"gnani-evon-v3.3-30b-a3b","score":68.79,"metric":"percent"},{"benchmark":"indicmmlu-pro","model":"gemma-4-26b-a4b-it","score":70.34,"metric":"percent"},{"benchmark":"indicmmlu-pro","model":"gemma-4-31b-it","score":79.02,"metric":"percent"},{"benchmark":"bharatmath","model":"gnani-evon-v3.3-30b-a3b","score":73.97,"metric":"percent"},{"benchmark":"bharatmath","model":"sarvam-30b","score":60.32,"metric":"percent"},{"benchmark":"bharatmath","model":"gemma-4-26b-a4b-it","score":76.48,"metric":"percent"},{"benchmark":"bharatmath","model":"gemma-4-31b-it","score":78.61,"metric":"percent"},{"benchmark":"xquad-in","model":"gnani-evon-v3.3-30b-a3b","score":64.59,"metric":"percent"},{"benchmark":"xquad-in","model":"sarvam-30b","score":37.86,"metric":"percent"},{"benchmark":"xquad-in","model":"sarvam-105b","score":56.65,"metric":"percent"},{"benchmark":"xquad-in","model":"gemma-4-26b-a4b-it","score":55.09,"metric":"percent"},{"benchmark":"xquad-in","model":"gemma-4-31b-it","score":42.21,"metric":"percent"},{"benchmark":"xorqa-in","model":"gnani-evon-v3.3-30b-a3b","score":41.83,"metric":"percent"},{"benchmark":"xorqa-in","model":"sarvam-30b","score":22.86,"metric":"percent"},{"benchmark":"xorqa-in","model":"sarvam-105b","score":34.98,"metric":"percent"},{"benchmark":"xorqa-in","model":"gemma-4-26b-a4b-it","score":34.47,"metric":"percent"},{"benchmark":"xorqa-in","model":"gemma-4-31b-it","score":30.16,"metric":"percent"},{"benchmark":"indicifeval-trans","model":"gnani-evon-v3.3-30b-a3b","score":47.45,"metric":"percent"},{"benchmark":"indicifeval-trans","model":"sarvam-30b","score":40.76,"metric":"percent"},{"benchmark":"indicifeval-trans","model":"sarvam-105b","score":51.79,"metric":"percent"},{"benchmark":"indicifeval-trans","model":"gemma-4-26b-a4b-it","score":75.2,"metric":"percent"},{"benchmark":"indicifeval-trans","model":"gemma-4-31b-it","score":81.12,"metric":"percent"},{"benchmark":"indicifeval-ground","model":"gnani-evon-v3.3-30b-a3b","score":28.66,"metric":"percent"},{"benchmark":"indicifeval-ground","model":"sarvam-30b","score":40.69,"metric":"percent"},{"benchmark":"indicifeval-ground","model":"sarvam-105b","score":37.88,"metric":"percent"},{"benchmark":"indicifeval-ground","model":"gemma-4-26b-a4b-it","score":34.73,"metric":"percent"},{"benchmark":"indicifeval-ground","model":"gemma-4-31b-it","score":37.79,"metric":"percent"},{"benchmark":"indicsafe5","model":"gnani-evon-v3.3-30b-a3b","score":86.5,"metric":"percent"},{"benchmark":"indicsafe5","model":"sarvam-30b","score":81.26,"metric":"percent"},{"benchmark":"indicsafe5","model":"gemma-4-26b-a4b-it","score":88.15,"metric":"percent"},{"benchmark":"indicsafe5","model":"gemma-4-31b-it","score":89.77,"metric":"percent"},{"benchmark":"medqa","model":"openevidence-darwin","score":100,"metric":"percent"},{"benchmark":"medxpertqa-text","model":"openevidence-darwin","score":72.8,"metric":"percent"},{"benchmark":"healthbench-professional","model":"openevidence-darwin","score":82.7,"metric":"percent"},{"benchmark":"noharm","model":"openevidence-darwin","score":87.2,"metric":"percent"},{"benchmark":"frontierxrd","model":"periodic-neon","score":55.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"celeris-1","score":75.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5","score":81.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-flash","score":73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mercury-2","score":63.7,"metric":"percent"},{"benchmark":"qwenclawbench","model":"granite-4.2-8b","score":37.01,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.5-9b","score":44.04,"metric":"percent"},{"benchmark":"qwenclawbench","model":"ornith-1.5-9b","score":47.27,"metric":"percent"},{"benchmark":"qwenclawbench","model":"gemma-4-12b-it","score":43.53,"metric":"percent"},{"benchmark":"qwenclawbench","model":"muse-glimmer-30b","score":46.11,"metric":"percent"},{"benchmark":"qwenclawbench","model":"neohorse-1-9b","score":48.73,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"granite-4.2-8b","score":35.07,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"qwen3.5-9b","score":39.6,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"ornith-1.5-9b","score":29.29,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"gemma-4-12b-it","score":29.65,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"muse-glimmer-30b","score":45.85,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"neohorse-1-9b","score":40.15,"metric":"percent"},{"benchmark":"pinchbench","model":"granite-4.2-8b","score":56.93,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-9b","score":74.55,"metric":"percent"},{"benchmark":"pinchbench","model":"ornith-1.5-9b","score":68.22,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-12b-it","score":58.89,"metric":"percent"},{"benchmark":"pinchbench","model":"muse-glimmer-30b","score":71.35,"metric":"percent"},{"benchmark":"pinchbench","model":"neohorse-1-9b","score":82.25,"metric":"percent"},{"benchmark":"vitabench","model":"granite-4.2-8b","score":23,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-9b","score":31.25,"metric":"percent"},{"benchmark":"vitabench","model":"ornith-1.5-9b","score":26.75,"metric":"percent"},{"benchmark":"vitabench","model":"gemma-4-12b-it","score":36.5,"metric":"percent"},{"benchmark":"vitabench","model":"muse-glimmer-30b","score":48.5,"metric":"percent"},{"benchmark":"vitabench","model":"neohorse-1-9b","score":42.25,"metric":"percent"},{"benchmark":"bfcl-v4","model":"granite-4.2-8b","score":52.06,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-9b","score":64.88,"metric":"percent"},{"benchmark":"bfcl-v4","model":"ornith-1.5-9b","score":65.03,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-12b-it","score":62.06,"metric":"percent"},{"benchmark":"bfcl-v4","model":"muse-glimmer-30b","score":53.74,"metric":"percent"},{"benchmark":"bfcl-v4","model":"neohorse-1-9b","score":67.43,"metric":"percent"},{"benchmark":"humaneval","model":"granite-4.2-8b","score":96.34,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3.5-9b","score":92.68,"metric":"percent"},{"benchmark":"humaneval","model":"ornith-1.5-9b","score":93.9,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-4-12b-it","score":100,"metric":"percent"},{"benchmark":"humaneval","model":"muse-glimmer-30b","score":98.17,"metric":"percent"},{"benchmark":"humaneval","model":"neohorse-1-9b","score":98.17,"metric":"percent"},{"benchmark":"livecodebench","model":"granite-4.2-8b","score":72,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-9b","score":65.14,"metric":"percent"},{"benchmark":"livecodebench","model":"ornith-1.5-9b","score":47.43,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-12b-it","score":73.14,"metric":"percent"},{"benchmark":"livecodebench","model":"muse-glimmer-30b","score":65.71,"metric":"percent"},{"benchmark":"livecodebench","model":"neohorse-1-9b","score":65.14,"metric":"percent"},{"benchmark":"ifbench","model":"granite-4.2-8b","score":78,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-9b","score":66.33,"metric":"percent"},{"benchmark":"ifbench","model":"ornith-1.5-9b","score":40,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-12b-it","score":77.67,"metric":"percent"},{"benchmark":"ifbench","model":"muse-glimmer-30b","score":78.67,"metric":"percent"},{"benchmark":"ifbench","model":"neohorse-1-9b","score":66.33,"metric":"percent"},{"benchmark":"ifeval","model":"granite-4.2-8b","score":92.98,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-9b","score":89.46,"metric":"percent"},{"benchmark":"ifeval","model":"ornith-1.5-9b","score":71.35,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-12b-it","score":94.27,"metric":"percent"},{"benchmark":"ifeval","model":"muse-glimmer-30b","score":93.9,"metric":"percent"},{"benchmark":"ifeval","model":"neohorse-1-9b","score":89.09,"metric":"percent"},{"benchmark":"qwenclawbench","model":"qwen3.5-4b","score":38.47,"metric":"percent"},{"benchmark":"qwenclawbench","model":"gemma-4-e4b-it","score":22.98,"metric":"percent"},{"benchmark":"qwenclawbench","model":"nanbeige4.2-3b","score":40.66,"metric":"percent"},{"benchmark":"qwenclawbench","model":"agents-a1-4b","score":43.16,"metric":"percent"},{"benchmark":"qwenclawbench","model":"spark-x2.5-4b","score":43.52,"metric":"percent"},{"benchmark":"qwenclawbench","model":"neohorse-1-4b","score":44.68,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"qwen3.5-4b","score":24.62,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"gemma-4-e4b-it","score":11.65,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"nanbeige4.2-3b","score":21.03,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"agents-a1-4b","score":33.37,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"spark-x2.5-4b","score":26.47,"metric":"percent"},{"benchmark":"workbuddy-bench","model":"neohorse-1-4b","score":34.41,"metric":"percent"},{"benchmark":"pinchbench","model":"qwen3.5-4b","score":71.19,"metric":"percent"},{"benchmark":"pinchbench","model":"gemma-4-e4b-it","score":47.6,"metric":"percent"},{"benchmark":"pinchbench","model":"nanbeige4.2-3b","score":66.78,"metric":"percent"},{"benchmark":"pinchbench","model":"agents-a1-4b","score":75.07,"metric":"percent"},{"benchmark":"pinchbench","model":"spark-x2.5-4b","score":62.37,"metric":"percent"},{"benchmark":"pinchbench","model":"neohorse-1-4b","score":77.33,"metric":"percent"},{"benchmark":"vitabench","model":"qwen3.5-4b","score":21.5,"metric":"percent"},{"benchmark":"vitabench","model":"gemma-4-e4b-it","score":5,"metric":"percent"},{"benchmark":"vitabench","model":"nanbeige4.2-3b","score":31.5,"metric":"percent"},{"benchmark":"vitabench","model":"agents-a1-4b","score":39.25,"metric":"percent"},{"benchmark":"vitabench","model":"spark-x2.5-4b","score":37,"metric":"percent"},{"benchmark":"vitabench","model":"neohorse-1-4b","score":32,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.5-4b","score":61.02,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-e4b-it","score":47.18,"metric":"percent"},{"benchmark":"bfcl-v4","model":"nanbeige4.2-3b","score":67.28,"metric":"percent"},{"benchmark":"bfcl-v4","model":"agents-a1-4b","score":46.6,"metric":"percent"},{"benchmark":"bfcl-v4","model":"spark-x2.5-4b","score":63.71,"metric":"percent"},{"benchmark":"bfcl-v4","model":"neohorse-1-4b","score":61.79,"metric":"percent"},{"benchmark":"humaneval","model":"qwen3.5-4b","score":87.2,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-4-e4b-it","score":84.76,"metric":"percent"},{"benchmark":"humaneval","model":"nanbeige4.2-3b","score":98.78,"metric":"percent"},{"benchmark":"humaneval","model":"agents-a1-4b","score":92.68,"metric":"percent"},{"benchmark":"humaneval","model":"spark-x2.5-4b","score":92.07,"metric":"percent"},{"benchmark":"humaneval","model":"neohorse-1-4b","score":96.95,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.5-4b","score":53.71,"metric":"percent"},{"benchmark":"livecodebench","model":"agents-a1-4b","score":56.57,"metric":"percent"},{"benchmark":"livecodebench","model":"spark-x2.5-4b","score":54.86,"metric":"percent"},{"benchmark":"livecodebench","model":"neohorse-1-4b","score":59.43,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.5-4b","score":60.33,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-e4b-it","score":40,"metric":"percent"},{"benchmark":"ifbench","model":"nanbeige4.2-3b","score":55,"metric":"percent"},{"benchmark":"ifbench","model":"agents-a1-4b","score":63.33,"metric":"percent"},{"benchmark":"ifbench","model":"spark-x2.5-4b","score":73.33,"metric":"percent"},{"benchmark":"ifbench","model":"neohorse-1-4b","score":65.33,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.5-4b","score":87.06,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-e4b-it","score":74.68,"metric":"percent"},{"benchmark":"ifeval","model":"nanbeige4.2-3b","score":84.47,"metric":"percent"},{"benchmark":"ifeval","model":"agents-a1-4b","score":83.55,"metric":"percent"},{"benchmark":"ifeval","model":"spark-x2.5-4b","score":91.13,"metric":"percent"},{"benchmark":"ifeval","model":"neohorse-1-4b","score":88.35,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"tinfield-1","score":33,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"qwen3.8-flash-next","score":29,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"tinfield-1","score":62,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"claude-opus-4.8","score":23.6,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"gpt-5.6-terra","score":21.5,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.3","score":69,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.3-flash","score":63,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro","score":63,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-flash","score":53,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grm-3.2-sky","score":89.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v4-flash","score":86.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"grm-3.2-sky","score":96.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"grm-3.2-sky","score":90.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v4-flash","score":88.1,"metric":"percent"},{"benchmark":"livecodebench","model":"grm-3.2-sky","score":87.7,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"grm-3.2-sky","score":86.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"deepseek-v4-flash","score":94.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"grm-3.2-sky","score":96.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"deepseek-v4-flash","score":95.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"grm-3.2-sky","score":81.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"grm-3.2-sky","score":58.3,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.6-27b","score":53.5,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"grm-3.2-sky","score":66.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.6-27b","score":59.3,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"deepseek-v4-flash","score":56.9,"metric":"percent"},{"benchmark":"nl2repo","model":"grm-3.2-sky","score":35.6,"metric":"percent"},{"benchmark":"deepswe","model":"grm-3.2-sky","score":19.5,"metric":"percent"},{"benchmark":"deepswe","model":"gpt-5.6-luna","score":67.2,"metric":"percent"},{"benchmark":"deepswe","model":"claude-sonnet-5","score":53.8,"metric":"percent"},{"benchmark":"deepswe","model":"deepseek-v4-flash","score":53,"metric":"percent"},{"benchmark":"aime-2026-i","model":"darwin-180b-rsi","score":100,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.5-397b-a17b","score":93.33,"metric":"percent"},{"benchmark":"aime-2026-i","model":"glm-5","score":95.83,"metric":"percent"},{"benchmark":"aime-2026-i","model":"step-3.5-flash-20260204","score":96.67,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"darwin-180b-rsi","score":94.44,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kimi-k2.6","score":90.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"minimax-m2.1","score":80.81,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"step-3.5-flash-20260204","score":83.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"darwin-180b-rsi","score":88.12,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-5","score":86,"metric":"percent"},{"benchmark":"mmlu-pro","model":"step-3.5-flash-20260204","score":84.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"darwin-180b-rsi","score":79.48,"metric":"percent"},{"benchmark":"mmmu-pro","model":"kimi-k2.6","score":79.4,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"darwin-180b-rsi","score":100,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"glm-5","score":86.36,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"step-3.5-flash-20260204","score":86.36,"metric":"percent"},{"benchmark":"lexam","model":"darwin-180b-rsi","score":68.94,"metric":"percent"},{"benchmark":"lexam","model":"deepseek-r1","score":52.41,"metric":"percent"},{"benchmark":"lexam","model":"qwen3-235b-a22b-thinking-2507","score":48.19,"metric":"percent"},{"benchmark":"lexam-hard","model":"darwin-180b-rsi","score":45.72,"metric":"percent"},{"benchmark":"lexam-hard","model":"inkling","score":40.82,"metric":"percent"},{"benchmark":"lexam-hard","model":"kimi-k3","score":29.54,"metric":"percent"},{"benchmark":"lexam-hard","model":"kimi-k2.6","score":36.18,"metric":"percent"},{"benchmark":"lexam-hard","model":"deepseek-v4-pro","score":38.93,"metric":"percent"},{"benchmark":"blink","model":"gemini-3.6-flash","score":89.2,"metric":"percent"},{"benchmark":"blink","model":"gpt-6-astra","score":80.6,"metric":"percent"},{"benchmark":"blink","model":"claude-opus-5","score":85.5,"metric":"percent"},{"benchmark":"blink","model":"hy-embodied-vlm-1.0","score":86.1,"metric":"percent"},{"benchmark":"blink","model":"embodied-r1.5-8b","score":78.6,"metric":"percent"},{"benchmark":"blink","model":"rynnbrain1.1-9b","score":84.8,"metric":"percent"},{"benchmark":"blink","model":"robobrain2.5-8b","score":80.4,"metric":"percent"},{"benchmark":"blink","model":"mimo-embodied-7b","score":69.5,"metric":"percent"},{"benchmark":"blink","model":"cosmos3-nano","score":80.6,"metric":"percent"},{"benchmark":"blink","model":"ace-brain-0.5-8b","score":77.8,"metric":"percent"},{"benchmark":"blink","model":"qwen3-vl-8b-instruct","score":81.7,"metric":"percent"},{"benchmark":"blink","model":"physbrain1.5-2b","score":81.9,"metric":"percent"},{"benchmark":"blink","model":"physbrain1.5-8b","score":87.9,"metric":"percent"},{"benchmark":"cv-bench","model":"gemini-3.6-flash","score":90,"metric":"percent"},{"benchmark":"cv-bench","model":"gpt-6-astra","score":84.9,"metric":"percent"},{"benchmark":"cv-bench","model":"claude-opus-5","score":87.8,"metric":"percent"},{"benchmark":"cv-bench","model":"hy-embodied-vlm-1.0","score":89.3,"metric":"percent"},{"benchmark":"cv-bench","model":"embodied-r1.5-8b","score":86.9,"metric":"percent"},{"benchmark":"cv-bench","model":"rynnbrain1.1-9b","score":88.1,"metric":"percent"},{"benchmark":"cv-bench","model":"robobrain2.5-8b","score":88,"metric":"percent"},{"benchmark":"cv-bench","model":"mimo-embodied-7b","score":89.4,"metric":"percent"},{"benchmark":"cv-bench","model":"cosmos3-nano","score":88.3,"metric":"percent"},{"benchmark":"cv-bench","model":"ace-brain-0.5-8b","score":85,"metric":"percent"},{"benchmark":"cv-bench","model":"qwen3-vl-8b-instruct","score":85.8,"metric":"percent"},{"benchmark":"cv-bench","model":"physbrain1.5-2b","score":87.6,"metric":"percent"},{"benchmark":"cv-bench","model":"physbrain1.5-8b","score":90,"metric":"percent"},{"benchmark":"3dsrbench","model":"gemini-3.6-flash","score":67.7,"metric":"percent"},{"benchmark":"3dsrbench","model":"gpt-6-astra","score":62.3,"metric":"percent"},{"benchmark":"3dsrbench","model":"claude-opus-5","score":63.3,"metric":"percent"},{"benchmark":"3dsrbench","model":"hy-embodied-vlm-1.0","score":62.1,"metric":"percent"},{"benchmark":"3dsrbench","model":"embodied-r1.5-8b","score":52.3,"metric":"percent"},{"benchmark":"3dsrbench","model":"rynnbrain1.1-9b","score":59,"metric":"percent"},{"benchmark":"3dsrbench","model":"robobrain2.5-8b","score":54.7,"metric":"percent"},{"benchmark":"3dsrbench","model":"mimo-embodied-7b","score":53.2,"metric":"percent"},{"benchmark":"3dsrbench","model":"cosmos3-nano","score":53.5,"metric":"percent"},{"benchmark":"3dsrbench","model":"ace-brain-0.5-8b","score":51.8,"metric":"percent"},{"benchmark":"3dsrbench","model":"qwen3-vl-8b-instruct","score":53.6,"metric":"percent"},{"benchmark":"3dsrbench","model":"physbrain1.5-2b","score":59.3,"metric":"percent"},{"benchmark":"3dsrbench","model":"physbrain1.5-8b","score":63,"metric":"percent"},{"benchmark":"embspatialbench","model":"gemini-3.6-flash","score":84.7,"metric":"percent"},{"benchmark":"embspatialbench","model":"gpt-6-astra","score":79.8,"metric":"percent"},{"benchmark":"embspatialbench","model":"claude-opus-5","score":81.1,"metric":"percent"},{"benchmark":"embspatialbench","model":"hy-embodied-vlm-1.0","score":80.5,"metric":"percent"},{"benchmark":"embspatialbench","model":"embodied-r1.5-8b","score":75.2,"metric":"percent"},{"benchmark":"embspatialbench","model":"rynnbrain1.1-9b","score":81.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"robobrain2.5-8b","score":77.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"mimo-embodied-7b","score":77,"metric":"percent"},{"benchmark":"embspatialbench","model":"cosmos3-nano","score":82.1,"metric":"percent"},{"benchmark":"embspatialbench","model":"ace-brain-0.5-8b","score":77.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"qwen3-vl-8b-instruct","score":79.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"physbrain1.5-2b","score":78.9,"metric":"percent"},{"benchmark":"embspatialbench","model":"physbrain1.5-8b","score":81.8,"metric":"percent"},{"benchmark":"mindcube","model":"gemini-3.6-flash","score":77.1,"metric":"percent"},{"benchmark":"mindcube","model":"gpt-6-astra","score":78.8,"metric":"percent"},{"benchmark":"mindcube","model":"claude-opus-5","score":66.7,"metric":"percent"},{"benchmark":"mindcube","model":"hy-embodied-vlm-1.0","score":65.4,"metric":"percent"},{"benchmark":"mindcube","model":"embodied-r1.5-8b","score":30.9,"metric":"percent"},{"benchmark":"mindcube","model":"rynnbrain1.1-9b","score":82.1,"metric":"percent"},{"benchmark":"mindcube","model":"robobrain2.5-8b","score":30.4,"metric":"percent"},{"benchmark":"mindcube","model":"mimo-embodied-7b","score":31.3,"metric":"percent"},{"benchmark":"mindcube","model":"cosmos3-nano","score":39.2,"metric":"percent"},{"benchmark":"mindcube","model":"ace-brain-0.5-8b","score":94.2,"metric":"percent"},{"benchmark":"mindcube","model":"qwen3-vl-8b-instruct","score":33.9,"metric":"percent"},{"benchmark":"mindcube","model":"physbrain1.5-2b","score":60.9,"metric":"percent"},{"benchmark":"mindcube","model":"physbrain1.5-8b","score":86.2,"metric":"percent"},{"benchmark":"mmsi-bench","model":"gemini-3.6-flash","score":52.8,"metric":"percent"},{"benchmark":"mmsi-bench","model":"gpt-6-astra","score":57.9,"metric":"percent"},{"benchmark":"mmsi-bench","model":"claude-opus-5","score":44.1,"metric":"percent"},{"benchmark":"mmsi-bench","model":"hy-embodied-vlm-1.0","score":39,"metric":"percent"},{"benchmark":"mmsi-bench","model":"embodied-r1.5-8b","score":30.1,"metric":"percent"},{"benchmark":"mmsi-bench","model":"rynnbrain1.1-9b","score":46,"metric":"percent"},{"benchmark":"mmsi-bench","model":"robobrain2.5-8b","score":29.4,"metric":"percent"},{"benchmark":"mmsi-bench","model":"mimo-embodied-7b","score":31.8,"metric":"percent"},{"benchmark":"mmsi-bench","model":"cosmos3-nano","score":35.7,"metric":"percent"},{"benchmark":"mmsi-bench","model":"ace-brain-0.5-8b","score":35.8,"metric":"percent"},{"benchmark":"mmsi-bench","model":"qwen3-vl-8b-instruct","score":30.8,"metric":"percent"},{"benchmark":"mmsi-bench","model":"physbrain1.5-2b","score":30.7,"metric":"percent"},{"benchmark":"mmsi-bench","model":"physbrain1.5-8b","score":41,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"gemini-3.6-flash","score":87.1,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"gpt-6-astra","score":68.3,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"claude-opus-5","score":74.3,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"hy-embodied-vlm-1.0","score":76.2,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"embodied-r1.5-8b","score":51.5,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"rynnbrain1.1-9b","score":66.3,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"robobrain2.5-8b","score":76.2,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"mimo-embodied-7b","score":47.5,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"cosmos3-nano","score":46.5,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"ace-brain-0.5-8b","score":35.6,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"qwen3-vl-8b-instruct","score":54.5,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"physbrain1.5-2b","score":69.3,"metric":"percent"},{"benchmark":"q-spatial-bench","model":"physbrain1.5-8b","score":81.2,"metric":"percent"},{"benchmark":"robospatialhome","model":"gemini-3.6-flash","score":71,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-6-astra","score":73.7,"metric":"percent"},{"benchmark":"robospatialhome","model":"claude-opus-5","score":72,"metric":"percent"},{"benchmark":"robospatialhome","model":"hy-embodied-vlm-1.0","score":71.2,"metric":"percent"},{"benchmark":"robospatialhome","model":"embodied-r1.5-8b","score":72,"metric":"percent"},{"benchmark":"robospatialhome","model":"rynnbrain1.1-9b","score":70.4,"metric":"percent"},{"benchmark":"robospatialhome","model":"robobrain2.5-8b","score":67.3,"metric":"percent"},{"benchmark":"robospatialhome","model":"mimo-embodied-7b","score":60.1,"metric":"percent"},{"benchmark":"robospatialhome","model":"cosmos3-nano","score":66.4,"metric":"percent"},{"benchmark":"robospatialhome","model":"ace-brain-0.5-8b","score":65.9,"metric":"percent"},{"benchmark":"robospatialhome","model":"qwen3-vl-8b-instruct","score":67.7,"metric":"percent"},{"benchmark":"robospatialhome","model":"physbrain1.5-2b","score":65,"metric":"percent"},{"benchmark":"robospatialhome","model":"physbrain1.5-8b","score":73.9,"metric":"percent"},{"benchmark":"sat","model":"gemini-3.6-flash","score":88.7,"metric":"percent"},{"benchmark":"sat","model":"gpt-6-astra","score":96.7,"metric":"percent"},{"benchmark":"sat","model":"claude-opus-5","score":88.7,"metric":"percent"},{"benchmark":"sat","model":"hy-embodied-vlm-1.0","score":81.3,"metric":"percent"},{"benchmark":"sat","model":"embodied-r1.5-8b","score":74,"metric":"percent"},{"benchmark":"sat","model":"rynnbrain1.1-9b","score":78,"metric":"percent"},{"benchmark":"sat","model":"robobrain2.5-8b","score":65.3,"metric":"percent"},{"benchmark":"sat","model":"mimo-embodied-7b","score":76,"metric":"percent"},{"benchmark":"sat","model":"cosmos3-nano","score":69.3,"metric":"percent"},{"benchmark":"sat","model":"ace-brain-0.5-8b","score":79.3,"metric":"percent"},{"benchmark":"sat","model":"qwen3-vl-8b-instruct","score":70.7,"metric":"percent"},{"benchmark":"sat","model":"physbrain1.5-2b","score":73.3,"metric":"percent"},{"benchmark":"sat","model":"physbrain1.5-8b","score":79.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"gemini-3.6-flash","score":51.8,"metric":"percent"},{"benchmark":"vsi-bench","model":"gpt-6-astra","score":59.8,"metric":"percent"},{"benchmark":"vsi-bench","model":"claude-opus-5","score":21.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"hy-embodied-vlm-1.0","score":55.7,"metric":"percent"},{"benchmark":"vsi-bench","model":"embodied-r1.5-8b","score":56.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"rynnbrain1.1-9b","score":65.9,"metric":"percent"},{"benchmark":"vsi-bench","model":"robobrain2.5-8b","score":43.9,"metric":"percent"},{"benchmark":"vsi-bench","model":"mimo-embodied-7b","score":45,"metric":"percent"},{"benchmark":"vsi-bench","model":"cosmos3-nano","score":50.4,"metric":"percent"},{"benchmark":"vsi-bench","model":"ace-brain-0.5-8b","score":57.9,"metric":"percent"},{"benchmark":"vsi-bench","model":"qwen3-vl-8b-instruct","score":55.1,"metric":"percent"},{"benchmark":"vsi-bench","model":"physbrain1.5-2b","score":57.3,"metric":"percent"},{"benchmark":"vsi-bench","model":"physbrain1.5-8b","score":61.9,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"gemini-3.6-flash","score":56.6,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"gpt-6-astra","score":54.2,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"claude-opus-5","score":49.8,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"hy-embodied-vlm-1.0","score":52.4,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"embodied-r1.5-8b","score":43.9,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"rynnbrain1.1-9b","score":56.4,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"robobrain2.5-8b","score":39.3,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"mimo-embodied-7b","score":39.7,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"cosmos3-nano","score":55,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"ace-brain-0.5-8b","score":48.3,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"qwen3-vl-8b-instruct","score":40.3,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"physbrain1.5-2b","score":58.1,"metric":"percent"},{"benchmark":"viewspatial-bench","model":"physbrain1.5-8b","score":62.5,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"gemini-3.6-flash","score":65.3,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"gpt-6-astra","score":75.7,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"claude-opus-5","score":71,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"hy-embodied-vlm-1.0","score":64.5,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"embodied-r1.5-8b","score":67.5,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"rynnbrain1.1-9b","score":64.3,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"robobrain2.5-8b","score":57.7,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"mimo-embodied-7b","score":56.5,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"cosmos3-nano","score":66.8,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"ace-brain-0.5-8b","score":46.5,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"qwen3-vl-8b-instruct","score":60.6,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"physbrain1.5-2b","score":71.2,"metric":"percent"},{"benchmark":"cosmos-reason-bench","model":"physbrain1.5-8b","score":72.8,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"gemini-3.6-flash","score":53.1,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"gpt-6-astra","score":69.3,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"claude-opus-5","score":48.4,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"hy-embodied-vlm-1.0","score":47.5,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"embodied-r1.5-8b","score":53.1,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"rynnbrain1.1-9b","score":37,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"robobrain2.5-8b","score":33.8,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"mimo-embodied-7b","score":37.9,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"cosmos3-nano","score":42.6,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"ace-brain-0.5-8b","score":33.5,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"qwen3-vl-8b-instruct","score":32.1,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"physbrain1.5-2b","score":56.1,"metric":"percent"},{"benchmark":"egoplan-bench2","model":"physbrain1.5-8b","score":62.1,"metric":"percent"},{"benchmark":"erqa","model":"gemini-3.6-flash","score":72.3,"metric":"percent"},{"benchmark":"erqa","model":"gpt-6-astra","score":75.8,"metric":"percent"},{"benchmark":"erqa","model":"claude-opus-5","score":61.5,"metric":"percent"},{"benchmark":"erqa","model":"hy-embodied-vlm-1.0","score":56.3,"metric":"percent"},{"benchmark":"erqa","model":"embodied-r1.5-8b","score":42.3,"metric":"percent"},{"benchmark":"erqa","model":"rynnbrain1.1-9b","score":46.5,"metric":"percent"},{"benchmark":"erqa","model":"robobrain2.5-8b","score":44.3,"metric":"percent"},{"benchmark":"erqa","model":"mimo-embodied-7b","score":44.8,"metric":"percent"},{"benchmark":"erqa","model":"cosmos3-nano","score":47.5,"metric":"percent"},{"benchmark":"erqa","model":"ace-brain-0.5-8b","score":45.3,"metric":"percent"},{"benchmark":"erqa","model":"qwen3-vl-8b-instruct","score":42.5,"metric":"percent"},{"benchmark":"erqa","model":"physbrain1.5-2b","score":44,"metric":"percent"},{"benchmark":"erqa","model":"physbrain1.5-8b","score":52.8,"metric":"percent"},{"benchmark":"erqa-plus","model":"gemini-3.6-flash","score":92.2,"metric":"percent"},{"benchmark":"erqa-plus","model":"gpt-6-astra","score":86.1,"metric":"percent"},{"benchmark":"erqa-plus","model":"claude-opus-5","score":88.3,"metric":"percent"},{"benchmark":"erqa-plus","model":"hy-embodied-vlm-1.0","score":82.2,"metric":"percent"},{"benchmark":"erqa-plus","model":"embodied-r1.5-8b","score":80.7,"metric":"percent"},{"benchmark":"erqa-plus","model":"rynnbrain1.1-9b","score":83.6,"metric":"percent"},{"benchmark":"erqa-plus","model":"robobrain2.5-8b","score":81.1,"metric":"percent"},{"benchmark":"erqa-plus","model":"mimo-embodied-7b","score":81.1,"metric":"percent"},{"benchmark":"erqa-plus","model":"cosmos3-nano","score":83.5,"metric":"percent"},{"benchmark":"erqa-plus","model":"ace-brain-0.5-8b","score":81.4,"metric":"percent"},{"benchmark":"erqa-plus","model":"qwen3-vl-8b-instruct","score":82.5,"metric":"percent"},{"benchmark":"erqa-plus","model":"physbrain1.5-2b","score":79.2,"metric":"percent"},{"benchmark":"erqa-plus","model":"physbrain1.5-8b","score":85.2,"metric":"percent"},{"benchmark":"robovqa","model":"gemini-3.6-flash","score":41.7,"metric":"percent"},{"benchmark":"robovqa","model":"gpt-6-astra","score":37,"metric":"percent"},{"benchmark":"robovqa","model":"claude-opus-5","score":36,"metric":"percent"},{"benchmark":"robovqa","model":"hy-embodied-vlm-1.0","score":41.2,"metric":"percent"},{"benchmark":"robovqa","model":"embodied-r1.5-8b","score":60.8,"metric":"percent"},{"benchmark":"robovqa","model":"rynnbrain1.1-9b","score":60.9,"metric":"percent"},{"benchmark":"robovqa","model":"robobrain2.5-8b","score":48.4,"metric":"percent"},{"benchmark":"robovqa","model":"mimo-embodied-7b","score":55.5,"metric":"percent"},{"benchmark":"robovqa","model":"cosmos3-nano","score":51.5,"metric":"percent"},{"benchmark":"robovqa","model":"ace-brain-0.5-8b","score":44.7,"metric":"percent"},{"benchmark":"robovqa","model":"qwen3-vl-8b-instruct","score":58.5,"metric":"percent"},{"benchmark":"robovqa","model":"physbrain1.5-2b","score":62.9,"metric":"percent"},{"benchmark":"robovqa","model":"physbrain1.5-8b","score":61.5,"metric":"percent"},{"benchmark":"vlabench","model":"gemini-3.6-flash","score":64.7,"metric":"percent"},{"benchmark":"vlabench","model":"gpt-6-astra","score":66.3,"metric":"percent"},{"benchmark":"vlabench","model":"claude-opus-5","score":60.3,"metric":"percent"},{"benchmark":"vlabench","model":"hy-embodied-vlm-1.0","score":50.9,"metric":"percent"},{"benchmark":"vlabench","model":"embodied-r1.5-8b","score":40.9,"metric":"percent"},{"benchmark":"vlabench","model":"rynnbrain1.1-9b","score":42.4,"metric":"percent"},{"benchmark":"vlabench","model":"robobrain2.5-8b","score":37.6,"metric":"percent"},{"benchmark":"vlabench","model":"mimo-embodied-7b","score":39.9,"metric":"percent"},{"benchmark":"vlabench","model":"cosmos3-nano","score":48.7,"metric":"percent"},{"benchmark":"vlabench","model":"ace-brain-0.5-8b","score":29.1,"metric":"percent"},{"benchmark":"vlabench","model":"qwen3-vl-8b-instruct","score":44.8,"metric":"percent"},{"benchmark":"vlabench","model":"physbrain1.5-2b","score":73.4,"metric":"percent"},{"benchmark":"vlabench","model":"physbrain1.5-8b","score":76.4,"metric":"percent"},{"benchmark":"part-affordance","model":"gemini-3.6-flash","score":64.7,"metric":"percent"},{"benchmark":"part-affordance","model":"gpt-6-astra","score":55,"metric":"percent"},{"benchmark":"part-affordance","model":"claude-opus-5","score":78.1,"metric":"percent"},{"benchmark":"part-affordance","model":"hy-embodied-vlm-1.0","score":62.8,"metric":"percent"},{"benchmark":"part-affordance","model":"embodied-r1.5-8b","score":83.4,"metric":"percent"},{"benchmark":"part-affordance","model":"rynnbrain1.1-9b","score":40.5,"metric":"percent"},{"benchmark":"part-affordance","model":"robobrain2.5-8b","score":24.7,"metric":"percent"},{"benchmark":"part-affordance","model":"mimo-embodied-7b","score":61.9,"metric":"percent"},{"benchmark":"part-affordance","model":"cosmos3-nano","score":33.3,"metric":"percent"},{"benchmark":"part-affordance","model":"ace-brain-0.5-8b","score":36.3,"metric":"percent"},{"benchmark":"part-affordance","model":"qwen3-vl-8b-instruct","score":56.4,"metric":"percent"},{"benchmark":"part-affordance","model":"physbrain1.5-2b","score":83.7,"metric":"percent"},{"benchmark":"part-affordance","model":"physbrain1.5-8b","score":84,"metric":"percent"},{"benchmark":"piobench","model":"gemini-3.6-flash","score":80.9,"metric":"percent"},{"benchmark":"piobench","model":"gpt-6-astra","score":79.7,"metric":"percent"},{"benchmark":"piobench","model":"claude-opus-5","score":71.6,"metric":"percent"},{"benchmark":"piobench","model":"hy-embodied-vlm-1.0","score":62.6,"metric":"percent"},{"benchmark":"piobench","model":"embodied-r1.5-8b","score":61.5,"metric":"percent"},{"benchmark":"piobench","model":"rynnbrain1.1-9b","score":64.8,"metric":"percent"},{"benchmark":"piobench","model":"robobrain2.5-8b","score":62.3,"metric":"percent"},{"benchmark":"piobench","model":"mimo-embodied-7b","score":56.2,"metric":"percent"},{"benchmark":"piobench","model":"cosmos3-nano","score":64.3,"metric":"percent"},{"benchmark":"piobench","model":"ace-brain-0.5-8b","score":60.4,"metric":"percent"},{"benchmark":"piobench","model":"qwen3-vl-8b-instruct","score":53.7,"metric":"percent"},{"benchmark":"piobench","model":"physbrain1.5-2b","score":54.4,"metric":"percent"},{"benchmark":"piobench","model":"physbrain1.5-8b","score":68.3,"metric":"percent"},{"benchmark":"pixmo-points","model":"gemini-3.6-flash","score":74.8,"metric":"percent"},{"benchmark":"pixmo-points","model":"gpt-6-astra","score":75.2,"metric":"percent"},{"benchmark":"pixmo-points","model":"claude-opus-5","score":56.7,"metric":"percent"},{"benchmark":"pixmo-points","model":"hy-embodied-vlm-1.0","score":55.8,"metric":"percent"},{"benchmark":"pixmo-points","model":"embodied-r1.5-8b","score":65.3,"metric":"percent"},{"benchmark":"pixmo-points","model":"rynnbrain1.1-9b","score":29.9,"metric":"percent"},{"benchmark":"pixmo-points","model":"robobrain2.5-8b","score":57.3,"metric":"percent"},{"benchmark":"pixmo-points","model":"mimo-embodied-7b","score":51.5,"metric":"percent"},{"benchmark":"pixmo-points","model":"cosmos3-nano","score":60.5,"metric":"percent"},{"benchmark":"pixmo-points","model":"ace-brain-0.5-8b","score":65.6,"metric":"percent"},{"benchmark":"pixmo-points","model":"qwen3-vl-8b-instruct","score":53.7,"metric":"percent"},{"benchmark":"pixmo-points","model":"physbrain1.5-2b","score":52.3,"metric":"percent"},{"benchmark":"pixmo-points","model":"physbrain1.5-8b","score":62.2,"metric":"percent"},{"benchmark":"point-bench","model":"gemini-3.6-flash","score":69.6,"metric":"percent"},{"benchmark":"point-bench","model":"gpt-6-astra","score":71.9,"metric":"percent"},{"benchmark":"point-bench","model":"claude-opus-5","score":68.6,"metric":"percent"},{"benchmark":"point-bench","model":"hy-embodied-vlm-1.0","score":61.1,"metric":"percent"},{"benchmark":"point-bench","model":"embodied-r1.5-8b","score":64.5,"metric":"percent"},{"benchmark":"point-bench","model":"rynnbrain1.1-9b","score":45.5,"metric":"percent"},{"benchmark":"point-bench","model":"robobrain2.5-8b","score":61.7,"metric":"percent"},{"benchmark":"point-bench","model":"mimo-embodied-7b","score":51.6,"metric":"percent"},{"benchmark":"point-bench","model":"cosmos3-nano","score":62.8,"metric":"percent"},{"benchmark":"point-bench","model":"ace-brain-0.5-8b","score":63,"metric":"percent"},{"benchmark":"point-bench","model":"qwen3-vl-8b-instruct","score":61.5,"metric":"percent"},{"benchmark":"point-bench","model":"physbrain1.5-2b","score":59.2,"metric":"percent"},{"benchmark":"point-bench","model":"physbrain1.5-8b","score":64.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-3.6-flash","score":76.4,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-6-astra","score":78,"metric":"percent"},{"benchmark":"refspatialbench","model":"claude-opus-5","score":56.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"hy-embodied-vlm-1.0","score":47.4,"metric":"percent"},{"benchmark":"refspatialbench","model":"embodied-r1.5-8b","score":55.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"rynnbrain1.1-9b","score":63.2,"metric":"percent"},{"benchmark":"refspatialbench","model":"robobrain2.5-8b","score":59.9,"metric":"percent"},{"benchmark":"refspatialbench","model":"mimo-embodied-7b","score":40,"metric":"percent"},{"benchmark":"refspatialbench","model":"cosmos3-nano","score":52.8,"metric":"percent"},{"benchmark":"refspatialbench","model":"ace-brain-0.5-8b","score":53.3,"metric":"percent"},{"benchmark":"refspatialbench","model":"qwen3-vl-8b-instruct","score":43.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"physbrain1.5-2b","score":37.6,"metric":"percent"},{"benchmark":"refspatialbench","model":"physbrain1.5-8b","score":50.9,"metric":"percent"},{"benchmark":"roboafford","model":"gemini-3.6-flash","score":83.4,"metric":"percent"},{"benchmark":"roboafford","model":"gpt-6-astra","score":84.6,"metric":"percent"},{"benchmark":"roboafford","model":"claude-opus-5","score":82.3,"metric":"percent"},{"benchmark":"roboafford","model":"hy-embodied-vlm-1.0","score":75.8,"metric":"percent"},{"benchmark":"roboafford","model":"embodied-r1.5-8b","score":76.9,"metric":"percent"},{"benchmark":"roboafford","model":"rynnbrain1.1-9b","score":74,"metric":"percent"},{"benchmark":"roboafford","model":"robobrain2.5-8b","score":71.7,"metric":"percent"},{"benchmark":"roboafford","model":"mimo-embodied-7b","score":71.8,"metric":"percent"},{"benchmark":"roboafford","model":"cosmos3-nano","score":81.1,"metric":"percent"},{"benchmark":"roboafford","model":"ace-brain-0.5-8b","score":71.8,"metric":"percent"},{"benchmark":"roboafford","model":"qwen3-vl-8b-instruct","score":66.8,"metric":"percent"},{"benchmark":"roboafford","model":"physbrain1.5-2b","score":75.9,"metric":"percent"},{"benchmark":"roboafford","model":"physbrain1.5-8b","score":80.4,"metric":"percent"},{"benchmark":"roborefit","model":"gemini-3.6-flash","score":85.9,"metric":"percent"},{"benchmark":"roborefit","model":"gpt-6-astra","score":85.1,"metric":"percent"},{"benchmark":"roborefit","model":"claude-opus-5","score":83.5,"metric":"percent"},{"benchmark":"roborefit","model":"hy-embodied-vlm-1.0","score":82.5,"metric":"percent"},{"benchmark":"roborefit","model":"embodied-r1.5-8b","score":86.1,"metric":"percent"},{"benchmark":"roborefit","model":"rynnbrain1.1-9b","score":81.9,"metric":"percent"},{"benchmark":"roborefit","model":"robobrain2.5-8b","score":82.8,"metric":"percent"},{"benchmark":"roborefit","model":"mimo-embodied-7b","score":75.5,"metric":"percent"},{"benchmark":"roborefit","model":"cosmos3-nano","score":86.2,"metric":"percent"},{"benchmark":"roborefit","model":"ace-brain-0.5-8b","score":84.6,"metric":"percent"},{"benchmark":"roborefit","model":"qwen3-vl-8b-instruct","score":81.3,"metric":"percent"},{"benchmark":"roborefit","model":"physbrain1.5-2b","score":86.8,"metric":"percent"},{"benchmark":"roborefit","model":"physbrain1.5-8b","score":89.6,"metric":"percent"},{"benchmark":"vabench-point","model":"gemini-3.6-flash","score":60.7,"metric":"percent"},{"benchmark":"vabench-point","model":"gpt-6-astra","score":65.3,"metric":"percent"},{"benchmark":"vabench-point","model":"claude-opus-5","score":64.7,"metric":"percent"},{"benchmark":"vabench-point","model":"hy-embodied-vlm-1.0","score":60.5,"metric":"percent"},{"benchmark":"vabench-point","model":"embodied-r1.5-8b","score":75.7,"metric":"percent"},{"benchmark":"vabench-point","model":"rynnbrain1.1-9b","score":15.8,"metric":"percent"},{"benchmark":"vabench-point","model":"robobrain2.5-8b","score":10.6,"metric":"percent"},{"benchmark":"vabench-point","model":"mimo-embodied-7b","score":47.7,"metric":"percent"},{"benchmark":"vabench-point","model":"cosmos3-nano","score":53.2,"metric":"percent"},{"benchmark":"vabench-point","model":"ace-brain-0.5-8b","score":5.3,"metric":"percent"},{"benchmark":"vabench-point","model":"qwen3-vl-8b-instruct","score":46.3,"metric":"percent"},{"benchmark":"vabench-point","model":"physbrain1.5-2b","score":60.3,"metric":"percent"},{"benchmark":"vabench-point","model":"physbrain1.5-8b","score":65.2,"metric":"percent"},{"benchmark":"where2place","model":"gemini-3.6-flash","score":73.4,"metric":"percent"},{"benchmark":"where2place","model":"gpt-6-astra","score":76.9,"metric":"percent"},{"benchmark":"where2place","model":"claude-opus-5","score":69,"metric":"percent"},{"benchmark":"where2place","model":"hy-embodied-vlm-1.0","score":65.4,"metric":"percent"},{"benchmark":"where2place","model":"embodied-r1.5-8b","score":75,"metric":"percent"},{"benchmark":"where2place","model":"rynnbrain1.1-9b","score":72.7,"metric":"percent"},{"benchmark":"where2place","model":"robobrain2.5-8b","score":72,"metric":"percent"},{"benchmark":"where2place","model":"mimo-embodied-7b","score":63.9,"metric":"percent"},{"benchmark":"where2place","model":"cosmos3-nano","score":74.4,"metric":"percent"},{"benchmark":"where2place","model":"ace-brain-0.5-8b","score":56,"metric":"percent"},{"benchmark":"where2place","model":"qwen3-vl-8b-instruct","score":64.7,"metric":"percent"},{"benchmark":"where2place","model":"physbrain1.5-2b","score":70.7,"metric":"percent"},{"benchmark":"where2place","model":"physbrain1.5-8b","score":72.1,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"gemini-3.6-flash","score":82.8,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"gpt-6-astra","score":83.1,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"claude-opus-5","score":81.9,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"hy-embodied-vlm-1.0","score":84.5,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"embodied-r1.5-8b","score":84,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"rynnbrain1.1-9b","score":79.3,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"robobrain2.5-8b","score":85.2,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"mimo-embodied-7b","score":69,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"cosmos3-nano","score":80.9,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"ace-brain-0.5-8b","score":82.1,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"qwen3-vl-8b-instruct","score":78.2,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"physbrain1.5-2b","score":85,"metric":"percent"},{"benchmark":"sharerobot-traj","model":"physbrain1.5-8b","score":84.9,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"gemini-3.6-flash","score":84.2,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"gpt-6-astra","score":91.6,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"claude-opus-5","score":88.9,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"hy-embodied-vlm-1.0","score":87.5,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"embodied-r1.5-8b","score":92.3,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"rynnbrain1.1-9b","score":86.6,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"robobrain2.5-8b","score":85.4,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"mimo-embodied-7b","score":82.1,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"cosmos3-nano","score":88.3,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"ace-brain-0.5-8b","score":82.7,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"qwen3-vl-8b-instruct","score":84.4,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"physbrain1.5-2b","score":88.9,"metric":"percent"},{"benchmark":"vabench-visual-trace","model":"physbrain1.5-8b","score":89.8,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"jina-ocr-v1","score":91.14,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.4-thinking","score":75,"metric":"percent"},{"benchmark":"webarena-verified","model":"gpt-5.4-thinking","score":67.3,"metric":"percent"},{"benchmark":"gdpval","model":"gpt-5.4-thinking","score":83,"metric":"percent"},{"benchmark":"browsecomp","model":"gpt-5.4-thinking","score":82.7,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.4-thinking","score":57.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-5.4-thinking","score":92.8,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"gpt-5.4-thinking","score":47.6,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"gpt-5.4-thinking","score":27.1,"metric":"percent"},{"benchmark":"toolathlon","model":"gpt-5.4-thinking","score":54.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"gpt-5.3-codex","score":56.8,"metric":"percent"},{"benchmark":"osworld-verified","model":"gpt-5.2-thinking","score":47.3,"metric":"percent"},{"benchmark":"webarena-verified","model":"gpt-5.2-thinking","score":65.4,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-1-3","model":"claude-opus-4.6","score":40.7,"metric":"percent"},{"benchmark":"scires-frontiermath-tier-4","model":"claude-opus-4.6","score":22.9,"metric":"percent"},{"benchmark":"hle","model":"gemini-3.1-flash-lite","score":16,"metric":"percent"},{"benchmark":"hle","model":"gpt-5-mini-high","score":16.7,"metric":"percent"},{"benchmark":"videommmu","model":"gpt-5-mini-high","score":82.5,"metric":"percent"},{"benchmark":"facts-benchmark-suite","model":"gpt-5-mini-high","score":33.7,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"claude-haiku-5.5-max","score":57.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"claude-haiku-5.5-max","score":69.3,"metric":"percent"},{"benchmark":"hle-multichoice","model":"claude-haiku-5.5-max","score":37.4,"metric":"percent"},{"benchmark":"when2call","model":"claude-haiku-5.5-max","score":79.4,"metric":"percent"},{"benchmark":"wildguardtest","model":"claude-haiku-5.5-max","score":93.2,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"claude-haiku-5.5-high","score":57.2,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"claude-haiku-5.5-high","score":48.6,"metric":"percent"},{"benchmark":"hle-multichoice","model":"claude-haiku-5.5-high","score":26.7,"metric":"percent"},{"benchmark":"when2call","model":"claude-haiku-5.5-high","score":76.9,"metric":"percent"},{"benchmark":"wildguardtest","model":"claude-haiku-5.5-high","score":93.8,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"claude-haiku-5.5-low","score":52.4,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"claude-haiku-5.5-low","score":54.6,"metric":"percent"},{"benchmark":"hle-multichoice","model":"claude-haiku-5.5-low","score":23.6,"metric":"percent"},{"benchmark":"when2call","model":"claude-haiku-5.5-low","score":72.6,"metric":"percent"},{"benchmark":"wildguardtest","model":"claude-haiku-5.5-low","score":92.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"claude-haiku-5.5-medium","score":58.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"claude-haiku-5.5-medium","score":48.8,"metric":"percent"},{"benchmark":"hle-multichoice","model":"claude-haiku-5.5-medium","score":23.2,"metric":"percent"},{"benchmark":"when2call","model":"claude-haiku-5.5-medium","score":75.4,"metric":"percent"},{"benchmark":"wildguardtest","model":"claude-haiku-5.5-medium","score":93.3,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"claude-haiku-5.5-xhigh","score":58.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"claude-haiku-5.5-xhigh","score":55.1,"metric":"percent"},{"benchmark":"hle-multichoice","model":"claude-haiku-5.5-xhigh","score":30.2,"metric":"percent"},{"benchmark":"when2call","model":"claude-haiku-5.5-xhigh","score":77.6,"metric":"percent"},{"benchmark":"wildguardtest","model":"claude-haiku-5.5-xhigh","score":93.1,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"claude-opus-5.5-max","score":93.4,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"claude-opus-5.5-max","score":30.3,"metric":"percent"},{"benchmark":"hle-multichoice","model":"claude-opus-5.5-max","score":70.2,"metric":"percent"},{"benchmark":"when2call","model":"claude-opus-5.5-max","score":90.5,"metric":"percent"},{"benchmark":"wildguardtest","model":"claude-opus-5.5-max","score":93.5,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"claude-opus-5.5-low","score":93.4,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"claude-opus-5.5-low","score":27.3,"metric":"percent"},{"benchmark":"hle-multichoice","model":"claude-opus-5.5-low","score":59.8,"metric":"percent"},{"benchmark":"when2call","model":"claude-opus-5.5-low","score":88.1,"metric":"percent"},{"benchmark":"wildguardtest","model":"claude-opus-5.5-low","score":93.5,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"celeris-1-decision","score":37.8,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"celeris-1-decision","score":0,"metric":"percent"},{"benchmark":"hle-multichoice","model":"celeris-1-decision","score":13.3,"metric":"percent"},{"benchmark":"when2call","model":"celeris-1-decision","score":83.7,"metric":"percent"},{"benchmark":"wildguardtest","model":"celeris-1-decision","score":93.3,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"clef","score":39,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"clef","score":4.3,"metric":"percent"},{"benchmark":"hle-multichoice","model":"clef","score":11.1,"metric":"percent"},{"benchmark":"when2call","model":"clef","score":71,"metric":"percent"},{"benchmark":"wildguardtest","model":"clef","score":90.7,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"clef-flash","score":32.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"clef-flash","score":2.7,"metric":"percent"},{"benchmark":"hle-multichoice","model":"clef-flash","score":10.3,"metric":"percent"},{"benchmark":"when2call","model":"clef-flash","score":64.4,"metric":"percent"},{"benchmark":"wildguardtest","model":"clef-flash","score":90.9,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"clef-omni","score":36,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"clef-omni","score":1.6,"metric":"percent"},{"benchmark":"hle-multichoice","model":"clef-omni","score":9,"metric":"percent"},{"benchmark":"when2call","model":"clef-omni","score":62.1,"metric":"percent"},{"benchmark":"wildguardtest","model":"clef-omni","score":87.2,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gemma-4-31b-it","score":47.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gemma-4-31b-it","score":4.2,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gemma-4-31b-it","score":25.7,"metric":"percent"},{"benchmark":"when2call","model":"gemma-4-31b-it","score":77.6,"metric":"percent"},{"benchmark":"wildguardtest","model":"gemma-4-31b-it","score":92.8,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"glide","score":36.4,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"glide","score":16.4,"metric":"percent"},{"benchmark":"hle-multichoice","model":"glide","score":10.5,"metric":"percent"},{"benchmark":"when2call","model":"glide","score":83.7,"metric":"percent"},{"benchmark":"wildguardtest","model":"glide","score":95.1,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"mercury-decide","score":35,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"mercury-decide","score":32,"metric":"percent"},{"benchmark":"hle-multichoice","model":"mercury-decide","score":10.1,"metric":"percent"},{"benchmark":"when2call","model":"mercury-decide","score":79.3,"metric":"percent"},{"benchmark":"wildguardtest","model":"mercury-decide","score":88,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"d1","score":41,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"d1","score":1.7,"metric":"percent"},{"benchmark":"hle-multichoice","model":"d1","score":11.5,"metric":"percent"},{"benchmark":"when2call","model":"d1","score":77.4,"metric":"percent"},{"benchmark":"wildguardtest","model":"d1","score":90.9,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"d1-ultra","score":31.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"d1-ultra","score":84.5,"metric":"percent"},{"benchmark":"hle-multichoice","model":"d1-ultra","score":15,"metric":"percent"},{"benchmark":"when2call","model":"d1-ultra","score":92.6,"metric":"percent"},{"benchmark":"wildguardtest","model":"d1-ultra","score":95.4,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gpt-6.1-sol-max","score":91,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gpt-6.1-sol-max","score":11.1,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gpt-6.1-sol-max","score":58.9,"metric":"percent"},{"benchmark":"when2call","model":"gpt-6.1-sol-max","score":81.2,"metric":"percent"},{"benchmark":"wildguardtest","model":"gpt-6.1-sol-max","score":92.5,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gpt-6.1-sol-low","score":93,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gpt-6.1-sol-low","score":22.9,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gpt-6.1-sol-low","score":55.4,"metric":"percent"},{"benchmark":"when2call","model":"gpt-6.1-sol-low","score":80.6,"metric":"percent"},{"benchmark":"wildguardtest","model":"gpt-6.1-sol-low","score":92,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gpt-6-luna-max","score":73.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gpt-6-luna-max","score":3,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gpt-6-luna-max","score":35.3,"metric":"percent"},{"benchmark":"when2call","model":"gpt-6-luna-max","score":79,"metric":"percent"},{"benchmark":"wildguardtest","model":"gpt-6-luna-max","score":90.5,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gpt-6-luna-decisions","score":40.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gpt-6-luna-decisions","score":10.1,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gpt-6-luna-decisions","score":11.7,"metric":"percent"},{"benchmark":"when2call","model":"gpt-6-luna-decisions","score":74.1,"metric":"percent"},{"benchmark":"wildguardtest","model":"gpt-6-luna-decisions","score":82.8,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gpt-6-luna-high","score":69.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gpt-6-luna-high","score":3.3,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gpt-6-luna-high","score":32.4,"metric":"percent"},{"benchmark":"when2call","model":"gpt-6-luna-high","score":78.6,"metric":"percent"},{"benchmark":"wildguardtest","model":"gpt-6-luna-high","score":88.9,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gpt-6-luna-low","score":66,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gpt-6-luna-low","score":0,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gpt-6-luna-low","score":22.2,"metric":"percent"},{"benchmark":"when2call","model":"gpt-6-luna-low","score":77,"metric":"percent"},{"benchmark":"wildguardtest","model":"gpt-6-luna-low","score":88.5,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gpt-6-luna-medium","score":71.2,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gpt-6-luna-medium","score":0,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gpt-6-luna-medium","score":29,"metric":"percent"},{"benchmark":"when2call","model":"gpt-6-luna-medium","score":78.2,"metric":"percent"},{"benchmark":"wildguardtest","model":"gpt-6-luna-medium","score":89.8,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"gpt-6-luna","score":45.4,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"gpt-6-luna","score":0.4,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gpt-6-luna","score":12.3,"metric":"percent"},{"benchmark":"when2call","model":"gpt-6-luna","score":76.1,"metric":"percent"},{"benchmark":"wildguardtest","model":"gpt-6-luna","score":87.1,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"microsoft-decision-1","score":28.2,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"microsoft-decision-1","score":39.8,"metric":"percent"},{"benchmark":"hle-multichoice","model":"microsoft-decision-1","score":10.9,"metric":"percent"},{"benchmark":"when2call","model":"microsoft-decision-1","score":81.9,"metric":"percent"},{"benchmark":"wildguardtest","model":"microsoft-decision-1","score":88.2,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"pplx-decider-v1.1-27b","score":39.8,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"pplx-decider-v1.1-27b","score":13.3,"metric":"percent"},{"benchmark":"hle-multichoice","model":"pplx-decider-v1.1-27b","score":15.4,"metric":"percent"},{"benchmark":"when2call","model":"pplx-decider-v1.1-27b","score":76.5,"metric":"percent"},{"benchmark":"wildguardtest","model":"pplx-decider-v1.1-27b","score":93.8,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"jev-1.13","score":34.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"jev-1.13","score":35.2,"metric":"percent"},{"benchmark":"hle-multichoice","model":"jev-1.13","score":20.9,"metric":"percent"},{"benchmark":"when2call","model":"jev-1.13","score":80.7,"metric":"percent"},{"benchmark":"wildguardtest","model":"jev-1.13","score":93.6,"metric":"percent"},{"benchmark":"aa-omniscience-decision-accuracy","model":"jev-1.14","score":33.8,"metric":"percent"},{"benchmark":"aa-omniscience-decision-non-hallucination","model":"jev-1.14","score":37.2,"metric":"percent"},{"benchmark":"hle-multichoice","model":"jev-1.14","score":18.9,"metric":"percent"},{"benchmark":"when2call","model":"jev-1.14","score":80.8,"metric":"percent"},{"benchmark":"wildguardtest","model":"jev-1.14","score":93.1,"metric":"percent"},{"benchmark":"bfcl-decision","model":"clef","score":98.5,"metric":"percent"},{"benchmark":"bfcl-decision","model":"clef-flash","score":98.8,"metric":"percent"},{"benchmark":"bfcl-decision","model":"jev-1.13","score":95.8,"metric":"percent"},{"benchmark":"bfcl-decision","model":"diffusiongemma-jev","score":96.5,"metric":"percent"},{"benchmark":"bfcl-decision","model":"kev-9b","score":94.5,"metric":"percent"},{"benchmark":"bfcl-decision","model":"laya","score":38.1,"metric":"percent"},{"benchmark":"toolret-decision","model":"clef","score":69.2,"metric":"ndcg@10"},{"benchmark":"toolret-decision","model":"clef-flash","score":66.4,"metric":"ndcg@10"},{"benchmark":"toolret-decision","model":"jev-1.13","score":65.3,"metric":"ndcg@10"},{"benchmark":"toolret-decision","model":"diffusiongemma-jev","score":61.2,"metric":"ndcg@10"},{"benchmark":"toolret-decision","model":"kev-9b","score":64.3,"metric":"ndcg@10"},{"benchmark":"toolret-decision","model":"laya","score":12.8,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"clef","score":91.9,"metric":"percent"},{"benchmark":"api-bank-decision","model":"clef-flash","score":93.1,"metric":"percent"},{"benchmark":"api-bank-decision","model":"jev-1.13","score":88.2,"metric":"percent"},{"benchmark":"api-bank-decision","model":"diffusiongemma-jev","score":83.7,"metric":"percent"},{"benchmark":"api-bank-decision","model":"kev-9b","score":56.3,"metric":"percent"},{"benchmark":"api-bank-decision","model":"laya","score":11.5,"metric":"percent"},{"benchmark":"banking77","model":"clef","score":94.2,"metric":"f1"},{"benchmark":"banking77","model":"clef-flash","score":90.9,"metric":"f1"},{"benchmark":"banking77","model":"jev-1.13","score":79.7,"metric":"f1"},{"benchmark":"banking77","model":"diffusiongemma-jev","score":74.3,"metric":"f1"},{"benchmark":"banking77","model":"kev-9b","score":84.8,"metric":"f1"},{"benchmark":"banking77","model":"laya","score":14.3,"metric":"f1"},{"benchmark":"clinc150-oos","model":"clef","score":97.4,"metric":"f1"},{"benchmark":"clinc150-oos","model":"clef-flash","score":66.8,"metric":"f1"},{"benchmark":"clinc150-oos","model":"jev-1.13","score":89.3,"metric":"f1"},{"benchmark":"clinc150-oos","model":"diffusiongemma-jev","score":83.5,"metric":"f1"},{"benchmark":"clinc150-oos","model":"kev-9b","score":79,"metric":"f1"},{"benchmark":"clinc150-oos","model":"laya","score":3.2,"metric":"f1"},{"benchmark":"routerbench-decision","model":"clef","score":79.7,"metric":"score"},{"benchmark":"routerbench-decision","model":"clef-flash","score":79.9,"metric":"score"},{"benchmark":"routerbench-decision","model":"jev-1.13","score":79.9,"metric":"score"},{"benchmark":"routerbench-decision","model":"diffusiongemma-jev","score":79,"metric":"score"},{"benchmark":"routerbench-decision","model":"kev-9b","score":80,"metric":"score"},{"benchmark":"routerbench-decision","model":"laya","score":57.1,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"clef","score":83,"metric":"percent"},{"benchmark":"home-appliance-simulator-decision","model":"clef-flash","score":97.7,"metric":"percent"},{"benchmark":"home-appliance-simulator-decision","model":"jev-1.13","score":52.3,"metric":"percent"},{"benchmark":"home-appliance-simulator-decision","model":"diffusiongemma-jev","score":42,"metric":"percent"},{"benchmark":"home-appliance-simulator-decision","model":"kev-9b","score":25,"metric":"percent"},{"benchmark":"home-appliance-simulator-decision","model":"laya","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"clef","score":43.8,"metric":"f1"},{"benchmark":"sgd-x-decision","model":"clef-flash","score":34.2,"metric":"f1"},{"benchmark":"sgd-x-decision","model":"jev-1.13","score":43,"metric":"f1"},{"benchmark":"sgd-x-decision","model":"diffusiongemma-jev","score":40.6,"metric":"f1"},{"benchmark":"sgd-x-decision","model":"kev-9b","score":64,"metric":"f1"},{"benchmark":"sgd-x-decision","model":"laya","score":42.4,"metric":"f1"},{"benchmark":"contractnli","model":"clef","score":81.4,"metric":"f1"},{"benchmark":"contractnli","model":"clef-flash","score":84.3,"metric":"f1"},{"benchmark":"contractnli","model":"jev-1.13","score":71.7,"metric":"f1"},{"benchmark":"contractnli","model":"diffusiongemma-jev","score":76,"metric":"f1"},{"benchmark":"contractnli","model":"kev-9b","score":57.8,"metric":"f1"},{"benchmark":"contractnli","model":"laya","score":29,"metric":"f1"},{"benchmark":"anli","model":"clef","score":69.8,"metric":"f1"},{"benchmark":"anli","model":"clef-flash","score":59.1,"metric":"f1"},{"benchmark":"anli","model":"jev-1.13","score":74.8,"metric":"f1"},{"benchmark":"anli","model":"diffusiongemma-jev","score":66.4,"metric":"f1"},{"benchmark":"anli","model":"kev-9b","score":56.3,"metric":"f1"},{"benchmark":"anli","model":"laya","score":48.7,"metric":"f1"},{"benchmark":"bpomp-decision","model":"clef","score":96.9,"metric":"percent"},{"benchmark":"bpomp-decision","model":"clef-flash","score":95.4,"metric":"percent"},{"benchmark":"bpomp-decision","model":"jev-1.13","score":90.6,"metric":"percent"},{"benchmark":"bpomp-decision","model":"diffusiongemma-jev","score":86.9,"metric":"percent"},{"benchmark":"bpomp-decision","model":"kev-9b","score":67,"metric":"percent"},{"benchmark":"bpomp-decision","model":"laya","score":51.6,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"clef","score":66.7,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"clef-flash","score":75.1,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"jev-1.13","score":61.9,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"diffusiongemma-jev","score":63,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"kev-9b","score":55.8,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"laya","score":47.2,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"clef","score":15.8,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"clef-flash","score":1.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"jev-1.13","score":18.1,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"diffusiongemma-jev","score":2.5,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"kev-9b","score":10.8,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"laya","score":5.1,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"clef","score":66,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"clef-flash","score":65.8,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"jev-1.13","score":64.7,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"diffusiongemma-jev","score":58.2,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"kev-9b","score":56.3,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"laya","score":52.3,"metric":"percent"},{"benchmark":"mmlu","model":"clef","score":90.3,"metric":"percent"},{"benchmark":"mmlu","model":"clef-flash","score":91.8,"metric":"percent"},{"benchmark":"mmlu","model":"jev-1.13","score":91.7,"metric":"percent"},{"benchmark":"mmlu","model":"diffusiongemma-jev","score":79.3,"metric":"percent"},{"benchmark":"mmlu","model":"kev-9b","score":75.3,"metric":"percent"},{"benchmark":"mmlu","model":"laya","score":30.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"clef","score":48,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"clef-flash","score":51,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"jev-1.13","score":78.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"diffusiongemma-jev","score":44.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"kev-9b","score":38.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"laya","score":27.6,"metric":"percent"},{"benchmark":"arc-easy","model":"clef","score":99,"metric":"percent"},{"benchmark":"arc-easy","model":"clef-flash","score":99.5,"metric":"percent"},{"benchmark":"arc-easy","model":"jev-1.13","score":99.3,"metric":"percent"},{"benchmark":"arc-easy","model":"diffusiongemma-jev","score":98.2,"metric":"percent"},{"benchmark":"arc-easy","model":"kev-9b","score":97.7,"metric":"percent"},{"benchmark":"arc-easy","model":"laya","score":47,"metric":"percent"},{"benchmark":"arc-challenge","model":"clef","score":97.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"clef-flash","score":98.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"jev-1.13","score":97.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"diffusiongemma-jev","score":94.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"kev-9b","score":93.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"laya","score":28.6,"metric":"percent"},{"benchmark":"winogrande","model":"clef","score":93.5,"metric":"percent"},{"benchmark":"winogrande","model":"clef-flash","score":97.5,"metric":"percent"},{"benchmark":"winogrande","model":"jev-1.13","score":92,"metric":"percent"},{"benchmark":"winogrande","model":"diffusiongemma-jev","score":73.6,"metric":"percent"},{"benchmark":"winogrande","model":"kev-9b","score":73.2,"metric":"percent"},{"benchmark":"winogrande","model":"laya","score":50.5,"metric":"percent"},{"benchmark":"hellaswag","model":"clef","score":98.2,"metric":"percent"},{"benchmark":"hellaswag","model":"clef-flash","score":98.6,"metric":"percent"},{"benchmark":"hellaswag","model":"jev-1.13","score":94.5,"metric":"percent"},{"benchmark":"hellaswag","model":"diffusiongemma-jev","score":83.3,"metric":"percent"},{"benchmark":"hellaswag","model":"kev-9b","score":81.9,"metric":"percent"},{"benchmark":"hellaswag","model":"laya","score":33.1,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"clef","score":80.8,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"clef-flash","score":67.3,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"jev-1.13","score":79.9,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"diffusiongemma-jev","score":50.3,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"kev-9b","score":48.7,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"laya","score":21.6,"metric":"percent"},{"benchmark":"chessbench-decision","model":"clef","score":24.7,"metric":"percent"},{"benchmark":"chessbench-decision","model":"clef-flash","score":23,"metric":"percent"},{"benchmark":"chessbench-decision","model":"jev-1.13","score":17.2,"metric":"percent"},{"benchmark":"chessbench-decision","model":"diffusiongemma-jev","score":14.2,"metric":"percent"},{"benchmark":"chessbench-decision","model":"kev-9b","score":11.2,"metric":"percent"},{"benchmark":"chessbench-decision","model":"laya","score":7.7,"metric":"percent"},{"benchmark":"musr","model":"clef","score":83.5,"metric":"percent"},{"benchmark":"musr","model":"clef-flash","score":86,"metric":"percent"},{"benchmark":"musr","model":"jev-1.13","score":66.1,"metric":"percent"},{"benchmark":"musr","model":"diffusiongemma-jev","score":61.2,"metric":"percent"},{"benchmark":"musr","model":"kev-9b","score":57.9,"metric":"percent"},{"benchmark":"musr","model":"laya","score":43.2,"metric":"percent"},{"benchmark":"sata-bench","model":"clef","score":33.8,"metric":"percent"},{"benchmark":"sata-bench","model":"clef-flash","score":36.7,"metric":"percent"},{"benchmark":"sata-bench","model":"jev-1.13","score":26.4,"metric":"percent"},{"benchmark":"sata-bench","model":"diffusiongemma-jev","score":27.5,"metric":"percent"},{"benchmark":"sata-bench","model":"kev-9b","score":26.7,"metric":"percent"},{"benchmark":"sata-bench","model":"laya","score":0.3,"metric":"percent"},{"benchmark":"bright-decision","model":"clef","score":45.9,"metric":"ndcg@10"},{"benchmark":"bright-decision","model":"clef-flash","score":39.3,"metric":"ndcg@10"},{"benchmark":"bright-decision","model":"jev-1.13","score":47.5,"metric":"ndcg@10"},{"benchmark":"bright-decision","model":"diffusiongemma-jev","score":42.9,"metric":"ndcg@10"},{"benchmark":"bright-decision","model":"kev-9b","score":38.5,"metric":"ndcg@10"},{"benchmark":"bright-decision","model":"laya","score":19.9,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"clef","score":57.5,"metric":"f1"},{"benchmark":"amazon-esci","model":"clef-flash","score":57.4,"metric":"f1"},{"benchmark":"amazon-esci","model":"jev-1.13","score":55.2,"metric":"f1"},{"benchmark":"amazon-esci","model":"diffusiongemma-jev","score":53.4,"metric":"f1"},{"benchmark":"amazon-esci","model":"kev-9b","score":49.2,"metric":"f1"},{"benchmark":"amazon-esci","model":"laya","score":24.4,"metric":"f1"},{"benchmark":"acos-decision","model":"clef","score":33.3,"metric":"f1"},{"benchmark":"acos-decision","model":"clef-flash","score":25.9,"metric":"f1"},{"benchmark":"acos-decision","model":"jev-1.13","score":29.5,"metric":"f1"},{"benchmark":"acos-decision","model":"diffusiongemma-jev","score":24.5,"metric":"f1"},{"benchmark":"acos-decision","model":"kev-9b","score":18.3,"metric":"f1"},{"benchmark":"acos-decision","model":"laya","score":3.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"clef","score":96.2,"metric":"f1"},{"benchmark":"finentity-decision","model":"clef-flash","score":97.1,"metric":"f1"},{"benchmark":"finentity-decision","model":"jev-1.13","score":87,"metric":"f1"},{"benchmark":"finentity-decision","model":"diffusiongemma-jev","score":89,"metric":"f1"},{"benchmark":"finentity-decision","model":"kev-9b","score":88.4,"metric":"f1"},{"benchmark":"finentity-decision","model":"laya","score":61,"metric":"f1"},{"benchmark":"vast-stance","model":"clef","score":59.5,"metric":"f1"},{"benchmark":"vast-stance","model":"clef-flash","score":49.6,"metric":"f1"},{"benchmark":"vast-stance","model":"jev-1.13","score":64.6,"metric":"f1"},{"benchmark":"vast-stance","model":"diffusiongemma-jev","score":55.7,"metric":"f1"},{"benchmark":"vast-stance","model":"kev-9b","score":55.4,"metric":"f1"},{"benchmark":"vast-stance","model":"laya","score":40.5,"metric":"f1"},{"benchmark":"nli4ct","model":"clef","score":82.9,"metric":"f1"},{"benchmark":"nli4ct","model":"clef-flash","score":78.6,"metric":"f1"},{"benchmark":"nli4ct","model":"jev-1.13","score":84.1,"metric":"f1"},{"benchmark":"nli4ct","model":"diffusiongemma-jev","score":78.4,"metric":"f1"},{"benchmark":"nli4ct","model":"kev-9b","score":74.9,"metric":"f1"},{"benchmark":"nli4ct","model":"laya","score":47.7,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"clef","score":86.7,"metric":"percent"},{"benchmark":"cruxeval-decision","model":"clef-flash","score":86.1,"metric":"percent"},{"benchmark":"cruxeval-decision","model":"jev-1.13","score":73,"metric":"percent"},{"benchmark":"cruxeval-decision","model":"diffusiongemma-jev","score":64.7,"metric":"percent"},{"benchmark":"cruxeval-decision","model":"kev-9b","score":51.2,"metric":"percent"},{"benchmark":"cruxeval-decision","model":"laya","score":40.2,"metric":"percent"},{"benchmark":"cladder","model":"clef","score":94,"metric":"percent"},{"benchmark":"cladder","model":"clef-flash","score":97.7,"metric":"percent"},{"benchmark":"cladder","model":"jev-1.13","score":72.6,"metric":"percent"},{"benchmark":"cladder","model":"diffusiongemma-jev","score":67.8,"metric":"percent"},{"benchmark":"cladder","model":"kev-9b","score":62,"metric":"percent"},{"benchmark":"cladder","model":"laya","score":52.9,"metric":"percent"},{"benchmark":"forecastbench-decision","model":"clef","score":13.9,"metric":"brier"},{"benchmark":"forecastbench-decision","model":"clef-flash","score":10.6,"metric":"brier"},{"benchmark":"forecastbench-decision","model":"jev-1.13","score":17.4,"metric":"brier"},{"benchmark":"forecastbench-decision","model":"diffusiongemma-jev","score":29.6,"metric":"brier"},{"benchmark":"forecastbench-decision","model":"kev-9b","score":17.6,"metric":"brier"},{"benchmark":"forecastbench-decision","model":"laya","score":41.1,"metric":"brier"},{"benchmark":"habermas-machine-decision","model":"clef","score":68.7,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"clef-flash","score":71.8,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"jev-1.13","score":45.9,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"diffusiongemma-jev","score":45,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"kev-9b","score":39.4,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"laya","score":33.4,"metric":"percent"},{"benchmark":"phishnchips","model":"clef","score":79.6,"metric":"percent"},{"benchmark":"phishnchips","model":"clef-flash","score":75,"metric":"percent"},{"benchmark":"phishnchips","model":"jev-1.13","score":62.5,"metric":"percent"},{"benchmark":"phishnchips","model":"diffusiongemma-jev","score":85.4,"metric":"percent"},{"benchmark":"phishnchips","model":"kev-9b","score":50.7,"metric":"percent"},{"benchmark":"phishnchips","model":"laya","score":50.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"clef","score":65.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"clef-flash","score":65.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"jev-1.13","score":82.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"diffusiongemma-jev","score":56.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kev-9b","score":51.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"laya","score":13.6,"metric":"percent"},{"benchmark":"bbh-decision","model":"clef","score":73.7,"metric":"percent"},{"benchmark":"bbh-decision","model":"clef-flash","score":68.9,"metric":"percent"},{"benchmark":"bbh-decision","model":"jev-1.13","score":92.9,"metric":"percent"},{"benchmark":"bbh-decision","model":"diffusiongemma-jev","score":70.7,"metric":"percent"},{"benchmark":"bbh-decision","model":"kev-9b","score":65.2,"metric":"percent"},{"benchmark":"bbh-decision","model":"laya","score":34.1,"metric":"percent"},{"benchmark":"ragtruth","model":"clef","score":79.4,"metric":"f1"},{"benchmark":"ragtruth","model":"clef-flash","score":35.6,"metric":"f1"},{"benchmark":"ragtruth","model":"jev-1.13","score":76.5,"metric":"f1"},{"benchmark":"ragtruth","model":"diffusiongemma-jev","score":70.4,"metric":"f1"},{"benchmark":"ragtruth","model":"kev-9b","score":46.2,"metric":"f1"},{"benchmark":"ragtruth","model":"laya","score":48.8,"metric":"f1"},{"benchmark":"hover","model":"clef","score":65.2,"metric":"percent"},{"benchmark":"hover","model":"clef-flash","score":61.2,"metric":"percent"},{"benchmark":"hover","model":"jev-1.13","score":72.9,"metric":"percent"},{"benchmark":"hover","model":"diffusiongemma-jev","score":70.9,"metric":"percent"},{"benchmark":"hover","model":"kev-9b","score":58.8,"metric":"percent"},{"benchmark":"hover","model":"laya","score":55.8,"metric":"percent"},{"benchmark":"when2call","model":"diffusiongemma-jev","score":75.4,"metric":"percent"},{"benchmark":"when2call","model":"kev-9b","score":49.6,"metric":"percent"},{"benchmark":"when2call","model":"laya","score":11.9,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"clef","score":69.5,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"clef-flash","score":66.1,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"jev-1.13","score":70.1,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"diffusiongemma-jev","score":63.6,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"kev-9b","score":58.1,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"laya","score":27.1,"metric":"percent"},{"benchmark":"bfcl-decision","model":"clef-omni","score":98.2,"metric":"percent"},{"benchmark":"toolret-decision","model":"clef-omni","score":66.6,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"clef-omni","score":92.7,"metric":"percent"},{"benchmark":"banking77","model":"clef-omni","score":94.8,"metric":"f1"},{"benchmark":"clinc150-oos","model":"clef-omni","score":97.7,"metric":"f1"},{"benchmark":"routerbench-decision","model":"clef-omni","score":79.9,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"clef-omni","score":69.3,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"clef-omni","score":39.2,"metric":"f1"},{"benchmark":"contractnli","model":"clef-omni","score":80.3,"metric":"f1"},{"benchmark":"anli","model":"clef-omni","score":65.5,"metric":"f1"},{"benchmark":"bpomp-decision","model":"clef-omni","score":96.8,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"clef-omni","score":70.1,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"clef-omni","score":2.6,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"clef-omni","score":62.9,"metric":"percent"},{"benchmark":"mmlu","model":"clef-omni","score":92.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"clef-omni","score":47.4,"metric":"percent"},{"benchmark":"arc-easy","model":"clef-omni","score":99.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"clef-omni","score":97.8,"metric":"percent"},{"benchmark":"winogrande","model":"clef-omni","score":96.7,"metric":"percent"},{"benchmark":"hellaswag","model":"clef-omni","score":99.1,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"clef-omni","score":79,"metric":"percent"},{"benchmark":"chessbench-decision","model":"clef-omni","score":22.1,"metric":"percent"},{"benchmark":"musr","model":"clef-omni","score":83.8,"metric":"percent"},{"benchmark":"sata-bench","model":"clef-omni","score":31.9,"metric":"percent"},{"benchmark":"bright-decision","model":"clef-omni","score":42,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"clef-omni","score":57.8,"metric":"f1"},{"benchmark":"acos-decision","model":"clef-omni","score":28.4,"metric":"f1"},{"benchmark":"finentity-decision","model":"clef-omni","score":96.3,"metric":"f1"},{"benchmark":"vast-stance","model":"clef-omni","score":50.9,"metric":"f1"},{"benchmark":"nli4ct","model":"clef-omni","score":76.8,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"clef-omni","score":88.8,"metric":"percent"},{"benchmark":"cladder","model":"clef-omni","score":97.2,"metric":"percent"},{"benchmark":"forecastbench-decision","model":"clef-omni","score":11.7,"metric":"brier"},{"benchmark":"habermas-machine-decision","model":"clef-omni","score":67.8,"metric":"percent"},{"benchmark":"phishnchips","model":"clef-omni","score":73.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"clef-omni","score":70.6,"metric":"percent"},{"benchmark":"bbh-decision","model":"clef-omni","score":69,"metric":"percent"},{"benchmark":"ragtruth","model":"clef-omni","score":42,"metric":"f1"},{"benchmark":"hover","model":"clef-omni","score":64.2,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"clef-omni","score":64.2,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"jev-1.13","score":100,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"jev-1.13","score":98.61,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"jev-1.13","score":72.07,"metric":"percent"},{"benchmark":"typed-decision","model":"jev-1.13","score":73.35,"metric":"percent"},{"benchmark":"toolace","model":"jev-1.13","score":91.29,"metric":"percent"},{"benchmark":"ag-news","model":"jev-1.13","score":89.57,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"jev-1.13","score":96.29,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"laya","score":95.83,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"laya","score":72.22,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"laya","score":28.83,"metric":"percent"},{"benchmark":"typed-decision","model":"laya","score":35.95,"metric":"percent"},{"benchmark":"toolace","model":"laya","score":63.87,"metric":"percent"},{"benchmark":"ag-news","model":"laya","score":92.84,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"laya","score":14.84,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"semif","score":100,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"semif","score":98.61,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"semif","score":61.26,"metric":"percent"},{"benchmark":"typed-decision","model":"semif","score":62.8,"metric":"percent"},{"benchmark":"toolace","model":"semif","score":85.16,"metric":"percent"},{"benchmark":"ag-news","model":"semif","score":89.22,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"semif","score":92.53,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"jevk5","score":100,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"jevk5","score":97.22,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"jevk5","score":73.87,"metric":"percent"},{"benchmark":"typed-decision","model":"jevk5","score":64.5,"metric":"percent"},{"benchmark":"toolace","model":"jevk5","score":80.97,"metric":"percent"},{"benchmark":"ag-news","model":"jevk5","score":89.13,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"jevk5","score":90.45,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"intern-decision-0.8b","score":97.92,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"intern-decision-0.8b","score":80.56,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"intern-decision-0.8b","score":52.25,"metric":"percent"},{"benchmark":"typed-decision","model":"intern-decision-0.8b","score":77.35,"metric":"percent"},{"benchmark":"toolace","model":"intern-decision-0.8b","score":94.52,"metric":"percent"},{"benchmark":"ag-news","model":"intern-decision-0.8b","score":88.61,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"intern-decision-0.8b","score":64.48,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"intern-decision-2b","score":100,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"intern-decision-2b","score":84.72,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"intern-decision-2b","score":63.96,"metric":"percent"},{"benchmark":"typed-decision","model":"intern-decision-2b","score":79.35,"metric":"percent"},{"benchmark":"toolace","model":"intern-decision-2b","score":96.45,"metric":"percent"},{"benchmark":"ag-news","model":"intern-decision-2b","score":89.96,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"intern-decision-2b","score":78.33,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"intern-decision-4b","score":100,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"intern-decision-4b","score":98.61,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"intern-decision-4b","score":73.87,"metric":"percent"},{"benchmark":"typed-decision","model":"intern-decision-4b","score":80.55,"metric":"percent"},{"benchmark":"toolace","model":"intern-decision-4b","score":96.45,"metric":"percent"},{"benchmark":"ag-news","model":"intern-decision-4b","score":90.82,"metric":"percent"},{"benchmark":"wild-jailbreak","model":"intern-decision-4b","score":89.86,"metric":"percent"},{"benchmark":"winogrande","model":"pplx-decider-v1-27b","score":83.3,"metric":"percent"},{"benchmark":"financialphrasebank","model":"jev-1.13","score":76.98,"metric":"percent"},{"benchmark":"financialphrasebank","model":"pplx-decider-v1-27b","score":84.18,"metric":"percent"},{"benchmark":"ragtruth","model":"pplx-decider-v1-27b","score":88.8,"metric":"f1"},{"benchmark":"judgebench","model":"jev-1.13","score":78.57,"metric":"percent"},{"benchmark":"judgebench","model":"pplx-decider-v1-27b","score":78.29,"metric":"percent"},{"benchmark":"bbh-decision","model":"pplx-decider-v1-27b","score":82.8,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"pplx-decider-v1-27b","score":70.3,"metric":"percent"},{"benchmark":"tabfact","model":"jev-1.13","score":89.8,"metric":"percent"},{"benchmark":"tabfact","model":"pplx-decider-v1-27b","score":90.6,"metric":"percent"},{"benchmark":"contractnli","model":"pplx-decider-v1-27b","score":80.78,"metric":"f1"},{"benchmark":"circa","model":"jev-1.13","score":84.6,"metric":"percent"},{"benchmark":"circa","model":"pplx-decider-v1-27b","score":89.2,"metric":"percent"},{"benchmark":"belebele","model":"jev-1.13","score":95,"metric":"percent"},{"benchmark":"belebele","model":"pplx-decider-v1-27b","score":94,"metric":"percent"},{"benchmark":"truthfulqa-binary","model":"jev-1.13","score":92,"metric":"percent"},{"benchmark":"truthfulqa-binary","model":"pplx-decider-v1-27b","score":85.4,"metric":"percent"},{"benchmark":"squad-v2.0","model":"d1-3b","score":85.3,"metric":"percent"},{"benchmark":"squad-v2.0","model":"mapika-decider-4b","score":76,"metric":"percent"},{"benchmark":"squad-v2.0","model":"mapika-decider-2b","score":67.7,"metric":"percent"},{"benchmark":"civil-comments","model":"d1-3b","score":93,"metric":"percent"},{"benchmark":"civil-comments","model":"mapika-decider-4b","score":92.8,"metric":"percent"},{"benchmark":"civil-comments","model":"mapika-decider-2b","score":93.6,"metric":"percent"},{"benchmark":"massive-intent","model":"d1-3b","score":87.3,"metric":"percent"},{"benchmark":"massive-intent","model":"mapika-decider-4b","score":88.3,"metric":"percent"},{"benchmark":"massive-intent","model":"mapika-decider-2b","score":81.1,"metric":"percent"},{"benchmark":"helpsteer2","model":"d1-3b","score":36.7,"metric":"percent"},{"benchmark":"helpsteer2","model":"mapika-decider-4b","score":42,"metric":"percent"},{"benchmark":"helpsteer2","model":"mapika-decider-2b","score":32,"metric":"percent"},{"benchmark":"pubmedqa","model":"d1-3b","score":66,"metric":"percent"},{"benchmark":"pubmedqa","model":"mapika-decider-4b","score":63.3,"metric":"percent"},{"benchmark":"pubmedqa","model":"mapika-decider-2b","score":65.7,"metric":"percent"},{"benchmark":"boolq","model":"d1-3b","score":86.7,"metric":"percent"},{"benchmark":"boolq","model":"mapika-decider-4b","score":89,"metric":"percent"},{"benchmark":"boolq","model":"mapika-decider-2b","score":87.3,"metric":"percent"},{"benchmark":"xnli","model":"d1-3b","score":85,"metric":"percent"},{"benchmark":"xnli","model":"mapika-decider-4b","score":88.6,"metric":"percent"},{"benchmark":"xnli","model":"mapika-decider-2b","score":85,"metric":"percent"},{"benchmark":"paws-x","model":"d1-3b","score":76.9,"metric":"percent"},{"benchmark":"paws-x","model":"mapika-decider-4b","score":69.8,"metric":"percent"},{"benchmark":"paws-x","model":"mapika-decider-2b","score":59.5,"metric":"percent"},{"benchmark":"squad-v2.0","model":"d1-omni-600m","score":74,"metric":"percent"},{"benchmark":"civil-comments","model":"d1-omni-600m","score":95.8,"metric":"percent"},{"benchmark":"massive-intent","model":"d1-omni-600m","score":86.1,"metric":"percent"},{"benchmark":"pubmedqa","model":"d1-omni-600m","score":61.3,"metric":"percent"},{"benchmark":"boolq","model":"d1-omni-600m","score":77.7,"metric":"percent"},{"benchmark":"xnli","model":"d1-omni-600m","score":74.7,"metric":"percent"},{"benchmark":"paws-x","model":"d1-omni-600m","score":79.5,"metric":"percent"},{"benchmark":"ai2d","model":"d1-3b","score":79.9,"metric":"percent"},{"benchmark":"blink","model":"d1-3b","score":59.2,"metric":"percent"},{"benchmark":"cv-bench","model":"d1-3b","score":82.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"d1-3b","score":65.3,"metric":"percent"},{"benchmark":"mmstar","model":"d1-3b","score":59.9,"metric":"percent"},{"benchmark":"mmvp","model":"d1-3b","score":77,"metric":"percent"},{"benchmark":"pope","model":"d1-3b","score":88.5,"metric":"percent"},{"benchmark":"vl-rewardbench","model":"d1-3b","score":65,"metric":"percent"},{"benchmark":"jevbench","model":"h2o-lightning-4b","score":60,"metric":"percent"},{"benchmark":"jevbench","model":"jev-1.13","score":63.6,"metric":"percent"},{"benchmark":"jevbench","model":"quyet-1.0-large","score":73.4,"metric":"percent"},{"benchmark":"jevbench-public","model":"h2o-lightning-4b","score":87.9,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"h2o-lightning-4b","score":100,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"h2o-lightning-4b","score":97.2,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"h2o-lightning-4b","score":76.6,"metric":"percent"},{"benchmark":"jevbench-public","model":"h2o-lightning-4b-nemotron-nano","score":83.1,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"h2o-lightning-4b-nemotron-nano","score":100,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"h2o-lightning-4b-nemotron-nano","score":98.6,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"h2o-lightning-4b-nemotron-nano","score":65.8,"metric":"percent"},{"benchmark":"jevbench-public","model":"strands-decider-2b","score":77.9,"metric":"percent"},{"benchmark":"jevbench-public-easy","model":"strands-decider-2b","score":100,"metric":"percent"},{"benchmark":"jevbench-public-original","model":"strands-decider-2b","score":93.1,"metric":"percent"},{"benchmark":"jevbench-public-hard","model":"strands-decider-2b","score":58.6,"metric":"percent"},{"benchmark":"jevbench-public","model":"strands-decider-e2b","score":77.9,"metric":"percent"},{"benchmark":"jevbench-public","model":"strands-decider-e4b","score":81,"metric":"percent"},{"benchmark":"jevbench-public","model":"strands-decider-12b","score":86.6,"metric":"percent"},{"benchmark":"jevbench-public","model":"strands-decider-26b-a4b","score":89.6,"metric":"percent"},{"benchmark":"jevbench","model":"mercury-decide","score":65.9,"metric":"percent"},{"benchmark":"jevbench","model":"bespoke-nimble-9b-v3","score":56.5,"metric":"percent"},{"benchmark":"jevbench","model":"clef-flash","score":42.2,"metric":"percent"},{"benchmark":"jevbench","model":"autotrust-jev-27b","score":56.8,"metric":"percent"},{"benchmark":"jevbench","model":"pplx-decider-v1.1-27b","score":75.7,"metric":"percent"},{"benchmark":"jevbench","model":"vllm-sr-decision-2.0-vega-27b","score":60.4,"metric":"percent"},{"benchmark":"jevbench","model":"clef","score":59.1,"metric":"percent"},{"benchmark":"jevbench","model":"gliner2.5-decide","score":7,"metric":"percent"},{"benchmark":"jevbench","model":"gpt-6-luna-low","score":96.6,"metric":"percent"},{"benchmark":"jevbench","model":"gpt-6-luna-medium","score":96.9,"metric":"percent"},{"benchmark":"jevbench","model":"glide","score":66.1,"metric":"percent"},{"benchmark":"jevbench","model":"gpt-6-luna-decisions","score":56.9,"metric":"percent"},{"benchmark":"jevbench","model":"d1","score":62.1,"metric":"percent"},{"benchmark":"jevbench","model":"microsoft-decision-1","score":57.2,"metric":"percent"},{"benchmark":"jevbench","model":"clef-omni","score":34.5,"metric":"percent"},{"benchmark":"jevbench","model":"d1-3b","score":22.1,"metric":"percent"},{"benchmark":"jevbench","model":"d1-omni-600m","score":3.3,"metric":"percent"},{"benchmark":"jevbench","model":"celeris-1-decision","score":58.9,"metric":"percent"},{"benchmark":"jevbench","model":"vllm-sr-decision-2.0-lux-9b","score":35.8,"metric":"percent"},{"benchmark":"jevbench","model":"jev-1.14","score":59.9,"metric":"percent"},{"benchmark":"jevbench","model":"d1-ultra","score":69.7,"metric":"percent"},{"benchmark":"jevbench","model":"vllm-sr-d3","score":73.7,"metric":"percent"},{"benchmark":"bfcl-decision","model":"glide-no-thinking","score":97.8,"metric":"percent"},{"benchmark":"toolret-decision","model":"glide-no-thinking","score":68.3,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"glide-no-thinking","score":85,"metric":"percent"},{"benchmark":"banking77","model":"glide-no-thinking","score":79.6,"metric":"f1"},{"benchmark":"clinc150-oos","model":"glide-no-thinking","score":87.4,"metric":"f1"},{"benchmark":"routerbench-decision","model":"glide-no-thinking","score":79.5,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"glide-no-thinking","score":92,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"glide-no-thinking","score":67.2,"metric":"f1"},{"benchmark":"contractnli","model":"glide-no-thinking","score":78.9,"metric":"f1"},{"benchmark":"anli","model":"glide-no-thinking","score":73.3,"metric":"f1"},{"benchmark":"bpomp-decision","model":"glide-no-thinking","score":93.8,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"glide-no-thinking","score":60.8,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"glide-no-thinking","score":70.5,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"glide-no-thinking","score":65.2,"metric":"percent"},{"benchmark":"mmlu","model":"glide-no-thinking","score":85.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"glide-no-thinking","score":52,"metric":"percent"},{"benchmark":"arc-easy","model":"glide-no-thinking","score":98.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"glide-no-thinking","score":97.3,"metric":"percent"},{"benchmark":"winogrande","model":"glide-no-thinking","score":86,"metric":"percent"},{"benchmark":"hellaswag","model":"glide-no-thinking","score":95,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"glide-no-thinking","score":67.6,"metric":"percent"},{"benchmark":"chessbench-decision","model":"glide-no-thinking","score":17.3,"metric":"percent"},{"benchmark":"musr","model":"glide-no-thinking","score":65.3,"metric":"percent"},{"benchmark":"sata-bench","model":"glide-no-thinking","score":29.6,"metric":"percent"},{"benchmark":"bright-decision","model":"glide-no-thinking","score":50.1,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"glide-no-thinking","score":58.5,"metric":"f1"},{"benchmark":"acos-decision","model":"glide-no-thinking","score":24.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"glide-no-thinking","score":92.1,"metric":"f1"},{"benchmark":"isarcasmeval","model":"glide-no-thinking","score":39.5,"metric":"f1"},{"benchmark":"vast-stance","model":"glide-no-thinking","score":69.6,"metric":"f1"},{"benchmark":"nli4ct","model":"glide-no-thinking","score":84.4,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"glide-no-thinking","score":73.2,"metric":"percent"},{"benchmark":"cladder","model":"glide-no-thinking","score":77.5,"metric":"percent"},{"benchmark":"hle-multichoice","model":"glide-no-thinking","score":12.6,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"glide-no-thinking","score":41.1,"metric":"percent"},{"benchmark":"phishnchips","model":"glide-no-thinking","score":68.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glide-no-thinking","score":70.5,"metric":"percent"},{"benchmark":"bbh-decision","model":"glide-no-thinking","score":78.3,"metric":"percent"},{"benchmark":"ragtruth","model":"glide-no-thinking","score":76.5,"metric":"f1"},{"benchmark":"hover","model":"glide-no-thinking","score":73.9,"metric":"percent"},{"benchmark":"when2call","model":"glide-no-thinking","score":83.4,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"glide-no-thinking","score":71.6,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-decision-2.0-vega-27b","score":95.6,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-decision-2.0-vega-27b","score":68.2,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-decision-2.0-vega-27b","score":85.4,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-decision-2.0-vega-27b","score":88.1,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-decision-2.0-vega-27b","score":93.6,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-decision-2.0-vega-27b","score":79.6,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-decision-2.0-vega-27b","score":65.9,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-decision-2.0-vega-27b","score":58.2,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-decision-2.0-vega-27b","score":76.1,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-decision-2.0-vega-27b","score":73.7,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-decision-2.0-vega-27b","score":91.1,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-decision-2.0-vega-27b","score":62,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-decision-2.0-vega-27b","score":36.5,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-decision-2.0-vega-27b","score":63.2,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-decision-2.0-vega-27b","score":82.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-decision-2.0-vega-27b","score":42.4,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-decision-2.0-vega-27b","score":98.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-decision-2.0-vega-27b","score":96.4,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-decision-2.0-vega-27b","score":85.5,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-decision-2.0-vega-27b","score":94.1,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-decision-2.0-vega-27b","score":76.4,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-decision-2.0-vega-27b","score":17.5,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-decision-2.0-vega-27b","score":65.7,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-decision-2.0-vega-27b","score":31.7,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-decision-2.0-vega-27b","score":48.8,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-decision-2.0-vega-27b","score":56.7,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-decision-2.0-vega-27b","score":22.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-decision-2.0-vega-27b","score":79.8,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-decision-2.0-vega-27b","score":56.2,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-decision-2.0-vega-27b","score":59.9,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-decision-2.0-vega-27b","score":85.1,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-decision-2.0-vega-27b","score":82.5,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-decision-2.0-vega-27b","score":74.7,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-decision-2.0-vega-27b","score":10.2,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-decision-2.0-vega-27b","score":41.1,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-decision-2.0-vega-27b","score":61.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-decision-2.0-vega-27b","score":64.8,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-decision-2.0-vega-27b","score":80.7,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-decision-2.0-vega-27b","score":81.4,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-decision-2.0-vega-27b","score":82.6,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-decision-2.0-vega-27b","score":64.6,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-decision-2.0-vega-27b","score":73.1,"metric":"percent"},{"benchmark":"bfcl-decision","model":"autotrust-jev-27b","score":96,"metric":"percent"},{"benchmark":"toolret-decision","model":"autotrust-jev-27b","score":65.7,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"autotrust-jev-27b","score":82.9,"metric":"percent"},{"benchmark":"banking77","model":"autotrust-jev-27b","score":74.2,"metric":"f1"},{"benchmark":"clinc150-oos","model":"autotrust-jev-27b","score":84.6,"metric":"f1"},{"benchmark":"routerbench-decision","model":"autotrust-jev-27b","score":79.9,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"autotrust-jev-27b","score":52.3,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"autotrust-jev-27b","score":61.2,"metric":"f1"},{"benchmark":"contractnli","model":"autotrust-jev-27b","score":75,"metric":"f1"},{"benchmark":"anli","model":"autotrust-jev-27b","score":77.2,"metric":"f1"},{"benchmark":"bpomp-decision","model":"autotrust-jev-27b","score":92.6,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"autotrust-jev-27b","score":61.2,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"autotrust-jev-27b","score":40.3,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"autotrust-jev-27b","score":63,"metric":"percent"},{"benchmark":"mmlu","model":"autotrust-jev-27b","score":83.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"autotrust-jev-27b","score":44.9,"metric":"percent"},{"benchmark":"arc-easy","model":"autotrust-jev-27b","score":99,"metric":"percent"},{"benchmark":"arc-challenge","model":"autotrust-jev-27b","score":96.7,"metric":"percent"},{"benchmark":"winogrande","model":"autotrust-jev-27b","score":82.6,"metric":"percent"},{"benchmark":"hellaswag","model":"autotrust-jev-27b","score":92.5,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"autotrust-jev-27b","score":61.6,"metric":"percent"},{"benchmark":"chessbench-decision","model":"autotrust-jev-27b","score":16.5,"metric":"percent"},{"benchmark":"musr","model":"autotrust-jev-27b","score":62.4,"metric":"percent"},{"benchmark":"sata-bench","model":"autotrust-jev-27b","score":33.6,"metric":"percent"},{"benchmark":"bright-decision","model":"autotrust-jev-27b","score":48.4,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"autotrust-jev-27b","score":54.6,"metric":"f1"},{"benchmark":"acos-decision","model":"autotrust-jev-27b","score":19.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"autotrust-jev-27b","score":83.4,"metric":"f1"},{"benchmark":"isarcasmeval","model":"autotrust-jev-27b","score":42,"metric":"f1"},{"benchmark":"vast-stance","model":"autotrust-jev-27b","score":54.8,"metric":"f1"},{"benchmark":"nli4ct","model":"autotrust-jev-27b","score":84.3,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"autotrust-jev-27b","score":73.7,"metric":"percent"},{"benchmark":"cladder","model":"autotrust-jev-27b","score":70.5,"metric":"percent"},{"benchmark":"hle-multichoice","model":"autotrust-jev-27b","score":7,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"autotrust-jev-27b","score":40.4,"metric":"percent"},{"benchmark":"phishnchips","model":"autotrust-jev-27b","score":61.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"autotrust-jev-27b","score":61.5,"metric":"percent"},{"benchmark":"bbh-decision","model":"autotrust-jev-27b","score":78.9,"metric":"percent"},{"benchmark":"ragtruth","model":"autotrust-jev-27b","score":80.9,"metric":"f1"},{"benchmark":"hover","model":"autotrust-jev-27b","score":73.9,"metric":"percent"},{"benchmark":"when2call","model":"autotrust-jev-27b","score":78.5,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"autotrust-jev-27b","score":68.6,"metric":"percent"},{"benchmark":"bfcl-decision","model":"autotrust-gev-26b-decide","score":94.6,"metric":"percent"},{"benchmark":"toolret-decision","model":"autotrust-gev-26b-decide","score":67.1,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"autotrust-gev-26b-decide","score":84.2,"metric":"percent"},{"benchmark":"banking77","model":"autotrust-gev-26b-decide","score":88,"metric":"f1"},{"benchmark":"clinc150-oos","model":"autotrust-gev-26b-decide","score":93,"metric":"f1"},{"benchmark":"routerbench-decision","model":"autotrust-gev-26b-decide","score":79.9,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"autotrust-gev-26b-decide","score":21.6,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"autotrust-gev-26b-decide","score":32,"metric":"f1"},{"benchmark":"contractnli","model":"autotrust-gev-26b-decide","score":83.1,"metric":"f1"},{"benchmark":"anli","model":"autotrust-gev-26b-decide","score":70.3,"metric":"f1"},{"benchmark":"bpomp-decision","model":"autotrust-gev-26b-decide","score":90.3,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"autotrust-gev-26b-decide","score":63,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"autotrust-gev-26b-decide","score":19.7,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"autotrust-gev-26b-decide","score":63.2,"metric":"percent"},{"benchmark":"mmlu","model":"autotrust-gev-26b-decide","score":83.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"autotrust-gev-26b-decide","score":43.9,"metric":"percent"},{"benchmark":"arc-easy","model":"autotrust-gev-26b-decide","score":98.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"autotrust-gev-26b-decide","score":96.6,"metric":"percent"},{"benchmark":"winogrande","model":"autotrust-gev-26b-decide","score":91,"metric":"percent"},{"benchmark":"hellaswag","model":"autotrust-gev-26b-decide","score":96.4,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"autotrust-gev-26b-decide","score":65,"metric":"percent"},{"benchmark":"chessbench-decision","model":"autotrust-gev-26b-decide","score":24,"metric":"percent"},{"benchmark":"musr","model":"autotrust-gev-26b-decide","score":66.1,"metric":"percent"},{"benchmark":"sata-bench","model":"autotrust-gev-26b-decide","score":34.4,"metric":"percent"},{"benchmark":"bright-decision","model":"autotrust-gev-26b-decide","score":46,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"autotrust-gev-26b-decide","score":60.8,"metric":"f1"},{"benchmark":"acos-decision","model":"autotrust-gev-26b-decide","score":24.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"autotrust-gev-26b-decide","score":88.9,"metric":"f1"},{"benchmark":"isarcasmeval","model":"autotrust-gev-26b-decide","score":60.3,"metric":"f1"},{"benchmark":"vast-stance","model":"autotrust-gev-26b-decide","score":60.9,"metric":"f1"},{"benchmark":"nli4ct","model":"autotrust-gev-26b-decide","score":77.3,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"autotrust-gev-26b-decide","score":67.2,"metric":"percent"},{"benchmark":"cladder","model":"autotrust-gev-26b-decide","score":71.6,"metric":"percent"},{"benchmark":"hle-multichoice","model":"autotrust-gev-26b-decide","score":8.6,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"autotrust-gev-26b-decide","score":60.8,"metric":"percent"},{"benchmark":"phishnchips","model":"autotrust-gev-26b-decide","score":78.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"autotrust-gev-26b-decide","score":65.2,"metric":"percent"},{"benchmark":"bbh-decision","model":"autotrust-gev-26b-decide","score":75.2,"metric":"percent"},{"benchmark":"ragtruth","model":"autotrust-gev-26b-decide","score":84.1,"metric":"f1"},{"benchmark":"hover","model":"autotrust-gev-26b-decide","score":87.9,"metric":"percent"},{"benchmark":"when2call","model":"autotrust-gev-26b-decide","score":85.7,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"autotrust-gev-26b-decide","score":82,"metric":"percent"},{"benchmark":"isarcasmeval","model":"clef","score":46.4,"metric":"f1"},{"benchmark":"bfcl-decision","model":"vllm-sr-decision-2.0-lux-9b","score":94,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-decision-2.0-lux-9b","score":66.5,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-decision-2.0-lux-9b","score":71.3,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-decision-2.0-lux-9b","score":84,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-decision-2.0-lux-9b","score":89.9,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-decision-2.0-lux-9b","score":78.7,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-decision-2.0-lux-9b","score":27.3,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-decision-2.0-lux-9b","score":64.2,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-decision-2.0-lux-9b","score":76.1,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-decision-2.0-lux-9b","score":64.6,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-decision-2.0-lux-9b","score":80.8,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-decision-2.0-lux-9b","score":61.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-decision-2.0-lux-9b","score":22.9,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-decision-2.0-lux-9b","score":62.7,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-decision-2.0-lux-9b","score":75.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-decision-2.0-lux-9b","score":40.8,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-decision-2.0-lux-9b","score":98.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-decision-2.0-lux-9b","score":94.4,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-decision-2.0-lux-9b","score":87.5,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-decision-2.0-lux-9b","score":88.5,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-decision-2.0-lux-9b","score":59.4,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-decision-2.0-lux-9b","score":12.4,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-decision-2.0-lux-9b","score":56.8,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-decision-2.0-lux-9b","score":32.6,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-decision-2.0-lux-9b","score":44.4,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-decision-2.0-lux-9b","score":44.6,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-decision-2.0-lux-9b","score":11.4,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-decision-2.0-lux-9b","score":82.7,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-decision-2.0-lux-9b","score":43.1,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-decision-2.0-lux-9b","score":44.7,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-decision-2.0-lux-9b","score":81.7,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-decision-2.0-lux-9b","score":59,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-decision-2.0-lux-9b","score":66.4,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-decision-2.0-lux-9b","score":7.6,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-decision-2.0-lux-9b","score":39.4,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-decision-2.0-lux-9b","score":59.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-decision-2.0-lux-9b","score":52.3,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-decision-2.0-lux-9b","score":70.2,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-decision-2.0-lux-9b","score":64.1,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-decision-2.0-lux-9b","score":82.2,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-decision-2.0-lux-9b","score":56.9,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-decision-2.0-lux-9b","score":65.1,"metric":"percent"},{"benchmark":"bfcl-decision","model":"bespoke-nimble-9b-v3","score":97.5,"metric":"percent"},{"benchmark":"toolret-decision","model":"bespoke-nimble-9b-v3","score":68.5,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"bespoke-nimble-9b-v3","score":79.1,"metric":"percent"},{"benchmark":"banking77","model":"bespoke-nimble-9b-v3","score":83.7,"metric":"f1"},{"benchmark":"clinc150-oos","model":"bespoke-nimble-9b-v3","score":88.3,"metric":"f1"},{"benchmark":"routerbench-decision","model":"bespoke-nimble-9b-v3","score":76.5,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"bespoke-nimble-9b-v3","score":98.9,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"bespoke-nimble-9b-v3","score":71.8,"metric":"f1"},{"benchmark":"contractnli","model":"bespoke-nimble-9b-v3","score":74.1,"metric":"f1"},{"benchmark":"anli","model":"bespoke-nimble-9b-v3","score":70.3,"metric":"f1"},{"benchmark":"bpomp-decision","model":"bespoke-nimble-9b-v3","score":90.5,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"bespoke-nimble-9b-v3","score":61.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"bespoke-nimble-9b-v3","score":74.6,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"bespoke-nimble-9b-v3","score":64,"metric":"percent"},{"benchmark":"mmlu","model":"bespoke-nimble-9b-v3","score":79.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"bespoke-nimble-9b-v3","score":46.4,"metric":"percent"},{"benchmark":"arc-easy","model":"bespoke-nimble-9b-v3","score":98.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"bespoke-nimble-9b-v3","score":95.6,"metric":"percent"},{"benchmark":"winogrande","model":"bespoke-nimble-9b-v3","score":86.4,"metric":"percent"},{"benchmark":"hellaswag","model":"bespoke-nimble-9b-v3","score":88.8,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"bespoke-nimble-9b-v3","score":59,"metric":"percent"},{"benchmark":"chessbench-decision","model":"bespoke-nimble-9b-v3","score":14.4,"metric":"percent"},{"benchmark":"musr","model":"bespoke-nimble-9b-v3","score":58.8,"metric":"percent"},{"benchmark":"sata-bench","model":"bespoke-nimble-9b-v3","score":25.6,"metric":"percent"},{"benchmark":"bright-decision","model":"bespoke-nimble-9b-v3","score":38.8,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"bespoke-nimble-9b-v3","score":58.3,"metric":"f1"},{"benchmark":"acos-decision","model":"bespoke-nimble-9b-v3","score":39,"metric":"f1"},{"benchmark":"finentity-decision","model":"bespoke-nimble-9b-v3","score":90.4,"metric":"f1"},{"benchmark":"isarcasmeval","model":"bespoke-nimble-9b-v3","score":53.5,"metric":"f1"},{"benchmark":"vast-stance","model":"bespoke-nimble-9b-v3","score":73.1,"metric":"f1"},{"benchmark":"nli4ct","model":"bespoke-nimble-9b-v3","score":82.4,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"bespoke-nimble-9b-v3","score":64.7,"metric":"percent"},{"benchmark":"cladder","model":"bespoke-nimble-9b-v3","score":75,"metric":"percent"},{"benchmark":"hle-multichoice","model":"bespoke-nimble-9b-v3","score":11.4,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"bespoke-nimble-9b-v3","score":36.2,"metric":"percent"},{"benchmark":"phishnchips","model":"bespoke-nimble-9b-v3","score":53.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"bespoke-nimble-9b-v3","score":60.1,"metric":"percent"},{"benchmark":"bbh-decision","model":"bespoke-nimble-9b-v3","score":84.5,"metric":"percent"},{"benchmark":"ragtruth","model":"bespoke-nimble-9b-v3","score":76.2,"metric":"f1"},{"benchmark":"hover","model":"bespoke-nimble-9b-v3","score":84.9,"metric":"percent"},{"benchmark":"when2call","model":"bespoke-nimble-9b-v3","score":86.8,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"bespoke-nimble-9b-v3","score":61.6,"metric":"percent"},{"benchmark":"bfcl-decision","model":"autotrust-jev-9b","score":92.6,"metric":"percent"},{"benchmark":"toolret-decision","model":"autotrust-jev-9b","score":62.7,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"autotrust-jev-9b","score":62.4,"metric":"percent"},{"benchmark":"banking77","model":"autotrust-jev-9b","score":72,"metric":"f1"},{"benchmark":"clinc150-oos","model":"autotrust-jev-9b","score":79,"metric":"f1"},{"benchmark":"routerbench-decision","model":"autotrust-jev-9b","score":79.7,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"autotrust-jev-9b","score":26.1,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"autotrust-jev-9b","score":62.6,"metric":"f1"},{"benchmark":"contractnli","model":"autotrust-jev-9b","score":70.7,"metric":"f1"},{"benchmark":"anli","model":"autotrust-jev-9b","score":67.6,"metric":"f1"},{"benchmark":"bpomp-decision","model":"autotrust-jev-9b","score":85.1,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"autotrust-jev-9b","score":60.5,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"autotrust-jev-9b","score":20.5,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"autotrust-jev-9b","score":61.6,"metric":"percent"},{"benchmark":"mmlu","model":"autotrust-jev-9b","score":76.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"autotrust-jev-9b","score":39.3,"metric":"percent"},{"benchmark":"arc-easy","model":"autotrust-jev-9b","score":98.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"autotrust-jev-9b","score":94.3,"metric":"percent"},{"benchmark":"winogrande","model":"autotrust-jev-9b","score":74.4,"metric":"percent"},{"benchmark":"hellaswag","model":"autotrust-jev-9b","score":84.8,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"autotrust-jev-9b","score":48.9,"metric":"percent"},{"benchmark":"chessbench-decision","model":"autotrust-jev-9b","score":12.5,"metric":"percent"},{"benchmark":"musr","model":"autotrust-jev-9b","score":60.2,"metric":"percent"},{"benchmark":"sata-bench","model":"autotrust-jev-9b","score":33.6,"metric":"percent"},{"benchmark":"bright-decision","model":"autotrust-jev-9b","score":44.2,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"autotrust-jev-9b","score":46.2,"metric":"f1"},{"benchmark":"acos-decision","model":"autotrust-jev-9b","score":18,"metric":"f1"},{"benchmark":"finentity-decision","model":"autotrust-jev-9b","score":76.2,"metric":"f1"},{"benchmark":"isarcasmeval","model":"autotrust-jev-9b","score":34.6,"metric":"f1"},{"benchmark":"vast-stance","model":"autotrust-jev-9b","score":42.3,"metric":"f1"},{"benchmark":"nli4ct","model":"autotrust-jev-9b","score":79.7,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"autotrust-jev-9b","score":51.2,"metric":"percent"},{"benchmark":"cladder","model":"autotrust-jev-9b","score":65.6,"metric":"percent"},{"benchmark":"hle-multichoice","model":"autotrust-jev-9b","score":7,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"autotrust-jev-9b","score":43.3,"metric":"percent"},{"benchmark":"phishnchips","model":"autotrust-jev-9b","score":60,"metric":"percent"},{"benchmark":"mmlu-pro","model":"autotrust-jev-9b","score":53.3,"metric":"percent"},{"benchmark":"bbh-decision","model":"autotrust-jev-9b","score":67.3,"metric":"percent"},{"benchmark":"ragtruth","model":"autotrust-jev-9b","score":66.2,"metric":"f1"},{"benchmark":"hover","model":"autotrust-jev-9b","score":64.7,"metric":"percent"},{"benchmark":"when2call","model":"autotrust-jev-9b","score":77.5,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"autotrust-jev-9b","score":60.4,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-decision-2.0-nox-4b","score":90.8,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-decision-2.0-nox-4b","score":65.6,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-decision-2.0-nox-4b","score":77.6,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-decision-2.0-nox-4b","score":78.5,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-decision-2.0-nox-4b","score":87.6,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-decision-2.0-nox-4b","score":77.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-decision-2.0-nox-4b","score":18.2,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-decision-2.0-nox-4b","score":61.5,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-decision-2.0-nox-4b","score":75.1,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-decision-2.0-nox-4b","score":59.8,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-decision-2.0-nox-4b","score":73.4,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-decision-2.0-nox-4b","score":60.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-decision-2.0-nox-4b","score":8.6,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-decision-2.0-nox-4b","score":58.5,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-decision-2.0-nox-4b","score":71.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-decision-2.0-nox-4b","score":32.6,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-decision-2.0-nox-4b","score":98,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-decision-2.0-nox-4b","score":92.1,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-decision-2.0-nox-4b","score":83,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-decision-2.0-nox-4b","score":81.4,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-decision-2.0-nox-4b","score":58.1,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-decision-2.0-nox-4b","score":10.7,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-decision-2.0-nox-4b","score":56.6,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-decision-2.0-nox-4b","score":28.9,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-decision-2.0-nox-4b","score":43.2,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-decision-2.0-nox-4b","score":46.1,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-decision-2.0-nox-4b","score":8.7,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-decision-2.0-nox-4b","score":88.9,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-decision-2.0-nox-4b","score":39.7,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-decision-2.0-nox-4b","score":52.2,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-decision-2.0-nox-4b","score":79.6,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-decision-2.0-nox-4b","score":53.3,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-decision-2.0-nox-4b","score":66.5,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-decision-2.0-nox-4b","score":9.4,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-decision-2.0-nox-4b","score":42.5,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-decision-2.0-nox-4b","score":55.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-decision-2.0-nox-4b","score":50.5,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-decision-2.0-nox-4b","score":66.3,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-decision-2.0-nox-4b","score":68,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-decision-2.0-nox-4b","score":80.2,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-decision-2.0-nox-4b","score":61.5,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-decision-2.0-nox-4b","score":59.3,"metric":"percent"},{"benchmark":"bfcl-decision","model":"bespoke-nimble-9b-v2","score":91.6,"metric":"percent"},{"benchmark":"toolret-decision","model":"bespoke-nimble-9b-v2","score":58,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"bespoke-nimble-9b-v2","score":80.5,"metric":"percent"},{"benchmark":"banking77","model":"bespoke-nimble-9b-v2","score":69.4,"metric":"f1"},{"benchmark":"clinc150-oos","model":"bespoke-nimble-9b-v2","score":30.8,"metric":"f1"},{"benchmark":"routerbench-decision","model":"bespoke-nimble-9b-v2","score":78.3,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"bespoke-nimble-9b-v2","score":2.3,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"bespoke-nimble-9b-v2","score":59.9,"metric":"f1"},{"benchmark":"contractnli","model":"bespoke-nimble-9b-v2","score":70.3,"metric":"f1"},{"benchmark":"anli","model":"bespoke-nimble-9b-v2","score":68.2,"metric":"f1"},{"benchmark":"bpomp-decision","model":"bespoke-nimble-9b-v2","score":86.7,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"bespoke-nimble-9b-v2","score":57.5,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"bespoke-nimble-9b-v2","score":14.6,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"bespoke-nimble-9b-v2","score":54.3,"metric":"percent"},{"benchmark":"mmlu","model":"bespoke-nimble-9b-v2","score":77.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"bespoke-nimble-9b-v2","score":43.9,"metric":"percent"},{"benchmark":"arc-easy","model":"bespoke-nimble-9b-v2","score":98.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"bespoke-nimble-9b-v2","score":94.1,"metric":"percent"},{"benchmark":"winogrande","model":"bespoke-nimble-9b-v2","score":75.6,"metric":"percent"},{"benchmark":"hellaswag","model":"bespoke-nimble-9b-v2","score":85,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"bespoke-nimble-9b-v2","score":43.3,"metric":"percent"},{"benchmark":"chessbench-decision","model":"bespoke-nimble-9b-v2","score":13.6,"metric":"percent"},{"benchmark":"musr","model":"bespoke-nimble-9b-v2","score":56.4,"metric":"percent"},{"benchmark":"sata-bench","model":"bespoke-nimble-9b-v2","score":23.5,"metric":"percent"},{"benchmark":"bright-decision","model":"bespoke-nimble-9b-v2","score":28.1,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"bespoke-nimble-9b-v2","score":45.5,"metric":"f1"},{"benchmark":"acos-decision","model":"bespoke-nimble-9b-v2","score":23.1,"metric":"f1"},{"benchmark":"finentity-decision","model":"bespoke-nimble-9b-v2","score":65.5,"metric":"f1"},{"benchmark":"isarcasmeval","model":"bespoke-nimble-9b-v2","score":53.7,"metric":"f1"},{"benchmark":"vast-stance","model":"bespoke-nimble-9b-v2","score":39.1,"metric":"f1"},{"benchmark":"nli4ct","model":"bespoke-nimble-9b-v2","score":76.3,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"bespoke-nimble-9b-v2","score":56.3,"metric":"percent"},{"benchmark":"cladder","model":"bespoke-nimble-9b-v2","score":66.9,"metric":"percent"},{"benchmark":"hle-multichoice","model":"bespoke-nimble-9b-v2","score":8.6,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"bespoke-nimble-9b-v2","score":40.4,"metric":"percent"},{"benchmark":"phishnchips","model":"bespoke-nimble-9b-v2","score":65.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"bespoke-nimble-9b-v2","score":51.7,"metric":"percent"},{"benchmark":"bbh-decision","model":"bespoke-nimble-9b-v2","score":67.4,"metric":"percent"},{"benchmark":"ragtruth","model":"bespoke-nimble-9b-v2","score":65.1,"metric":"f1"},{"benchmark":"hover","model":"bespoke-nimble-9b-v2","score":62.9,"metric":"percent"},{"benchmark":"when2call","model":"bespoke-nimble-9b-v2","score":72.7,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"bespoke-nimble-9b-v2","score":55.7,"metric":"percent"},{"benchmark":"bfcl-decision","model":"intern-decision-4b","score":92.7,"metric":"percent"},{"benchmark":"toolret-decision","model":"intern-decision-4b","score":52.8,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"intern-decision-4b","score":76,"metric":"percent"},{"benchmark":"banking77","model":"intern-decision-4b","score":62.6,"metric":"f1"},{"benchmark":"clinc150-oos","model":"intern-decision-4b","score":72.7,"metric":"f1"},{"benchmark":"routerbench-decision","model":"intern-decision-4b","score":79.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"intern-decision-4b","score":12.5,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"intern-decision-4b","score":66.5,"metric":"f1"},{"benchmark":"contractnli","model":"intern-decision-4b","score":62,"metric":"f1"},{"benchmark":"anli","model":"intern-decision-4b","score":58.4,"metric":"f1"},{"benchmark":"bpomp-decision","model":"intern-decision-4b","score":81.8,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"intern-decision-4b","score":58.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"intern-decision-4b","score":7,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"intern-decision-4b","score":58.5,"metric":"percent"},{"benchmark":"mmlu","model":"intern-decision-4b","score":71.4,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"intern-decision-4b","score":41.3,"metric":"percent"},{"benchmark":"arc-easy","model":"intern-decision-4b","score":96.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"intern-decision-4b","score":91.4,"metric":"percent"},{"benchmark":"winogrande","model":"intern-decision-4b","score":68.3,"metric":"percent"},{"benchmark":"hellaswag","model":"intern-decision-4b","score":77.5,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"intern-decision-4b","score":25.6,"metric":"percent"},{"benchmark":"chessbench-decision","model":"intern-decision-4b","score":12.6,"metric":"percent"},{"benchmark":"musr","model":"intern-decision-4b","score":53.7,"metric":"percent"},{"benchmark":"sata-bench","model":"intern-decision-4b","score":30.8,"metric":"percent"},{"benchmark":"bright-decision","model":"intern-decision-4b","score":33.1,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"intern-decision-4b","score":45.3,"metric":"f1"},{"benchmark":"acos-decision","model":"intern-decision-4b","score":15.9,"metric":"f1"},{"benchmark":"finentity-decision","model":"intern-decision-4b","score":80.9,"metric":"f1"},{"benchmark":"isarcasmeval","model":"intern-decision-4b","score":46.4,"metric":"f1"},{"benchmark":"vast-stance","model":"intern-decision-4b","score":40.7,"metric":"f1"},{"benchmark":"nli4ct","model":"intern-decision-4b","score":77.8,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"intern-decision-4b","score":45.1,"metric":"percent"},{"benchmark":"cladder","model":"intern-decision-4b","score":60,"metric":"percent"},{"benchmark":"hle-multichoice","model":"intern-decision-4b","score":12.8,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"intern-decision-4b","score":45.1,"metric":"percent"},{"benchmark":"phishnchips","model":"intern-decision-4b","score":61.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-decision-4b","score":46.1,"metric":"percent"},{"benchmark":"bbh-decision","model":"intern-decision-4b","score":62.1,"metric":"percent"},{"benchmark":"ragtruth","model":"intern-decision-4b","score":71.9,"metric":"f1"},{"benchmark":"hover","model":"intern-decision-4b","score":60.5,"metric":"percent"},{"benchmark":"when2call","model":"intern-decision-4b","score":57.8,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"intern-decision-4b","score":58.5,"metric":"percent"},{"benchmark":"isarcasmeval","model":"clef-flash","score":19.7,"metric":"f1"},{"benchmark":"bfcl-decision","model":"tev1-4b-experimental","score":90.2,"metric":"percent"},{"benchmark":"toolret-decision","model":"tev1-4b-experimental","score":65,"metric":"ndcg@10"},{"benchmark":"routerbench-decision","model":"tev1-4b-experimental","score":67.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"tev1-4b-experimental","score":14.8,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"tev1-4b-experimental","score":40.7,"metric":"f1"},{"benchmark":"contractnli","model":"tev1-4b-experimental","score":67.7,"metric":"f1"},{"benchmark":"anli","model":"tev1-4b-experimental","score":56.4,"metric":"f1"},{"benchmark":"bpomp-decision","model":"tev1-4b-experimental","score":76.6,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"tev1-4b-experimental","score":58.3,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"tev1-4b-experimental","score":58.4,"metric":"percent"},{"benchmark":"mmlu","model":"tev1-4b-experimental","score":72.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"tev1-4b-experimental","score":42.4,"metric":"percent"},{"benchmark":"arc-easy","model":"tev1-4b-experimental","score":97.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"tev1-4b-experimental","score":92.2,"metric":"percent"},{"benchmark":"winogrande","model":"tev1-4b-experimental","score":69.6,"metric":"percent"},{"benchmark":"hellaswag","model":"tev1-4b-experimental","score":81.9,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"tev1-4b-experimental","score":29.5,"metric":"percent"},{"benchmark":"chessbench-decision","model":"tev1-4b-experimental","score":22,"metric":"percent"},{"benchmark":"musr","model":"tev1-4b-experimental","score":58,"metric":"percent"},{"benchmark":"sata-bench","model":"tev1-4b-experimental","score":20.3,"metric":"percent"},{"benchmark":"bright-decision","model":"tev1-4b-experimental","score":43,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"tev1-4b-experimental","score":44.2,"metric":"f1"},{"benchmark":"acos-decision","model":"tev1-4b-experimental","score":10.3,"metric":"f1"},{"benchmark":"finentity-decision","model":"tev1-4b-experimental","score":86.3,"metric":"f1"},{"benchmark":"isarcasmeval","model":"tev1-4b-experimental","score":35.9,"metric":"f1"},{"benchmark":"vast-stance","model":"tev1-4b-experimental","score":47.7,"metric":"f1"},{"benchmark":"nli4ct","model":"tev1-4b-experimental","score":77.3,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"tev1-4b-experimental","score":50.2,"metric":"percent"},{"benchmark":"cladder","model":"tev1-4b-experimental","score":63.1,"metric":"percent"},{"benchmark":"hle-multichoice","model":"tev1-4b-experimental","score":11.7,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"tev1-4b-experimental","score":41.6,"metric":"percent"},{"benchmark":"phishnchips","model":"tev1-4b-experimental","score":50.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"tev1-4b-experimental","score":45.4,"metric":"percent"},{"benchmark":"bbh-decision","model":"tev1-4b-experimental","score":63.5,"metric":"percent"},{"benchmark":"ragtruth","model":"tev1-4b-experimental","score":50.3,"metric":"f1"},{"benchmark":"hover","model":"tev1-4b-experimental","score":64.1,"metric":"percent"},{"benchmark":"when2call","model":"tev1-4b-experimental","score":60.5,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"tev1-4b-experimental","score":55.5,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-decision-2.0-sol-2b","score":82.2,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-decision-2.0-sol-2b","score":62,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-decision-2.0-sol-2b","score":67.9,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-decision-2.0-sol-2b","score":78.3,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-decision-2.0-sol-2b","score":78.6,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-decision-2.0-sol-2b","score":73.4,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-decision-2.0-sol-2b","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-decision-2.0-sol-2b","score":62,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-decision-2.0-sol-2b","score":60.5,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-decision-2.0-sol-2b","score":44.4,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-decision-2.0-sol-2b","score":61.3,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-decision-2.0-sol-2b","score":55.3,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-decision-2.0-sol-2b","score":1.4,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-decision-2.0-sol-2b","score":56.7,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-decision-2.0-sol-2b","score":50.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-decision-2.0-sol-2b","score":31.6,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-decision-2.0-sol-2b","score":91.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-decision-2.0-sol-2b","score":74,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-decision-2.0-sol-2b","score":70.1,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-decision-2.0-sol-2b","score":63.3,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-decision-2.0-sol-2b","score":36.5,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-decision-2.0-sol-2b","score":6.7,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-decision-2.0-sol-2b","score":56.1,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-decision-2.0-sol-2b","score":13,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-decision-2.0-sol-2b","score":39.2,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-decision-2.0-sol-2b","score":33.8,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-decision-2.0-sol-2b","score":10.1,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-decision-2.0-sol-2b","score":61,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-decision-2.0-sol-2b","score":23.4,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-decision-2.0-sol-2b","score":45,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-decision-2.0-sol-2b","score":68.5,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-decision-2.0-sol-2b","score":37.4,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-decision-2.0-sol-2b","score":59,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-decision-2.0-sol-2b","score":11.4,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-decision-2.0-sol-2b","score":38.1,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-decision-2.0-sol-2b","score":50.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-decision-2.0-sol-2b","score":25.2,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-decision-2.0-sol-2b","score":49.6,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-decision-2.0-sol-2b","score":10.2,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-decision-2.0-sol-2b","score":78.4,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-decision-2.0-sol-2b","score":51.7,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-decision-2.0-sol-2b","score":46.6,"metric":"percent"},{"benchmark":"bfcl-decision","model":"intern-decision-2b","score":71,"metric":"percent"},{"benchmark":"toolret-decision","model":"intern-decision-2b","score":49,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"intern-decision-2b","score":28.5,"metric":"percent"},{"benchmark":"banking77","model":"intern-decision-2b","score":12.9,"metric":"f1"},{"benchmark":"clinc150-oos","model":"intern-decision-2b","score":4.3,"metric":"f1"},{"benchmark":"routerbench-decision","model":"intern-decision-2b","score":79.3,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"intern-decision-2b","score":1.1,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"intern-decision-2b","score":59.3,"metric":"f1"},{"benchmark":"contractnli","model":"intern-decision-2b","score":44.8,"metric":"f1"},{"benchmark":"anli","model":"intern-decision-2b","score":46.9,"metric":"f1"},{"benchmark":"bpomp-decision","model":"intern-decision-2b","score":58.9,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"intern-decision-2b","score":57.8,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"intern-decision-2b","score":0.9,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"intern-decision-2b","score":55.8,"metric":"percent"},{"benchmark":"mmlu","model":"intern-decision-2b","score":57.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"intern-decision-2b","score":34.2,"metric":"percent"},{"benchmark":"arc-easy","model":"intern-decision-2b","score":90.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"intern-decision-2b","score":78.2,"metric":"percent"},{"benchmark":"winogrande","model":"intern-decision-2b","score":57.5,"metric":"percent"},{"benchmark":"hellaswag","model":"intern-decision-2b","score":60.4,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"intern-decision-2b","score":22,"metric":"percent"},{"benchmark":"chessbench-decision","model":"intern-decision-2b","score":10.6,"metric":"percent"},{"benchmark":"musr","model":"intern-decision-2b","score":54.4,"metric":"percent"},{"benchmark":"sata-bench","model":"intern-decision-2b","score":11.2,"metric":"percent"},{"benchmark":"bright-decision","model":"intern-decision-2b","score":21.4,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"intern-decision-2b","score":34.6,"metric":"f1"},{"benchmark":"acos-decision","model":"intern-decision-2b","score":4,"metric":"f1"},{"benchmark":"finentity-decision","model":"intern-decision-2b","score":63.2,"metric":"f1"},{"benchmark":"isarcasmeval","model":"intern-decision-2b","score":28.7,"metric":"f1"},{"benchmark":"vast-stance","model":"intern-decision-2b","score":39.3,"metric":"f1"},{"benchmark":"nli4ct","model":"intern-decision-2b","score":66.3,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"intern-decision-2b","score":33.9,"metric":"percent"},{"benchmark":"cladder","model":"intern-decision-2b","score":53.8,"metric":"percent"},{"benchmark":"hle-multichoice","model":"intern-decision-2b","score":12.8,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"intern-decision-2b","score":45.7,"metric":"percent"},{"benchmark":"phishnchips","model":"intern-decision-2b","score":70,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-decision-2b","score":33,"metric":"percent"},{"benchmark":"bbh-decision","model":"intern-decision-2b","score":47.3,"metric":"percent"},{"benchmark":"ragtruth","model":"intern-decision-2b","score":29.7,"metric":"f1"},{"benchmark":"hover","model":"intern-decision-2b","score":56.8,"metric":"percent"},{"benchmark":"when2call","model":"intern-decision-2b","score":49.1,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"intern-decision-2b","score":40.3,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":41.6,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":61.8,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":38.8,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-decision-2.0-kai-0.6b","score":71.6,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-decision-2.0-kai-0.6b","score":65.2,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":71.2,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":59,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-decision-2.0-kai-0.6b","score":31,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-decision-2.0-kai-0.6b","score":30.5,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":49.2,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":49.5,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":2.3,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":51.7,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-decision-2.0-kai-0.6b","score":41,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-decision-2.0-kai-0.6b","score":25.5,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-decision-2.0-kai-0.6b","score":78.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-decision-2.0-kai-0.6b","score":53.2,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-decision-2.0-kai-0.6b","score":57.5,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-decision-2.0-kai-0.6b","score":44.5,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":25.2,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":7.1,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-decision-2.0-kai-0.6b","score":44.8,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-decision-2.0-kai-0.6b","score":13.7,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":34.3,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-decision-2.0-kai-0.6b","score":28.2,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":4.9,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":68,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-decision-2.0-kai-0.6b","score":16.3,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-decision-2.0-kai-0.6b","score":34.2,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-decision-2.0-kai-0.6b","score":59.5,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":33.2,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-decision-2.0-kai-0.6b","score":51,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-decision-2.0-kai-0.6b","score":12,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":38,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-decision-2.0-kai-0.6b","score":50,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-decision-2.0-kai-0.6b","score":18.4,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-decision-2.0-kai-0.6b","score":37.9,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-decision-2.0-kai-0.6b","score":1,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-decision-2.0-kai-0.6b","score":53.4,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-decision-2.0-kai-0.6b","score":38.6,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-decision-2.0-kai-0.6b","score":45.5,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":57.9,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":59.7,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":49.6,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-decision-2.0-eos-0.8b","score":79.5,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-decision-2.0-eos-0.8b","score":63.1,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":76.5,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":60.9,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-decision-2.0-eos-0.8b","score":44.5,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-decision-2.0-eos-0.8b","score":36.5,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":51.5,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":54.5,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":7.9,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":51.2,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-decision-2.0-eos-0.8b","score":39.8,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-decision-2.0-eos-0.8b","score":25.5,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-decision-2.0-eos-0.8b","score":78,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-decision-2.0-eos-0.8b","score":57,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-decision-2.0-eos-0.8b","score":51.8,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-decision-2.0-eos-0.8b","score":43.7,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":20.7,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":8.5,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-decision-2.0-eos-0.8b","score":50,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-decision-2.0-eos-0.8b","score":10.8,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":27.3,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-decision-2.0-eos-0.8b","score":35,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":7.1,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":59.8,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-decision-2.0-eos-0.8b","score":21.2,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-decision-2.0-eos-0.8b","score":42.6,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-decision-2.0-eos-0.8b","score":63.6,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":40.7,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-decision-2.0-eos-0.8b","score":54.5,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-decision-2.0-eos-0.8b","score":12,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":36.3,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-decision-2.0-eos-0.8b","score":50,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-decision-2.0-eos-0.8b","score":18.2,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-decision-2.0-eos-0.8b","score":42.6,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-decision-2.0-eos-0.8b","score":4.5,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-decision-2.0-eos-0.8b","score":71.5,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-decision-2.0-eos-0.8b","score":40.2,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-decision-2.0-eos-0.8b","score":40,"metric":"percent"},{"benchmark":"bfcl-decision","model":"tev1-0.8b-experimental","score":66.1,"metric":"percent"},{"benchmark":"toolret-decision","model":"tev1-0.8b-experimental","score":57.2,"metric":"ndcg@10"},{"benchmark":"routerbench-decision","model":"tev1-0.8b-experimental","score":58.7,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"tev1-0.8b-experimental","score":1.1,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"tev1-0.8b-experimental","score":59.7,"metric":"f1"},{"benchmark":"contractnli","model":"tev1-0.8b-experimental","score":46.1,"metric":"f1"},{"benchmark":"anli","model":"tev1-0.8b-experimental","score":37.6,"metric":"f1"},{"benchmark":"bpomp-decision","model":"tev1-0.8b-experimental","score":50.7,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"tev1-0.8b-experimental","score":51.3,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"tev1-0.8b-experimental","score":53.7,"metric":"percent"},{"benchmark":"mmlu","model":"tev1-0.8b-experimental","score":45.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"tev1-0.8b-experimental","score":27.6,"metric":"percent"},{"benchmark":"arc-easy","model":"tev1-0.8b-experimental","score":82,"metric":"percent"},{"benchmark":"arc-challenge","model":"tev1-0.8b-experimental","score":62,"metric":"percent"},{"benchmark":"winogrande","model":"tev1-0.8b-experimental","score":52.2,"metric":"percent"},{"benchmark":"hellaswag","model":"tev1-0.8b-experimental","score":44.8,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"tev1-0.8b-experimental","score":19.9,"metric":"percent"},{"benchmark":"chessbench-decision","model":"tev1-0.8b-experimental","score":19.5,"metric":"percent"},{"benchmark":"musr","model":"tev1-0.8b-experimental","score":52,"metric":"percent"},{"benchmark":"sata-bench","model":"tev1-0.8b-experimental","score":5.8,"metric":"percent"},{"benchmark":"bright-decision","model":"tev1-0.8b-experimental","score":29.4,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"tev1-0.8b-experimental","score":21.8,"metric":"f1"},{"benchmark":"acos-decision","model":"tev1-0.8b-experimental","score":5.4,"metric":"f1"},{"benchmark":"finentity-decision","model":"tev1-0.8b-experimental","score":57.8,"metric":"f1"},{"benchmark":"isarcasmeval","model":"tev1-0.8b-experimental","score":21.3,"metric":"f1"},{"benchmark":"vast-stance","model":"tev1-0.8b-experimental","score":44.6,"metric":"f1"},{"benchmark":"nli4ct","model":"tev1-0.8b-experimental","score":61.3,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"tev1-0.8b-experimental","score":38.1,"metric":"percent"},{"benchmark":"cladder","model":"tev1-0.8b-experimental","score":50.5,"metric":"percent"},{"benchmark":"hle-multichoice","model":"tev1-0.8b-experimental","score":14.9,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"tev1-0.8b-experimental","score":40,"metric":"percent"},{"benchmark":"phishnchips","model":"tev1-0.8b-experimental","score":50,"metric":"percent"},{"benchmark":"mmlu-pro","model":"tev1-0.8b-experimental","score":22.9,"metric":"percent"},{"benchmark":"bbh-decision","model":"tev1-0.8b-experimental","score":43.6,"metric":"percent"},{"benchmark":"ragtruth","model":"tev1-0.8b-experimental","score":18.2,"metric":"f1"},{"benchmark":"hover","model":"tev1-0.8b-experimental","score":53.1,"metric":"percent"},{"benchmark":"when2call","model":"tev1-0.8b-experimental","score":66.8,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"tev1-0.8b-experimental","score":30.7,"metric":"percent"},{"benchmark":"bfcl-decision","model":"intern-decision-0.8b","score":64.5,"metric":"percent"},{"benchmark":"toolret-decision","model":"intern-decision-0.8b","score":47.4,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"intern-decision-0.8b","score":21.1,"metric":"percent"},{"benchmark":"banking77","model":"intern-decision-0.8b","score":11.8,"metric":"f1"},{"benchmark":"clinc150-oos","model":"intern-decision-0.8b","score":4.9,"metric":"f1"},{"benchmark":"routerbench-decision","model":"intern-decision-0.8b","score":56.6,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"intern-decision-0.8b","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"intern-decision-0.8b","score":57.4,"metric":"f1"},{"benchmark":"contractnli","model":"intern-decision-0.8b","score":35.4,"metric":"f1"},{"benchmark":"anli","model":"intern-decision-0.8b","score":34.1,"metric":"f1"},{"benchmark":"bpomp-decision","model":"intern-decision-0.8b","score":50.4,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"intern-decision-0.8b","score":53.7,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"intern-decision-0.8b","score":1.6,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"intern-decision-0.8b","score":56.7,"metric":"percent"},{"benchmark":"mmlu","model":"intern-decision-0.8b","score":46.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"intern-decision-0.8b","score":28.1,"metric":"percent"},{"benchmark":"arc-easy","model":"intern-decision-0.8b","score":81.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"intern-decision-0.8b","score":62.9,"metric":"percent"},{"benchmark":"winogrande","model":"intern-decision-0.8b","score":53.1,"metric":"percent"},{"benchmark":"hellaswag","model":"intern-decision-0.8b","score":43.6,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"intern-decision-0.8b","score":18.6,"metric":"percent"},{"benchmark":"chessbench-decision","model":"intern-decision-0.8b","score":8.8,"metric":"percent"},{"benchmark":"musr","model":"intern-decision-0.8b","score":51.3,"metric":"percent"},{"benchmark":"sata-bench","model":"intern-decision-0.8b","score":3.4,"metric":"percent"},{"benchmark":"bright-decision","model":"intern-decision-0.8b","score":22.4,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"intern-decision-0.8b","score":24.4,"metric":"f1"},{"benchmark":"acos-decision","model":"intern-decision-0.8b","score":4.6,"metric":"f1"},{"benchmark":"finentity-decision","model":"intern-decision-0.8b","score":57.1,"metric":"f1"},{"benchmark":"isarcasmeval","model":"intern-decision-0.8b","score":26.3,"metric":"f1"},{"benchmark":"vast-stance","model":"intern-decision-0.8b","score":28,"metric":"f1"},{"benchmark":"nli4ct","model":"intern-decision-0.8b","score":57.6,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"intern-decision-0.8b","score":32.8,"metric":"percent"},{"benchmark":"cladder","model":"intern-decision-0.8b","score":50.5,"metric":"percent"},{"benchmark":"hle-multichoice","model":"intern-decision-0.8b","score":13.6,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"intern-decision-0.8b","score":44.6,"metric":"percent"},{"benchmark":"phishnchips","model":"intern-decision-0.8b","score":45.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-decision-0.8b","score":26.5,"metric":"percent"},{"benchmark":"bbh-decision","model":"intern-decision-0.8b","score":42.7,"metric":"percent"},{"benchmark":"ragtruth","model":"intern-decision-0.8b","score":53.3,"metric":"f1"},{"benchmark":"hover","model":"intern-decision-0.8b","score":52.3,"metric":"percent"},{"benchmark":"when2call","model":"intern-decision-0.8b","score":46.1,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"intern-decision-0.8b","score":27.1,"metric":"percent"},{"benchmark":"bfcl-decision","model":"gliner2.5-decide","score":46.2,"metric":"percent"},{"benchmark":"toolret-decision","model":"gliner2.5-decide","score":38.2,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"gliner2.5-decide","score":7.7,"metric":"percent"},{"benchmark":"banking77","model":"gliner2.5-decide","score":65.6,"metric":"f1"},{"benchmark":"clinc150-oos","model":"gliner2.5-decide","score":60.4,"metric":"f1"},{"benchmark":"routerbench-decision","model":"gliner2.5-decide","score":59.4,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"gliner2.5-decide","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"gliner2.5-decide","score":0.8,"metric":"f1"},{"benchmark":"contractnli","model":"gliner2.5-decide","score":21.8,"metric":"f1"},{"benchmark":"anli","model":"gliner2.5-decide","score":30.9,"metric":"f1"},{"benchmark":"bpomp-decision","model":"gliner2.5-decide","score":58.2,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"gliner2.5-decide","score":50.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"gliner2.5-decide","score":1.7,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"gliner2.5-decide","score":53.4,"metric":"percent"},{"benchmark":"mmlu","model":"gliner2.5-decide","score":33.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gliner2.5-decide","score":21.4,"metric":"percent"},{"benchmark":"arc-easy","model":"gliner2.5-decide","score":54.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"gliner2.5-decide","score":36.8,"metric":"percent"},{"benchmark":"winogrande","model":"gliner2.5-decide","score":50.7,"metric":"percent"},{"benchmark":"hellaswag","model":"gliner2.5-decide","score":32.2,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"gliner2.5-decide","score":17.3,"metric":"percent"},{"benchmark":"chessbench-decision","model":"gliner2.5-decide","score":8.1,"metric":"percent"},{"benchmark":"musr","model":"gliner2.5-decide","score":45.2,"metric":"percent"},{"benchmark":"sata-bench","model":"gliner2.5-decide","score":0.7,"metric":"percent"},{"benchmark":"bright-decision","model":"gliner2.5-decide","score":20.1,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"gliner2.5-decide","score":23.3,"metric":"f1"},{"benchmark":"acos-decision","model":"gliner2.5-decide","score":0,"metric":"f1"},{"benchmark":"finentity-decision","model":"gliner2.5-decide","score":66.2,"metric":"f1"},{"benchmark":"isarcasmeval","model":"gliner2.5-decide","score":32.4,"metric":"f1"},{"benchmark":"vast-stance","model":"gliner2.5-decide","score":35.3,"metric":"f1"},{"benchmark":"nli4ct","model":"gliner2.5-decide","score":48,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"gliner2.5-decide","score":40.2,"metric":"percent"},{"benchmark":"cladder","model":"gliner2.5-decide","score":50.1,"metric":"percent"},{"benchmark":"hle-multichoice","model":"gliner2.5-decide","score":16.8,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"gliner2.5-decide","score":45.5,"metric":"percent"},{"benchmark":"phishnchips","model":"gliner2.5-decide","score":50,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gliner2.5-decide","score":16.1,"metric":"percent"},{"benchmark":"bbh-decision","model":"gliner2.5-decide","score":31.1,"metric":"percent"},{"benchmark":"ragtruth","model":"gliner2.5-decide","score":25.3,"metric":"f1"},{"benchmark":"hover","model":"gliner2.5-decide","score":50.7,"metric":"percent"},{"benchmark":"when2call","model":"gliner2.5-decide","score":33.4,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"gliner2.5-decide","score":32.2,"metric":"percent"},{"benchmark":"bfcl-decision","model":"strands-decider-2b","score":81.3,"metric":"percent"},{"benchmark":"toolret-decision","model":"strands-decider-2b","score":60.5,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"strands-decider-2b","score":39.6,"metric":"percent"},{"benchmark":"banking77","model":"strands-decider-2b","score":80.4,"metric":"f1"},{"benchmark":"clinc150-oos","model":"strands-decider-2b","score":64.7,"metric":"f1"},{"benchmark":"routerbench-decision","model":"strands-decider-2b","score":78.9,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"strands-decider-2b","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"strands-decider-2b","score":59.6,"metric":"f1"},{"benchmark":"contractnli","model":"strands-decider-2b","score":73,"metric":"f1"},{"benchmark":"anli","model":"strands-decider-2b","score":39.9,"metric":"f1"},{"benchmark":"bpomp-decision","model":"strands-decider-2b","score":56,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"strands-decider-2b","score":49.7,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"strands-decider-2b","score":6.9,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"strands-decider-2b","score":50.7,"metric":"percent"},{"benchmark":"mmlu","model":"strands-decider-2b","score":51,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"strands-decider-2b","score":33.2,"metric":"percent"},{"benchmark":"arc-easy","model":"strands-decider-2b","score":90.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"strands-decider-2b","score":71.1,"metric":"percent"},{"benchmark":"winogrande","model":"strands-decider-2b","score":57.4,"metric":"percent"},{"benchmark":"hellaswag","model":"strands-decider-2b","score":57.4,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"strands-decider-2b","score":24.7,"metric":"percent"},{"benchmark":"chessbench-decision","model":"strands-decider-2b","score":9.2,"metric":"percent"},{"benchmark":"musr","model":"strands-decider-2b","score":51.1,"metric":"percent"},{"benchmark":"sata-bench","model":"strands-decider-2b","score":9.8,"metric":"percent"},{"benchmark":"bright-decision","model":"strands-decider-2b","score":36.8,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"strands-decider-2b","score":26,"metric":"f1"},{"benchmark":"acos-decision","model":"strands-decider-2b","score":6,"metric":"f1"},{"benchmark":"finentity-decision","model":"strands-decider-2b","score":72.7,"metric":"f1"},{"benchmark":"isarcasmeval","model":"strands-decider-2b","score":29.6,"metric":"f1"},{"benchmark":"vast-stance","model":"strands-decider-2b","score":40.4,"metric":"f1"},{"benchmark":"nli4ct","model":"strands-decider-2b","score":65.8,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"strands-decider-2b","score":33.3,"metric":"percent"},{"benchmark":"cladder","model":"strands-decider-2b","score":54.4,"metric":"percent"},{"benchmark":"hle-multichoice","model":"strands-decider-2b","score":14,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"strands-decider-2b","score":38,"metric":"percent"},{"benchmark":"phishnchips","model":"strands-decider-2b","score":50.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"strands-decider-2b","score":31.1,"metric":"percent"},{"benchmark":"bbh-decision","model":"strands-decider-2b","score":46.5,"metric":"percent"},{"benchmark":"ragtruth","model":"strands-decider-2b","score":35.7,"metric":"f1"},{"benchmark":"hover","model":"strands-decider-2b","score":54,"metric":"percent"},{"benchmark":"when2call","model":"strands-decider-2b","score":59.6,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"strands-decider-2b","score":45.5,"metric":"percent"},{"benchmark":"bfcl-decision","model":"d1-3b","score":89.4,"metric":"percent"},{"benchmark":"toolret-decision","model":"d1-3b","score":65.7,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"d1-3b","score":78.1,"metric":"percent"},{"benchmark":"banking77","model":"d1-3b","score":88,"metric":"f1"},{"benchmark":"clinc150-oos","model":"d1-3b","score":91.2,"metric":"f1"},{"benchmark":"routerbench-decision","model":"d1-3b","score":79.5,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"d1-3b","score":63.6,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"d1-3b","score":69.2,"metric":"f1"},{"benchmark":"contractnli","model":"d1-3b","score":80.6,"metric":"f1"},{"benchmark":"anli","model":"d1-3b","score":62.4,"metric":"f1"},{"benchmark":"bpomp-decision","model":"d1-3b","score":82.4,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"d1-3b","score":63.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"d1-3b","score":25.3,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"d1-3b","score":62,"metric":"percent"},{"benchmark":"mmlu","model":"d1-3b","score":66.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"d1-3b","score":28.6,"metric":"percent"},{"benchmark":"arc-easy","model":"d1-3b","score":95.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"d1-3b","score":88,"metric":"percent"},{"benchmark":"winogrande","model":"d1-3b","score":77.7,"metric":"percent"},{"benchmark":"hellaswag","model":"d1-3b","score":89.2,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"d1-3b","score":32.7,"metric":"percent"},{"benchmark":"chessbench-decision","model":"d1-3b","score":15.8,"metric":"percent"},{"benchmark":"musr","model":"d1-3b","score":56.8,"metric":"percent"},{"benchmark":"sata-bench","model":"d1-3b","score":31.3,"metric":"percent"},{"benchmark":"bright-decision","model":"d1-3b","score":40.6,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"d1-3b","score":51.2,"metric":"f1"},{"benchmark":"acos-decision","model":"d1-3b","score":37.7,"metric":"f1"},{"benchmark":"finentity-decision","model":"d1-3b","score":88,"metric":"f1"},{"benchmark":"isarcasmeval","model":"d1-3b","score":36,"metric":"f1"},{"benchmark":"vast-stance","model":"d1-3b","score":77,"metric":"f1"},{"benchmark":"nli4ct","model":"d1-3b","score":74.1,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"d1-3b","score":31.1,"metric":"percent"},{"benchmark":"cladder","model":"d1-3b","score":56.6,"metric":"percent"},{"benchmark":"hle-multichoice","model":"d1-3b","score":14.2,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"d1-3b","score":58.8,"metric":"percent"},{"benchmark":"phishnchips","model":"d1-3b","score":53.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"d1-3b","score":44.9,"metric":"percent"},{"benchmark":"bbh-decision","model":"d1-3b","score":72.4,"metric":"percent"},{"benchmark":"ragtruth","model":"d1-3b","score":77.6,"metric":"f1"},{"benchmark":"hover","model":"d1-3b","score":74.1,"metric":"percent"},{"benchmark":"when2call","model":"d1-3b","score":86.6,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"d1-3b","score":64,"metric":"percent"},{"benchmark":"bfcl-decision","model":"d1-omni-600m","score":47.6,"metric":"percent"},{"benchmark":"toolret-decision","model":"d1-omni-600m","score":15.7,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"d1-omni-600m","score":40,"metric":"percent"},{"benchmark":"banking77","model":"d1-omni-600m","score":83.7,"metric":"f1"},{"benchmark":"clinc150-oos","model":"d1-omni-600m","score":85.3,"metric":"f1"},{"benchmark":"routerbench-decision","model":"d1-omni-600m","score":59.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"d1-omni-600m","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"d1-omni-600m","score":61.3,"metric":"f1"},{"benchmark":"contractnli","model":"d1-omni-600m","score":66.2,"metric":"f1"},{"benchmark":"anli","model":"d1-omni-600m","score":36,"metric":"f1"},{"benchmark":"bpomp-decision","model":"d1-omni-600m","score":45.7,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"d1-omni-600m","score":51.1,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"d1-omni-600m","score":0.8,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"d1-omni-600m","score":56.4,"metric":"percent"},{"benchmark":"mmlu","model":"d1-omni-600m","score":39.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"d1-omni-600m","score":21.9,"metric":"percent"},{"benchmark":"arc-easy","model":"d1-omni-600m","score":70.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"d1-omni-600m","score":51.4,"metric":"percent"},{"benchmark":"winogrande","model":"d1-omni-600m","score":60.5,"metric":"percent"},{"benchmark":"hellaswag","model":"d1-omni-600m","score":60,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"d1-omni-600m","score":18.4,"metric":"percent"},{"benchmark":"chessbench-decision","model":"d1-omni-600m","score":12.9,"metric":"percent"},{"benchmark":"musr","model":"d1-omni-600m","score":38,"metric":"percent"},{"benchmark":"sata-bench","model":"d1-omni-600m","score":7.4,"metric":"percent"},{"benchmark":"bright-decision","model":"d1-omni-600m","score":10.4,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"d1-omni-600m","score":27.3,"metric":"f1"},{"benchmark":"acos-decision","model":"d1-omni-600m","score":0.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"d1-omni-600m","score":62.9,"metric":"f1"},{"benchmark":"isarcasmeval","model":"d1-omni-600m","score":27.5,"metric":"f1"},{"benchmark":"vast-stance","model":"d1-omni-600m","score":38.8,"metric":"f1"},{"benchmark":"nli4ct","model":"d1-omni-600m","score":53.2,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"d1-omni-600m","score":40.9,"metric":"percent"},{"benchmark":"cladder","model":"d1-omni-600m","score":49.7,"metric":"percent"},{"benchmark":"hle-multichoice","model":"d1-omni-600m","score":14.8,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"d1-omni-600m","score":36.3,"metric":"percent"},{"benchmark":"phishnchips","model":"d1-omni-600m","score":44.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"d1-omni-600m","score":20,"metric":"percent"},{"benchmark":"bbh-decision","model":"d1-omni-600m","score":43.2,"metric":"percent"},{"benchmark":"ragtruth","model":"d1-omni-600m","score":2.3,"metric":"f1"},{"benchmark":"hover","model":"d1-omni-600m","score":59.8,"metric":"percent"},{"benchmark":"when2call","model":"d1-omni-600m","score":40.8,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"d1-omni-600m","score":36,"metric":"percent"},{"benchmark":"isarcasmeval","model":"clef-omni","score":37.2,"metric":"f1"},{"benchmark":"bfcl-decision","model":"vllm-sr-d3","score":97.3,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-d3","score":69.1,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-d3","score":86.4,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-d3","score":92,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-d3","score":96.9,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-d3","score":79.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-d3","score":80.7,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-d3","score":57.3,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-d3","score":78.5,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-d3","score":76,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-d3","score":95.8,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-d3","score":63.7,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-d3","score":62.9,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-d3","score":65.6,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-d3","score":88.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-d3","score":56.6,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-d3","score":99.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-d3","score":97.4,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-d3","score":95.4,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-d3","score":98.2,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-d3","score":85.2,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-d3","score":17.6,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-d3","score":69.3,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-d3","score":38.4,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-d3","score":49.3,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-d3","score":59,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-d3","score":30,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-d3","score":95.7,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-d3","score":66.8,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-d3","score":74.8,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-d3","score":86,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-d3","score":88.1,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-d3","score":81.2,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-d3","score":14,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-d3","score":41.6,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-d3","score":73.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-d3","score":73,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-d3","score":85.7,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-d3","score":82.1,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-d3","score":83.5,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-d3","score":86.4,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-d3","score":82,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-d3-flash","score":96.2,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-d3-flash","score":65.1,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-d3-flash","score":84.8,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-d3-flash","score":92.7,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-d3-flash","score":96.4,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-d3-flash","score":79.9,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-d3-flash","score":53.4,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-d3-flash","score":57.9,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-d3-flash","score":73.9,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-d3-flash","score":70,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-d3-flash","score":94.1,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-d3-flash","score":61,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-d3-flash","score":31.9,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-d3-flash","score":62.9,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-d3-flash","score":83.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-d3-flash","score":48.5,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-d3-flash","score":99.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-d3-flash","score":96.2,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-d3-flash","score":92.2,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-d3-flash","score":97,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-d3-flash","score":72.8,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-d3-flash","score":15.1,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-d3-flash","score":61,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-d3-flash","score":19.6,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-d3-flash","score":47.3,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-d3-flash","score":53.7,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-d3-flash","score":26.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-d3-flash","score":94.3,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-d3-flash","score":51.6,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-d3-flash","score":68.8,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-d3-flash","score":83.6,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-d3-flash","score":71,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-d3-flash","score":72.7,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-d3-flash","score":11.4,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-d3-flash","score":37.4,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-d3-flash","score":68.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-d3-flash","score":64.1,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-d3-flash","score":75.9,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-d3-flash","score":76.3,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-d3-flash","score":84.4,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-d3-flash","score":86.6,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-d3-flash","score":80.3,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-d3-mini","score":95.5,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-d3-mini","score":64.4,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-d3-mini","score":83.9,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-d3-mini","score":92.8,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-d3-mini","score":96.3,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-d3-mini","score":77.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-d3-mini","score":37.5,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-d3-mini","score":47.3,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-d3-mini","score":74.7,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-d3-mini","score":67.9,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-d3-mini","score":89.5,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-d3-mini","score":59.7,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-d3-mini","score":21.7,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-d3-mini","score":61.8,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-d3-mini","score":80.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-d3-mini","score":44.9,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-d3-mini","score":98.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-d3-mini","score":95.5,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-d3-mini","score":90.2,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-d3-mini","score":96,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-d3-mini","score":69.6,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-d3-mini","score":14.1,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-d3-mini","score":60.8,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-d3-mini","score":19,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-d3-mini","score":45.1,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-d3-mini","score":52,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-d3-mini","score":17.4,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-d3-mini","score":93.5,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-d3-mini","score":50.2,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-d3-mini","score":70.5,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-d3-mini","score":82.6,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-d3-mini","score":64.6,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-d3-mini","score":72.8,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-d3-mini","score":10.8,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-d3-mini","score":41.2,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-d3-mini","score":72.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-d3-mini","score":58.9,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-d3-mini","score":71.5,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-d3-mini","score":71.5,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-d3-mini","score":81.5,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-d3-mini","score":84.5,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-d3-mini","score":76.1,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-d3-nano","score":92.2,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-d3-nano","score":61.2,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-d3-nano","score":56.3,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-d3-nano","score":91.3,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-d3-nano","score":95.1,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-d3-nano","score":79,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-d3-nano","score":12.5,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-d3-nano","score":63.2,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-d3-nano","score":68.8,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-d3-nano","score":56,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-d3-nano","score":56.6,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-d3-nano","score":60.5,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-d3-nano","score":10.9,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-d3-nano","score":61.1,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-d3-nano","score":67.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-d3-nano","score":32.1,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-d3-nano","score":96.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-d3-nano","score":88.8,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-d3-nano","score":79.9,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-d3-nano","score":91,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-d3-nano","score":51.8,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-d3-nano","score":8.7,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-d3-nano","score":59.6,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-d3-nano","score":29.8,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-d3-nano","score":39,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-d3-nano","score":47.1,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-d3-nano","score":13,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-d3-nano","score":87.6,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-d3-nano","score":40.1,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-d3-nano","score":57,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-d3-nano","score":71.6,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-d3-nano","score":41.8,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-d3-nano","score":60.3,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-d3-nano","score":14,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-d3-nano","score":36.7,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-d3-nano","score":67,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-d3-nano","score":43.5,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-d3-nano","score":54.4,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-d3-nano","score":29.5,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-d3-nano","score":79.9,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-d3-nano","score":82.3,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-d3-nano","score":70.6,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-d3-lite","score":86,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-d3-lite","score":61.4,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-d3-lite","score":56.9,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-d3-lite","score":90.3,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-d3-lite","score":94,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-d3-lite","score":74.5,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-d3-lite","score":11.4,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-d3-lite","score":64.3,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-d3-lite","score":54.2,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-d3-lite","score":49.3,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-d3-lite","score":71.3,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-d3-lite","score":57.3,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-d3-lite","score":1.6,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-d3-lite","score":58.7,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-d3-lite","score":56.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-d3-lite","score":33.2,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-d3-lite","score":90.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-d3-lite","score":77.6,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-d3-lite","score":70.9,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-d3-lite","score":82.7,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-d3-lite","score":41.6,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-d3-lite","score":8.3,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-d3-lite","score":57.9,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-d3-lite","score":19.6,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-d3-lite","score":36.7,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-d3-lite","score":41.3,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-d3-lite","score":6.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-d3-lite","score":88.1,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-d3-lite","score":32.9,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-d3-lite","score":55.4,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-d3-lite","score":66.1,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-d3-lite","score":33.7,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-d3-lite","score":61.1,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-d3-lite","score":14.4,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-d3-lite","score":38,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-d3-lite","score":54.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-d3-lite","score":32.5,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-d3-lite","score":46.6,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-d3-lite","score":29.7,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-d3-lite","score":81.8,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-d3-lite","score":79.6,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-d3-lite","score":61.6,"metric":"percent"},{"benchmark":"bfcl-decision","model":"vllm-sr-d3-edge","score":72.5,"metric":"percent"},{"benchmark":"toolret-decision","model":"vllm-sr-d3-edge","score":57,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"vllm-sr-d3-edge","score":40.2,"metric":"percent"},{"benchmark":"banking77","model":"vllm-sr-d3-edge","score":90,"metric":"f1"},{"benchmark":"clinc150-oos","model":"vllm-sr-d3-edge","score":91.9,"metric":"f1"},{"benchmark":"routerbench-decision","model":"vllm-sr-d3-edge","score":51.6,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"vllm-sr-d3-edge","score":0,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"vllm-sr-d3-edge","score":51.3,"metric":"f1"},{"benchmark":"contractnli","model":"vllm-sr-d3-edge","score":56.5,"metric":"f1"},{"benchmark":"anli","model":"vllm-sr-d3-edge","score":40.8,"metric":"f1"},{"benchmark":"bpomp-decision","model":"vllm-sr-d3-edge","score":54.9,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"vllm-sr-d3-edge","score":53.3,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"vllm-sr-d3-edge","score":1.1,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"vllm-sr-d3-edge","score":52.1,"metric":"percent"},{"benchmark":"mmlu","model":"vllm-sr-d3-edge","score":41.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"vllm-sr-d3-edge","score":28.1,"metric":"percent"},{"benchmark":"arc-easy","model":"vllm-sr-d3-edge","score":74.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"vllm-sr-d3-edge","score":58,"metric":"percent"},{"benchmark":"winogrande","model":"vllm-sr-d3-edge","score":61.8,"metric":"percent"},{"benchmark":"hellaswag","model":"vllm-sr-d3-edge","score":59,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"vllm-sr-d3-edge","score":34.9,"metric":"percent"},{"benchmark":"chessbench-decision","model":"vllm-sr-d3-edge","score":7.4,"metric":"percent"},{"benchmark":"musr","model":"vllm-sr-d3-edge","score":49.9,"metric":"percent"},{"benchmark":"sata-bench","model":"vllm-sr-d3-edge","score":11.4,"metric":"percent"},{"benchmark":"bright-decision","model":"vllm-sr-d3-edge","score":31.1,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"vllm-sr-d3-edge","score":29.5,"metric":"f1"},{"benchmark":"acos-decision","model":"vllm-sr-d3-edge","score":7.8,"metric":"f1"},{"benchmark":"finentity-decision","model":"vllm-sr-d3-edge","score":80.5,"metric":"f1"},{"benchmark":"isarcasmeval","model":"vllm-sr-d3-edge","score":31.7,"metric":"f1"},{"benchmark":"vast-stance","model":"vllm-sr-d3-edge","score":45.3,"metric":"f1"},{"benchmark":"nli4ct","model":"vllm-sr-d3-edge","score":56.7,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"vllm-sr-d3-edge","score":43.2,"metric":"percent"},{"benchmark":"cladder","model":"vllm-sr-d3-edge","score":54.1,"metric":"percent"},{"benchmark":"hle-multichoice","model":"vllm-sr-d3-edge","score":16.8,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"vllm-sr-d3-edge","score":34.1,"metric":"percent"},{"benchmark":"phishnchips","model":"vllm-sr-d3-edge","score":67.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"vllm-sr-d3-edge","score":23.1,"metric":"percent"},{"benchmark":"bbh-decision","model":"vllm-sr-d3-edge","score":38.3,"metric":"percent"},{"benchmark":"ragtruth","model":"vllm-sr-d3-edge","score":35.7,"metric":"f1"},{"benchmark":"hover","model":"vllm-sr-d3-edge","score":81,"metric":"percent"},{"benchmark":"when2call","model":"vllm-sr-d3-edge","score":68.4,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"vllm-sr-d3-edge","score":56.6,"metric":"percent"},{"benchmark":"bfcl-decision","model":"autotrust-jev-35b","score":96.3,"metric":"percent"},{"benchmark":"toolret-decision","model":"autotrust-jev-35b","score":65.3,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"autotrust-jev-35b","score":85.8,"metric":"percent"},{"benchmark":"banking77","model":"autotrust-jev-35b","score":92.2,"metric":"f1"},{"benchmark":"clinc150-oos","model":"autotrust-jev-35b","score":94.3,"metric":"f1"},{"benchmark":"routerbench-decision","model":"autotrust-jev-35b","score":79.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"autotrust-jev-35b","score":50,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"autotrust-jev-35b","score":60.7,"metric":"f1"},{"benchmark":"contractnli","model":"autotrust-jev-35b","score":81.5,"metric":"f1"},{"benchmark":"anli","model":"autotrust-jev-35b","score":69.6,"metric":"f1"},{"benchmark":"bpomp-decision","model":"autotrust-jev-35b","score":87.1,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"autotrust-jev-35b","score":61.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"autotrust-jev-35b","score":14.1,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"autotrust-jev-35b","score":62.2,"metric":"percent"},{"benchmark":"mmlu","model":"autotrust-jev-35b","score":86.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"autotrust-jev-35b","score":52,"metric":"percent"},{"benchmark":"arc-easy","model":"autotrust-jev-35b","score":99,"metric":"percent"},{"benchmark":"arc-challenge","model":"autotrust-jev-35b","score":97.7,"metric":"percent"},{"benchmark":"winogrande","model":"autotrust-jev-35b","score":92,"metric":"percent"},{"benchmark":"hellaswag","model":"autotrust-jev-35b","score":97.2,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"autotrust-jev-35b","score":46.2,"metric":"percent"},{"benchmark":"chessbench-decision","model":"autotrust-jev-35b","score":19.8,"metric":"percent"},{"benchmark":"musr","model":"autotrust-jev-35b","score":59.8,"metric":"percent"},{"benchmark":"sata-bench","model":"autotrust-jev-35b","score":29.3,"metric":"percent"},{"benchmark":"bright-decision","model":"autotrust-jev-35b","score":48.8,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"autotrust-jev-35b","score":61.7,"metric":"f1"},{"benchmark":"acos-decision","model":"autotrust-jev-35b","score":29.8,"metric":"f1"},{"benchmark":"finentity-decision","model":"autotrust-jev-35b","score":90.2,"metric":"f1"},{"benchmark":"isarcasmeval","model":"autotrust-jev-35b","score":55.4,"metric":"f1"},{"benchmark":"vast-stance","model":"autotrust-jev-35b","score":69.9,"metric":"f1"},{"benchmark":"nli4ct","model":"autotrust-jev-35b","score":80.8,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"autotrust-jev-35b","score":71.4,"metric":"percent"},{"benchmark":"cladder","model":"autotrust-jev-35b","score":72,"metric":"percent"},{"benchmark":"hle-multichoice","model":"autotrust-jev-35b","score":10.8,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"autotrust-jev-35b","score":59.8,"metric":"percent"},{"benchmark":"phishnchips","model":"autotrust-jev-35b","score":83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"autotrust-jev-35b","score":68.2,"metric":"percent"},{"benchmark":"bbh-decision","model":"autotrust-jev-35b","score":75.7,"metric":"percent"},{"benchmark":"ragtruth","model":"autotrust-jev-35b","score":83.9,"metric":"f1"},{"benchmark":"hover","model":"autotrust-jev-35b","score":88.1,"metric":"percent"},{"benchmark":"when2call","model":"autotrust-jev-35b","score":89.7,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"autotrust-jev-35b","score":79.5,"metric":"percent"},{"benchmark":"isarcasmeval","model":"jev-1.13","score":50.5,"metric":"f1"},{"benchmark":"bfcl-decision","model":"pplx-decider-v1.2","score":97.8,"metric":"percent"},{"benchmark":"toolret-decision","model":"pplx-decider-v1.2","score":67.5,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"pplx-decider-v1.2","score":87.4,"metric":"percent"},{"benchmark":"banking77","model":"pplx-decider-v1.2","score":91,"metric":"f1"},{"benchmark":"clinc150-oos","model":"pplx-decider-v1.2","score":94.4,"metric":"f1"},{"benchmark":"routerbench-decision","model":"pplx-decider-v1.2","score":79.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"pplx-decider-v1.2","score":90.9,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"pplx-decider-v1.2","score":36.3,"metric":"f1"},{"benchmark":"contractnli","model":"pplx-decider-v1.2","score":84,"metric":"f1"},{"benchmark":"anli","model":"pplx-decider-v1.2","score":75.5,"metric":"f1"},{"benchmark":"bpomp-decision","model":"pplx-decider-v1.2","score":95.1,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"pplx-decider-v1.2","score":65.8,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"pplx-decider-v1.2","score":61.6,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"pplx-decider-v1.2","score":68.2,"metric":"percent"},{"benchmark":"mmlu","model":"pplx-decider-v1.2","score":88,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"pplx-decider-v1.2","score":55.1,"metric":"percent"},{"benchmark":"arc-easy","model":"pplx-decider-v1.2","score":99.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"pplx-decider-v1.2","score":97.1,"metric":"percent"},{"benchmark":"winogrande","model":"pplx-decider-v1.2","score":94,"metric":"percent"},{"benchmark":"hellaswag","model":"pplx-decider-v1.2","score":96.6,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"pplx-decider-v1.2","score":83.7,"metric":"percent"},{"benchmark":"chessbench-decision","model":"pplx-decider-v1.2","score":24.6,"metric":"percent"},{"benchmark":"musr","model":"pplx-decider-v1.2","score":70.7,"metric":"percent"},{"benchmark":"sata-bench","model":"pplx-decider-v1.2","score":23.2,"metric":"percent"},{"benchmark":"bright-decision","model":"pplx-decider-v1.2","score":50.1,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"pplx-decider-v1.2","score":62.4,"metric":"f1"},{"benchmark":"acos-decision","model":"pplx-decider-v1.2","score":40.9,"metric":"f1"},{"benchmark":"finentity-decision","model":"pplx-decider-v1.2","score":94.3,"metric":"f1"},{"benchmark":"isarcasmeval","model":"pplx-decider-v1.2","score":74.7,"metric":"f1"},{"benchmark":"vast-stance","model":"pplx-decider-v1.2","score":80.2,"metric":"f1"},{"benchmark":"nli4ct","model":"pplx-decider-v1.2","score":85.7,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"pplx-decider-v1.2","score":86,"metric":"percent"},{"benchmark":"cladder","model":"pplx-decider-v1.2","score":90.8,"metric":"percent"},{"benchmark":"hle-multichoice","model":"pplx-decider-v1.2","score":16,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"pplx-decider-v1.2","score":58.9,"metric":"percent"},{"benchmark":"phishnchips","model":"pplx-decider-v1.2","score":74.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"pplx-decider-v1.2","score":71.9,"metric":"percent"},{"benchmark":"bbh-decision","model":"pplx-decider-v1.2","score":85.2,"metric":"percent"},{"benchmark":"ragtruth","model":"pplx-decider-v1.2","score":84.4,"metric":"f1"},{"benchmark":"hover","model":"pplx-decider-v1.2","score":86.2,"metric":"percent"},{"benchmark":"when2call","model":"pplx-decider-v1.2","score":90.3,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"pplx-decider-v1.2","score":79,"metric":"percent"},{"benchmark":"bfcl-decision","model":"pplx-decider-flash-v1.2","score":95.8,"metric":"percent"},{"benchmark":"toolret-decision","model":"pplx-decider-flash-v1.2","score":65.1,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"pplx-decider-flash-v1.2","score":86.4,"metric":"percent"},{"benchmark":"banking77","model":"pplx-decider-flash-v1.2","score":90.1,"metric":"f1"},{"benchmark":"clinc150-oos","model":"pplx-decider-flash-v1.2","score":93.3,"metric":"f1"},{"benchmark":"routerbench-decision","model":"pplx-decider-flash-v1.2","score":79.8,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"pplx-decider-flash-v1.2","score":75,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"pplx-decider-flash-v1.2","score":35.7,"metric":"f1"},{"benchmark":"contractnli","model":"pplx-decider-flash-v1.2","score":82.9,"metric":"f1"},{"benchmark":"anli","model":"pplx-decider-flash-v1.2","score":69.3,"metric":"f1"},{"benchmark":"bpomp-decision","model":"pplx-decider-flash-v1.2","score":91.3,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"pplx-decider-flash-v1.2","score":61.6,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"pplx-decider-flash-v1.2","score":27.2,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"pplx-decider-flash-v1.2","score":66.2,"metric":"percent"},{"benchmark":"mmlu","model":"pplx-decider-flash-v1.2","score":80.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"pplx-decider-flash-v1.2","score":44.4,"metric":"percent"},{"benchmark":"arc-easy","model":"pplx-decider-flash-v1.2","score":99.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"pplx-decider-flash-v1.2","score":95.7,"metric":"percent"},{"benchmark":"winogrande","model":"pplx-decider-flash-v1.2","score":88.6,"metric":"percent"},{"benchmark":"hellaswag","model":"pplx-decider-flash-v1.2","score":93.8,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"pplx-decider-flash-v1.2","score":67.6,"metric":"percent"},{"benchmark":"chessbench-decision","model":"pplx-decider-flash-v1.2","score":21.2,"metric":"percent"},{"benchmark":"musr","model":"pplx-decider-flash-v1.2","score":60.2,"metric":"percent"},{"benchmark":"sata-bench","model":"pplx-decider-flash-v1.2","score":11.7,"metric":"percent"},{"benchmark":"bright-decision","model":"pplx-decider-flash-v1.2","score":45.6,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"pplx-decider-flash-v1.2","score":57.8,"metric":"f1"},{"benchmark":"acos-decision","model":"pplx-decider-flash-v1.2","score":35.5,"metric":"f1"},{"benchmark":"finentity-decision","model":"pplx-decider-flash-v1.2","score":90.5,"metric":"f1"},{"benchmark":"isarcasmeval","model":"pplx-decider-flash-v1.2","score":59.4,"metric":"f1"},{"benchmark":"vast-stance","model":"pplx-decider-flash-v1.2","score":76.9,"metric":"f1"},{"benchmark":"nli4ct","model":"pplx-decider-flash-v1.2","score":82.3,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"pplx-decider-flash-v1.2","score":62.6,"metric":"percent"},{"benchmark":"cladder","model":"pplx-decider-flash-v1.2","score":85.4,"metric":"percent"},{"benchmark":"hle-multichoice","model":"pplx-decider-flash-v1.2","score":12.6,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"pplx-decider-flash-v1.2","score":61.6,"metric":"percent"},{"benchmark":"phishnchips","model":"pplx-decider-flash-v1.2","score":72.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"pplx-decider-flash-v1.2","score":59.1,"metric":"percent"},{"benchmark":"bbh-decision","model":"pplx-decider-flash-v1.2","score":73.4,"metric":"percent"},{"benchmark":"ragtruth","model":"pplx-decider-flash-v1.2","score":82.5,"metric":"f1"},{"benchmark":"hover","model":"pplx-decider-flash-v1.2","score":86.2,"metric":"percent"},{"benchmark":"when2call","model":"pplx-decider-flash-v1.2","score":89.6,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"pplx-decider-flash-v1.2","score":74.1,"metric":"percent"},{"benchmark":"bfcl-decision","model":"jev-1.14","score":96.4,"metric":"percent"},{"benchmark":"toolret-decision","model":"jev-1.14","score":65,"metric":"ndcg@10"},{"benchmark":"api-bank-decision","model":"jev-1.14","score":86.6,"metric":"percent"},{"benchmark":"banking77","model":"jev-1.14","score":79.9,"metric":"f1"},{"benchmark":"clinc150-oos","model":"jev-1.14","score":90.3,"metric":"f1"},{"benchmark":"routerbench-decision","model":"jev-1.14","score":79.9,"metric":"score"},{"benchmark":"home-appliance-simulator-decision","model":"jev-1.14","score":45.5,"metric":"percent"},{"benchmark":"sgd-x-decision","model":"jev-1.14","score":9,"metric":"f1"},{"benchmark":"contractnli","model":"jev-1.14","score":70.8,"metric":"f1"},{"benchmark":"anli","model":"jev-1.14","score":74.3,"metric":"f1"},{"benchmark":"bpomp-decision","model":"jev-1.14","score":90.1,"metric":"percent"},{"benchmark":"humicroedit-decision","model":"jev-1.14","score":61.8,"metric":"percent"},{"benchmark":"pop909-cl-decision","model":"jev-1.14","score":16.4,"metric":"percent"},{"benchmark":"cfcolor-decision","model":"jev-1.14","score":66.3,"metric":"percent"},{"benchmark":"mmlu","model":"jev-1.14","score":91.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"jev-1.14","score":75.5,"metric":"percent"},{"benchmark":"arc-easy","model":"jev-1.14","score":99.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"jev-1.14","score":97.6,"metric":"percent"},{"benchmark":"winogrande","model":"jev-1.14","score":91.1,"metric":"percent"},{"benchmark":"hellaswag","model":"jev-1.14","score":94.3,"metric":"percent"},{"benchmark":"gsm8k-decision","model":"jev-1.14","score":73,"metric":"percent"},{"benchmark":"chessbench-decision","model":"jev-1.14","score":16.9,"metric":"percent"},{"benchmark":"musr","model":"jev-1.14","score":72.6,"metric":"percent"},{"benchmark":"sata-bench","model":"jev-1.14","score":27.9,"metric":"percent"},{"benchmark":"bright-decision","model":"jev-1.14","score":47,"metric":"ndcg@10"},{"benchmark":"amazon-esci","model":"jev-1.14","score":57.2,"metric":"f1"},{"benchmark":"acos-decision","model":"jev-1.14","score":33.1,"metric":"f1"},{"benchmark":"finentity-decision","model":"jev-1.14","score":87.7,"metric":"f1"},{"benchmark":"isarcasmeval","model":"jev-1.14","score":53.3,"metric":"f1"},{"benchmark":"vast-stance","model":"jev-1.14","score":73.7,"metric":"f1"},{"benchmark":"nli4ct","model":"jev-1.14","score":85.1,"metric":"f1"},{"benchmark":"cruxeval-decision","model":"jev-1.14","score":74.7,"metric":"percent"},{"benchmark":"cladder","model":"jev-1.14","score":88.6,"metric":"percent"},{"benchmark":"habermas-machine-decision","model":"jev-1.14","score":44.6,"metric":"percent"},{"benchmark":"phishnchips","model":"jev-1.14","score":83.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"jev-1.14","score":82.1,"metric":"percent"},{"benchmark":"bbh-decision","model":"jev-1.14","score":93.2,"metric":"percent"},{"benchmark":"ragtruth","model":"jev-1.14","score":75.1,"metric":"f1"},{"benchmark":"hover","model":"jev-1.14","score":76.8,"metric":"percent"},{"benchmark":"new-yorker-caption-matching","model":"jev-1.14","score":72.5,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gemini-4-argon","score":82.4,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-sonnet-5.5","score":75.5,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-opus-5.5","score":73.5,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-fable-5.1","score":68.6,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gemini-3.7-flash","score":67.8,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"grok-4.6","score":65.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-6-astra","score":64.7,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gemini-3.8-flash","score":64.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-fable-5","score":63.6,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"qwen3.8-max","score":63.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-6.1-sol","score":60,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"muse-spark-1.3","score":58.6,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-5.6-terra","score":58.2,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"mimo-v2.6-flash-rl","score":57.4,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"grok-4.5","score":56.2,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-haiku-5.5","score":56.1,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"deepseek-v4-flash","score":55.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-5.5","score":55.1,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"grok-4.7","score":54.6,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-sonnet-5","score":54.5,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"mimo-v2.6-pro","score":54.4,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-6-sol","score":54.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"glm-5.3-flash","score":52.8,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-5.4","score":52.4,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-5.6-sol","score":51.5,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-opus-4.7","score":49.2,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-opus-4.8","score":48.9,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"qwen3.8-27b","score":47.5,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"deepseek-v4-pro-0813","score":47.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gemini-3.6-flash","score":46.9,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-opus-4.6","score":46.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"muse-spark-1.2","score":45.4,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"glm-5.2","score":45.2,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-6-luna","score":44.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"claude-sonnet-4.6","score":43,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-5.6-luna","score":43,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"glm-5.1","score":40.9,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"deepseek-v4.1-flash","score":39.5,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"minimax-m3","score":37.7,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"kimi-k2.7-code","score":37.6,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gemini-3.1-pro","score":35.1,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"inkling","score":33.8,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"muse-spark-open","score":33.4,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"muse-spark-1.1","score":31.8,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gemini-3.5-flash-lite","score":29.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gemini-3.5-flash","score":27.5,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"qwen3.5-397b-a17b","score":24.9,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"nemotron-3-ultra","score":22.7,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"deepseek-v3.2","score":21.3,"metric":"percent"},{"benchmark":"apex-agents-v1.1","model":"gpt-oss-120b","score":4.4,"metric":"percent"},{"benchmark":"astabench","model":"claude-opus-4.7","score":58,"metric":"percent"},{"benchmark":"astabench","model":"claude-opus-4.6","score":55.3,"metric":"percent"},{"benchmark":"astabench","model":"claude-sonnet-4.6","score":54.5,"metric":"percent"},{"benchmark":"astabench","model":"gpt-5.5","score":52.9,"metric":"percent"},{"benchmark":"astabench","model":"gemini-3.1-pro","score":49.6,"metric":"percent"},{"benchmark":"astabench","model":"gpt-5.4","score":46.5,"metric":"percent"},{"benchmark":"astabench","model":"o3","score":37.8,"metric":"percent"},{"benchmark":"astabench","model":"claude-sonnet-4","score":37.5,"metric":"percent"},{"benchmark":"cybench","model":"claude-mythos-preview","score":100,"metric":"percent"},{"benchmark":"cybench","model":"claude-opus-4.7","score":96,"metric":"percent"},{"benchmark":"cybench","model":"claude-opus-4.6","score":93,"metric":"percent"},{"benchmark":"cybench","model":"claude-opus-4.5","score":82,"metric":"percent"},{"benchmark":"cybench","model":"muse-spark","score":65.4,"metric":"percent"},{"benchmark":"cybench","model":"claude-sonnet-4.5","score":60,"metric":"percent"},{"benchmark":"cybench","model":"claude-opus-4.1","score":42,"metric":"percent"},{"benchmark":"cybench","model":"claude-opus-4","score":38,"metric":"percent"},{"benchmark":"cybench","model":"claude-sonnet-4","score":35,"metric":"percent"},{"benchmark":"cybench","model":"grok-4-fast","score":30,"metric":"percent"},{"benchmark":"cybench","model":"claude-3.7-sonnet","score":20,"metric":"percent"},{"benchmark":"cybench","model":"gpt-4.5-preview","score":17.5,"metric":"percent"},{"benchmark":"cybench","model":"claude-3.5-sonnet","score":17.5,"metric":"percent"},{"benchmark":"cybench","model":"gpt-4o","score":12.5,"metric":"percent"},{"benchmark":"cybench","model":"o1-mini","score":10,"metric":"percent"},{"benchmark":"cybench","model":"claude-3-opus","score":10,"metric":"percent"},{"benchmark":"cybench","model":"o1-preview","score":10,"metric":"percent"},{"benchmark":"cybench","model":"llama-3.1-405b-instruct","score":7.5,"metric":"percent"},{"benchmark":"cybench","model":"mixtral-8x22b-instruct","score":7.5,"metric":"percent"},{"benchmark":"cybench","model":"gemini-1.5-pro","score":7.5,"metric":"percent"},{"benchmark":"cybench","model":"llama-3-70b","score":5,"metric":"percent"},{"benchmark":"designarena","model":"claude-opus-5.5","score":1345,"metric":"elo"},{"benchmark":"designarena","model":"gpt-6-astra-xhigh","score":1339,"metric":"elo"},{"benchmark":"designarena","model":"claude-fable-5.1","score":1334,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-5.5","score":1333,"metric":"elo"},{"benchmark":"designarena","model":"muse-spark-1.3-max","score":1332,"metric":"elo"},{"benchmark":"designarena","model":"muse-spark-1.3-xhigh","score":1329,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k3","score":1328,"metric":"elo"},{"benchmark":"designarena","model":"muse-wonder","score":1323,"metric":"elo"},{"benchmark":"designarena","model":"gpt-6-astra-max","score":1318,"metric":"elo"},{"benchmark":"designarena","model":"claude-fable-5","score":1309,"metric":"elo"},{"benchmark":"designarena","model":"gemini-4-argon","score":1308,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-5","score":1307,"metric":"elo"},{"benchmark":"designarena","model":"gemini-3.7-flash","score":1303,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v4.1-flash","score":1301,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.6-sol-medium","score":1299,"metric":"elo"},{"benchmark":"designarena","model":"deca-2.6-ultra","score":1298,"metric":"elo"},{"benchmark":"designarena","model":"gemini-3.8-flash","score":1298,"metric":"elo"},{"benchmark":"designarena","model":"muse-spark-1.2","score":1295,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.6-sol-xhigh","score":1294,"metric":"elo"},{"benchmark":"designarena","model":"glm-5.3","score":1293,"metric":"elo"},{"benchmark":"designarena","model":"gemini-3.6-flash","score":1291,"metric":"elo"},{"benchmark":"designarena","model":"gpt-6-sol","score":1290,"metric":"elo"},{"benchmark":"designarena","model":"deca-2.5-mini","score":1288,"metric":"elo"},{"benchmark":"designarena","model":"grok-4.6","score":1288,"metric":"elo"},{"benchmark":"designarena","model":"mimo-v2.6-pro","score":1288,"metric":"elo"},{"benchmark":"designarena","model":"grok-4.5","score":1286,"metric":"elo"},{"benchmark":"designarena","model":"glm-5.3-flash","score":1286,"metric":"elo"},{"benchmark":"designarena","model":"grok-4.7","score":1285,"metric":"elo"},{"benchmark":"designarena","model":"deca-2.6-pro","score":1282,"metric":"elo"},{"benchmark":"designarena","model":"gpt-6.1-sol","score":1282,"metric":"elo"},{"benchmark":"designarena","model":"qwen3.8-max","score":1281,"metric":"elo"},{"benchmark":"designarena","model":"claude-haiku-5.5","score":1273,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-4.6","score":1272,"metric":"elo"},{"benchmark":"designarena","model":"qwen3.7-max","score":1272,"metric":"elo"},{"benchmark":"designarena","model":"glm-5.2","score":1272,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.5","score":1271,"metric":"elo"},{"benchmark":"designarena","model":"muse-spark-1.1","score":1270,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-4.6-thinking","score":1266,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2.7-code","score":1265,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2.6","score":1264,"metric":"elo"},{"benchmark":"designarena","model":"glm-5.1","score":1263,"metric":"elo"},{"benchmark":"designarena","model":"gemini-3.5-flash","score":1261,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-4.6","score":1259,"metric":"elo"},{"benchmark":"designarena","model":"gpt-6-luna","score":1259,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.6-terra","score":1258,"metric":"elo"},{"benchmark":"designarena","model":"ling-3.1-flash","score":1258,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-5","score":1256,"metric":"elo"},{"benchmark":"designarena","model":"muse-spark","score":1256,"metric":"elo"},{"benchmark":"designarena","model":"qwen3.7-plus","score":1253,"metric":"elo"},{"benchmark":"designarena","model":"deca-2.5-ultra","score":1252,"metric":"elo"},{"benchmark":"designarena","model":"glm-5-turbo","score":1251,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-4.8","score":1247,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2.5-thinking","score":1246,"metric":"elo"},{"benchmark":"designarena","model":"nex-n2-pro","score":1246,"metric":"elo"},{"benchmark":"designarena","model":"mimo-v2.5-pro","score":1245,"metric":"elo"},{"benchmark":"designarena","model":"mimo-v2.5","score":1243,"metric":"elo"},{"benchmark":"designarena","model":"qwen3.6-plus","score":1243,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.6-luna","score":1240,"metric":"elo"},{"benchmark":"designarena","model":"minimax-m3","score":1237,"metric":"elo"},{"benchmark":"designarena","model":"gemini-3.1-pro","score":1233,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v4-flash-0731","score":1231,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.4-medium","score":1230,"metric":"elo"},{"benchmark":"designarena","model":"gemini-3-pro-preview","score":1230,"metric":"elo"},{"benchmark":"designarena","model":"mistral-large-4","score":1230,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-4.5","score":1229,"metric":"elo"},{"benchmark":"designarena","model":"glm-5","score":1228,"metric":"elo"},{"benchmark":"designarena","model":"glm-4.7","score":1227,"metric":"elo"},{"benchmark":"designarena","model":"glm-5v-turbo","score":1223,"metric":"elo"},{"benchmark":"designarena","model":"hy3","score":1222,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v4-pro","score":1220,"metric":"elo"},{"benchmark":"designarena","model":"minimax-m2.7","score":1213,"metric":"elo"},{"benchmark":"designarena","model":"grok-4.2","score":1210,"metric":"elo"},{"benchmark":"designarena","model":"minimax-m2.5","score":1205,"metric":"elo"},{"benchmark":"designarena","model":"step-3.7-flash","score":1204,"metric":"elo"},{"benchmark":"designarena","model":"inkling","score":1203,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.1-low","score":1201,"metric":"elo"},{"benchmark":"designarena","model":"minimax-m2.1","score":1201,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.4-low","score":1199,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.2-none","score":1199,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-coder-480b-a35b-instruct","score":1198,"metric":"elo"},{"benchmark":"designarena","model":"qwen3.5-plus","score":1197,"metric":"elo"},{"benchmark":"designarena","model":"grok-4.2-non-reasoning","score":1195,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5-minimal","score":1193,"metric":"elo"},{"benchmark":"designarena","model":"nemotron-3.5-super-vl-120b-a12b","score":1193,"metric":"elo"},{"benchmark":"designarena","model":"grok-4.3","score":1192,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.2-medium","score":1192,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.1-medium","score":1190,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.1-high","score":1189,"metric":"elo"},{"benchmark":"designarena","model":"glm-4.7-flash","score":1188,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-4.5","score":1187,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.1-none","score":1186,"metric":"elo"},{"benchmark":"designarena","model":"qwen3.5-397b-a17b","score":1185,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5-high","score":1184,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.2-low","score":1184,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3.2-exp","score":1182,"metric":"elo"},{"benchmark":"designarena","model":"solar-pro-4","score":1182,"metric":"elo"},{"benchmark":"designarena","model":"claude-4.5-sonnet-thinking","score":1181,"metric":"elo"},{"benchmark":"designarena","model":"claude-4.1-opus-thinking","score":1180,"metric":"elo"},{"benchmark":"designarena","model":"gemini-2.5-pro","score":1179,"metric":"elo"},{"benchmark":"designarena","model":"glm-4.6","score":1178,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-4","score":1177,"metric":"elo"},{"benchmark":"designarena","model":"claude-opus-4.1","score":1176,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v4-flash","score":1176,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.3-codex","score":1174,"metric":"elo"},{"benchmark":"designarena","model":"glm-4.5","score":1171,"metric":"elo"},{"benchmark":"designarena","model":"gemini-3-flash-preview","score":1170,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3.1-thinking","score":1169,"metric":"elo"},{"benchmark":"designarena","model":"claude-3.7-sonnet","score":1168,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3.2","score":1167,"metric":"elo"},{"benchmark":"designarena","model":"mimo-v2-flash","score":1164,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-4","score":1163,"metric":"elo"},{"benchmark":"designarena","model":"glm-4.5-air","score":1160,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2-thinking","score":1160,"metric":"elo"},{"benchmark":"designarena","model":"hy3-low","score":1160,"metric":"elo"},{"benchmark":"designarena","model":"mistral-large-3","score":1158,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5-mini","score":1156,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2-turbo-preview","score":1156,"metric":"elo"},{"benchmark":"designarena","model":"minimax-m2","score":1153,"metric":"elo"},{"benchmark":"designarena","model":"claude-sonnet-4-thinking","score":1152,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2-0905-preview","score":1150,"metric":"elo"},{"benchmark":"designarena","model":"nemotron-3-ultra","score":1150,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.2-high","score":1148,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.1-codex","score":1147,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-r1-0528","score":1146,"metric":"elo"},{"benchmark":"designarena","model":"solar-mini-4","score":1146,"metric":"elo"},{"benchmark":"designarena","model":"aescoder-4b","score":1142,"metric":"elo"},{"benchmark":"designarena","model":"v0-1.5-lg","score":1139,"metric":"elo"},{"benchmark":"designarena","model":"mistral-medium-3.1","score":1138,"metric":"elo"},{"benchmark":"designarena","model":"intellect-3","score":1137,"metric":"elo"},{"benchmark":"designarena","model":"grok-4.1-fast","score":1136,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3.1","score":1134,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5-nano","score":1134,"metric":"elo"},{"benchmark":"designarena","model":"gemini-3.1-flash-lite","score":1132,"metric":"elo"},{"benchmark":"designarena","model":"claude-4.5-haiku","score":1130,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-max","score":1130,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.2-thinking-xhigh","score":1128,"metric":"elo"},{"benchmark":"designarena","model":"trinity-large-thinking","score":1127,"metric":"elo"},{"benchmark":"designarena","model":"gpt-5.1-codex-mini","score":1126,"metric":"elo"},{"benchmark":"designarena","model":"grok-4-fast","score":1126,"metric":"elo"},{"benchmark":"designarena","model":"grok-4.1-fast-thinking","score":1123,"metric":"elo"},{"benchmark":"designarena","model":"gemini-2.5-flash-preview-09-2025","score":1120,"metric":"elo"},{"benchmark":"designarena","model":"agi-01-swift","score":1120,"metric":"elo"},{"benchmark":"designarena","model":"mistral-medium-3.5","score":1118,"metric":"elo"},{"benchmark":"designarena","model":"deepseek-v3-0324","score":1116,"metric":"elo"},{"benchmark":"designarena","model":"ministral-3-14b-instruct","score":1104,"metric":"elo"},{"benchmark":"designarena","model":"v0-1.5-md","score":1103,"metric":"elo"},{"benchmark":"designarena","model":"grok-3","score":1101,"metric":"elo"},{"benchmark":"designarena","model":"gemini-2.5-flash-lite-preview-09-2025","score":1098,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-coder-30b-a3b-instruct","score":1094,"metric":"elo"},{"benchmark":"designarena","model":"mistral-medium-3","score":1093,"metric":"elo"},{"benchmark":"designarena","model":"grok-4-fast-thinking","score":1088,"metric":"elo"},{"benchmark":"designarena","model":"gemini-2.5-flash","score":1081,"metric":"elo"},{"benchmark":"designarena","model":"ministral-3-8b-instruct","score":1080,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-235b-a22b-instruct-2507","score":1078,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-235b-a22b-thinking-2507","score":1076,"metric":"elo"},{"benchmark":"designarena","model":"gpt-4.1","score":1076,"metric":"elo"},{"benchmark":"designarena","model":"grok-4","score":1065,"metric":"elo"},{"benchmark":"designarena","model":"devstral-medium","score":1063,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-235b-a22b","score":1062,"metric":"elo"},{"benchmark":"designarena","model":"o3","score":1058,"metric":"elo"},{"benchmark":"designarena","model":"grok-code-fast-1","score":1057,"metric":"elo"},{"benchmark":"designarena","model":"magistral-small-1.2","score":1054,"metric":"elo"},{"benchmark":"designarena","model":"olmo-3.1-think-32b","score":1051,"metric":"elo"},{"benchmark":"designarena","model":"magistral-medium-1.2","score":1050,"metric":"elo"},{"benchmark":"designarena","model":"mercury-2","score":1043,"metric":"elo"},{"benchmark":"designarena","model":"codestral-2508","score":1039,"metric":"elo"},{"benchmark":"designarena","model":"ministral-3-3b-instruct","score":1036,"metric":"elo"},{"benchmark":"designarena","model":"kimi-k2","score":1023,"metric":"elo"},{"benchmark":"designarena","model":"o4-mini","score":1016,"metric":"elo"},{"benchmark":"designarena","model":"gpt-4.1-mini","score":1004,"metric":"elo"},{"benchmark":"designarena","model":"grok-3-mini","score":1002,"metric":"elo"},{"benchmark":"designarena","model":"gpt-oss-120b","score":989,"metric":"elo"},{"benchmark":"designarena","model":"llama-3.1-nemotron-ultra-253b-v1","score":982,"metric":"elo"},{"benchmark":"designarena","model":"gpt-4.1-nano","score":960,"metric":"elo"},{"benchmark":"designarena","model":"qwen3-30b-a3b","score":951,"metric":"elo"},{"benchmark":"designarena","model":"magistral-small-1.1","score":895,"metric":"elo"},{"benchmark":"designarena","model":"mistral-small-3.2-24b-instruct","score":885,"metric":"elo"},{"benchmark":"designarena","model":"llama-4-maverick","score":881,"metric":"elo"},{"benchmark":"designarena","model":"devstral-small-1.1","score":862,"metric":"elo"},{"benchmark":"designarena","model":"gpt-4o","score":859,"metric":"elo"},{"benchmark":"designarena","model":"gpt-oss-20b","score":856,"metric":"elo"},{"benchmark":"designarena","model":"llama-4-scout","score":810,"metric":"elo"},{"benchmark":"designarena","model":"codestral-2501","score":803,"metric":"elo"},{"benchmark":"designarena","model":"mistral-large-2.1-2411","score":794,"metric":"elo"},{"benchmark":"designarena","model":"amazon-nova-pro-v1.0","score":763,"metric":"elo"},{"benchmark":"deepswe-v1.0","model":"gpt-5.5","score":70.05,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-opus-4.8","score":58.19,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"gpt-5.4","score":55.53,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-opus-4.7","score":54.2,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"glm-5.2","score":41.52,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-sonnet-4.6","score":31.77,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"gemini-3.5-flash","score":28.32,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-opus-4.6","score":27.6,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"gpt-5.4-mini","score":24.34,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"kimi-k2.6","score":23.89,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"minimax-m3","score":20.44,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"mimo-v2.5-pro","score":19.47,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"qwen3.7-max","score":17.7,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"glm-5.1","score":17.52,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"grok-build-0.1","score":13.08,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"gemini-3.1-pro","score":9.73,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"deepseek-v4-pro","score":7.52,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"gemini-3-flash-preview","score":5.14,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"qwen3.6-plus","score":2.65,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-4.5-haiku","score":0.22,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"minimax-m2.7","score":0.22,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-6-astra","score":74.12,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.8-flash","score":73.83,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-5","score":73.65,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-sol","score":72.67,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-fable-5","score":69.91,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-terra","score":69.62,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.3","score":68.96,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k3","score":68.51,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.6","score":67.48,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.6-luna","score":67.19,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.5","score":67.04,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.7-flash","score":65.49,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.3-flash","score":63.39,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-pro","score":62.83,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-opus-4.8","score":58.97,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"qwen3.8-max","score":57.46,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-1.2","score":54.87,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-sonnet-5","score":53.85,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"grok-4.5","score":53.76,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"deepseek-v4-flash","score":53.32,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"muse-spark-1.1","score":53.32,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gpt-5.4","score":51.77,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.6-flash","score":46.68,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"glm-5.2","score":43.78,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.5-flash","score":36.06,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"kimi-k2.7-code","score":30.53,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"claude-sonnet-4.6","score":29.93,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"gemini-3.1-pro","score":11.73,"metric":"percent"},{"benchmark":"eebench","model":"claude-opus-5.5","score":75,"metric":"percent"},{"benchmark":"eebench","model":"gpt-6-astra","score":69.3,"metric":"percent"},{"benchmark":"eebench","model":"claude-sonnet-5.5","score":67.2,"metric":"percent"},{"benchmark":"eebench","model":"claude-haiku-5.5","score":67.1,"metric":"percent"},{"benchmark":"eebench","model":"gpt-6.1-sol","score":63.6,"metric":"percent"},{"benchmark":"eebench","model":"muse-wonder","score":62.7,"metric":"percent"},{"benchmark":"eebench","model":"claude-opus-5","score":61.6,"metric":"percent"},{"benchmark":"eebench","model":"grok-4.6","score":57.1,"metric":"percent"},{"benchmark":"eebench","model":"gpt-6-sol","score":56.3,"metric":"percent"},{"benchmark":"eebench","model":"gemini-3.8-flash","score":55.4,"metric":"percent"},{"benchmark":"eebench","model":"claude-fable-5","score":54.3,"metric":"percent"},{"benchmark":"eebench","model":"claude-opus-4.8","score":51.4,"metric":"percent"},{"benchmark":"eebench","model":"grok-4.5","score":50.9,"metric":"percent"},{"benchmark":"eebench","model":"muse-spark-1.3","score":49.4,"metric":"percent"},{"benchmark":"eebench","model":"gemini-3.1-pro","score":46.3,"metric":"percent"},{"benchmark":"eebench","model":"claude-sonnet-5","score":40.3,"metric":"percent"},{"benchmark":"eebench","model":"gemini-3.6-flash","score":37.4,"metric":"percent"},{"benchmark":"eebench","model":"gemini-3.5-flash","score":34.3,"metric":"percent"},{"benchmark":"eebench","model":"gpt-6-luna","score":31.1,"metric":"percent"},{"benchmark":"eebench","model":"claude-sonnet-4.6","score":20.4,"metric":"percent"},{"benchmark":"eebench","model":"gemini-3-flash","score":19.5,"metric":"percent"},{"benchmark":"eebench","model":"grok-build-0.1","score":18,"metric":"percent"},{"benchmark":"eebench","model":"claude-4.5-haiku","score":3.5,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-opus-5.5","score":65.3,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-sonnet-5.5","score":64.4,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"swe-2","score":62.5,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-6-sol","score":60.7,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gemini-4-argon","score":60.6,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-6.1-sol","score":60.4,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-opus-4.8","score":59.6,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"grok-4.7","score":59.4,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-haiku-5.5","score":58.4,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"kimi-k3","score":58.2,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-5.5","score":56.7,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"deepseek-v4.1-flash","score":56.6,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"grok-4.5","score":56.5,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gemini-3.7-flash","score":56.3,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-sonnet-5","score":56.2,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-6-luna","score":56.1,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-5.6-terra","score":55.8,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-5.6-luna","score":55.1,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"swe-1.7","score":54.3,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-opus-4.7","score":53.9,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gemini-3.8-flash","score":53.4,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"mistral-large-4","score":53.2,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"glm-5.3","score":52.6,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gemini-3.6-flash","score":48,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"glm-5.3-flash","score":46.2,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"kimi-k2.7-code","score":45.4,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"deepseek-v4-pro-0813","score":44.5,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-opus-4.6","score":43.7,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"gpt-5.4-mini","score":43,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"composer-2.5","score":40.8,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"glm-5.2","score":40.1,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"claude-sonnet-4.6","score":40,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"deepseek-v4-flash-0731","score":31.7,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"deepseek-v4-pro","score":31,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"minimax-m3","score":28.5,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"nemotron-3-ultra","score":27.2,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"inkling","score":24.8,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"qwen3.7-plus","score":21.8,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"swe-1.6","score":20.5,"metric":"percent"},{"benchmark":"frontiercode-extended","model":"mistral-medium-3.5","score":18.7,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-opus-5.5","score":54.6,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-opus-5","score":53.4,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-6.1-sol","score":50.2,"metric":"percent"},{"benchmark":"frontiercode-main","model":"grok-4.7","score":47.6,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gemini-4-argon","score":47.5,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-haiku-5.5","score":46.4,"metric":"percent"},{"benchmark":"frontiercode-main","model":"deepseek-v4.1-flash","score":43.9,"metric":"percent"},{"benchmark":"frontiercode-main","model":"grok-4.5","score":42.4,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gemini-3.8-flash","score":41.2,"metric":"percent"},{"benchmark":"frontiercode-main","model":"glm-5.3","score":40.1,"metric":"percent"},{"benchmark":"frontiercode-main","model":"mistral-large-4","score":39.4,"metric":"percent"},{"benchmark":"frontiercode-main","model":"glm-5.3-flash","score":31.8,"metric":"percent"},{"benchmark":"frontiercode-main","model":"deepseek-v4-pro-0813","score":28.5,"metric":"percent"},{"benchmark":"frontiercode-main","model":"gpt-5.4-mini","score":27,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-opus-4.6","score":26.6,"metric":"percent"},{"benchmark":"frontiercode-main","model":"claude-sonnet-4.6","score":24.3,"metric":"percent"},{"benchmark":"frontiercode-main","model":"deepseek-v4-flash-0731","score":18.8,"metric":"percent"},{"benchmark":"frontiercode-main","model":"deepseek-v4-pro","score":17.6,"metric":"percent"},{"benchmark":"frontiercode-main","model":"minimax-m3","score":14.7,"metric":"percent"},{"benchmark":"frontiercode-main","model":"inkling","score":14,"metric":"percent"},{"benchmark":"frontiercode-main","model":"nemotron-3-ultra","score":13.6,"metric":"percent"},{"benchmark":"frontiercode-main","model":"qwen3.7-plus","score":10.2,"metric":"percent"},{"benchmark":"frontiercode-main","model":"mistral-medium-3.5","score":8,"metric":"percent"},{"benchmark":"gaia","model":"gpt-4o","score":38.21,"metric":"percent"},{"benchmark":"gaia","model":"gpt-4-turbo","score":32.23,"metric":"percent"},{"benchmark":"gaia","model":"o1","score":49.83,"metric":"percent"},{"benchmark":"gaia","model":"gpt-4o-mini","score":26.91,"metric":"percent"},{"benchmark":"gaia","model":"claude-3.7-sonnet","score":74.75,"metric":"percent"},{"benchmark":"gaia","model":"qwq-32b","score":22.26,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-r1","score":40.2,"metric":"percent"},{"benchmark":"gaia","model":"gpt-4.1","score":83.06,"metric":"percent"},{"benchmark":"gaia","model":"mistral-small-3.1-24b-instruct","score":20.6,"metric":"percent"},{"benchmark":"gaia","model":"gemini-2.5-pro","score":73.09,"metric":"percent"},{"benchmark":"gaia","model":"o4-mini","score":42.52,"metric":"percent"},{"benchmark":"gaia","model":"llama-3-70b-instruct","score":13.95,"metric":"percent"},{"benchmark":"gaia","model":"claude-sonnet-4","score":55.48,"metric":"percent"},{"benchmark":"gaia","model":"qwen3-32b","score":21.59,"metric":"percent"},{"benchmark":"gaia","model":"o3","score":62.13,"metric":"percent"},{"benchmark":"gaia","model":"gemini-2.5-flash","score":58.8,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5","score":78.41,"metric":"percent"},{"benchmark":"gaia","model":"gemini-2.0-flash","score":6.31,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-v3.1","score":27.91,"metric":"percent"},{"benchmark":"gaia","model":"claude-sonnet-4.5","score":73.42,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.1","score":75.75,"metric":"percent"},{"benchmark":"gaia","model":"gemini-3-pro","score":78.07,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.2","score":86.05,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-v3.2","score":37.21,"metric":"percent"},{"benchmark":"gaia","model":"qwen2.5-coder-14b-instruct","score":9.3,"metric":"percent"},{"benchmark":"gaia","model":"claude-opus-4.5","score":74.09,"metric":"percent"},{"benchmark":"gaia","model":"gemini-3-flash","score":68.44,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.4","score":84.72,"metric":"percent"},{"benchmark":"gaia","model":"mistral-small-4","score":17.61,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-v4-pro","score":74.75,"metric":"percent"},{"benchmark":"gaia","model":"glm-5.1","score":68.77,"metric":"percent"},{"benchmark":"gaia","model":"gemini-3.1-pro","score":55.48,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.5","score":91.69,"metric":"percent"},{"benchmark":"gaia","model":"qwen3.5-9b","score":13.95,"metric":"percent"},{"benchmark":"gaia","model":"gemini-3.5-flash","score":24.92,"metric":"percent"},{"benchmark":"gaia","model":"qwen3.6-35b-a3b","score":56.15,"metric":"percent"},{"benchmark":"gaia","model":"claude-sonnet-4.6","score":54.49,"metric":"percent"},{"benchmark":"gaia","model":"claude-4.5-haiku","score":23.59,"metric":"percent"},{"benchmark":"gaia","model":"glm-5.2","score":89.04,"metric":"percent"},{"benchmark":"gaia","model":"claude-opus-4.8","score":88.7,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-v4-flash","score":69.1,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.6-sol","score":77.41,"metric":"percent"},{"benchmark":"gaia","model":"qwen3-next-80b-a3b-instruct","score":33.22,"metric":"percent"},{"benchmark":"gaia","model":"deepseek-v4-flash-0731","score":66.45,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.4-mini","score":64.45,"metric":"percent"},{"benchmark":"gaia","model":"qwen3.8-27b-nvfp4","score":62.79,"metric":"percent"},{"benchmark":"gaia","model":"k-exaone-2.0","score":23.26,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.6-terra","score":71.76,"metric":"percent"},{"benchmark":"gaia","model":"glm-5.3-flash","score":43.85,"metric":"percent"},{"benchmark":"gaia","model":"gpt-5.6-luna","score":60.8,"metric":"percent"},{"benchmark":"gaia","model":"kimi-k3","score":80.4,"metric":"percent"},{"benchmark":"gaia","model":"gpt-6.1-sol","score":86.38,"metric":"percent"},{"benchmark":"gaia","model":"qwen3.8-27b","score":35.55,"metric":"percent"},{"benchmark":"gaia","model":"claude-haiku-5.5","score":37.21,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5.2-high","score":57.5,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-medium","score":52.6,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-high","score":51.6,"metric":"percent"},{"benchmark":"mcpmark","model":"gemini-3-pro-low","score":50.8,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-low","score":46.9,"metric":"percent"},{"benchmark":"mcpmark","model":"deepseek-v3.2-thinking","score":36.8,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-sonnet-4.5","score":32.1,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-mini-high","score":30.3,"metric":"percent"},{"benchmark":"mcpmark","model":"deepseek-v3.2","score":29.7,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-sonnet-4-high","score":28.3,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-sonnet-4","score":28.1,"metric":"percent"},{"benchmark":"mcpmark","model":"claude-sonnet-4-low","score":27.4,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-mini-medium","score":27.4,"metric":"percent"},{"benchmark":"mcpmark","model":"grok-4-fast","score":24,"metric":"percent"},{"benchmark":"mcpmark","model":"kimi-k2-0905-preview","score":21.9,"metric":"percent"},{"benchmark":"mcpmark","model":"deepseek-v3.1-terminus-thinking","score":21.3,"metric":"percent"},{"benchmark":"mcpmark","model":"kimi-k2-0711-preview","score":19.1,"metric":"percent"},{"benchmark":"mcpmark","model":"deepseek-v3.1","score":16.7,"metric":"percent"},{"benchmark":"mcpmark","model":"deepseek-v3.1-terminus","score":16.5,"metric":"percent"},{"benchmark":"mcpmark","model":"gemini-2.5-pro","score":15.8,"metric":"percent"},{"benchmark":"mcpmark","model":"glm-4.5","score":15.6,"metric":"percent"},{"benchmark":"mcpmark","model":"gemini-2.5-flash","score":9.1,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-mini-low","score":8.3,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-4.1","score":8.1,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-nano-medium","score":6.3,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-nano-high","score":5.1,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-oss-120b","score":4.7,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-5-nano-low","score":4.3,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-4.1-mini","score":3.9,"metric":"percent"},{"benchmark":"mcpmark","model":"gpt-4.1-nano","score":0,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"kimi-k3","score":96.06,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"gpt-5.5","score":92.91,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"gpt-5.6-sol","score":92.91,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"claude-fable-5","score":86.61,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"kimi-k2.7-code","score":81.89,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"claude-opus-4.8","score":76.38,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"kimi-k2.6-thinking","score":72.83,"metric":"percent"},{"benchmark":"mcpmark-verified","model":"deepseek-v4-pro-thinking-max","score":71.65,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-sonnet-4-thinking","score":31.6,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-sonnet-4","score":32.9,"metric":"percent"},{"benchmark":"mcp-universe","model":"grok-4-fast","score":32.47,"metric":"percent"},{"benchmark":"mcp-universe","model":"o3-medium","score":31.6,"metric":"percent"},{"benchmark":"mcp-universe","model":"gpt-4.1","score":19.91,"metric":"percent"},{"benchmark":"mcp-universe","model":"glm-4.6","score":25.97,"metric":"percent"},{"benchmark":"mcp-universe","model":"deepseek-v3.2-exp","score":19.91,"metric":"percent"},{"benchmark":"mcp-universe","model":"gemini-3-pro-preview","score":44.59,"metric":"percent"},{"benchmark":"mcp-universe","model":"grok-4.1-fast","score":40.69,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-sonnet-4.5","score":35.06,"metric":"percent"},{"benchmark":"mcp-universe","model":"kimi-k2-thinking","score":26.41,"metric":"percent"},{"benchmark":"mcp-universe","model":"claude-4.5-haiku","score":26.41,"metric":"percent"},{"benchmark":"mcp-universe","model":"gpt-oss-120b","score":31.17,"metric":"percent"},{"benchmark":"mcp-universe","model":"gpt-oss-20b","score":24.24,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"claude-opus-5","score":70.19,"metric":"percent"},{"benchmark":"osworld-2.0-offline","model":"gpt-5.6-sol","score":64.13,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-fable-5","score":37.27,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-fable-5.1","score":44.65,"metric":"percent"},{"benchmark":"posttrainbench","model":"glm-5.2","score":30.4,"metric":"percent"},{"benchmark":"posttrainbench","model":"glm-5.3","score":34.52,"metric":"percent"},{"benchmark":"posttrainbench","model":"glm-5.3-flash","score":36.79,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.4","score":17.76,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.5","score":23.87,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-5.6-sol","score":31.01,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-6-astra","score":41.88,"metric":"percent"},{"benchmark":"posttrainbench","model":"gpt-6.1-sol","score":38.79,"metric":"percent"},{"benchmark":"posttrainbench","model":"gemini-3.1-pro","score":18.11,"metric":"percent"},{"benchmark":"posttrainbench","model":"grok-4.5","score":22.62,"metric":"percent"},{"benchmark":"posttrainbench","model":"kimi-k3","score":31.48,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-4.7","score":24.34,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-4.8","score":31,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-5","score":35.66,"metric":"percent"},{"benchmark":"posttrainbench","model":"claude-opus-5.5","score":43.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-sonnet-4.5","score":64.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4.1","score":58.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-sonnet-4","score":54.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5","score":52.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"claude-opus-4","score":45.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5-codex","score":42.8,"metric":"percent"},{"benchmark":"terminal-bench","model":"minimax-m2","score":42,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-coder-480b-a35b-instruct","score":39,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-4","score":39,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-4.1","score":35,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-4-fast","score":31.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"grok-3-beta","score":17.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"llama-4-maverick","score":15.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-32b","score":15.5,"metric":"percent"},{"benchmark":"terminal-bench","model":"gpt-5-nano","score":12.2,"metric":"percent"},{"benchmark":"terminal-bench","model":"codex-mini-latest","score":11.3,"metric":"percent"},{"benchmark":"terminal-bench","model":"qwen3-235b-a22b","score":6.6,"metric":"percent"},{"benchmark":"terminal-bench","model":"deepseek-r1","score":5.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.5","score":84.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3.1-pro","score":80.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.7","score":80.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.3-codex","score":78.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.6","score":76.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-pro","score":69.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2-codex","score":66.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.2","score":64.9,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gemini-3-flash","score":64.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-opus-4.5","score":63.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1-codex-mini","score":61.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5.1-codex","score":57.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"grok-4.2","score":57.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-sonnet-4.6","score":53.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"glm-5","score":52.4,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-sonnet-4.5","score":46.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"minimax-m2.7","score":45.1,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"kimi-k2.5","score":43.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"minimax-m2.5","score":42.7,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"deepseek-v3.2","score":39.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"minimax-m2.1","score":36.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"claude-4.5-haiku","score":35.5,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5-mini","score":34.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3-coder-480b-a35b-instruct","score":27.2,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.6-35b-a3b","score":24.6,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"gpt-5-nano","score":21.8,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"termigen-32b","score":19.3,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"afterquery-gpt-oss-20b","score":17,"metric":"percent"},{"benchmark":"terminal-bench-2.0","model":"qwen3.5-9b","score":9.2,"metric":"percent"},{"benchmark":"vals-index","model":"claude-sonnet-5.5","score":67.04,"metric":"percent"},{"benchmark":"vals-index","model":"claude-opus-5.5","score":66.97,"metric":"percent"},{"benchmark":"vals-index","model":"claude-fable-5.1","score":65.83,"metric":"percent"},{"benchmark":"vals-index","model":"muse-wonder-full","score":64.57,"metric":"percent"},{"benchmark":"vals-index","model":"claude-opus-5","score":63.67,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-6-astra","score":63.12,"metric":"percent"},{"benchmark":"vals-index","model":"claude-fable-5","score":61.39,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-6.1-sol","score":61.15,"metric":"percent"},{"benchmark":"vals-index","model":"muse-wonder","score":61.06,"metric":"percent"},{"benchmark":"vals-index","model":"muse-spark-1.3","score":58.16,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-5.6-sol","score":58.01,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-6-sol","score":57.54,"metric":"percent"},{"benchmark":"vals-index","model":"mimo-v2.6-pro","score":55.2,"metric":"percent"},{"benchmark":"vals-index","model":"claude-opus-4.8","score":55.1,"metric":"percent"},{"benchmark":"vals-index","model":"grok-4.7","score":54.95,"metric":"percent"},{"benchmark":"vals-index","model":"gemini-3.8-flash","score":54.89,"metric":"percent"},{"benchmark":"vals-index","model":"claude-haiku-5.5","score":54.44,"metric":"percent"},{"benchmark":"vals-index","model":"glm-5.3","score":53.51,"metric":"percent"},{"benchmark":"vals-index","model":"mimo-v2.6-flash","score":53.23,"metric":"percent"},{"benchmark":"vals-index","model":"muse-spark-1.3-xhigh","score":53.2,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-5.6-terra","score":53.09,"metric":"percent"},{"benchmark":"vals-index","model":"grok-4.6","score":52.09,"metric":"percent"},{"benchmark":"vals-index","model":"claude-sonnet-5","score":51.9,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-5.6-luna","score":51.69,"metric":"percent"},{"benchmark":"vals-index","model":"deepseek-v4.1-flash-high","score":51.32,"metric":"percent"},{"benchmark":"vals-index","model":"gemini-3.7-flash","score":51.27,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-6-luna","score":51.22,"metric":"percent"},{"benchmark":"vals-index","model":"ember-1","score":50.94,"metric":"percent"},{"benchmark":"vals-index","model":"kimi-k3","score":50.3,"metric":"percent"},{"benchmark":"vals-index","model":"hy4-preview","score":49.94,"metric":"percent"},{"benchmark":"vals-index","model":"step-5-preview","score":49.35,"metric":"percent"},{"benchmark":"vals-index","model":"muse-spark-1.2","score":49.29,"metric":"percent"},{"benchmark":"vals-index","model":"mistral-large-4","score":48.66,"metric":"percent"},{"benchmark":"vals-index","model":"qwen3.8-max","score":48.27,"metric":"percent"},{"benchmark":"vals-index","model":"deepseek-v4-flash-0731-high","score":47.96,"metric":"percent"},{"benchmark":"vals-index","model":"deepseek-v4-pro-0813","score":47.63,"metric":"percent"},{"benchmark":"vals-index","model":"muse-spark-open","score":46.61,"metric":"percent"},{"benchmark":"vals-index","model":"gemini-3.5-flash","score":44.79,"metric":"percent"},{"benchmark":"vals-index","model":"grok-4.5","score":44.72,"metric":"percent"},{"benchmark":"vals-index","model":"glm-5.3-flash","score":44.58,"metric":"percent"},{"benchmark":"vals-index","model":"deepseek-v4-pro-thinking-max","score":38.63,"metric":"percent"},{"benchmark":"vals-index","model":"minimax-m3","score":36.53,"metric":"percent"},{"benchmark":"vals-index","model":"mimo-v2.5-pro","score":33.84,"metric":"percent"},{"benchmark":"vals-index","model":"gemini-3.1-pro","score":33.44,"metric":"percent"},{"benchmark":"vals-index","model":"gpt-5.4-mini","score":33.17,"metric":"percent"},{"benchmark":"vals-index","model":"inkling","score":28.67,"metric":"percent"},{"benchmark":"vals-index","model":"inkling-small","score":25.46,"metric":"percent"},{"benchmark":"vals-index","model":"mercury-2.5","score":8.86,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-4.3","score":79.31,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5.1-high","score":73.42,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-4.1","score":69.88,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5-mini-high","score":68.49,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-opus-4.7","score":68.38,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5-high","score":66.45,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5.5","score":66.24,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5.2-thinking-xhigh","score":66.02,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-4-0709","score":65.81,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-4-fast-thinking","score":65.7,"metric":"percent"},{"benchmark":"caselaw-v2","model":"kimi-k2-thinking","score":65.7,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gemini-3.1-pro","score":64.84,"metric":"percent"},{"benchmark":"caselaw-v2","model":"command-a-03-2025","score":64.52,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-sonnet-4.6","score":63.99,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gemini-2.5-pro","score":63.88,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5.4","score":63.77,"metric":"percent"},{"benchmark":"caselaw-v2","model":"muse-spark","score":63.13,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-opus-4.5-thinking","score":62.59,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-4.5-sonnet-thinking","score":62.16,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-opus-4.6","score":62.06,"metric":"percent"},{"benchmark":"caselaw-v2","model":"mistral-large-3","score":61.41,"metric":"percent"},{"benchmark":"caselaw-v2","model":"kimi-k2.6","score":61.2,"metric":"percent"},{"benchmark":"caselaw-v2","model":"minimax-m2.7","score":60.88,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-4.1-fast","score":60.45,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-4o-2024-11-20","score":59.7,"metric":"percent"},{"benchmark":"caselaw-v2","model":"qwen3.5-plus-thinking","score":59.7,"metric":"percent"},{"benchmark":"caselaw-v2","model":"deepseek-v4-pro-thinking-max","score":59.38,"metric":"percent"},{"benchmark":"caselaw-v2","model":"kimi-k2.5-thinking","score":58.73,"metric":"percent"},{"benchmark":"caselaw-v2","model":"trinity-large-thinking","score":57.88,"metric":"percent"},{"benchmark":"caselaw-v2","model":"claude-4.5-haiku-thinking","score":56.48,"metric":"percent"},{"benchmark":"caselaw-v2","model":"qwen3.5-flash","score":55.95,"metric":"percent"},{"benchmark":"caselaw-v2","model":"minimax-m2.1","score":55.84,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gemini-3-flash-preview","score":55.84,"metric":"percent"},{"benchmark":"caselaw-v2","model":"deepseek-v3.2-thinking","score":55.41,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gemini-3.1-flash-lite","score":54.98,"metric":"percent"},{"benchmark":"caselaw-v2","model":"qwen3-max-thinking","score":54.98,"metric":"percent"},{"benchmark":"caselaw-v2","model":"glm-4.7","score":54.88,"metric":"percent"},{"benchmark":"caselaw-v2","model":"grok-4.2-0309","score":54.45,"metric":"percent"},{"benchmark":"caselaw-v2","model":"deepseek-v3.1","score":53.91,"metric":"percent"},{"benchmark":"caselaw-v2","model":"minimax-m2.5","score":53.48,"metric":"percent"},{"benchmark":"caselaw-v2","model":"qwen3.6-27b","score":53.16,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gemini-3-pro-preview","score":53.05,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gemma-4-31b-it","score":52.63,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5-nano-high","score":52.63,"metric":"percent"},{"benchmark":"caselaw-v2","model":"glm-5","score":52.52,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5.4-nano-high","score":51.88,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-5.4-mini","score":51.66,"metric":"percent"},{"benchmark":"caselaw-v2","model":"glm-5.1","score":51.55,"metric":"percent"},{"benchmark":"caselaw-v2","model":"qwen3.6-plus","score":51.45,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-oss-120b","score":48.77,"metric":"percent"},{"benchmark":"caselaw-v2","model":"qwen3.6-max-preview","score":47.91,"metric":"percent"},{"benchmark":"caselaw-v2","model":"qwen3-max","score":47.48,"metric":"percent"},{"benchmark":"caselaw-v2","model":"mistral-medium-3.5","score":44.16,"metric":"percent"},{"benchmark":"caselaw-v2","model":"gpt-oss-20b","score":43.84,"metric":"percent"},{"benchmark":"gsm8k","model":"mimo-v2.5-pro","score":99.6,"metric":"percent"},{"benchmark":"gsm8k","model":"o1-2024-12-17","score":97.1,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-405b-instruct","score":96.8,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3.5-sonnet-20240620","score":96.4,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3.5-sonnet-20241022","score":96.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-27b-it","score":95.9,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3-opus-20240229","score":95,"metric":"percent"},{"benchmark":"gsm8k","model":"nova-pro","score":94.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-14b-instruct","score":94.8,"metric":"percent"},{"benchmark":"gsm8k","model":"nova-lite","score":94.5,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-12b-it","score":94.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3-235b-a22b","score":94.39,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-large-2407","score":93,"metric":"percent"},{"benchmark":"gsm8k","model":"nova-micro","score":92.3,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3-sonnet-20240229","score":92.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-7b-instruct","score":91.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-nemotron-70b-instruct","score":91.43,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-72b-instruct","score":91.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-32b-instruct","score":91.1,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-1.5-pro","score":90.8,"metric":"percent"},{"benchmark":"gsm8k","model":"grok-1.5","score":90,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-4b-it","score":89.2,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3-haiku-20240307","score":88.9,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3.5-moe-instruct","score":88.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-omni-7b","score":88.7,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-4-mini","score":88.6,"metric":"percent"},{"benchmark":"gsm8k","model":"jamba-1.5-large","score":87,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3.5-mini-instruct","score":86.2,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-1.5-flash","score":86.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-7b-instruct","score":83.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-7b-instruct","score":82.3,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-small-3-24b-base","score":80.73,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.2-3b-instruct","score":77.7,"metric":"percent"},{"benchmark":"gsm8k","model":"jamba-1.5-mini","score":75.8,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-27b-it","score":74,"metric":"percent"},{"benchmark":"gsm8k","model":"command-r-plus","score":70.7,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-4.0-tiny-preview","score":70.1,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-9b-it","score":68.6,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-3-1b-it","score":62.8,"metric":"percent"},{"benchmark":"gsm8k","model":"granite-3.3-8b-base","score":59,"metric":"percent"},{"benchmark":"gsm8k","model":"ernie-4.5","score":25.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.3-nemotron-49b-super-v1","score":91.3,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-72b-instruct","score":88.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-vl-32b-instruct","score":84,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-32b-instruct","score":84,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-14b-instruct","score":82,"metric":"percent"},{"benchmark":"mbpp","model":"qwen3-235b-a22b","score":81.4,"metric":"percent"},{"benchmark":"mbpp","model":"phi-3.5-moe-instruct","score":80.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-72b-instruct","score":80.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-7b-instruct","score":79.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-4-maverick","score":77.6,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-diffusion","score":76,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-small-3.1-24b-instruct-2503","score":74.71,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-27b-it","score":74.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-omni-7b","score":73.2,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-12b-it","score":73,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-small-3-24b-base","score":69.64,"metric":"percent"},{"benchmark":"mbpp","model":"phi-3.5-mini-instruct","score":69.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-4-scout","score":67.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-7b-instruct","score":67.2,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3n-e4b-instructed-litert-preview","score":63.6,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3n-e4b-it","score":63.6,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-4b-it","score":63.2,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-27b-it","score":62.6,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3n-e2b-it","score":56.6,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3n-e2b-instructed-litert-preview","score":56.6,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-9b-it","score":52.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-3-1b-it","score":35.2,"metric":"percent"},{"benchmark":"humaneval","model":"o1-mini","score":92.4,"metric":"percent"},{"benchmark":"humaneval","model":"o1-preview","score":92.4,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3.5-sonnet-20240620","score":92,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o","score":90.2,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-diffusion","score":89.6,"metric":"percent"},{"benchmark":"humaneval","model":"grok-2","score":88.4,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3.5-haiku","score":88.1,"metric":"percent"},{"benchmark":"humaneval","model":"grok-2-mini","score":85.7,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3-opus","score":84.9,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v3","score":82.6,"metric":"percent"},{"benchmark":"codeforces","model":"o1","score":1673,"metric":"ELO"},{"benchmark":"lmarena-text","model":"gemini-4-argon-high","score":1524,"metric":"elo"},{"benchmark":"lmarena-text","model":"muse-wonder-max","score":1509,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-5.5-high","score":1508,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-fable-5-high","score":1504,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.6-high","score":1503,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-fable-5.1-max","score":1502,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.7-high","score":1501,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.6","score":1497,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3.8-flash-high","score":1496,"metric":"elo"},{"benchmark":"lmarena-text","model":"muse-spark-1.3-max","score":1494,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.7","score":1494,"metric":"elo"},{"benchmark":"lmarena-text","model":"muse-spark-1.2-xhigh","score":1493,"metric":"elo"},{"benchmark":"lmarena-text","model":"muse-spark-1.1","score":1490,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-5-max","score":1490,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-5-high","score":1490,"metric":"elo"},{"benchmark":"lmarena-text","model":"muse-spark","score":1489,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3.7-flash-high","score":1488,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k3-max","score":1487,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3.1-pro","score":1487,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3-pro","score":1485,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.6-sol-xhigh","score":1485,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-6.1-sol-max","score":1484,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3.6-flash-high","score":1483,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.8-max","score":1482,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.8-high","score":1481,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.5-high","score":1481,"metric":"elo"},{"benchmark":"lmarena-text","model":"mimo-v2.6-pro","score":1479,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-5.3-max","score":1479,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3.5-flash-high","score":1477,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-6-astra-max","score":1477,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.5","score":1477,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-5.2-max","score":1476,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3.5-flash-medium","score":1476,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.2-instant","score":1476,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.4-high","score":1475,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-sonnet-5.5-xhigh","score":1475,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.2-beta1","score":1475,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v4.1-flash-max","score":1475,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.7-max-preview","score":1474,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.8","score":1474,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-5.3-flash","score":1474,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.5-thinking-32k","score":1474,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.5-instant","score":1473,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3-flash","score":1473,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-sonnet-4.6","score":1472,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.2","score":1472,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.2-multi-agent","score":1470,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.5","score":1470,"metric":"elo"},{"benchmark":"lmarena-text","model":"mimo-v2.5-pro","score":1467,"metric":"elo"},{"benchmark":"lmarena-text","model":"ernie-5.1","score":1467,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.6-terra-xhigh","score":1466,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.5","score":1466,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.1-thinking","score":1465,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-5.1","score":1465,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.4","score":1465,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v4-pro-0813-high","score":1465,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.5-max-preview","score":1464,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-sonnet-5-high","score":1461,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k2.6","score":1461,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.6-max-preview","score":1461,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-6-sol-max","score":1459,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.1","score":1459,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3-flash-minimal","score":1458,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v4-pro","score":1458,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-5","score":1457,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-4.5-sonnet-thinking-32k","score":1456,"metric":"elo"},{"benchmark":"lmarena-text","model":"seed2.0-pro","score":1456,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.1-high","score":1456,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.7-plus","score":1456,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-sonnet-4.5","score":1455,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v4-pro-preview-high","score":1455,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3.5-flash-lite","score":1455,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.6-high","score":1454,"metric":"elo"},{"benchmark":"lmarena-text","model":"hy3","score":1453,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.6-luna-xhigh","score":1453,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-4-31b-it","score":1452,"metric":"elo"},{"benchmark":"lmarena-text","model":"mimo-v2.6-flash","score":1451,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.3-instant","score":1450,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k2.5-thinking","score":1450,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4-1-20250805-thinking-16k","score":1450,"metric":"elo"},{"benchmark":"lmarena-text","model":"ernie-5.0-preview-1203","score":1449,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4.1-20250805","score":1448,"metric":"elo"},{"benchmark":"lmarena-text","model":"mimo-v2-pro","score":1448,"metric":"elo"},{"benchmark":"lmarena-text","model":"step-5-preview","score":1447,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.4-mini-high","score":1447,"metric":"elo"},{"benchmark":"lmarena-text","model":"ernie-5.0","score":1446,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.5-pro","score":1445,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4.5-preview-2025-02-27","score":1445,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.7-xhigh","score":1444,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.6-plus","score":1443,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-6-luna-max","score":1443,"metric":"elo"},{"benchmark":"lmarena-text","model":"chatgpt-4o-latest-20250326","score":1443,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.3","score":1442,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.5-397b-a17b","score":1442,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.7","score":1441,"metric":"elo"},{"benchmark":"lmarena-text","model":"minimax-m3","score":1441,"metric":"elo"},{"benchmark":"lmarena-text","model":"inkling","score":1441,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v4-flash-preview-high","score":1439,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.1","score":1439,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.8-27b","score":1438,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-4-26b-a4b","score":1438,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.2-high","score":1437,"metric":"elo"},{"benchmark":"lmarena-text","model":"longcat-flash-chat-2602-exp","score":1436,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v4-flash","score":1436,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.2","score":1435,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5-high","score":1435,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-max-preview","score":1434,"metric":"elo"},{"benchmark":"lmarena-text","model":"mimo-v2.5","score":1434,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-5v-turbo","score":1434,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-3.1-flash-lite","score":1433,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-large-4","score":1432,"metric":"elo"},{"benchmark":"lmarena-text","model":"o3-2025-04-16","score":1432,"metric":"elo"},{"benchmark":"lmarena-text","model":"mimo-v2-omni","score":1431,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k2.5","score":1431,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4.1-fast-thinking","score":1430,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k2-thinking","score":1430,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-medium-3.5","score":1426,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4-20250514-thinking-16k","score":1426,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-experimental-chat-26-02-10","score":1426,"metric":"elo"},{"benchmark":"lmarena-text","model":"nemotron-3-ultra","score":1426,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.2-exp-thinking","score":1425,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.2","score":1425,"metric":"elo"},{"benchmark":"lmarena-text","model":"muse-glimmer-30b","score":1425,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.6","score":1424,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-max-2025-09-23","score":1423,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.2-thinking","score":1422,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-235b-a22b-instruct-2507","score":1422,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.2-exp","score":1422,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-r1-0528","score":1421,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4-fast","score":1419,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k2-0905-preview","score":1419,"metric":"elo"},{"benchmark":"lmarena-text","model":"ernie-5.0-preview-1022","score":1418,"metric":"elo"},{"benchmark":"lmarena-text","model":"kimi-k2-0711-preview","score":1418,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.1","score":1417,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.5-122b-a10b","score":1416,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.1-terminus-thinking","score":1416,"metric":"elo"},{"benchmark":"lmarena-text","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":1416,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3.1-thinking","score":1416,"metric":"elo"},{"benchmark":"lmarena-text","model":"minimax-m2.7","score":1415,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4.1-2025-04-14","score":1415,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-opus-4-20250514","score":1414,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-4.5-haiku","score":1414,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-large-3","score":1414,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-vl-235b-a22b-instruct","score":1413,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-experimental-chat-26-01-10","score":1413,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-3-preview-02-24","score":1411,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4-0709","score":1411,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.5","score":1411,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.5-flash","score":1409,"metric":"elo"},{"benchmark":"lmarena-text","model":"hy3-preview","score":1409,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.5-27b","score":1409,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-4-fast-thinking","score":1405,"metric":"elo"},{"benchmark":"lmarena-text","model":"inkling-small","score":1404,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.5-flash-preview-09-2025","score":1403,"metric":"elo"},{"benchmark":"lmarena-text","model":"o1-2024-12-17","score":1402,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-235b-a22b-no-thinking","score":1402,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-sonnet-4-20250514-thinking-32k","score":1402,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5.4-nano-high","score":1401,"metric":"elo"},{"benchmark":"lmarena-text","model":"longcat-flash-chat","score":1401,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-235b-a22b-thinking-2507","score":1400,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-next-80b-a3b-instruct","score":1399,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-r1","score":1398,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.5-flash","score":1396,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3-0324","score":1395,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-vl-235b-a22b-thinking","score":1395,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3.5-35b-a3b","score":1394,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-vision-1.5-thinking","score":1394,"metric":"elo"},{"benchmark":"lmarena-text","model":"step-3.5-flash-20260204","score":1393,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-experimental-chat-12-10","score":1393,"metric":"elo"},{"benchmark":"lmarena-text","model":"mimo-v2-flash","score":1392,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-sonnet-4-20250514","score":1391,"metric":"elo"},{"benchmark":"lmarena-text","model":"minimax-m2.5","score":1391,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5-mini-high","score":1390,"metric":"elo"},{"benchmark":"lmarena-text","model":"o1-preview","score":1389,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3-7-sonnet-20250219-thinking-32k","score":1388,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-coder-480b-a35b-instruct","score":1388,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-medium-2505","score":1387,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-t1-20250711","score":1387,"metric":"elo"},{"benchmark":"lmarena-text","model":"solar-pro-4","score":1386,"metric":"elo"},{"benchmark":"lmarena-text","model":"mimo-v2-flash-thinking","score":1386,"metric":"elo"},{"benchmark":"lmarena-text","model":"minimax-m2.1","score":1384,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-turbos-20250416","score":1383,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4.1-mini-2025-04-14","score":1383,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-30b-a3b-instruct-2507","score":1382,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.5-flash-lite-preview-09-2025","score":1379,"metric":"elo"},{"benchmark":"lmarena-text","model":"trinity-large-preview","score":1379,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.6v","score":1378,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-235b-a22b","score":1375,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.5-flash-lite-preview-thinking","score":1375,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3.5-sonnet-20241022","score":1374,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2.5-max","score":1374,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.5-air","score":1373,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3.7-sonnet-20250219","score":1373,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-next-80b-a3b-thinking","score":1369,"metric":"elo"},{"benchmark":"lmarena-text","model":"trinity-large-thinking","score":1367,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-3-27b-it","score":1365,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.7-flash","score":1365,"metric":"elo"},{"benchmark":"lmarena-text","model":"minimax-m1","score":1364,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-experimental-chat-11-10","score":1364,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-3-mini-high","score":1364,"metric":"elo"},{"benchmark":"lmarena-text","model":"o3-mini-high","score":1364,"metric":"elo"},{"benchmark":"lmarena-text","model":"nemotron-3-super-120b-a12b","score":1360,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.0-flash-001","score":1360,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v3","score":1358,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-3-mini-beta","score":1358,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-small-2506","score":1356,"metric":"elo"},{"benchmark":"lmarena-text","model":"intellect-3","score":1356,"metric":"elo"},{"benchmark":"lmarena-text","model":"command-a-03-2025","score":1354,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-2.0-flash-lite-preview-02-05","score":1354,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4.5v","score":1352,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-oss-120b","score":1352,"metric":"elo"},{"benchmark":"lmarena-text","model":"nemotron-3.5-lightning-30b-a3b","score":1351,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-pro-002","score":1351,"metric":"elo"},{"benchmark":"lmarena-text","model":"step-3","score":1349,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-turbos-20250226","score":1349,"metric":"elo"},{"benchmark":"lmarena-text","model":"o3-mini","score":1348,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-experimental-chat-10-20","score":1348,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-nemotron-ultra-253b-v1","score":1348,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-32b","score":1347,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-experimental-chat-10-09","score":1346,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4o-2024-05-13","score":1346,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen-plus-0125","score":1346,"metric":"elo"},{"benchmark":"lmarena-text","model":"minimax-m2","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3.5-sonnet-20240620","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"ling-flash-2.0","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"mercury-2","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"nvidia-llama-3.3-nemotron-super-49b-v1.5","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4-plus-0111","score":1343,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-3-12b-it","score":1342,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-turbo-0110","score":1341,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-4.2-30b","score":1340,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-5-nano-high","score":1338,"metric":"elo"},{"benchmark":"lmarena-text","model":"o1-mini","score":1337,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-advanced-0514","score":1336,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-2-2024-08-13","score":1336,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4o-2024-08-06","score":1336,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwq-32b","score":1336,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-405b-instruct-bf16","score":1335,"metric":"elo"},{"benchmark":"lmarena-text","model":"nova-2-lite","score":1335,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-405b-instruct-fp8","score":1334,"metric":"elo"},{"benchmark":"lmarena-text","model":"step-2-16k-exp-202412","score":1333,"metric":"elo"},{"benchmark":"lmarena-text","model":"olmo-3.1-instruct-32b","score":1329,"metric":"elo"},{"benchmark":"lmarena-text","model":"yi-lightning","score":1328,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.3-nemotron-49b-super-v1","score":1328,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-4-maverick-17b-128e-instruct","score":1327,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen3-30b-a3b","score":1327,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-large-2025-02-10","score":1326,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3.5-haiku-20241022","score":1325,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-turbo-2024-04-09","score":1325,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-pro-001","score":1324,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v2.5-1210","score":1323,"metric":"elo"},{"benchmark":"lmarena-text","model":"ring-flash-2.0","score":1323,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3-opus-20240229","score":1322,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4.1-nano-2025-04-14","score":1322,"metric":"elo"},{"benchmark":"lmarena-text","model":"molmo2-8b","score":1322,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-4-scout-17b-16e-instruct","score":1322,"metric":"elo"},{"benchmark":"lmarena-text","model":"step-1o-turbo-202506","score":1320,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4-plus","score":1319,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen-max-0919","score":1318,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.3-70b-instruct","score":1318,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4o-mini-2024-07-18","score":1318,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-oss-20b","score":1317,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2.5-plus-1127","score":1315,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-large-2407","score":1314,"metric":"elo"},{"benchmark":"lmarena-text","model":"athene-v2-chat","score":1314,"metric":"elo"},{"benchmark":"lmarena-text","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":1314,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-0125-preview","score":1313,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-standard-2025-02-10","score":1311,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-flash-002","score":1309,"metric":"elo"},{"benchmark":"lmarena-text","model":"grok-2-mini-2024-08-13","score":1308,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-v2.5","score":1307,"metric":"elo"},{"benchmark":"lmarena-text","model":"athene-70b-0725","score":1307,"metric":"elo"},{"benchmark":"lmarena-text","model":"olmo-3-think-32b","score":1306,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-large-2411","score":1306,"metric":"elo"},{"benchmark":"lmarena-text","model":"mercury","score":1305,"metric":"elo"},{"benchmark":"lmarena-text","model":"magistral-medium-2506","score":1305,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-4.1-8b","score":1304,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-3-4b-it","score":1303,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2.5-72b-instruct","score":1303,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-small-3.1-24b-instruct-2503","score":1303,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-nemotron-70b-instruct","score":1299,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-large-vision","score":1294,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-70b-instruct","score":1293,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-4.2-8b","score":1290,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-pro-v1.0","score":1290,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-4.2-3b","score":1290,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2-27b-it","score":1290,"metric":"elo"},{"benchmark":"lmarena-text","model":"jamba-1.5-large","score":1289,"metric":"elo"},{"benchmark":"lmarena-text","model":"reka-core-20240904","score":1288,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-0314","score":1288,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-4.0-h-small","score":1287,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-nemotron-51b-instruct","score":1287,"metric":"elo"},{"benchmark":"lmarena-text","model":"olmo-3.1-think-32b","score":1287,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-flash-001","score":1287,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-tulu-3-70b","score":1286,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3-sonnet-20240229","score":1281,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2-9b-it-simpo","score":1280,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3-70b-instruct","score":1277,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-4-0613","score":1276,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-small-24b-instruct-2501","score":1274,"metric":"elo"},{"benchmark":"lmarena-text","model":"glm-4-0520","score":1273,"metric":"elo"},{"benchmark":"lmarena-text","model":"reka-flash-20240904","score":1272,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2.5-coder-32b-instruct","score":1271,"metric":"elo"},{"benchmark":"lmarena-text","model":"c4ai-aya-expanse-32b","score":1267,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2-9b-it","score":1267,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-coder-v2","score":1265,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen2-72b-instruct","score":1262,"metric":"elo"},{"benchmark":"lmarena-text","model":"claude-3-haiku-20240307","score":1262,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-lite-v1.0","score":1260,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-1.5-flash-8b-001","score":1259,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-4","score":1256,"metric":"elo"},{"benchmark":"lmarena-text","model":"command-r-08-2024","score":1251,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-large-2402","score":1243,"metric":"elo"},{"benchmark":"lmarena-text","model":"amazon-nova-micro-v1.0","score":1241,"metric":"elo"},{"benchmark":"lmarena-text","model":"jamba-1.5-mini","score":1240,"metric":"elo"},{"benchmark":"lmarena-text","model":"ministral-8b-2410","score":1238,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-pro-dev-api","score":1237,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-110b-chat","score":1234,"metric":"elo"},{"benchmark":"lmarena-text","model":"reka-flash-21b-20240226-online","score":1234,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-72b-chat","score":1234,"metric":"elo"},{"benchmark":"lmarena-text","model":"hunyuan-standard-256k","score":1233,"metric":"elo"},{"benchmark":"lmarena-text","model":"mixtral-8x22b-instruct-v0.1","score":1230,"metric":"elo"},{"benchmark":"lmarena-text","model":"reka-flash-21b-20240226","score":1227,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-3.5-turbo-0125","score":1226,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemini-pro","score":1224,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3-8b-instruct","score":1224,"metric":"elo"},{"benchmark":"lmarena-text","model":"c4ai-aya-expanse-8b","score":1223,"metric":"elo"},{"benchmark":"lmarena-text","model":"zephyr-orpo-141b-a35b-v0.1","score":1213,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.1-8b-instruct","score":1211,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt-3.5-turbo-1106","score":1204,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2-2b-it","score":1200,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-3-medium-4k-instruct","score":1198,"metric":"elo"},{"benchmark":"lmarena-text","model":"dbrx-instruct-preview","score":1196,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-14b-chat","score":1191,"metric":"elo"},{"benchmark":"lmarena-text","model":"internlm2_5-20b-chat","score":1191,"metric":"elo"},{"benchmark":"lmarena-text","model":"deepseek-llm-67b-chat","score":1185,"metric":"elo"},{"benchmark":"lmarena-text","model":"wizardlm-70b","score":1185,"metric":"elo"},{"benchmark":"lmarena-text","model":"yi-34b-chat","score":1184,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-3.0-8b-instruct","score":1183,"metric":"elo"},{"benchmark":"lmarena-text","model":"openchat-3.5","score":1183,"metric":"elo"},{"benchmark":"lmarena-text","model":"openchat-3.5-0106","score":1183,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-1.1-7b-it","score":1183,"metric":"elo"},{"benchmark":"lmarena-text","model":"snowflake-arctic-instruct","score":1180,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-3.1-2b-instruct","score":1179,"metric":"elo"},{"benchmark":"lmarena-text","model":"openhermes-2.5-mistral-7b","score":1176,"metric":"elo"},{"benchmark":"lmarena-text","model":"vicuna-33b","score":1173,"metric":"elo"},{"benchmark":"lmarena-text","model":"starling-lm-7b-beta","score":1171,"metric":"elo"},{"benchmark":"lmarena-text","model":"starling-lm-7b-alpha","score":1168,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.2-3b-instruct","score":1167,"metric":"elo"},{"benchmark":"lmarena-text","model":"granite-3.0-2b-instruct","score":1157,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama2-70b-steerlm-chat","score":1155,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwq-32b-preview","score":1154,"metric":"elo"},{"benchmark":"lmarena-text","model":"dolphin-2.2.1-mistral-7b","score":1152,"metric":"elo"},{"benchmark":"lmarena-text","model":"mpt-30b-chat","score":1151,"metric":"elo"},{"benchmark":"lmarena-text","model":"wizardlm-13b","score":1150,"metric":"elo"},{"benchmark":"lmarena-text","model":"falcon-180b-chat","score":1148,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-7b-chat","score":1144,"metric":"elo"},{"benchmark":"lmarena-text","model":"phi-3-mini-4k-instruct-june-2024","score":1143,"metric":"elo"},{"benchmark":"lmarena-text","model":"vicuna-13b","score":1142,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen-14b-chat","score":1139,"metric":"elo"},{"benchmark":"lmarena-text","model":"palm-2","score":1139,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-7b-it","score":1138,"metric":"elo"},{"benchmark":"lmarena-text","model":"codellama-34b-instruct","score":1137,"metric":"elo"},{"benchmark":"lmarena-text","model":"guanaco-33b","score":1128,"metric":"elo"},{"benchmark":"lmarena-text","model":"zephyr-7b-alpha","score":1127,"metric":"elo"},{"benchmark":"lmarena-text","model":"stripedhyena-nous-7b","score":1122,"metric":"elo"},{"benchmark":"lmarena-text","model":"codellama-70b-instruct","score":1119,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-1.1-2b-it","score":1117,"metric":"elo"},{"benchmark":"lmarena-text","model":"vicuna-7b","score":1115,"metric":"elo"},{"benchmark":"lmarena-text","model":"smollm2-1.7b-instruct","score":1115,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-3.2-1b-instruct","score":1111,"metric":"elo"},{"benchmark":"lmarena-text","model":"mistral-7b-instruct","score":1110,"metric":"elo"},{"benchmark":"lmarena-text","model":"gemma-2b-it","score":1094,"metric":"elo"},{"benchmark":"lmarena-text","model":"qwen1.5-4b-chat","score":1091,"metric":"elo"},{"benchmark":"lmarena-text","model":"olmo-7b-instruct","score":1074,"metric":"elo"},{"benchmark":"lmarena-text","model":"koala-13b","score":1071,"metric":"elo"},{"benchmark":"lmarena-text","model":"alpaca-13b","score":1070,"metric":"elo"},{"benchmark":"lmarena-text","model":"gpt4all-13b-snoozy","score":1068,"metric":"elo"},{"benchmark":"lmarena-text","model":"mpt-7b-chat","score":1064,"metric":"elo"},{"benchmark":"lmarena-text","model":"chatglm3-6b","score":1057,"metric":"elo"},{"benchmark":"lmarena-text","model":"rwkv-4-raven-14b","score":1042,"metric":"elo"},{"benchmark":"lmarena-text","model":"chatglm2-6b","score":1025,"metric":"elo"},{"benchmark":"lmarena-text","model":"oasst-pythia-12b","score":1024,"metric":"elo"},{"benchmark":"lmarena-text","model":"chatglm-6b","score":996,"metric":"elo"},{"benchmark":"lmarena-text","model":"fastchat-t5-3b","score":993,"metric":"elo"},{"benchmark":"lmarena-text","model":"dolly-v2-12b","score":983,"metric":"elo"},{"benchmark":"lmarena-text","model":"llama-1-13b","score":975,"metric":"elo"},{"benchmark":"lmarena-text","model":"stablelm-tuned-alpha-7b","score":953,"metric":"elo"},{"benchmark":"lmarena-vision","model":"claude-fable-5-high","score":1308,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3.8-max","score":1301,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4.6-high","score":1299,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4.7","score":1298,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4.7-high","score":1298,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3.7-flash-high","score":1297,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4.6","score":1294,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-6.1-sol-max","score":1294,"metric":"score"},{"benchmark":"lmarena-vision","model":"muse-spark","score":1294,"metric":"score"},{"benchmark":"lmarena-vision","model":"muse-spark-1.2-xhigh","score":1293,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-5.5-high","score":1293,"metric":"score"},{"benchmark":"lmarena-vision","model":"muse-spark-1.3-max","score":1290,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3-pro","score":1289,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3.8-flash-high","score":1289,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-5-high","score":1287,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.6-sol-xhigh","score":1287,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-fable-5.1-max","score":1286,"metric":"score"},{"benchmark":"lmarena-vision","model":"muse-spark-1.3-xhigh","score":1286,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-6-astra-max","score":1286,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.5","score":1286,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4.8-high","score":1286,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3.5-flash-medium","score":1285,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.4-high","score":1285,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3.5-flash-high","score":1284,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.5-high","score":1281,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3.6-flash-high","score":1281,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4.5","score":1280,"metric":"score"},{"benchmark":"lmarena-vision","model":"muse-spark-1.1","score":1280,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3.1-pro","score":1280,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4.8","score":1279,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.4","score":1279,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.2-instant","score":1278,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.5-instant","score":1276,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-sonnet-4.6","score":1275,"metric":"score"},{"benchmark":"lmarena-vision","model":"glm-5.3-flash","score":1273,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3-flash","score":1273,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-6-sol-max","score":1270,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.6-terra-xhigh","score":1268,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-sonnet-5.5-xhigh","score":1266,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3.5-flash-lite","score":1266,"metric":"score"},{"benchmark":"lmarena-vision","model":"kimi-k2.6","score":1265,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3.7-plus","score":1264,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-sonnet-5-high","score":1263,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemma-4-31b-it","score":1262,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4.6-high","score":1262,"metric":"score"},{"benchmark":"lmarena-vision","model":"deepseek-v4.1-flash-max","score":1260,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3-flash-minimal","score":1260,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.6-luna-xhigh","score":1258,"metric":"score"},{"benchmark":"lmarena-vision","model":"seed2.0-pro","score":1256,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4.2","score":1256,"metric":"score"},{"benchmark":"lmarena-vision","model":"kimi-k2.5-thinking","score":1252,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.1-high","score":1251,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.4-mini-high","score":1251,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4.2-multi-agent","score":1250,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-5-preview","score":1250,"metric":"score"},{"benchmark":"lmarena-vision","model":"mimo-v2.6-flash","score":1248,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.5-pro","score":1248,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4.7-xhigh","score":1248,"metric":"score"},{"benchmark":"lmarena-vision","model":"mimo-v2.6-pro","score":1246,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3.5-397b-a17b","score":1246,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3.8-27b","score":1244,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.2-high","score":1243,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4.3","score":1243,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemma-4-26b-a4b","score":1242,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-6-luna-max","score":1241,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.1","score":1240,"metric":"score"},{"benchmark":"lmarena-vision","model":"chatgpt-4o-latest-20250326","score":1239,"metric":"score"},{"benchmark":"lmarena-vision","model":"kimi-k2.5","score":1236,"metric":"score"},{"benchmark":"lmarena-vision","model":"minimax-m3","score":1236,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-3.1-flash-lite","score":1235,"metric":"score"},{"benchmark":"lmarena-vision","model":"mimo-v2.5","score":1234,"metric":"score"},{"benchmark":"lmarena-vision","model":"glm-5v-turbo","score":1231,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.5-flash-preview-09-2025","score":1229,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.2","score":1229,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3.5-122b-a10b","score":1226,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5-chat","score":1226,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4.5-preview-2025-02-27","score":1225,"metric":"score"},{"benchmark":"lmarena-vision","model":"ernie-5.0-preview-1220","score":1219,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3.5-27b","score":1217,"metric":"score"},{"benchmark":"lmarena-vision","model":"mimo-v2-omni","score":1216,"metric":"score"},{"benchmark":"lmarena-vision","model":"o3-2025-04-16","score":1216,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.5-flash","score":1215,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3-vl-235b-a22b-instruct","score":1215,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4.1-2025-04-14","score":1214,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5-high","score":1210,"metric":"score"},{"benchmark":"lmarena-vision","model":"inkling-small","score":1208,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4-20250514-thinking-16k","score":1208,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-sonnet-4-20250514-thinking-32k","score":1206,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4.1-mini-2025-04-14","score":1201,"metric":"score"},{"benchmark":"lmarena-vision","model":"o4-mini-2025-04-16","score":1201,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-medium-3.5","score":1200,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-large-3","score":1200,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5.4-nano-high","score":1199,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4.1-fast-thinking","score":1196,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3-7-sonnet-20250219-thinking-32k","score":1193,"metric":"score"},{"benchmark":"lmarena-vision","model":"o1-2024-12-17","score":1193,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen3-vl-235b-a22b-thinking","score":1189,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.5-flash-lite-preview-thinking","score":1188,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-opus-4-20250514","score":1188,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-sonnet-4-20250514","score":1188,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen-vl-max-2025-08-13","score":1185,"metric":"score"},{"benchmark":"lmarena-vision","model":"grok-4-0709","score":1184,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5-mini-high","score":1183,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-pro-002","score":1179,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3.7-sonnet-20250219","score":1175,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.0-flash-001","score":1172,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4o-2024-05-13","score":1162,"metric":"score"},{"benchmark":"lmarena-vision","model":"glm-4.6v","score":1161,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3.5-sonnet-20241022","score":1160,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemma-3-27b-it","score":1160,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-medium-2508","score":1159,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-1o-turbo-202506","score":1156,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-medium-2505","score":1155,"metric":"score"},{"benchmark":"lmarena-vision","model":"hunyuan-vision-1.5-thinking","score":1155,"metric":"score"},{"benchmark":"lmarena-vision","model":"glm-4.5v","score":1153,"metric":"score"},{"benchmark":"lmarena-vision","model":"hunyuan-large-vision","score":1149,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-5-nano-high","score":1146,"metric":"score"},{"benchmark":"lmarena-vision","model":"llama-4-maverick-17b-128e-instruct","score":1145,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-3","score":1145,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3.5-sonnet-20240620","score":1145,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-flash-002","score":1141,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-small-2506","score":1140,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-2.0-flash-lite-preview-02-05","score":1136,"metric":"score"},{"benchmark":"lmarena-vision","model":"llama-4-scout-17b-16e-instruct","score":1127,"metric":"score"},{"benchmark":"lmarena-vision","model":"mistral-small-3.1-24b-instruct-2503","score":1127,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3.5-haiku-20241022","score":1127,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-1o-vision-32k-highres","score":1124,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen2.5-vl-72b-instruct","score":1121,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-pro-001","score":1120,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen2.5-vl-32b-instruct","score":1119,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4o-2024-08-06","score":1118,"metric":"score"},{"benchmark":"lmarena-vision","model":"molmo2-8b","score":1112,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4-turbo-2024-04-09","score":1112,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4o-mini-2024-07-18","score":1097,"metric":"score"},{"benchmark":"lmarena-vision","model":"pixtral-large-2411","score":1095,"metric":"score"},{"benchmark":"lmarena-vision","model":"gpt-4.1-nano-2025-04-14","score":1089,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen-vl-max-1119","score":1085,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen2-vl-72b","score":1084,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-flash-8b-001","score":1071,"metric":"score"},{"benchmark":"lmarena-vision","model":"step-1v-32k","score":1064,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3-opus-20240229","score":1061,"metric":"score"},{"benchmark":"lmarena-vision","model":"gemini-1.5-flash-001","score":1059,"metric":"score"},{"benchmark":"lmarena-vision","model":"molmo-72b-0924","score":1045,"metric":"score"},{"benchmark":"lmarena-vision","model":"hunyuan-standard-vision-2024-12-31","score":1041,"metric":"score"},{"benchmark":"lmarena-vision","model":"llama-3.2-vision-90b-instruct","score":1032,"metric":"score"},{"benchmark":"lmarena-vision","model":"qwen2-vl-7b-instruct","score":1031,"metric":"score"},{"benchmark":"lmarena-vision","model":"pixtral-12b-2409","score":1025,"metric":"score"},{"benchmark":"lmarena-vision","model":"internvl2-26b","score":1025,"metric":"score"},{"benchmark":"lmarena-vision","model":"amazon-nova-lite-v1.0","score":1019,"metric":"score"},{"benchmark":"lmarena-vision","model":"amazon-nova-pro-v1.0","score":1018,"metric":"score"},{"benchmark":"lmarena-vision","model":"yi-vision","score":1002,"metric":"score"},{"benchmark":"lmarena-vision","model":"c4ai-aya-vision-32b","score":1000,"metric":"score"},{"benchmark":"lmarena-vision","model":"claude-3-haiku-20240307","score":1000,"metric":"score"},{"benchmark":"lmarena-vision","model":"molmo-7b-d-0924","score":993,"metric":"score"},{"benchmark":"lmarena-vision","model":"llama-3.2-vision-11b-instruct","score":993,"metric":"score"},{"benchmark":"lmarena-vision","model":"nvila-internal-15b-v1","score":985,"metric":"score"},{"benchmark":"lmarena-vision","model":"llava-onevision-qwen2-72b-ov","score":978,"metric":"score"},{"benchmark":"lmarena-vision","model":"llava-1.6-34b","score":964,"metric":"score"},{"benchmark":"lmarena-vision","model":"cogvlm2-llama3-chat-19b","score":963,"metric":"score"},{"benchmark":"lmarena-vision","model":"minicpm-v-2_6","score":962,"metric":"score"},{"benchmark":"lmarena-vision","model":"internvl2-4b","score":958,"metric":"score"},{"benchmark":"mmlu-redux","model":"o1-preview-2024-09-12","score":92.84,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-3.5-sonnet-20241022","score":88.91,"metric":"percent"},{"benchmark":"mmlu-redux","model":"chatgpt-4o-latest-20240903","score":88.88,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4o-2024-08-06","score":88.26,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4o-2024-05-13","score":88.01,"metric":"percent"},{"benchmark":"mmlu-redux","model":"grok-2-1212","score":87.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"o1-mini-2024-09-12","score":86.72,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3.1-405b-instruct-bf16","score":86.21,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemini-1.5-pro-exp-0827","score":86.14,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-3.5-sonnet-20240620","score":86,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3.1-405b-instruct-fp8","score":85.64,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-72b-instruct","score":85.57,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemini-1.5-pro-exp-0801","score":85.53,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4-turbo-2024-04-09","score":85.31,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-32b-instruct","score":83.66,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3.1-70b-instruct","score":82.97,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mistral-large-2407","score":82.97,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemini-1.5-pro","score":82.76,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-3-opus-20240229","score":82.54,"metric":"percent"},{"benchmark":"mmlu-redux","model":"yi-large-preview","score":82.15,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemini-1.5-flash-exp-0827","score":82.11,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4-0314","score":81.64,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-72b-instruct","score":81.61,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4o-mini-2024-07-18","score":81.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"yi-large","score":81.17,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v2-chat-0628","score":80.81,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v2.5","score":80.35,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-coder-v2-instruct-0724","score":80.24,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-coder-v2-instruct","score":79.63,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-3.5-haiku-20241022","score":79.63,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3-70b-instruct","score":78.01,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemini-1.5-flash","score":77.36,"metric":"percent"},{"benchmark":"mmlu-redux","model":"athene-70b","score":76.64,"metric":"percent"},{"benchmark":"mmlu-redux","model":"reka-core-20240501","score":76.42,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-2-27b-it","score":75.67,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-7b-instruct","score":75.13,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-3-sonnet-20240229","score":74.87,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-2-9b-it","score":72.82,"metric":"percent"},{"benchmark":"mmlu-redux","model":"yi-1.5-34b-chat","score":72.79,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-3-haiku-20240307","score":72.32,"metric":"percent"},{"benchmark":"mmlu-redux","model":"phi-3-mini-4k-instruct","score":70.34,"metric":"percent"},{"benchmark":"mmlu-redux","model":"command-r-plus","score":68.61,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-3.5-turbo-0125","score":68.36,"metric":"percent"},{"benchmark":"mmlu-redux","model":"phi-3.5-mini-instruct","score":67.67,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3.1-8b-instruct","score":67.24,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-7b-instruct","score":66.92,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mistral-nemo-instruct-2407","score":66.88,"metric":"percent"},{"benchmark":"mmlu-redux","model":"yi-1.5-9b-chat","score":65.05,"metric":"percent"},{"benchmark":"mmlu-redux","model":"reka-flash-21b-20240226","score":64.72,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen-2.5-3b-instruct","score":64.25,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mixtral-8x7b-instruct-v0.1","score":63.17,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3-8b-instruct","score":61.66,"metric":"percent"},{"benchmark":"mmlu-redux","model":"command-r","score":61.12,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3-instruct-8b-simpo-v0.2","score":55.22,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-2-2b-it","score":51.94,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-1.5b-instruct","score":41.11,"metric":"percent"},{"benchmark":"zebralogic","model":"grok-3-mini-fast-high-reasoning","score":92.6,"metric":"percent"},{"benchmark":"zebralogic","model":"o3-mini-2025-01-31-high","score":91.7,"metric":"percent"},{"benchmark":"zebralogic","model":"o3-mini-2025-01-31-med","score":88.9,"metric":"percent"},{"benchmark":"zebralogic","model":"o1-2024-12-17","score":81,"metric":"percent"},{"benchmark":"zebralogic","model":"grok-3-mini-fast-low-reasoning","score":80.7,"metric":"percent"},{"benchmark":"zebralogic","model":"o3-mini-2025-01-31-low","score":74.8,"metric":"percent"},{"benchmark":"zebralogic","model":"o1-preview-2024-09-12","score":71.4,"metric":"percent"},{"benchmark":"zebralogic","model":"o1-mini-2024-09-12","score":59.7,"metric":"percent"},{"benchmark":"zebralogic","model":"grok-3-beta","score":57.9,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-v3","score":42.1,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-3.5-sonnet-20241022","score":36.2,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-3.5-sonnet-20240620","score":33.4,"metric":"percent"},{"benchmark":"zebralogic","model":"llama-3.1-405b-instruct-fp8","score":32.6,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4o-2024-08-06","score":31.7,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-1.5-pro-exp-0827","score":30.5,"metric":"percent"},{"benchmark":"zebralogic","model":"llama-3.1-405b-instruct-bf16","score":30.1,"metric":"percent"},{"benchmark":"zebralogic","model":"chatgpt-4o-latest-20240903","score":29.9,"metric":"percent"},{"benchmark":"zebralogic","model":"mistral-large-2407","score":29,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4-turbo-2024-04-09","score":28.4,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4o-2024-05-13","score":28.2,"metric":"percent"},{"benchmark":"zebralogic","model":"grok-2-1212","score":27.7,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4-0314","score":27.1,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-3-opus-20240229","score":27,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen2.5-32b-instruct","score":26.1,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-1.5-pro-exp-0801","score":25.2,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-1.5-flash-exp-0827","score":25,"metric":"percent"},{"benchmark":"zebralogic","model":"llama-3.1-70b-instruct","score":24.9,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-v2-chat-0628","score":22.7,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-v2.5","score":22.1,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen2-72b-instruct","score":21.4,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-coder-v2-instruct","score":21.1,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-coder-v2-instruct-0724","score":20.5,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4o-mini-2024-07-18","score":20.1,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-1.5-flash","score":19.4,"metric":"percent"},{"benchmark":"zebralogic","model":"gemini-1.5-pro","score":19.4,"metric":"percent"},{"benchmark":"zebralogic","model":"yi-large-preview","score":18.9,"metric":"percent"},{"benchmark":"zebralogic","model":"yi-large","score":18.8,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-3.5-haiku-20241022","score":18.7,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-3-sonnet-20240229","score":18.7,"metric":"percent"},{"benchmark":"zebralogic","model":"llama-3-70b-instruct","score":16.8,"metric":"percent"},{"benchmark":"zebralogic","model":"athene-70b","score":16.7,"metric":"percent"},{"benchmark":"zebralogic","model":"gemma-2-27b-it","score":16.3,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-3-haiku-20240307","score":14.3,"metric":"percent"},{"benchmark":"zebralogic","model":"command-r-plus","score":13.9,"metric":"percent"},{"benchmark":"zebralogic","model":"reka-core-20240501","score":13,"metric":"percent"},{"benchmark":"zebralogic","model":"gemma-2-9b-it","score":12.8,"metric":"percent"},{"benchmark":"zebralogic","model":"llama-3.1-8b-instruct","score":12.8,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen2.5-7b-instruct","score":12,"metric":"percent"},{"benchmark":"zebralogic","model":"llama-3-8b-instruct","score":11.9,"metric":"percent"},{"benchmark":"zebralogic","model":"mistral-nemo-instruct-2407","score":11.8,"metric":"percent"},{"benchmark":"zebralogic","model":"phi-3-mini-4k-instruct","score":11.6,"metric":"percent"},{"benchmark":"zebralogic","model":"yi-1.5-34b-chat","score":11.5,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-3.5-turbo-0125","score":10.1,"metric":"percent"},{"benchmark":"zebralogic","model":"command-r","score":9.9,"metric":"percent"},{"benchmark":"zebralogic","model":"reka-flash-21b-20240226","score":9.3,"metric":"percent"},{"benchmark":"zebralogic","model":"mathstral-7b","score":9,"metric":"percent"},{"benchmark":"zebralogic","model":"mixtral-8x7b-instruct-v0.1","score":8.7,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen2-7b-instruct","score":8.4,"metric":"percent"},{"benchmark":"zebralogic","model":"llama-3.2-3b-instruct","score":7.4,"metric":"percent"},{"benchmark":"zebralogic","model":"phi-3.5-mini-instruct","score":6.4,"metric":"percent"},{"benchmark":"zebralogic","model":"qwen-2.5-3b-instruct","score":4.8,"metric":"percent"},{"benchmark":"zebralogic","model":"gemma-2-2b-it","score":4.2,"metric":"percent"},{"benchmark":"zebralogic","model":"yi-1.5-9b-chat","score":2.3,"metric":"percent"},{"benchmark":"math-lvl5","model":"o1-mini-2024-09-12","score":89.32,"metric":"percent"},{"benchmark":"math-lvl5","model":"o1-preview-2024-09-12","score":84.47,"metric":"percent"},{"benchmark":"math-lvl5","model":"gemini-1.5-pro-exp-0827","score":68.1,"metric":"percent"},{"benchmark":"math-lvl5","model":"grok-2-1212","score":60.89,"metric":"percent"},{"benchmark":"math-lvl5","model":"qwen2.5-72b-instruct","score":60.19,"metric":"percent"},{"benchmark":"math-lvl5","model":"qwen2.5-32b-instruct","score":59.5,"metric":"percent"},{"benchmark":"math-lvl5","model":"claude-3.5-sonnet-20241022","score":59.36,"metric":"percent"},{"benchmark":"math-lvl5","model":"gpt-4o-2024-08-06","score":55.34,"metric":"percent"},{"benchmark":"math-lvl5","model":"gpt-4o-2024-05-13","score":54.79,"metric":"percent"},{"benchmark":"math-lvl5","model":"gemini-1.5-flash-exp-0827","score":54.51,"metric":"percent"},{"benchmark":"math-lvl5","model":"chatgpt-4o-latest-20240903","score":53.12,"metric":"percent"},{"benchmark":"math-lvl5","model":"gpt-4o-mini-2024-07-18","score":52.15,"metric":"percent"},{"benchmark":"math-lvl5","model":"claude-3.5-sonnet-20240620","score":51.87,"metric":"percent"},{"benchmark":"math-lvl5","model":"llama-3.1-405b-instruct-bf16","score":51.56,"metric":"percent"},{"benchmark":"math-lvl5","model":"qwen2.5-7b-instruct","score":51.46,"metric":"percent"},{"benchmark":"math-lvl5","model":"mistral-large-2407","score":48.54,"metric":"percent"},{"benchmark":"math-lvl5","model":"claude-3.5-haiku-20241022","score":46.46,"metric":"percent"},{"benchmark":"math-lvl5","model":"gpt-4-turbo-2024-04-09","score":46.46,"metric":"percent"},{"benchmark":"math-lvl5","model":"deepseek-v2.5","score":44.66,"metric":"percent"},{"benchmark":"math-lvl5","model":"llama-3.1-70b-instruct","score":43.13,"metric":"percent"},{"benchmark":"math-lvl5","model":"gemini-1.5-pro","score":39.81,"metric":"percent"},{"benchmark":"math-lvl5","model":"qwen2-72b-instruct","score":38.28,"metric":"percent"},{"benchmark":"math-lvl5","model":"claude-3-opus-20240229","score":36.89,"metric":"percent"},{"benchmark":"math-lvl5","model":"gemini-1.5-flash","score":34.81,"metric":"percent"},{"benchmark":"math-lvl5","model":"gemma-2-27b-it","score":26.63,"metric":"percent"},{"benchmark":"math-lvl5","model":"gpt-4-0314","score":26.07,"metric":"percent"},{"benchmark":"math-lvl5","model":"qwen-2.5-3b-instruct","score":25.52,"metric":"percent"},{"benchmark":"math-lvl5","model":"llama-3-70b-instruct","score":25.1,"metric":"percent"},{"benchmark":"math-lvl5","model":"qwen2-7b-instruct","score":23.86,"metric":"percent"},{"benchmark":"math-lvl5","model":"llama-3.1-8b-instruct","score":22.19,"metric":"percent"},{"benchmark":"math-lvl5","model":"reka-core-20240501","score":21.91,"metric":"percent"},{"benchmark":"math-lvl5","model":"athene-70b","score":20.67,"metric":"percent"},{"benchmark":"math-lvl5","model":"yi-1.5-9b-chat","score":19.97,"metric":"percent"},{"benchmark":"math-lvl5","model":"gemma-2-9b-it","score":19.42,"metric":"percent"},{"benchmark":"math-lvl5","model":"phi-3.5-mini-instruct","score":18.72,"metric":"percent"},{"benchmark":"math-lvl5","model":"yi-1.5-34b-chat","score":18.17,"metric":"percent"},{"benchmark":"math-lvl5","model":"phi-3-mini-4k-instruct","score":16.23,"metric":"percent"},{"benchmark":"math-lvl5","model":"claude-3-haiku-20240307","score":15.12,"metric":"percent"},{"benchmark":"math-lvl5","model":"gpt-3.5-turbo-0125","score":13.73,"metric":"percent"},{"benchmark":"math-lvl5","model":"llama-3-8b-instruct","score":7.91,"metric":"percent"},{"benchmark":"math-lvl5","model":"gemma-2-2b-it","score":4.3,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3.5-sonnet-20241022","score":96.66,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4o-2024-08-06","score":96.21,"metric":"percent"},{"benchmark":"gsm8k","model":"o1-mini-2024-09-12","score":96.06,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-405b-instruct-bf16","score":95.98,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-405b-instruct-fp8","score":95.91,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3.5-sonnet-20240620","score":95.6,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3-opus-20240229","score":95.6,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-large-2407","score":95.53,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4o-2024-05-13","score":95.38,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-1.5-flash-exp-0827","score":95.01,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-1.5-pro-exp-0801","score":95,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3.5-haiku-20241022","score":94.47,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4o-mini-2024-07-18","score":94.24,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b-instruct","score":94.16,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2-chat-0628","score":93.93,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-instruct","score":93.78,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-1.5-pro","score":93.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b-instruct","score":93.03,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-72b-instruct","score":92.65,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2.5","score":92.49,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-instruct-0724","score":91.51,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3-sonnet-20240229","score":91.51,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-1.5-flash","score":91.36,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-27b-it","score":90.22,"metric":"percent"},{"benchmark":"gsm8k","model":"claude-3-haiku-20240307","score":88.78,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-9b-it","score":87.41,"metric":"percent"},{"benchmark":"gsm8k","model":"reka-core-20240501","score":87.41,"metric":"percent"},{"benchmark":"gsm8k","model":"athene-70b","score":86.66,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-34b-chat","score":84.08,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-nemo-instruct-2407","score":82.79,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-large-preview","score":82.64,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3.5-mini-instruct","score":82.03,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5-turbo-0125","score":80.36,"metric":"percent"},{"benchmark":"gsm8k","model":"command-r-plus","score":80.14,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-7b-instruct","score":80.06,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-large","score":80.06,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b-instruct","score":78.47,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-9b-chat","score":76.42,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3-mini-4k-instruct","score":75.51,"metric":"percent"},{"benchmark":"gsm8k","model":"reka-flash-21b-20240226","score":74.68,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x7b-instruct-v0.1","score":70.13,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-instruct-8b-simpo-v0.2","score":57.54,"metric":"percent"},{"benchmark":"gsm8k","model":"command-r","score":52.99,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-2b-it","score":51.63,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-1.5b-instruct","score":43.37,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4o-2024-05-13","score":72.55,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-1.5-pro","score":69.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3-opus","score":68.45,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-1.5-flash","score":59.12,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-70b-instruct","score":56.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3-sonnet","score":56.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v2-chat","score":54.81,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-70b","score":52.78,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-8b-instruct","score":40.98,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-8b","score":35.36,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-1.5-34b-chat","score":52.29,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-1.5-9b-chat","score":45.95,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-1.5-6b-chat","score":38.23,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mixtral-8x7b-instruct-v0.1","score":43.27,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mixtral-8x7b","score":41.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-7b-chat","score":29.06,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-14b-chat","score":38.02,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-2-13b","score":25.34,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-2-7b","score":20.32,"metric":"percent"},{"benchmark":"mmlu-pro","model":"command-r","score":37.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-6b-chat","score":28.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-large","score":58.09,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4-turbo","score":63.71,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mammoth2-7b-plus","score":40.85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mammoth2-8b-plus","score":43.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mammoth2-8x7b-plus","score":50.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-7b","score":33.73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-72b-chat","score":52.64,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-110b","score":49.93,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-7b-instruct-v0.2","score":30.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-7b-v0.1","score":30.88,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-7b-v0.2","score":30.43,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-7b-instruct-v0.1","score":25.75,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-34b","score":43.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-2-70b","score":37.53,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-6b","score":26.51,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llemma-7b","score":23.45,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-math-7b-instruct","score":35.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"openchat-3.5-8b","score":37.24,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2b","score":15.85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"zephyr-7b-beta","score":32.97,"metric":"percent"},{"benchmark":"mmlu-pro","model":"map-neo-7b","score":25.85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"starling-lm-7b-beta","score":37.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"internlm2-math-plus-7b","score":33.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"internlm2-math-plus-20b","score":37.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-smaug-8b","score":36.93,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3-medium-128k-instruct","score":51.91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3-medium-4k-instruct","score":55.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3-mini-128k-instruct","score":43.86,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3-mini-4k-instruct","score":45.66,"metric":"percent"},{"benchmark":"mmlu-pro","model":"map-neo-7b-instruct","score":28.74,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4-9b-chat","score":48.01,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm4-9b","score":47.92,"metric":"percent"},{"benchmark":"mmlu-pro","model":"higgs-llama-3-70b","score":63.16,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-72b-chat","score":64.38,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-72b","score":55.59,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3.5-sonnet-20240620","score":76.12,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-v2-instruct","score":63.63,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-9b","score":45.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-9b-it","score":52.08,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-7b-instruct","score":47.24,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-7b","score":40.73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-1.5b-instruct","score":22.62,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-1.5b","score":22.56,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-0.5b-instruct","score":15.93,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-0.5b","score":14.97,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-v2-lite-base","score":34.37,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-v2-lite-instruct","score":41.57,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mathstral-7b","score":42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4o-mini","score":63.09,"metric":"percent"},{"benchmark":"mmlu-pro","model":"magnum-72b-v1","score":63.93,"metric":"percent"},{"benchmark":"mmlu-pro","model":"wizardlm-2-8x22b","score":39.24,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-nemo-instruct-2407","score":44.81,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-nemo-base-2407","score":39.77,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b","score":36.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b-instruct","score":44.25,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-70b","score":52.47,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-70b-instruct","score":62.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-2","score":75.46,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-2-mini","score":71.85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3.5-mini-instruct","score":47.87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"reflection-llama-3.1-70b","score":60.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4o-2024-08-06","score":74.68,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v2.5","score":65.83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-turbo","score":55.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-3b","score":43.73,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen-2.5-72b","score":71.59,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-14b","score":63.69,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-32b-base","score":69.23,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-7b","score":45,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-1.5b","score":32.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-0.5b","score":14.92,"metric":"percent"},{"benchmark":"mmlu-pro","model":"rrd2.5-9b","score":61.84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-1.5-flash-002","score":64.09,"metric":"percent"},{"benchmark":"mmlu-pro","model":"jamba-1.5-large","score":49.46,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-1.5-pro-002","score":70.25,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-nemotron-70b-instruct-hf","score":62.78,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ministral-8b-2410","score":37.93,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3.5-sonnet-20241022","score":78,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-instruct-2409","score":48.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-lightning","score":62.38,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm-135m","score":11.22,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm-360m","score":10.95,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-1b","score":11.95,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.2-3b","score":22.17,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm1-1.7b-pretrained","score":11.93,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.0-2b-base","score":21.72,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.0-8b-base","score":31.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm2-1.7b-base","score":18.31,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm2-360m-base","score":11.38,"metric":"percent"},{"benchmark":"mmlu-pro","model":"smollm2-135m-base","score":10.85,"metric":"percent"},{"benchmark":"mmlu-pro","model":"aya-expanse-8b","score":33.74,"metric":"percent"},{"benchmark":"mmlu-pro","model":"aya-expanse-32b","score":45.41,"metric":"percent"},{"benchmark":"mmlu-pro","model":"athene-v2-chat","score":73.11,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3.5-haiku-20241022","score":62.12,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-27b-it","score":56.54,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-large-instruct-2407","score":65.91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mixtral-8x22b-instruct-v0.1","score":56.33,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3-haiku-20240307","score":42.29,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-3.5-2.4b-instruct","score":39.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-3.5-7.8b-instruct","score":46.24,"metric":"percent"},{"benchmark":"mmlu-pro","model":"exaone-3.5-32b-instruct","score":58.91,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwq-32b","score":69.07,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.3-70b-instruct","score":65.92,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-large-2411","score":67.94,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.0-flash-exp","score":76.24,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.1-1b-a400m-base","score":12.34,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.1-1b-a400m-instruct","score":13.27,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.1-2b-base","score":23.89,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.1-2b-instruct","score":31.97,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.1-3b-a800m-base","score":20.39,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.1-3b-a800m-instruct","score":25.42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.1-8b-base","score":33.08,"metric":"percent"},{"benchmark":"mmlu-pro","model":"granite-3.1-8b-instruct","score":41.03,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3","score":75.87,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwq-32b-preview","score":70.97,"metric":"percent"},{"benchmark":"mmlu-pro","model":"sky-t1-32b-preview","score":69.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-text-01","score":75.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-405b-instruct","score":73.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-405b","score":61.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"internlm3-8b-instruct","score":57.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"hunyuan-large","score":60.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-4","score":70.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4o-2024-11-20","score":77.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"doubao-1.5-pro","score":80.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-max","score":76.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-3-24b-base","score":54.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-24b-instruct-2501","score":66.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.0-flash-lite","score":71.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"azerogpt","score":63.07,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-3-mini-beta","score":78.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-3-beta","score":79.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-4-mini","score":52.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llada-8b-base","score":37,"metric":"percent"},{"benchmark":"mmlu-pro","model":"hunyuan-turbos","score":79,"metric":"percent"},{"benchmark":"mmlu-pro","model":"reka-flash-3","score":65,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-2b-it","score":15.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-1b-it","score":14.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-4b-it","score":43.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-12b-it","score":60.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-3-27b-it","score":67.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"c4ai-aya-vision-32b","score":47.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-small-3.1-24b-instruct-2503","score":66.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-h-56b-base","score":60.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-h-8b-base","score":44,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3-0324","score":81.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-scout","score":74.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-4-behemoth","score":82.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-2.5-pro-exp-03.25","score":84.52,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-3-mini","score":83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"o4-mini-high","score":83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3.7-sonnet-thinking","score":84,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-a22b","score":68.18,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-7b-base","score":41.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mimo-7b-rl","score":58.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"general-reasoner-7b","score":58.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"general-reasoner-14b","score":66.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-4-reasoning","score":74.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-4-reasoning-plus","score":76,"metric":"percent"},{"benchmark":"mmlu-pro","model":"o3-mini","score":79.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"echo-ego-v2-14b","score":71.24,"metric":"percent"},{"benchmark":"mmlu-pro","model":"hunyuan-80b-a13b-instruct","score":67.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ernie-4.5-21b-a3b-pt","score":56.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ernie-4.5-300b-a47b-base","score":69.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"ernie-4.5-300b-a47b","score":78.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-m1","score":81.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"kimi-k2-instruct","score":81,"metric":"percent"},{"benchmark":"mmlu-pro","model":"intern-s1","score":83.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-r1-0528","score":83.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4-thinking","score":87.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed1.6-adaptive-thinking","score":86.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"glm-4.5","score":84.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-235b-a22b-instruct-2507","score":83,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b-medium","score":73.14,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-20b-high","score":73.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-oss-120b-high","score":80.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed-oss-36b-instruct","score":82.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed1.6-thinking","score":86.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed1.6-base","score":86.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed-oss-36b-base","score":65.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"seed-oss-36b-base-wosyn","score":60.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.1","score":83.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3.1-thinking","score":84.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"longcat-flash-chat","score":82.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-5.1","score":86.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.5-thinking","score":87.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-4.5-sonnet-thinking","score":87.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-opus-4.6-high","score":89.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3-flash","score":88.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minimax-m2.5","score":80.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-30b-a3b-fp8","score":78.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"nemotron-3-nano-30b-a3b-base","score":65.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3-30b-a3b-base","score":61.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3.1-pro","score":91.16,"metric":"percent"},{"benchmark":"mmlu-pro","model":"newenai-phi4-sft","score":57.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-0.8b","score":29.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.5-2b","score":55.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemini-3.1-flash-lite","score":86.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-sonnet-4.6-high","score":87.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-4.1-fast-thinking","score":84.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"grok-4.1-fast","score":75.2,"metric":"percent"},{"benchmark":"rewardbench","model":"inf-orm-llama3.1-70b","score":95.1,"metric":"percent"},{"benchmark":"rewardbench","model":"ldl-reward-gemma-2-27b-v0.1","score":95,"metric":"percent"},{"benchmark":"rewardbench","model":"qrm-gemma-2-27b","score":94.4,"metric":"percent"},{"benchmark":"rewardbench","model":"skywork-reward-gemma-2-27b-v0.2","score":94.3,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-nemotron-70b-reward","score":94.1,"metric":"percent"},{"benchmark":"rewardbench","model":"skywork-reward-gemma-2-27b","score":93.8,"metric":"percent"},{"benchmark":"rewardbench","model":"texteval-llama3.1-70b","score":93.5,"metric":"percent"},{"benchmark":"rewardbench","model":"metametrics-rm-v1.0","score":93.4,"metric":"percent"},{"benchmark":"rewardbench","model":"skywork-critic-llama-3.1-70b","score":93.3,"metric":"percent"},{"benchmark":"rewardbench","model":"qrm-llama3.1-8b-v2","score":93.1,"metric":"percent"},{"benchmark":"rewardbench","model":"skywork-reward-llama-3.1-8b-v0.2","score":93.1,"metric":"percent"},{"benchmark":"rewardbench","model":"qrm-llama3.1-8b","score":93.1,"metric":"percent"},{"benchmark":"rewardbench","model":"urm-llama-3.1-8b","score":92.9,"metric":"percent"},{"benchmark":"rewardbench","model":"sfr-llama-3.1-70b-judge-r","score":92.7,"metric":"percent"},{"benchmark":"rewardbench","model":"rise-judge-qwen2.5-32b","score":92.7,"metric":"percent"},{"benchmark":"rewardbench","model":"skywork-reward-llama-3.1-8b","score":92.5,"metric":"percent"},{"benchmark":"rewardbench","model":"selene-1","score":92.4,"metric":"percent"},{"benchmark":"rewardbench","model":"gpm-llama-3.1-8b","score":92.2,"metric":"percent"},{"benchmark":"rewardbench","model":"nemotron-4-340b-reward","score":92,"metric":"percent"},{"benchmark":"rewardbench","model":"grm-llama3-8b-rewardmodel-ft","score":91.5,"metric":"percent"},{"benchmark":"rewardbench","model":"qrm-llama3-8b","score":91.1,"metric":"percent"},{"benchmark":"rewardbench","model":"texteval-offsetbias-12b","score":91,"metric":"percent"},{"benchmark":"rewardbench","model":"grm-llama3.2-3b-rewardmodel-ft","score":90.9,"metric":"percent"},{"benchmark":"rewardbench","model":"sfr-nemo-12b-judge-r","score":90.3,"metric":"percent"},{"benchmark":"rewardbench","model":"internlm2-20b-reward","score":90.2,"metric":"percent"},{"benchmark":"rewardbench","model":"skywork-vl-reward-7b","score":90.1,"metric":"percent"},{"benchmark":"rewardbench","model":"self-taught-evaluator-llama3.1-70b","score":90,"metric":"percent"},{"benchmark":"rewardbench","model":"urm-llama-3-8b","score":89.9,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3-offsetbias-rm-8b","score":89.4,"metric":"percent"},{"benchmark":"rewardbench","model":"selene-1-mini-llama-3.1-8b","score":89.1,"metric":"percent"},{"benchmark":"rewardbench","model":"skywork-critic-llama-3.1-8b","score":89,"metric":"percent"},{"benchmark":"rewardbench","model":"llama3-70b-steerlm-rm","score":88.8,"metric":"percent"},{"benchmark":"rewardbench","model":"sfr-llama-3.1-8b-judge-r","score":88.7,"metric":"percent"},{"benchmark":"rewardbench","model":"self-taught-llama-3-70b","score":88.6,"metric":"percent"},{"benchmark":"rewardbench","model":"armorm-llama3-8b-v0.1","score":88.6,"metric":"percent"},{"benchmark":"rewardbench","model":"grm-gemma2-2b-rewardmodel-ft","score":88.4,"metric":"percent"},{"benchmark":"rewardbench","model":"gemini-1.5-pro-api-0514","score":88.2,"metric":"percent"},{"benchmark":"rewardbench","model":"rise-judge-qwen2.5-7b","score":88.2,"metric":"percent"},{"benchmark":"rewardbench","model":"cohere-rm-may-2024","score":88.2,"metric":"percent"},{"benchmark":"rewardbench","model":"flame-1.0-24b-july-2024","score":87.8,"metric":"percent"},{"benchmark":"rewardbench","model":"internlm2-7b-reward","score":87.6,"metric":"percent"},{"benchmark":"rewardbench","model":"con-j-qwen2-7b","score":87.1,"metric":"percent"},{"benchmark":"rewardbench","model":"gemini-1.5-pro-002","score":86.8,"metric":"percent"},{"benchmark":"rewardbench","model":"gpt-4o-2024-08-06","score":86.7,"metric":"percent"},{"benchmark":"rewardbench","model":"pair-preference-model-llama3-8b","score":85.7,"metric":"percent"},{"benchmark":"rewardbench","model":"grm-llama3-8b-sftreg","score":85.4,"metric":"percent"},{"benchmark":"rewardbench","model":"compassjudger-1-32b-instruct","score":85.2,"metric":"percent"},{"benchmark":"rewardbench","model":"cohere-rm-march-2024","score":85.1,"metric":"percent"},{"benchmark":"rewardbench","model":"grm-llama3-8b-distill","score":84.6,"metric":"percent"},{"benchmark":"rewardbench","model":"grm-gemma-2b-rewardmodel-ft","score":84.5,"metric":"percent"},{"benchmark":"rewardbench","model":"gpt-4-0125-preview","score":84.3,"metric":"percent"},{"benchmark":"rewardbench","model":"reflection-llama-3.1-70b","score":84.2,"metric":"percent"},{"benchmark":"rewardbench","model":"claude-3.5-sonnet-20240620","score":84.2,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-405b-instruct","score":84.1,"metric":"percent"},{"benchmark":"rewardbench","model":"compassjudger-1-14b-instruct","score":84.1,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-70b-instruct","score":84.1,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3-offsetbias-8b","score":84,"metric":"percent"},{"benchmark":"rewardbench","model":"gpt-4-turbo-2024-04-09","score":84,"metric":"percent"},{"benchmark":"rewardbench","model":"fsfairx-llama3-rm-v0.1","score":83.4,"metric":"percent"},{"benchmark":"rewardbench","model":"gpt-4o-2024-05-13","score":83.3,"metric":"percent"},{"benchmark":"rewardbench","model":"compassjudger-1-7b-instruct","score":83.2,"metric":"percent"},{"benchmark":"rewardbench","model":"internlm2-1-8b-reward","score":82.2,"metric":"percent"},{"benchmark":"rewardbench","model":"btrm-qwen2-7b-0613","score":81.7,"metric":"percent"},{"benchmark":"rewardbench","model":"eurus-rm-7b","score":81.6,"metric":"percent"},{"benchmark":"rewardbench","model":"starling-rm-34b","score":81.3,"metric":"percent"},{"benchmark":"rewardbench","model":"gemma-2-27b-it","score":80.9,"metric":"percent"},{"benchmark":"rewardbench","model":"gemini-1.5-flash-001","score":80.5,"metric":"percent"},{"benchmark":"rewardbench","model":"gemma-2b-rewardmodel-ft","score":80.5,"metric":"percent"},{"benchmark":"rewardbench","model":"tulu-v2.5-13b-preference-mix-rm","score":80.3,"metric":"percent"},{"benchmark":"rewardbench","model":"claude-3-opus-20240229","score":80.1,"metric":"percent"},{"benchmark":"rewardbench","model":"gpt-4o-mini-2024-07-18","score":80.1,"metric":"percent"},{"benchmark":"rewardbench","model":"rm-mistral-7b","score":79.8,"metric":"percent"},{"benchmark":"rewardbench","model":"hermes-3-llama-3.1-70b","score":78.5,"metric":"percent"},{"benchmark":"rewardbench","model":"mistral-rm-for-raft-gshf-v0","score":78.5,"metric":"percent"},{"benchmark":"rewardbench","model":"reward-model-mistral-7b-instruct-unified-feedback","score":76.6,"metric":"percent"},{"benchmark":"rewardbench","model":"mmpo-gemma-7b-gamma1.1-epoch3","score":76.5,"metric":"percent"},{"benchmark":"rewardbench","model":"stablelm-2-12b-chat","score":76.4,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3-70b-instruct","score":76.3,"metric":"percent"},{"benchmark":"rewardbench","model":"tulu-2-dpo-70b","score":76.2,"metric":"percent"},{"benchmark":"rewardbench","model":"gemini-1.5-flash-8b-001","score":76,"metric":"percent"},{"benchmark":"rewardbench","model":"mmpo-gemma-7b","score":75.9,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3-tulu-2-dpo-70b","score":75,"metric":"percent"},{"benchmark":"rewardbench","model":"nous-hermes-2-mistral-7b-dpo","score":74.8,"metric":"percent"},{"benchmark":"rewardbench","model":"claude-3-sonnet-20240229","score":74.6,"metric":"percent"},{"benchmark":"rewardbench","model":"mixtral-8x7b-instruct-v0.1","score":74.5,"metric":"percent"},{"benchmark":"rewardbench","model":"prometheus-8x7b-v2.0","score":74.5,"metric":"percent"},{"benchmark":"rewardbench","model":"grm-gemma-2b-sftreg","score":74.5,"metric":"percent"},{"benchmark":"rewardbench","model":"gpm-gemma-2b","score":74.5,"metric":"percent"},{"benchmark":"rewardbench","model":"matter-0.1-7b-boost-dpo-preview","score":74.5,"metric":"percent"},{"benchmark":"rewardbench","model":"tulu-v2.5-70b-uf-rm","score":74,"metric":"percent"},{"benchmark":"rewardbench","model":"zephyr-7b-alpha","score":73.9,"metric":"percent"},{"benchmark":"rewardbench","model":"solar-10.7b-instruct-v1.0","score":73.9,"metric":"percent"},{"benchmark":"rewardbench","model":"tulu-2-dpo-13b","score":73.7,"metric":"percent"},{"benchmark":"rewardbench","model":"compassjudger-1-1.5b-instruct","score":73.4,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3-tulu-2-8b-uf-mean-rm","score":73.4,"metric":"percent"},{"benchmark":"rewardbench","model":"starchat2-15b-v0.1","score":73.2,"metric":"percent"},{"benchmark":"rewardbench","model":"gemma-2b-rewardmodel-baseline","score":72.9,"metric":"percent"},{"benchmark":"rewardbench","model":"claude-3-haiku-20240307","score":72.9,"metric":"percent"},{"benchmark":"rewardbench","model":"zephyr-7b-beta","score":72.8,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3-tulu-2-dpo-8b","score":72.7,"metric":"percent"},{"benchmark":"rewardbench","model":"matter-0.1-7b-dpo-preview","score":72.5,"metric":"percent"},{"benchmark":"rewardbench","model":"bagel-dpo-34b-v0.5","score":72.2,"metric":"percent"},{"benchmark":"rewardbench","model":"tulu-2-dpo-7b","score":72.1,"metric":"percent"},{"benchmark":"rewardbench","model":"prometheus-7b-v2.0","score":72,"metric":"percent"},{"benchmark":"rewardbench","model":"stablelm-zephyr-3b","score":71.5,"metric":"percent"},{"benchmark":"rewardbench","model":"nous-hermes-2-mixtral-8x7b-dpo","score":71.4,"metric":"percent"},{"benchmark":"rewardbench","model":"starling-rm-7b-alpha","score":71.1,"metric":"percent"},{"benchmark":"rewardbench","model":"command-r-plus","score":70.6,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3-tulu-2-70b-uf-mean-rm","score":70.2,"metric":"percent"},{"benchmark":"rewardbench","model":"rm-gemma-7b","score":69.7,"metric":"percent"},{"benchmark":"rewardbench","model":"rm-gemma-7b-4096","score":69.2,"metric":"percent"},{"benchmark":"rewardbench","model":"ultrarm-13b","score":69,"metric":"percent"},{"benchmark":"rewardbench","model":"oasst-rm-2.1-pythia-1.4b-epoch-2.5","score":69,"metric":"percent"},{"benchmark":"rewardbench","model":"eurus-7b-kto","score":69,"metric":"percent"},{"benchmark":"rewardbench","model":"qwen1.5-14b-chat","score":68.6,"metric":"percent"},{"benchmark":"rewardbench","model":"llama3-iterative-dpo-final","score":67.8,"metric":"percent"},{"benchmark":"rewardbench","model":"zephyr-7b-gemma-v0.1","score":67.6,"metric":"percent"},{"benchmark":"rewardbench","model":"qwen1.5-7b-chat","score":67.5,"metric":"percent"},{"benchmark":"rewardbench","model":"minicpm-2b-dpo-fp32","score":67.3,"metric":"percent"},{"benchmark":"rewardbench","model":"better-pairrm","score":67.3,"metric":"percent"},{"benchmark":"rewardbench","model":"olmo-7b-instruct","score":67.3,"metric":"percent"},{"benchmark":"rewardbench","model":"qwen1.5-72b-chat","score":67.2,"metric":"percent"},{"benchmark":"rewardbench","model":"qwen1.5-moe-a2.7b-chat","score":66.4,"metric":"percent"},{"benchmark":"rewardbench","model":"rewardmodel-mistral-7b-for-dpa-v1","score":66.3,"metric":"percent"},{"benchmark":"rewardbench","model":"stablelm-2-zephyr-1.6b","score":65.7,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-8b-instruct","score":65.7,"metric":"percent"},{"benchmark":"rewardbench","model":"rm-gemma-2b","score":65.5,"metric":"percent"},{"benchmark":"rewardbench","model":"gpt-3.5-turbo-0125","score":65.3,"metric":"percent"},{"benchmark":"rewardbench","model":"tulu-v2.5-70b-preference-mix-rm","score":65.2,"metric":"percent"},{"benchmark":"rewardbench","model":"faro-yi-9b-dpo","score":64.6,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3-8b-instruct","score":64.5,"metric":"percent"},{"benchmark":"rewardbench","model":"ziya-llama-7b-reward","score":63.8,"metric":"percent"},{"benchmark":"rewardbench","model":"beaver-7b-v2.0-reward","score":63.7,"metric":"percent"},{"benchmark":"rewardbench","model":"stable-code-instruct-3b","score":62.2,"metric":"percent"},{"benchmark":"rewardbench","model":"oasst-rm-2-pythia-6.9b-epoch-1","score":61.5,"metric":"percent"},{"benchmark":"rewardbench","model":"reward-model-deberta-v3-large-v2","score":61.3,"metric":"percent"},{"benchmark":"rewardbench","model":"pairrm-hf","score":60.9,"metric":"percent"},{"benchmark":"rewardbench","model":"beaver-7b-v2.0-cost","score":59.6,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-kto-llama13b","score":59.5,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-kto-llama30b","score":59,"metric":"percent"},{"benchmark":"rewardbench","model":"qwen1.5-1.8b-chat","score":58.9,"metric":"percent"},{"benchmark":"rewardbench","model":"beaver-7b-v1.0-cost","score":58,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-dpo-llama30b","score":56.2,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-kto-pythia1-4b","score":55.8,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-kto-pythia6-9b","score":55.6,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-kto-pythia2-8b","score":55,"metric":"percent"},{"benchmark":"rewardbench","model":"qwen1.5-4b-chat","score":54.8,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-dpo-llama13b","score":54,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-kto-llama7b","score":53.9,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-dpo-llama7b","score":53,"metric":"percent"},{"benchmark":"rewardbench","model":"qwen1.5-0.5b-chat","score":53,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-dpo-pythia2-8b","score":52.9,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-dpo-pythia6-9b","score":52.6,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-dpo-pythia1-4b","score":52.3,"metric":"percent"},{"benchmark":"rewardbench","model":"steamshp-flan-t5-xl","score":51.3,"metric":"percent"},{"benchmark":"rewardbench","model":"smoltulu-1.7b-rm","score":50.9,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-kto-pythia12-0b","score":50.5,"metric":"percent"},{"benchmark":"rewardbench","model":"hh-rlhf-rm-open-llama-3b","score":50.3,"metric":"percent"},{"benchmark":"rewardbench","model":"archangel-sft-dpo-pythia12-0b","score":50.1,"metric":"percent"},{"benchmark":"rewardbench","model":"steamshp-flan-t5-large","score":49.6,"metric":"percent"},{"benchmark":"rewardbench","model":"tulu-v2.5-13b-uf-rm","score":48.1,"metric":"percent"},{"benchmark":"rewardbench","model":"beaver-7b-v1.0-reward","score":47.3,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-70b-instruct-rm-rb2","score":90.2,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-8b-instruct-rm-rb2","score":88.9,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-8b-base-rm-rb2","score":84.6,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-tulu-3-8b-sft-rm-rb2","score":85.5,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-tulu-3-8b-dpo-rm-rb2","score":84.3,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-tulu-3-8b-rl-rm-rb2","score":83.7,"metric":"percent"},{"benchmark":"rewardbench","model":"llama-3.1-tulu-3-70b-sft-rm-rb2","score":88.9,"metric":"percent"},{"benchmark":"mmlu","model":"mpt-7b","score":26.8,"metric":"percent"},{"benchmark":"triviaqa","model":"mpt-7b","score":59.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"mpt-7b","score":17.8,"metric":"percent"},{"benchmark":"gsm8k","model":"mpt-7b","score":6.8,"metric":"percent"},{"benchmark":"humaneval","model":"mpt-7b","score":18.3,"metric":"percent"},{"benchmark":"agieval","model":"mpt-7b","score":23.5,"metric":"percent"},{"benchmark":"boolq","model":"mpt-7b","score":75,"metric":"percent"},{"benchmark":"hellaswag","model":"mpt-7b","score":76.4,"metric":"percent"},{"benchmark":"openbookqa","model":"mpt-7b","score":51.4,"metric":"percent"},{"benchmark":"quac","model":"mpt-7b","score":37.7,"metric":"percent"},{"benchmark":"winogrande","model":"mpt-7b","score":68.3,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-7b","score":26.2,"metric":"percent"},{"benchmark":"triviaqa","model":"falcon-7b","score":56.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"falcon-7b","score":18.1,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-7b","score":6.8,"metric":"percent"},{"benchmark":"agieval","model":"falcon-7b","score":21.2,"metric":"percent"},{"benchmark":"boolq","model":"falcon-7b","score":67.5,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-7b","score":74.1,"metric":"percent"},{"benchmark":"openbookqa","model":"falcon-7b","score":51.6,"metric":"percent"},{"benchmark":"quac","model":"falcon-7b","score":18.8,"metric":"percent"},{"benchmark":"winogrande","model":"falcon-7b","score":66.3,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b","score":45.3,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-7b","score":68.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b","score":22.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b","score":14.6,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b","score":12.8,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-7b","score":29.3,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-7b","score":77.4,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b","score":77.2,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-7b","score":58.6,"metric":"percent"},{"benchmark":"quac","model":"llama-2-7b","score":39.7,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-7b","score":69.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b","score":54.8,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-13b","score":77.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-13b","score":28,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b","score":28.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b","score":18.3,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-13b","score":39.1,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-13b","score":81.7,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-13b","score":57,"metric":"percent"},{"benchmark":"quac","model":"llama-2-13b","score":44.8,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-13b","score":72.8,"metric":"percent"},{"benchmark":"mmlu","model":"mpt-30b","score":46.9,"metric":"percent"},{"benchmark":"triviaqa","model":"mpt-30b","score":71.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"mpt-30b","score":23,"metric":"percent"},{"benchmark":"gsm8k","model":"mpt-30b","score":15.2,"metric":"percent"},{"benchmark":"humaneval","model":"mpt-30b","score":25,"metric":"percent"},{"benchmark":"agieval","model":"mpt-30b","score":33.8,"metric":"percent"},{"benchmark":"boolq","model":"mpt-30b","score":79,"metric":"percent"},{"benchmark":"hellaswag","model":"mpt-30b","score":79.9,"metric":"percent"},{"benchmark":"openbookqa","model":"mpt-30b","score":52,"metric":"percent"},{"benchmark":"quac","model":"mpt-30b","score":41.1,"metric":"percent"},{"benchmark":"winogrande","model":"mpt-30b","score":71,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-40b","score":55.4,"metric":"percent"},{"benchmark":"triviaqa","model":"falcon-40b","score":78.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"falcon-40b","score":29.5,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-40b","score":19.6,"metric":"percent"},{"benchmark":"agieval","model":"falcon-40b","score":37,"metric":"percent"},{"benchmark":"boolq","model":"falcon-40b","score":83.1,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-40b","score":83.6,"metric":"percent"},{"benchmark":"openbookqa","model":"falcon-40b","score":56.6,"metric":"percent"},{"benchmark":"quac","model":"falcon-40b","score":43.3,"metric":"percent"},{"benchmark":"winogrande","model":"falcon-40b","score":76.9,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-65b","score":63.4,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-1-65b","score":84.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-65b","score":31,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-65b","score":50.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-65b","score":23.7,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-65b","score":47.6,"metric":"percent"},{"benchmark":"quac","model":"llama-1-65b","score":39.8,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b","score":68.9,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-70b","score":85,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-70b","score":33,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b","score":56.8,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":29.9,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-70b","score":54.2,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-70b","score":85,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-70b","score":85.3,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-70b","score":60.2,"metric":"percent"},{"benchmark":"quac","model":"llama-2-70b","score":49.3,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-70b","score":80.2,"metric":"percent"},{"benchmark":"glue","model":"vega-v1","score":91.3,"metric":"percent"},{"benchmark":"glue","model":"turing-nlr-v5","score":91.2,"metric":"percent"},{"benchmark":"glue","model":"deberta-plus-clever","score":91.1,"metric":"percent"},{"benchmark":"glue","model":"ernie","score":91.1,"metric":"percent"},{"benchmark":"glue","model":"structbert-plus-clever","score":91,"metric":"percent"},{"benchmark":"glue","model":"salsa","score":90.8,"metric":"percent"},{"benchmark":"glue","model":"deberta-turingnlrv4","score":90.8,"metric":"percent"},{"benchmark":"glue","model":"macalbert-plus-dkm","score":90.7,"metric":"percent"},{"benchmark":"glue","model":"albert-plus-daaf-plus-nas","score":90.6,"metric":"percent"},{"benchmark":"glue","model":"t5","score":90.3,"metric":"percent"},{"benchmark":"glue","model":"mt-dnn-smart","score":89.9,"metric":"percent"},{"benchmark":"glue","model":"nezha-large","score":89.8,"metric":"percent"},{"benchmark":"glue","model":"anna","score":89.8,"metric":"percent"},{"benchmark":"glue","model":"funnel-transformer-ensemble-b10-10-10h1024","score":89.7,"metric":"percent"},{"benchmark":"glue","model":"electra-large-plus-standard-tricks","score":89.4,"metric":"percent"},{"benchmark":"glue","model":"2digit-lanet","score":89.3,"metric":"percent"},{"benchmark":"glue","model":"dropattack-roberta-large","score":88.8,"metric":"percent"},{"benchmark":"glue","model":"freelb-roberta-ensemble","score":88.4,"metric":"percent"},{"benchmark":"glue","model":"hire-roberta","score":88.3,"metric":"percent"},{"benchmark":"glue","model":"electra-large-m-bert4keras","score":88.3,"metric":"percent"},{"benchmark":"glue","model":"roberta","score":88.1,"metric":"percent"},{"benchmark":"glue","model":"mt-dnn-ensemble","score":87.6,"metric":"percent"},{"benchmark":"glue","model":"electra-large-newscl-single","score":85.6,"metric":"percent"},{"benchmark":"glue","model":"bort-alexa-ai","score":83.6,"metric":"percent"},{"benchmark":"glue","model":"convbert-base","score":83.2,"metric":"percent"},{"benchmark":"glue","model":"snorkel-metal","score":83.2,"metric":"percent"},{"benchmark":"glue","model":"xlm-english-only","score":83.1,"metric":"percent"},{"benchmark":"glue","model":"convbert-base-paddle-v1.1","score":83.1,"metric":"percent"},{"benchmark":"glue","model":"robertamoe","score":83,"metric":"percent"},{"benchmark":"glue","model":"sembert","score":82.9,"metric":"percent"},{"benchmark":"glue","model":"mpnet-base-paddle","score":82.9,"metric":"percent"},{"benchmark":"glue","model":"spanbert-single-task-training","score":82.8,"metric":"percent"},{"benchmark":"glue","model":"distilroberta-plus-gal-6-layer-transformer-single-model","score":82.6,"metric":"percent"},{"benchmark":"glue","model":"bert-plus-bam","score":82.3,"metric":"percent"},{"benchmark":"glue","model":"span-extractive-bert-on-stilts","score":82.3,"metric":"percent"},{"benchmark":"glue","model":"lv-bert-base","score":82.1,"metric":"percent"},{"benchmark":"glue","model":"bert-on-stilts","score":82,"metric":"percent"},{"benchmark":"glue","model":"robustroberta","score":81.9,"metric":"percent"},{"benchmark":"glue","model":"warp-with-roberta","score":81.6,"metric":"percent"},{"benchmark":"glue","model":"bigs-128-1000k","score":81.5,"metric":"percent"},{"benchmark":"glue","model":"combinedkd-tinyroberta-6-layer-82m-parameters-mate-kd-plus-annealingkd","score":81.5,"metric":"percent"},{"benchmark":"glue","model":"segabert-large","score":81.4,"metric":"percent"},{"benchmark":"glue","model":"u-pmlm-r-huawei-noah-s-ark-lab","score":81.3,"metric":"percent"},{"benchmark":"glue","model":"ambert-base","score":81,"metric":"percent"},{"benchmark":"glue","model":"routed-berts","score":80.7,"metric":"percent"},{"benchmark":"glue","model":"cert","score":80.7,"metric":"percent"},{"benchmark":"glue","model":"bert-24-layers-16-heads-1024-hidden","score":80.5,"metric":"percent"},{"benchmark":"glue","model":"kerasnlp-xlm-r","score":80.4,"metric":"percent"},{"benchmark":"glue","model":"kerasnlp-roberta","score":80.4,"metric":"percent"},{"benchmark":"glue","model":"multiple-adapter-t5-base","score":80.3,"metric":"percent"},{"benchmark":"glue","model":"hf-bert-large-uncased-default-fine-tuning","score":80.2,"metric":"percent"},{"benchmark":"glue","model":"bert-plus-single-task-adapters","score":80.2,"metric":"percent"},{"benchmark":"glue","model":"ki-bert","score":80,"metric":"percent"},{"benchmark":"glue","model":"elasticbert-large-12l","score":79.9,"metric":"percent"},{"benchmark":"glue","model":"roberta-large-12l","score":79.8,"metric":"percent"},{"benchmark":"glue","model":"macaron-net-base","score":79.7,"metric":"percent"},{"benchmark":"glue","model":"gat-bert-base","score":79.6,"metric":"percent"},{"benchmark":"glue","model":"wt-vat-bert-base","score":79.5,"metric":"percent"},{"benchmark":"glue","model":"fd-cmic-plus-cm-mic-best-mnli-mm","score":79.3,"metric":"percent"},{"benchmark":"glue","model":"bert-n-pals","score":79.1,"metric":"percent"},{"benchmark":"glue","model":"deeppavlov-multitask-palbert","score":78.8,"metric":"percent"},{"benchmark":"glue","model":"bert-emd-6-layer-single-model-no-da","score":78.7,"metric":"percent"},{"benchmark":"glue","model":"sesamebert-base","score":78.6,"metric":"percent"},{"benchmark":"glue","model":"reptiledistil","score":78.5,"metric":"percent"},{"benchmark":"glue","model":"mobilebert","score":78.5,"metric":"percent"},{"benchmark":"glue","model":"stackingbert-base","score":78.4,"metric":"percent"},{"benchmark":"glue","model":"tinybert-6-layer-single-model","score":78.1,"metric":"percent"},{"benchmark":"glue","model":"squeezebert-4.3x-faster-than-bert-base-on-smartphone","score":78.1,"metric":"percent"},{"benchmark":"glue","model":"camtl","score":77.9,"metric":"percent"},{"benchmark":"glue","model":"krisfu","score":77.8,"metric":"percent"},{"benchmark":"glue","model":"memel-tune","score":77.6,"metric":"percent"},{"benchmark":"glue","model":"pocket-glue","score":77.6,"metric":"percent"},{"benchmark":"glue","model":"pavan-neerudu-bert","score":77.6,"metric":"percent"},{"benchmark":"glue","model":"bert-of-theseus-6-layer-single-model","score":77.1,"metric":"percent"},{"benchmark":"glue","model":"el-bert-6-layer-single-model","score":75.6,"metric":"percent"},{"benchmark":"superglue","model":"ernie-3.0","score":90.6,"metric":"percent"},{"benchmark":"boolq","model":"ernie-3.0","score":91,"metric":"percent"},{"benchmark":"copa","model":"ernie-3.0","score":97.4,"metric":"percent"},{"benchmark":"wsc","model":"ernie-3.0","score":97.3,"metric":"percent"},{"benchmark":"superglue","model":"ailabs-team-transformers","score":82.6,"metric":"percent"},{"benchmark":"boolq","model":"ailabs-team-transformers","score":88.1,"metric":"percent"},{"benchmark":"copa","model":"ailabs-team-transformers","score":86.8,"metric":"percent"},{"benchmark":"wsc","model":"ailabs-team-transformers","score":78.8,"metric":"percent"},{"benchmark":"superglue","model":"select-step-by-step","score":51.9,"metric":"percent"},{"benchmark":"boolq","model":"select-step-by-step","score":62.2,"metric":"percent"},{"benchmark":"copa","model":"select-step-by-step","score":96.4,"metric":"percent"},{"benchmark":"wsc","model":"select-step-by-step","score":67.8,"metric":"percent"},{"benchmark":"superglue","model":"adapet-albert-few-shot","score":76,"metric":"percent"},{"benchmark":"boolq","model":"adapet-albert-few-shot","score":80,"metric":"percent"},{"benchmark":"copa","model":"adapet-albert-few-shot","score":85.4,"metric":"percent"},{"benchmark":"wsc","model":"adapet-albert-few-shot","score":85.6,"metric":"percent"},{"benchmark":"superglue","model":"palm-540b","score":90.4,"metric":"percent"},{"benchmark":"boolq","model":"palm-540b","score":91.9,"metric":"percent"},{"benchmark":"copa","model":"palm-540b","score":99,"metric":"percent"},{"benchmark":"wsc","model":"palm-540b","score":95.9,"metric":"percent"},{"benchmark":"superglue","model":"pai-albert","score":86.1,"metric":"percent"},{"benchmark":"boolq","model":"pai-albert","score":88.1,"metric":"percent"},{"benchmark":"copa","model":"pai-albert","score":91.8,"metric":"percent"},{"benchmark":"wsc","model":"pai-albert","score":93.2,"metric":"percent"},{"benchmark":"superglue","model":"roberta-icets","score":86,"metric":"percent"},{"benchmark":"boolq","model":"roberta-icets","score":88.5,"metric":"percent"},{"benchmark":"copa","model":"roberta-icets","score":91.2,"metric":"percent"},{"benchmark":"wsc","model":"roberta-icets","score":89,"metric":"percent"},{"benchmark":"superglue","model":"nezha-plus","score":86.7,"metric":"percent"},{"benchmark":"boolq","model":"nezha-plus","score":87.8,"metric":"percent"},{"benchmark":"copa","model":"nezha-plus","score":93.6,"metric":"percent"},{"benchmark":"wsc","model":"nezha-plus","score":93.2,"metric":"percent"},{"benchmark":"superglue","model":"ipet-albert-few-shot-32-examples","score":75.4,"metric":"percent"},{"benchmark":"boolq","model":"ipet-albert-few-shot-32-examples","score":81.2,"metric":"percent"},{"benchmark":"copa","model":"ipet-albert-few-shot-32-examples","score":90.8,"metric":"percent"},{"benchmark":"wsc","model":"ipet-albert-few-shot-32-examples","score":88.4,"metric":"percent"},{"benchmark":"superglue","model":"roberta-ensemble","score":85.9,"metric":"percent"},{"benchmark":"boolq","model":"roberta-ensemble","score":88.2,"metric":"percent"},{"benchmark":"copa","model":"roberta-ensemble","score":90.8,"metric":"percent"},{"benchmark":"wsc","model":"roberta-ensemble","score":91.8,"metric":"percent"},{"benchmark":"superglue","model":"text-to-text-petl","score":77,"metric":"percent"},{"benchmark":"boolq","model":"text-to-text-petl","score":82,"metric":"percent"},{"benchmark":"copa","model":"text-to-text-petl","score":80.2,"metric":"percent"},{"benchmark":"wsc","model":"text-to-text-petl","score":74,"metric":"percent"},{"benchmark":"superglue","model":"st-moe-32b","score":91.2,"metric":"percent"},{"benchmark":"boolq","model":"st-moe-32b","score":92.4,"metric":"percent"},{"benchmark":"copa","model":"st-moe-32b","score":99.2,"metric":"percent"},{"benchmark":"wsc","model":"st-moe-32b","score":96.6,"metric":"percent"},{"benchmark":"superglue","model":"vega-v2","score":91.3,"metric":"percent"},{"benchmark":"boolq","model":"vega-v2","score":90.5,"metric":"percent"},{"benchmark":"copa","model":"vega-v2","score":99.4,"metric":"percent"},{"benchmark":"wsc","model":"vega-v2","score":98.6,"metric":"percent"},{"benchmark":"superglue","model":"install-albert-few-shot-32examples","score":76.6,"metric":"percent"},{"benchmark":"boolq","model":"install-albert-few-shot-32examples","score":78.4,"metric":"percent"},{"benchmark":"copa","model":"install-albert-few-shot-32examples","score":85.6,"metric":"percent"},{"benchmark":"wsc","model":"install-albert-few-shot-32examples","score":84.9,"metric":"percent"},{"benchmark":"superglue","model":"turing-nlr-v5","score":90.9,"metric":"percent"},{"benchmark":"boolq","model":"turing-nlr-v5","score":92,"metric":"percent"},{"benchmark":"copa","model":"turing-nlr-v5","score":98.2,"metric":"percent"},{"benchmark":"wsc","model":"turing-nlr-v5","score":97.3,"metric":"percent"},{"benchmark":"superglue","model":"frozen-t5-1.1-plus-spot","score":89.2,"metric":"percent"},{"benchmark":"boolq","model":"frozen-t5-1.1-plus-spot","score":91.1,"metric":"percent"},{"benchmark":"copa","model":"frozen-t5-1.1-plus-spot","score":95.6,"metric":"percent"},{"benchmark":"wsc","model":"frozen-t5-1.1-plus-spot","score":93.8,"metric":"percent"},{"benchmark":"superglue","model":"bert-plus-plus","score":71.5,"metric":"percent"},{"benchmark":"boolq","model":"bert-plus-plus","score":79,"metric":"percent"},{"benchmark":"copa","model":"bert-plus-plus","score":73.8,"metric":"percent"},{"benchmark":"wsc","model":"bert-plus-plus","score":64.4,"metric":"percent"},{"benchmark":"superglue","model":"deberta-turingnlrv4","score":90.3,"metric":"percent"},{"benchmark":"boolq","model":"deberta-turingnlrv4","score":90.4,"metric":"percent"},{"benchmark":"copa","model":"deberta-turingnlrv4","score":98.4,"metric":"percent"},{"benchmark":"wsc","model":"deberta-turingnlrv4","score":95.9,"metric":"percent"},{"benchmark":"superglue","model":"roberta-mtl-adv","score":85.7,"metric":"percent"},{"benchmark":"boolq","model":"roberta-mtl-adv","score":87.1,"metric":"percent"},{"benchmark":"copa","model":"roberta-mtl-adv","score":91.2,"metric":"percent"},{"benchmark":"wsc","model":"roberta-mtl-adv","score":91.8,"metric":"percent"},{"benchmark":"superglue","model":"t5","score":89.3,"metric":"percent"},{"benchmark":"boolq","model":"t5","score":91.2,"metric":"percent"},{"benchmark":"copa","model":"t5","score":94.8,"metric":"percent"},{"benchmark":"wsc","model":"t5","score":93.8,"metric":"percent"},{"benchmark":"superglue","model":"roberta","score":84.6,"metric":"percent"},{"benchmark":"boolq","model":"roberta","score":87.1,"metric":"percent"},{"benchmark":"copa","model":"roberta","score":90.6,"metric":"percent"},{"benchmark":"wsc","model":"roberta","score":89,"metric":"percent"},{"benchmark":"superglue","model":"gpt-3","score":71.8,"metric":"percent"},{"benchmark":"boolq","model":"gpt-3","score":76.4,"metric":"percent"},{"benchmark":"copa","model":"gpt-3","score":92,"metric":"percent"},{"benchmark":"wsc","model":"gpt-3","score":80.1,"metric":"percent"},{"benchmark":"superglue","model":"hairuo","score":90.6,"metric":"percent"},{"benchmark":"boolq","model":"hairuo","score":91.7,"metric":"percent"},{"benchmark":"copa","model":"hairuo","score":98.8,"metric":"percent"},{"benchmark":"wsc","model":"hairuo","score":100,"metric":"percent"},{"benchmark":"superglue","model":"t5-plus-udg-single-model-google-brain","score":90.4,"metric":"percent"},{"benchmark":"boolq","model":"t5-plus-udg-single-model-google-brain","score":91.4,"metric":"percent"},{"benchmark":"copa","model":"t5-plus-udg-single-model-google-brain","score":98,"metric":"percent"},{"benchmark":"wsc","model":"t5-plus-udg-single-model-google-brain","score":96.6,"metric":"percent"},{"benchmark":"superglue","model":"warp-albert-xxl-v2-few-shot-32-examples","score":48.7,"metric":"percent"},{"benchmark":"boolq","model":"warp-albert-xxl-v2-few-shot-32-examples","score":62.2,"metric":"percent"},{"benchmark":"copa","model":"warp-albert-xxl-v2-few-shot-32-examples","score":51.6,"metric":"percent"},{"benchmark":"wsc","model":"warp-albert-xxl-v2-few-shot-32-examples","score":63.7,"metric":"percent"},{"benchmark":"superglue","model":"bert-mtl","score":73.5,"metric":"percent"},{"benchmark":"boolq","model":"bert-mtl","score":84.8,"metric":"percent"},{"benchmark":"copa","model":"bert-mtl","score":73.8,"metric":"percent"},{"benchmark":"wsc","model":"bert-mtl","score":61,"metric":"percent"},{"benchmark":"superglue","model":"bort-alexa-ai","score":74.1,"metric":"percent"},{"benchmark":"boolq","model":"bort-alexa-ai","score":83.7,"metric":"percent"},{"benchmark":"copa","model":"bort-alexa-ai","score":89.6,"metric":"percent"},{"benchmark":"wsc","model":"bort-alexa-ai","score":65.8,"metric":"percent"},{"benchmark":"superglue","model":"snorkel-superglue-v1.9","score":74.5,"metric":"percent"},{"benchmark":"copa","model":"snorkel-superglue-v1.9","score":76.2,"metric":"percent"},{"benchmark":"wsc","model":"snorkel-superglue-v1.9","score":72.6,"metric":"percent"},{"benchmark":"superglue","model":"fsl-plus-plus-albert-few-shot-32-examples","score":77.7,"metric":"percent"},{"benchmark":"boolq","model":"fsl-plus-plus-albert-few-shot-32-examples","score":81.1,"metric":"percent"},{"benchmark":"copa","model":"fsl-plus-plus-albert-few-shot-32-examples","score":87,"metric":"percent"},{"benchmark":"wsc","model":"fsl-plus-plus-albert-few-shot-32-examples","score":88.4,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-3.5-sonnet-20241022","score":51.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-3.5-haiku-20241022","score":28,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-3-7-sonnet-20250219-thinking-32k","score":64.9,"metric":"percent"},{"benchmark":"aider-polyglot","model":"llama-4-maverick","score":15.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen3-235b-a22b-no-thinking","score":59.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-sonnet-4-20250514-thinking-32k","score":61.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-opus-4-thinking","score":72,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gemini-2.5-flash-preview-05-20-thinking","score":55.1,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3.2-exp-thinking","score":74.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3.2-exp","score":70.2,"metric":"percent"},{"benchmark":"aider-polyglot-diff","model":"claude-3.5-sonnet-20241022","score":51.6,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-4o-2024-11-20","score":18.2,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-4o-2024-08-06","score":23.1,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"o1-2024-12-17-high","score":61.7,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"deepseek-chat-v2.5","score":17.8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-3.5-haiku-20241022","score":28,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen2.5-coder-32b-instruct","score":8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"deepseek-chat-v3-prev","score":48.4,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"deepseek-r1","score":56.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen-max-2025-01-25","score":21.8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"o3-mini-medium","score":53.8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"o3-mini-high","score":60.4,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gemini-2.0-flash-thinking-exp-01-21","score":18.2,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"chatgpt-4o-latest-20250215","score":27.1,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-3.7-sonnet-20250219","score":60.4,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-3-7-sonnet-20250219-thinking-32k","score":64.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-4.5-preview","score":44.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwq-32b","score":20.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"deepseek-v3-0324","score":55.1,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"chatgpt-4o-latest-20250329","score":45.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"quasar-alpha","score":54.7,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"grok-3-beta","score":53.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"optimus-alpha","score":52.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-4.1","score":52.4,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-4.1-mini","score":32.4,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"o4-mini-high","score":72,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gemini-2.5-flash-preview-04-17","score":47.1,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen3-32b","score":40,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"qwen3-235b-a22b-no-thinking","score":59.6,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-sonnet-4-20250514","score":56.4,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-sonnet-4-20250514-thinking-32k","score":61.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-opus-4-20250514","score":70.7,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"claude-opus-4-thinking","score":72,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gemini-2.5-flash-preview-05-20","score":44,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gemini-2.5-flash-preview-05-20-thinking","score":55.1,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"deepseek-r1-0528","score":71.4,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"o3-high","score":81.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"o3","score":76.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"o3-pro-high","score":84.9,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"grok-4-high","score":79.6,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"kimi-k2","score":59.1,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-oss-120b-high","score":41.8,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-5-high","score":88,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-5-medium","score":86.7,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"gpt-5-low","score":81.3,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"deepseek-v3.2-exp-thinking","score":74.2,"metric":"pass@2"},{"benchmark":"aider-polyglot-diff","model":"deepseek-v3.2-exp","score":70.2,"metric":"pass@2"},{"benchmark":"livecodebench","model":"claude-3-haiku-20240307","score":20.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepseek-r1-preview","score":64.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepseek-r1-lite-preview","score":47.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepseek-v3","score":33.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-4-turbo-2024-04-09","score":26.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-4o-2024-05-13","score":32.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-4o-2024-08-06","score":29.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gpt-4o-mini-2024-07-18","score":27.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o1-preview-2024-09-12","score":42.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o1-mini-2024-09-12","score":49.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o1-2024-12-17-low","score":59.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o1-2024-12-17-high","score":72.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o3-mini-2025-01-31-low","score":62,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o3-mini-2025-01-31-med","score":66.3,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o3-mini-2025-01-31-high","score":74.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"o4-mini-high","score":74.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"claude-3.5-sonnet-20240620","score":32.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"claude-3.5-sonnet-20241022","score":40.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"claude-3-haiku-20240307","score":18,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-1.5-pro-002","score":34.2,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-1.5-flash-002","score":30.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-2.0-flash-exp","score":33.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"gemini-2.5-pro-exp-03.25","score":69.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"mistral-large-2411","score":26.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"codestral-2501","score":21.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwq-32b-preview","score":41.6,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"azerogpt-64b","score":10.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"kimi-k1.6-ioi-high","score":76.5,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"kimi-k1.6-ioi","score":67.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"qwq-max-preview","score":65.1,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"metastone-l1-7b","score":37.4,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"grok-3-mini-high","score":74.7,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"llama-3.1-nemotron-ultra-253b-v1","score":66.9,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"llama-3.1-nemotron-nano-8b-v1","score":51.8,"metric":"percent"},{"benchmark":"livecodebench-v5","model":"deepcoder-14b-preview","score":60.2,"metric":"percent"},{"benchmark":"livecodebench-pro","model":"claude-3.5-sonnet","score":572,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-4o-2024-11-20","score":210,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"o3-mini-2025-01-31","score":1688,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"deepseek-r1","score":1161,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"claude-3.7-sonnet-thinking","score":504,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-4.5-preview-2025-02-27","score":864,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"deepseek-v3","score":672,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"claude-3.7-sonnet","score":671,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"qwq-32b","score":981,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gemma-3-27b-it","score":402,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"deepseek-v3-0324","score":1124,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gemini-2.5-pro-preview-03-25","score":1694,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-4.1-mini","score":875,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"llama-4-maverick","score":528,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-4.1","score":606,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gemini-2.5-flash-preview-04-17","score":1334,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"qwen3-235b-a22b","score":1012,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gemini-2.5-flash","score":1288,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"deepseek-r1-0528","score":1284,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"seed1.6-thinking","score":1270,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gemini-2.5-pro","score":1769,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-oss-120b","score":1299,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-oss-20b","score":1030,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"grok-4-fast-thinking","score":962,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"grok-4-fast","score":770,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-5-high","score":2176,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"o3-high","score":1010,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"o4-mini-high","score":2092,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"qwen3-max","score":1226,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"qwen3-next-80b-a3b-thinking","score":1603,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"qwen3-30b-a3b","score":1206,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"glm-4.5","score":941,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"qwen3-235b-a22b-thinking-2507","score":1673,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"claude-4.5-sonnet-thinking","score":1412,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-5.1-high","score":2269,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"nemotron-cascade-14b-thinking","score":923,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gpt-5.2-high","score":2393,"metric":"elo"},{"benchmark":"livecodebench-pro","model":"gemini-3-deep-think","score":3298,"metric":"elo"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gemini-3-pro","score":94.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gemini-3.1-pro","score":94.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gemini-3-deep-think","score":94.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gemini-3-flash","score":92.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gpt-5.2-high","score":91.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"gpt-5-high","score":85.6,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"o4-mini-high","score":84.5,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"qwen3-next-80b-a3b-thinking","score":74.2,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"nemotron-cascade-14b-thinking","score":70.1,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-easy","model":"claude-4.5-sonnet-thinking","score":55.7,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gemini-3-deep-think","score":86,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gemini-3.1-pro","score":64.9,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gpt-5.2-high","score":59.6,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gemini-3-flash","score":50.9,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gemini-3-pro","score":45.6,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"gpt-5-high","score":43.9,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"o4-mini-high","score":29.8,"metric":"percent"},{"benchmark":"livecodebench-pro-25q2-med","model":"qwen3-next-80b-a3b-thinking","score":10.5,"metric":"percent"},{"benchmark":"evalplus","model":"opencoder-8b-instruct","score":77.4,"metric":"percent"},{"benchmark":"evalplus","model":"artigenz-coder-ds-6.7b","score":72.6,"metric":"percent"},{"benchmark":"evalplus","model":"code-13b","score":52.4,"metric":"percent"},{"benchmark":"evalplus","model":"code-290k-6.7b-instruct","score":59.7,"metric":"percent"},{"benchmark":"evalplus","model":"code-33b","score":49.4,"metric":"percent"},{"benchmark":"evalplus","model":"codegen-16b","score":28,"metric":"percent"},{"benchmark":"evalplus","model":"codegen-2b","score":22.6,"metric":"percent"},{"benchmark":"evalplus","model":"codegen-6b","score":25.6,"metric":"percent"},{"benchmark":"evalplus","model":"codegen2-16b","score":16.5,"metric":"percent"},{"benchmark":"evalplus","model":"codegen2-1b","score":9.1,"metric":"percent"},{"benchmark":"humaneval","model":"codegen2-1b","score":11,"metric":"percent"},{"benchmark":"evalplus","model":"codegen2-3b","score":12.8,"metric":"percent"},{"benchmark":"evalplus","model":"codegen2-7b","score":17.7,"metric":"percent"},{"benchmark":"evalplus","model":"codellama-13b","score":38.4,"metric":"percent"},{"benchmark":"evalplus","model":"codellama-34b","score":43.9,"metric":"percent"},{"benchmark":"evalplus","model":"codellama-70b","score":50.6,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-70b","score":55.5,"metric":"percent"},{"benchmark":"evalplus","model":"codellama-70b-instruct","score":65.9,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-70b-instruct","score":72,"metric":"percent"},{"benchmark":"evalplus","model":"codellama-7b","score":35.4,"metric":"percent"},{"benchmark":"evalplus","model":"codeqwen1.5-7b","score":45.7,"metric":"percent"},{"benchmark":"evalplus","model":"codeqwen1.5-7b-chat","score":78.7,"metric":"percent"},{"benchmark":"evalplus","model":"qwen1.5-72b-chat","score":59.1,"metric":"percent"},{"benchmark":"evalplus","model":"codet5plus-16b","score":26.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codet5plus-16b","score":26.8,"metric":"percent"},{"benchmark":"mbpp","model":"codet5plus-16b","score":56.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codet5plus-16b","score":47.1,"metric":"percent"},{"benchmark":"evalplus","model":"codet5-2b","score":22,"metric":"percent"},{"benchmark":"humaneval","model":"codet5-2b","score":25,"metric":"percent"},{"benchmark":"evalplus","model":"codet5plus-6b","score":24.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codet5plus-6b","score":24.4,"metric":"percent"},{"benchmark":"mbpp","model":"codet5plus-6b","score":52.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codet5plus-6b","score":41.5,"metric":"percent"},{"benchmark":"evalplus","model":"command-r-plus","score":56.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"command-r-plus","score":56.7,"metric":"percent"},{"benchmark":"humaneval","model":"command-r-plus","score":64,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-v3","score":86.6,"metric":"percent"},{"benchmark":"evalplus","model":"gemini-1.5-pro-002","score":79.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-1.5-pro-002","score":79.3,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-1.5-pro-002","score":89,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-1.5-pro-002","score":89.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-1.5-pro-002","score":74.6,"metric":"percent"},{"benchmark":"evalplus","model":"gemini-1.5-flash-002","score":75.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemini-1.5-flash-002","score":75.6,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-1.5-flash-002","score":82.3,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-1.5-flash-002","score":84.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemini-1.5-flash-002","score":67.5,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-coder-1.3b-base","score":25.6,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-coder-1.3b-instruct","score":60.4,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-coder-33b-base","score":44.5,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-coder-33b-instruct","score":75,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-coder-6.7b-base","score":39.6,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-coder-6.7b-instruct","score":71.3,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-coder-7b-instruct-v1.5","score":71.3,"metric":"percent"},{"benchmark":"evalplus","model":"claude-3.5-sonnet-20240620","score":81.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3.5-sonnet-20240620","score":81.7,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3.5-sonnet-20240620","score":87.2,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3.5-sonnet-20240620","score":89.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3.5-sonnet-20240620","score":74.3,"metric":"percent"},{"benchmark":"evalplus","model":"grok-beta","score":80.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"grok-beta","score":80.5,"metric":"percent"},{"benchmark":"humaneval","model":"grok-beta","score":88.4,"metric":"percent"},{"benchmark":"mbpp","model":"grok-beta","score":86,"metric":"percent"},{"benchmark":"mbpp-plus","model":"grok-beta","score":65.6,"metric":"percent"},{"benchmark":"evalplus","model":"o1-preview-2024-09-12","score":89,"metric":"percent"},{"benchmark":"humaneval-plus","model":"o1-preview-2024-09-12","score":89,"metric":"percent"},{"benchmark":"humaneval","model":"o1-preview-2024-09-12","score":96.3,"metric":"percent"},{"benchmark":"mbpp","model":"o1-preview-2024-09-12","score":95.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"o1-preview-2024-09-12","score":80.2,"metric":"percent"},{"benchmark":"evalplus","model":"o1-mini-2024-09-12","score":89,"metric":"percent"},{"benchmark":"humaneval-plus","model":"o1-mini-2024-09-12","score":89,"metric":"percent"},{"benchmark":"humaneval","model":"o1-mini-2024-09-12","score":96.3,"metric":"percent"},{"benchmark":"mbpp","model":"o1-mini-2024-09-12","score":93.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"o1-mini-2024-09-12","score":78.8,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-4o-2024-08-06","score":87.2,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-4o-mini-2024-07-18","score":83.5,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-3.5-may-2023","score":66.5,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5-may-2023","score":73.2,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-3.5-turbo-1106","score":70.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-3.5-turbo-1106","score":70.7,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5-turbo-1106","score":76.8,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-3.5-turbo-1106","score":82.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-3.5-turbo-1106","score":69.7,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-4","score":79.3,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-4-turbo-2024-04-09","score":86.6,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-4-1106-preview","score":81.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4-1106-preview","score":81.7,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4-1106-preview","score":85.4,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4-1106-preview","score":85.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4-1106-preview","score":73.3,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-j-6b","score":11,"metric":"percent"},{"benchmark":"evalplus","model":"gpt-neo-2.7b","score":6.7,"metric":"percent"},{"benchmark":"evalplus","model":"gemini-1.0-pro","score":55.5,"metric":"percent"},{"benchmark":"evalplus","model":"gemini-1.5-pro","score":61,"metric":"percent"},{"benchmark":"evalplus","model":"incoder-1.3b","score":11,"metric":"percent"},{"benchmark":"evalplus","model":"incoder-6.7b","score":12.2,"metric":"percent"},{"benchmark":"evalplus","model":"llama-3-70b-instruct","score":72,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3-70b-instruct","score":72,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b-instruct","score":77.4,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-70b-instruct","score":82.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-70b-instruct","score":69,"metric":"percent"},{"benchmark":"evalplus","model":"llama-3-8b-base","score":29.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3-8b-base","score":29.3,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-8b-base","score":33.5,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b-base","score":61.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-8b-base","score":51.6,"metric":"percent"},{"benchmark":"evalplus","model":"llama-3.1-8b-instruct","score":62.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-8b-instruct","score":62.8,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-8b-instruct","score":69.5,"metric":"percent"},{"benchmark":"evalplus","model":"llama-3-8b-instruct","score":56.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3-8b-instruct","score":56.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-8b-instruct","score":61.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b-instruct","score":64.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-8b-instruct","score":54.8,"metric":"percent"},{"benchmark":"evalplus","model":"wavecoder-ultra-6.7b","score":69.5,"metric":"percent"},{"benchmark":"humaneval","model":"wavecoder-ultra-6.7b","score":75,"metric":"percent"},{"benchmark":"evalplus","model":"magicoder-s-cl-7b","score":67.7,"metric":"percent"},{"benchmark":"evalplus","model":"magicoder-s-ds-6.7b","score":71.3,"metric":"percent"},{"benchmark":"evalplus","model":"mistral-large-2402","score":62.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-large-2402","score":62.2,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-large-2402","score":69.5,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-large-2402","score":72.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistral-large-2402","score":59.5,"metric":"percent"},{"benchmark":"evalplus","model":"mistral-7b","score":23.8,"metric":"percent"},{"benchmark":"evalplus","model":"mistral-codealpaca-7b","score":42.1,"metric":"percent"},{"benchmark":"evalplus","model":"mistralhermes-codepro-7b-v1","score":42.1,"metric":"percent"},{"benchmark":"evalplus","model":"databricks-dbrx-instruct","score":70.1,"metric":"percent"},{"benchmark":"humaneval","model":"databricks-dbrx-instruct","score":75,"metric":"percent"},{"benchmark":"evalplus","model":"codestral-22b-v0.1","score":73.8,"metric":"percent"},{"benchmark":"humaneval","model":"codestral-22b-v0.1","score":79.9,"metric":"percent"},{"benchmark":"evalplus","model":"mistral-7b-instruct-v0.2","score":36,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-instruct-v0.2","score":42.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistral-7b-instruct-v0.2","score":37,"metric":"percent"},{"benchmark":"evalplus","model":"mixtral-8x22b-instruct-v0.1","score":72,"metric":"percent"},{"benchmark":"evalplus","model":"mixtral-8x7b-instruct-v0.1","score":39.6,"metric":"percent"},{"benchmark":"evalplus","model":"openchat-3.5-7b-0106","score":67.7,"metric":"percent"},{"benchmark":"evalplus","model":"opencodeinterpreter-ds-33b","score":73.8,"metric":"percent"},{"benchmark":"evalplus","model":"opencodeinterpreter-ds-6.7b","score":72,"metric":"percent"},{"benchmark":"evalplus","model":"openhermes-2.5-code-290k-13b","score":48.8,"metric":"percent"},{"benchmark":"evalplus","model":"phind-codellama-34b-v2","score":67.1,"metric":"percent"},{"benchmark":"evalplus","model":"polycoder-2.7b","score":6.1,"metric":"percent"},{"benchmark":"evalplus","model":"python-code-13b","score":30.5,"metric":"percent"},{"benchmark":"evalplus","model":"solar-10.7b-instruct-v1.0","score":37.2,"metric":"percent"},{"benchmark":"evalplus","model":"santacoder-1.1b","score":14,"metric":"percent"},{"benchmark":"evalplus","model":"stablelm-7b","score":2.4,"metric":"percent"},{"benchmark":"evalplus","model":"starchat2-15b-v0.1","score":71.3,"metric":"percent"},{"benchmark":"evalplus","model":"starcoder-15b","score":29.3,"metric":"percent"},{"benchmark":"evalplus","model":"starcoder2-15b-instruct-v0.1","score":60.4,"metric":"percent"},{"benchmark":"evalplus","model":"starcoder2-15b","score":37.8,"metric":"percent"},{"benchmark":"evalplus","model":"starcoder2-3b","score":27.4,"metric":"percent"},{"benchmark":"evalplus","model":"starcoder2-7b","score":29.9,"metric":"percent"},{"benchmark":"evalplus","model":"starcoderbase-1b","score":12.2,"metric":"percent"},{"benchmark":"evalplus","model":"starcoderbase-3b","score":15.9,"metric":"percent"},{"benchmark":"evalplus","model":"starcoderbase-7b","score":21.3,"metric":"percent"},{"benchmark":"evalplus","model":"vicuna-13b","score":15.9,"metric":"percent"},{"benchmark":"evalplus","model":"vicuna-7b","score":11.6,"metric":"percent"},{"benchmark":"evalplus","model":"whiterabbitneo-33b-v1","score":65.9,"metric":"percent"},{"benchmark":"humaneval","model":"whiterabbitneo-33b-v1","score":72,"metric":"percent"},{"benchmark":"evalplus","model":"wizardcoder-15b-v1.0","score":50.6,"metric":"percent"},{"benchmark":"evalplus","model":"wizardcoder-33b-v1.1","score":73.2,"metric":"percent"},{"benchmark":"evalplus","model":"wizardcoder-python-34b-v1.0","score":64.6,"metric":"percent"},{"benchmark":"evalplus","model":"wizardcoder-python-7b-v1.0","score":45.1,"metric":"percent"},{"benchmark":"evalplus","model":"xwincoder-34b","score":69.5,"metric":"percent"},{"benchmark":"evalplus","model":"zephyr-7b-beta","score":23.2,"metric":"percent"},{"benchmark":"humaneval","model":"zephyr-7b-beta","score":30,"metric":"percent"},{"benchmark":"evalplus","model":"claude-2","score":61.6,"metric":"percent"},{"benchmark":"evalplus","model":"claude-3-haiku-20240307","score":68.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3-haiku-20240307","score":68.9,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3-haiku-20240307","score":76.8,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3-haiku-20240307","score":80.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3-haiku-20240307","score":68.8,"metric":"percent"},{"benchmark":"evalplus","model":"claude-3-opus-20240229","score":77.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3-opus-20240229","score":77.4,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3-opus-20240229","score":82.9,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3-opus-20240229","score":89.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3-opus-20240229","score":73.3,"metric":"percent"},{"benchmark":"evalplus","model":"claude-3-sonnet-20240229","score":64,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3-sonnet-20240229","score":64,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3-sonnet-20240229","score":70.7,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3-sonnet-20240229","score":83.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3-sonnet-20240229","score":69.3,"metric":"percent"},{"benchmark":"evalplus","model":"claude-instant-1-mar-2024","score":50.6,"metric":"percent"},{"benchmark":"evalplus","model":"code-millenials-34b","score":70.7,"metric":"percent"},{"benchmark":"evalplus","model":"codegemma-2b","score":20.7,"metric":"percent"},{"benchmark":"evalplus","model":"codegemma-7b","score":41.5,"metric":"percent"},{"benchmark":"evalplus","model":"codegemma-7b-it","score":51.8,"metric":"percent"},{"benchmark":"evalplus","model":"dolphin-2.6-mixtral-8x7b","score":57.3,"metric":"percent"},{"benchmark":"humaneval","model":"dolphin-2.6-mixtral-8x7b","score":64,"metric":"percent"},{"benchmark":"evalplus","model":"gemma-1.1-2b-it","score":17.7,"metric":"percent"},{"benchmark":"evalplus","model":"gemma-1.1-7b-it","score":35.4,"metric":"percent"},{"benchmark":"evalplus","model":"gemma-2b","score":20.7,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2b","score":25,"metric":"percent"},{"benchmark":"evalplus","model":"gemma-2b-it","score":15.2,"metric":"percent"},{"benchmark":"evalplus","model":"gemma-7b","score":28.7,"metric":"percent"},{"benchmark":"evalplus","model":"gemma-7b-it","score":25,"metric":"percent"},{"benchmark":"evalplus","model":"phi-3-mini-4k-instruct","score":59.1,"metric":"percent"},{"benchmark":"evalplus","model":"phi-2","score":45.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"phi-2","score":45.1,"metric":"percent"},{"benchmark":"humaneval","model":"phi-2","score":49.4,"metric":"percent"},{"benchmark":"mbpp","model":"phi-2","score":64,"metric":"percent"},{"benchmark":"mbpp-plus","model":"phi-2","score":54.2,"metric":"percent"},{"benchmark":"evalplus","model":"speechless-code-mistral-7b-v1.0","score":41.5,"metric":"percent"},{"benchmark":"evalplus","model":"speechless-codellama-34b-v2.0","score":72,"metric":"percent"},{"benchmark":"evalplus","model":"speechless-coder-ds-6.7b","score":65.9,"metric":"percent"},{"benchmark":"evalplus","model":"speechless-coding-7b-16k-tora","score":50.6,"metric":"percent"},{"benchmark":"evalplus","model":"speechless-starcoder2-15b","score":62.8,"metric":"percent"},{"benchmark":"evalplus","model":"speechless-starcoder2-7b","score":51.8,"metric":"percent"},{"benchmark":"evalplus","model":"stablecode-3b","score":25.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"stablecode-3b","score":25.6,"metric":"percent"},{"benchmark":"humaneval","model":"stablecode-3b","score":29.3,"metric":"percent"},{"benchmark":"mbpp","model":"stablecode-3b","score":54.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"stablecode-3b","score":45.8,"metric":"percent"},{"benchmark":"evalplus","model":"xdan-l1-chat-rl-v1-7b","score":32.9,"metric":"percent"},{"benchmark":"evalplus","model":"zyte-1b","score":1.8,"metric":"percent"},{"benchmark":"evalperf","model":"claude-3.5-sonnet-20240620","score":93.9,"metric":"percent"},{"benchmark":"crux-i","model":"phind-codellama-34b-v2","score":47.2,"metric":"percent"},{"benchmark":"crux-o","model":"phind-codellama-34b-v2","score":39.7,"metric":"pass@1"},{"benchmark":"crux-o","model":"phind-codellama-34b-v2","score":52.8,"metric":"pass@5"},{"benchmark":"crux-i","model":"claude-3-opus","score":64.2,"metric":"percent"},{"benchmark":"crux-o","model":"claude-3-opus","score":65.8,"metric":"pass@1"},{"benchmark":"crux-i","model":"claude-3-opus-cot","score":73.4,"metric":"percent"},{"benchmark":"crux-o","model":"claude-3-opus-cot","score":82,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"mistral-large-2402","score":34.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen1.5-32b-chat","score":37.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-coder-33b-instruct","score":46.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-coder-6.7b-instruct","score":39.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3-70b-instruct","score":49.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3-8b-instruct","score":34.4,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"granite-code-20b-instruct","score":38,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemini-1.5-pro-api-0514","score":50.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"codestral-22b-v0.1","score":47.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"autocoder-qw-7b","score":37,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"reflectioncoder-ds-33b","score":47.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-v2-chat-0628","score":54.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gemma-2-27b-it","score":47.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"artigenz-coder-ds-6.7b","score":42.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"openchat-3.6-8b-20240522","score":32.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"athene-70b","score":42.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"tess-v2.5.2-qwen2-72b","score":41.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"whiterabbitneo-33b-v1.5","score":47.2,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3.1-8b-instruct","score":36.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"phi-3.5-mini-instruct","score":35.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"yi-coder-9b-chat","score":43.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-1.5b-instruct","score":23.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-14b-instruct","score":46,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"qwen2.5-32b-instruct","score":48.7,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-3.2-1b-instruct","score":9.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"claude-3.5-sonnet-20241022","score":51.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"claude-3.5-haiku-20241022","score":52.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"opencoder-1.5b-instruct","score":36.8,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"opencoder-8b-instruct","score":47.1,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"athene-v2-chat","score":52,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"deepseek-r1-distill-llama-8b","score":13,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"sky-t1-32b-preview","score":48,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"llama-4-maverick","score":55.6,"metric":"pass@1"},{"benchmark":"bigcodebench","model":"gpt-4.1-mini-2025-04-14","score":54.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codegemma-7b-it","score":10.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4-0613","score":17.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-large-2402","score":8.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3-70b-instruct","score":24.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3-8b-instruct","score":7.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"granite-code-34b-instruct","score":14.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3-opus-20240229","score":26,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2-72b-chat","score":20.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-1.5-flash-api-0514","score":23.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"command-r-plus","score":13.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-instruct","score":27,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"hermes-2-theta-llama-3-70b","score":22.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"wavecoder-ultra-6.7b","score":14.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"reflectioncoder-cl-7b","score":9.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"phi-3.1-mini-128k-instruct","score":22,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"internlm2.5-7b-chat","score":5.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"hermes-2-pro-llama-3-70b","score":21.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-v2-chat-0628","score":28.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemma-2-27b-it","score":20,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3-70b-synthia-v3.5","score":23.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"tess-v2.5.2-qwen2-72b","score":16.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"whiterabbitneo-33b-v1.5","score":19.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-large-instruct-2407","score":26,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-instruct-0724","score":29.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"phi-3.5-mini-instruct","score":14.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"c4ai-command-r-08-2024","score":13.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-1.5-pro-002","score":26.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"mistral-small-instruct-2409","score":14.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-1.5b-instruct","score":3.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-32b-instruct","score":24.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3.2-1b-instruct","score":1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"llama-3.1-nemotron-70b-instruct","score":24.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"granite-3.0-8b-instruct","score":8.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"grok-beta","score":26.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-14b-instruct","score":26.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-v2.5-1210","score":26.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemini-2.0-flash-thinking-exp-01-21","score":27,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-2024-12-17-low","score":34.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-2024-12-17-high","score":35.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o3-mini-2025-01-31-med","score":35.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o3-mini-2025-01-31-low","score":34.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o3-mini-2025-01-31-high","score":35.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"sky-t1-32b-preview","score":28,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3.7-sonnet-thinking","score":35.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gemma-3-27b-it","score":26,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwq-32b","score":29,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"grok-3-mini-beta-low","score":31.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"grok-3-mini-beta-high","score":26.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4.1-mini-2025-04-14","score":32.8,"metric":"pass@1"},{"benchmark":"gso-benchmark","model":"claude-opus-4.8","score":47.06,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-sonnet-5","score":37.25,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-opus-4.7","score":44.12,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-opus-4.6","score":41.18,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-5.5","score":40.2,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-5.4","score":31.37,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gemini-3.1-pro","score":22.55,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gemini-3-flash","score":9.8,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-5.2-high","score":27.45,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-5.1-high","score":13.73,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-opus-4.5","score":26.47,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gemini-3-pro","score":18.63,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gemini-2.5-pro","score":3.92,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-sonnet-4.5","score":14.71,"metric":"percent"},{"benchmark":"gso-benchmark","model":"qwen3-coder-480b-a35b-instruct","score":4.9,"metric":"percent"},{"benchmark":"gso-benchmark","model":"glm-4.5-air","score":2.94,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-5-high","score":6.86,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-opus-4","score":6.86,"metric":"percent"},{"benchmark":"gso-benchmark","model":"o3-high","score":8.82,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-sonnet-4","score":4.9,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-4o","score":0,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-fable-5.1","score":88.24,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-6-astra","score":79.41,"metric":"percent"},{"benchmark":"gso-benchmark","model":"claude-fable-5","score":78.43,"metric":"percent"},{"benchmark":"gso-benchmark","model":"gpt-5.6-sol","score":76.47,"metric":"percent"},{"benchmark":"autocodebench","model":"kimi-k2-0711-preview","score":47.8,"metric":"percent"},{"benchmark":"autocodebench","model":"seed1.6-enabled","score":45.3,"metric":"percent"},{"benchmark":"autocodebench","model":"seed1.6-thinking-250715","score":45,"metric":"percent"},{"benchmark":"autocodebench","model":"qwen3-coder-480b-a35b-instruct","score":44.8,"metric":"percent"},{"benchmark":"autocodebench","model":"hunyuan-turbos-20250716","score":43.8,"metric":"percent"},{"benchmark":"autocodebench","model":"ernie-x1-turbo-32k","score":39.6,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"claude-opus-4-thinking","score":64.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"claude-sonnet-4-thinking","score":62,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"claude-opus-4","score":61.7,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"deepseek-r1-0528","score":61.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"claude-sonnet-4","score":59.8,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-235b-a22b-thinking-2507","score":57.3,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"gpt-4.1-2025-04-14","score":56.9,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"deepseek-v3-0324","score":56.8,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"kimi-k2-0711-preview","score":55.4,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"glm-4.5","score":55,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen-3-235b-a22b-thinking","score":54.7,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"seed1.6-thinking-250715","score":53.9,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"seed1.6-enabled","score":53.2,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"gemini-2.5-flash","score":52.9,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-coder-480b-a35b-instruct","score":51.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"seed1.6-thinking","score":51.2,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"hunyuan-turbos-20250716","score":50.3,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-235b-a22b-instruct-2507","score":49.8,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"seed1.6","score":48.8,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-32b-thinking","score":47.6,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"glm-4.5-air","score":46.2,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"gpt-4o-2024-11-20","score":45.8,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"ernie-x1-turbo-32k","score":44.4,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-14b-thinking","score":40.7,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"deepseek-coder-v2-instruct","score":40.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen2.5-coder-32b-instruct","score":37,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"hunyuan-coder-b8-preview","score":36.4,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen2.5-72b-instruct","score":35.1,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"seed-coder-8b-instruct","score":32.7,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-32b","score":32.3,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-8b-thinking","score":28.9,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-14b","score":27.8,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"deepseek-coder-33b-instruct","score":27.7,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-4b-thinking","score":23.2,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen2.5-coder-7b-instruct","score":21.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"qwen3-8b","score":21.4,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"deepseek-coder-6.7b-instruct","score":20.5,"metric":"percent"},{"benchmark":"autocodebench-lite","model":"opencoder-8b-instruct","score":20.1,"metric":"percent"},{"benchmark":"cwe-bench","model":"grok-4.7","score":68,"metric":"percent"},{"benchmark":"cwe-bench","model":"grok-4.6","score":57,"metric":"percent"},{"benchmark":"cwe-bench","model":"deepseek-v4.1-flash","score":55,"metric":"percent"},{"benchmark":"cwe-bench","model":"muse-spark-1.3","score":55,"metric":"percent"},{"benchmark":"cwe-bench","model":"hy4-preview","score":53,"metric":"percent"},{"benchmark":"cwe-bench","model":"gpt-6-sol","score":52,"metric":"percent"},{"benchmark":"cwe-bench","model":"inkling","score":37,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-opus-4.6","score":100,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gpt-5.2-medium","score":100,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-opus-4.5","score":100,"metric":"percent"},{"benchmark":"roo-code-evals","model":"gemini-3-pro-preview","score":100,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-sonnet-4.5","score":100,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-sonnet-4","score":98,"metric":"percent"},{"benchmark":"roo-code-evals","model":"grok-4-fast","score":97,"metric":"percent"},{"benchmark":"roo-code-evals","model":"claude-4.5-haiku","score":95,"metric":"percent"},{"benchmark":"roo-code-evals","model":"minimax-m2","score":89,"metric":"percent"},{"benchmark":"roo-code-evals","model":"glm-4.6","score":85,"metric":"percent"},{"benchmark":"roo-code-evals","model":"qwen3-coder-480b-a35b-instruct","score":84,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-4o-2024-11-20","score":4.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"llama-4-maverick","score":4.38,"metric":"percent"},{"benchmark":"arc-agi-1","model":"llama-4-scout","score":0.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-4.1-nano","score":0,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-4.1-mini","score":3.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-mini-low","score":14.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-mini-medium","score":22.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-medium","score":53.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-high","score":60.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o4-mini-low","score":21.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o4-mini-medium","score":41.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o4-mini-high","score":58.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-05-20","score":33.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-thinking-8k","score":25.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-thinking-16k","score":33.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-flash-preview-thinking-24k","score":32.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"codex-mini-latest","score":27.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4-20250514","score":23.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4-20250514-thinking-16k","score":35.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4-20250514-thinking-8k","score":30.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4-20250514-thinking-1k","score":27,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4-20250514","score":22.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-r1-0528","score":21.21,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-3","score":5.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-3-mini-beta-low","score":16.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-pro-low","score":44.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"o3-pro-high","score":59.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"magistral-small-2506","score":5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"magistral-medium-2506","score":5.91,"metric":"percent"},{"benchmark":"arc-agi-1","model":"magistral-medium-thinking","score":6.12,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-2.5-pro-thinking-1k","score":16,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4","score":66.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-high","score":65.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-medium","score":56.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-minimal","score":6,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-high","score":54.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-medium","score":37.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-low","score":26.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-mini-minimal","score":5.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-nano-high","score":16.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-nano-medium","score":20.71,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-nano-low","score":4.04,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-nano-minimal","score":1.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"berman-grok-4-refine","score":79.6,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4.5","score":25.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-sonnet-thinking-16k","score":48.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-sonnet-thinking-32k","score":63.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5-pro","score":70.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"trm","score":40,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-haiku","score":14.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-haiku-thinking-1k","score":16.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-haiku-thinking-8k","score":25.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-haiku-thinking-16k","score":37.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-4.5-haiku-thinking-32k","score":47.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4-fast-thinking","score":48.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.1-none","score":5.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.1-low","score":33.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.1-medium","score":57.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.1-high","score":72.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-pro-preview","score":75,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-deep-think-preview","score":87.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.5","score":40,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.5-thinking-8k","score":58.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.5-thinking-16k","score":72,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.5-thinking-32k","score":75.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.5-thinking-64k","score":80,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-none","score":12.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-low","score":55.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-medium","score":72.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-high","score":78.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-thinking-xhigh","score":86.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-pro-medium","score":81.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-pro-high","score":85.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.2-pro-xhigh","score":90.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-flash-minimal","score":21.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-flash-low","score":29,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-flash-medium","score":57.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-flash-high","score":84.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.2","score":89.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"johan-land-gpt-5.2-refine","score":94.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.6-low","score":86,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.6-medium","score":92,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.6-high","score":94,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.6-max","score":93,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.8-low","score":88,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.8-medium","score":91.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.8-high","score":92,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.8-max","score":92.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3-deep-think","score":96,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4.6-max","score":86,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-sonnet-4.6-high","score":86.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"kimi-k2.5-thinking","score":65.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"minimax-m2.5","score":63.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v3.2","score":57,"metric":"percent"},{"benchmark":"arc-agi-1","model":"glm-5","score":44.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-low","score":68.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-medium","score":86.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-high","score":92.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-xhigh","score":93.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-pro-xhigh","score":94.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-mini-xhigh","score":63.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-mini-high","score":58,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-mini-medium","score":40.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-mini-low","score":13,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-nano-xhigh","score":51.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-nano-high","score":38.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-nano-medium","score":33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.4-nano-low","score":18.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.7-low","score":91,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.7-medium","score":91,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.7-high","score":93.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-4.7-max","score":92,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.5-low","score":76.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.5-medium","score":92.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.5-high","score":94.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.5-xhigh","score":95,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.5-pro-high","score":96.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.5-pro-xhigh","score":95,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.5-flash-minimal","score":48.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.5-flash-high","score":92.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-sol-low","score":74.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-sol-medium","score":92.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-sol-high","score":97,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-sol-xhigh","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-sol-max","score":96.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-terra-low","score":60.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-terra-medium","score":77,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-terra-high","score":92,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-terra-xhigh","score":94,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-terra-max","score":96.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-low","score":34.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-medium","score":56.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-high","score":76.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-xhigh","score":87.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-max","score":88,"metric":"percent"},{"benchmark":"arc-agi-1","model":"glm-5.2","score":77,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.5-high","score":85.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.5-medium","score":87.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.5-low","score":79.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-5-high","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-5-max","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"inkling-small-xhigh","score":84,"metric":"percent"},{"benchmark":"arc-agi-1","model":"inkling-small-high","score":78,"metric":"percent"},{"benchmark":"arc-agi-1","model":"inkling-small-medium","score":67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"inkling-small-low","score":52.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"inkling-small-minimal","score":48.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"inkling-small-none","score":5.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"kimi-k3-max","score":94.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"kimi-k3-high","score":86.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"kimi-k3-low","score":65.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5-max","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5-xhigh","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5-high","score":95.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5-medium","score":92.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5-low","score":90.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4-flash-0731-max","score":89,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4-flash-0731-high","score":87,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4-flash-0731-low","score":84,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4-flash-0731-none","score":11.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-0730-max","score":90.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-0730-xhigh","score":85,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-0730-high","score":78,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-0730-medium","score":54,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-0730-low","score":39.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-5.6-luna-0730-none","score":3.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.5-flash-lite-high","score":53.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.5-flash-lite-medium","score":32.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.5-flash-lite-low","score":17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.5-flash-lite-minimal","score":7.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.6-flash-high","score":91.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.6-flash-medium","score":83.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.6-flash-low","score":76.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.6-flash-minimal","score":34.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.6-xhigh","score":87,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.6-high","score":87,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.6-medium","score":87.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.6-low","score":74.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.7-flash-high","score":95.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.7-flash-medium","score":91.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.7-flash-low","score":85.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4-pro-0813-max","score":90,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4-pro-0813-high","score":87.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4-pro-0813-low","score":90.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4-pro-0813-none","score":13,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5.1-max","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5.1-xhigh","score":96.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5.1-high","score":96,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5.1-medium","score":94.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-fable-5.1-low","score":90,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-astra-max","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-astra-xhigh","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-astra-high","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-astra-medium","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-astra-low","score":96.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-astra-none","score":86,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-luna-max","score":86.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-luna-xhigh","score":73,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-luna-high","score":70.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-luna-medium","score":61,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-luna-low","score":37.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-luna-none","score":8.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-5.5-max","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-5.5-xhigh","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-5.5-high","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-5.5-medium","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-opus-5.5-low","score":88.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.8-flash-high","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.8-flash-medium","score":97.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-3.8-flash-low","score":90.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-sol-max","score":95.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-sol-xhigh","score":92.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-sol-high","score":91,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-sol-medium","score":83.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-sol-low","score":72.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6-sol-none","score":29.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"glm-5.3-flash-max","score":91,"metric":"percent"},{"benchmark":"arc-agi-1","model":"glm-5.3-flash-high","score":71.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"glm-5.3-flash-low","score":47,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6.1-sol-max","score":96.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6.1-sol-xhigh","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6.1-sol-high","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6.1-sol-medium","score":95.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gpt-6.1-sol-low","score":93.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3.8-27b-xhigh","score":87.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3.8-27b-medium","score":68.67,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3.8-27b-low","score":69.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"qwen3.8-27b-none","score":34,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4.1-flash-max","score":94.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4.1-flash-high","score":88.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4.1-flash-low","score":90.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"deepseek-v4.1-flash-none","score":7.83,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.7-xhigh","score":89.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.7-high","score":90.17,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.7-medium","score":90,"metric":"percent"},{"benchmark":"arc-agi-1","model":"grok-4.7-low","score":63.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-haiku-5.5-max","score":89,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-haiku-5.5-xhigh","score":87.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-haiku-5.5-high","score":81.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-haiku-5.5-medium","score":57.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"claude-haiku-5.5-low","score":50.33,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-4-argon-high","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-4-argon-medium","score":98.5,"metric":"percent"},{"benchmark":"arc-agi-1","model":"gemini-4-argon-low","score":76.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"nvarc","score":27.64,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4o-2024-11-20","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4o-mini-2024-07-18","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"llama-4-maverick","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"llama-4-scout","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4.1-mini","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-4.1","score":0.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o1-mini","score":0.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-mini-low","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-mini-medium","score":2.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-mini-high","score":2.99,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-low","score":1.99,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-medium","score":2.98,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-high","score":6.53,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o4-mini-low","score":1.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o4-mini-medium","score":2.36,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o4-mini-high","score":6.11,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-05-20","score":1.69,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-thinking-1k","score":2.16,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-thinking-8k","score":2.12,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-thinking-16k","score":1.98,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-flash-preview-thinking-24k","score":2.54,"metric":"percent"},{"benchmark":"arc-agi-2","model":"codex-mini-latest","score":1.27,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4-20250514","score":1.27,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4-20250514-thinking-1k","score":0.85,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4-20250514-thinking-8k","score":2.12,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4-20250514-thinking-16k","score":5.93,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4-20250514-thinking-16k","score":8.61,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4-20250514-thinking-8k","score":4.52,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4-20250514-thinking-1k","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4-20250514","score":1.27,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-r1-0528","score":1.12,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-3","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-3-mini-beta-low","score":0.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-pro-low","score":2.05,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-pro-medium","score":1.94,"metric":"percent"},{"benchmark":"arc-agi-2","model":"o3-pro-high","score":4.86,"metric":"percent"},{"benchmark":"arc-agi-2","model":"magistral-small-2506","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"magistral-medium-2506","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"magistral-medium-thinking","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-thinking-1k","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-thinking-8k","score":2.92,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-thinking-16k","score":4.03,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-2.5-pro-thinking-32k","score":4.86,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4","score":15.97,"metric":"percent"},{"benchmark":"arc-agi-2","model":"qwen3-235b-a22b-instruct-2507","score":1.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-high","score":9.86,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-medium","score":7.49,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-low","score":1.94,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-minimal","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-high","score":4.44,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-medium","score":4.03,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-low","score":0.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-mini-minimal","score":1.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-nano-high","score":2.61,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-nano-medium","score":0.88,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-nano-low","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-nano-minimal","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"berman-grok-4-refine","score":29.44,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4.5","score":3.75,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking-1k","score":5.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking-8k","score":6.94,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking-16k","score":6.94,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-sonnet-thinking-32k","score":13.61,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5-pro","score":18.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"trm","score":6.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-haiku","score":1.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-haiku-thinking-1k","score":1.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-haiku-thinking-8k","score":1.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-haiku-thinking-16k","score":2.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-4.5-haiku-thinking-32k","score":4.03,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4-fast-thinking","score":5.28,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.1-none","score":0.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.1-low","score":1.94,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.1-medium","score":6.53,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.1-high","score":17.64,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-pro-preview","score":31.11,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-deep-think-preview","score":45.14,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.5","score":7.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.5-thinking-8k","score":13.89,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.5-thinking-16k","score":22.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.5-thinking-64k","score":37.64,"metric":"percent"},{"benchmark":"arc-agi-2","model":"poetiq-gemini-3-pro-refine","score":54,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-none","score":0.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-low","score":9.72,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-medium","score":26.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-high","score":43.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-thinking-xhigh","score":52.91,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-pro-medium","score":38.47,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.2-pro-high","score":54.16,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-flash-minimal","score":3.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-flash-low","score":1.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-flash-medium","score":12.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-flash-high","score":33.61,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.2","score":65.14,"metric":"percent"},{"benchmark":"arc-agi-2","model":"johan-land-gpt-5.2-refine","score":72.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.6-low","score":64.58,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.6-medium","score":66.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.6-high","score":69.17,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.6-max","score":68.75,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.8-low","score":62.22,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.8-medium","score":71.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.8-high","score":72.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3-deep-think","score":84.58,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4.6-max","score":58.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-sonnet-4.6-high","score":60.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.1-pro","score":77.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k2.5-thinking","score":11.81,"metric":"percent"},{"benchmark":"arc-agi-2","model":"minimax-m2.5","score":4.86,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v3.2","score":4.03,"metric":"percent"},{"benchmark":"arc-agi-2","model":"glm-5","score":4.86,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-low","score":29.17,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-medium","score":55.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-high","score":67.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-xhigh","score":73.95,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-pro-xhigh","score":83.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-mini-xhigh","score":18.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-mini-high","score":13.19,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-mini-medium","score":4.44,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-mini-low","score":1.11,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-nano-xhigh","score":5.69,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-nano-high","score":3.61,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-nano-medium","score":1.94,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.4-nano-low","score":1.53,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.7-low","score":62.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.7-medium","score":67.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.7-high","score":68.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-4.7-max","score":75.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.5-low","score":33.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.5-medium","score":70.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.5-high","score":83.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.5-xhigh","score":85,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.5-pro-high","score":84.58,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.5-pro-xhigh","score":84.16,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.5-flash-minimal","score":8.89,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.5-flash-high","score":72.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-sol-low","score":42.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-sol-medium","score":67.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-sol-high","score":85.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-sol-xhigh","score":90,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-sol-max","score":92.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-terra-low","score":18.75,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-terra-medium","score":37.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-terra-high","score":67.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-terra-xhigh","score":74.17,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-terra-max","score":83.9,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-low","score":5.14,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-medium","score":7.36,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-high","score":29.31,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-xhigh","score":47.64,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-max","score":59.54,"metric":"percent"},{"benchmark":"arc-agi-2","model":"glm-5.2","score":22.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling","score":36.53,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.5-high","score":52.64,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.5-medium","score":52.64,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.5-low","score":33.06,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5-high","score":88.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5-max","score":90.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling-small-xhigh","score":40.14,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling-small-high","score":33.06,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling-small-medium","score":13.61,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling-small-low","score":4.86,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling-small-minimal","score":4.03,"metric":"percent"},{"benchmark":"arc-agi-2","model":"inkling-small-none","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k3-max","score":60.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k3-high","score":55,"metric":"percent"},{"benchmark":"arc-agi-2","model":"kimi-k3-low","score":12.36,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5-max","score":89.17,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5-xhigh","score":88.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5-high","score":87.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5-medium","score":82.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5-low","score":76.81,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-flash-0731-max","score":61.39,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-flash-0731-high","score":55.97,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-flash-0731-low","score":45.97,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-flash-0731-none","score":2.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-0730-max","score":59.58,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-0730-xhigh","score":43.47,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-0730-high","score":33.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-0730-medium","score":7.36,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-0730-low","score":3.61,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-5.6-luna-0730-none","score":0.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.5-flash-lite-high","score":10.28,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.5-flash-lite-medium","score":5.28,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.5-flash-lite-low","score":1.53,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.5-flash-lite-minimal","score":0.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.6-flash-high","score":60.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.6-flash-medium","score":50.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.6-flash-low","score":30.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.6-flash-minimal","score":2.64,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.6-xhigh","score":67.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.6-high","score":65.14,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.6-medium","score":61.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.6-low","score":27.64,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.7-flash-high","score":84.58,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.7-flash-medium","score":63.75,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.7-flash-low","score":52.92,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-pro-0813-max","score":61.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-pro-0813-high","score":59.72,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-pro-0813-low","score":56.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4-pro-0813-none","score":0.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5.1-max","score":90,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5.1-xhigh","score":90,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5.1-high","score":88.75,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5.1-medium","score":86.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-fable-5.1-low","score":78.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-astra-max","score":95,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-astra-xhigh","score":93.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-astra-high","score":92.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-astra-medium","score":92.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-astra-low","score":85.42,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-astra-none","score":59.58,"metric":"percent"},{"benchmark":"arc-agi-2","model":"dots3-note-preview-max","score":76.81,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-luna-max","score":59.31,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-luna-xhigh","score":41.94,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-luna-high","score":31.39,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-luna-medium","score":18.06,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-luna-low","score":4.58,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-luna-none","score":0,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5.5-max","score":91.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5.5-xhigh","score":92.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5.5-high","score":93.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5.5-medium","score":87.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-opus-5.5-low","score":70.14,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.8-flash-high","score":89.17,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.8-flash-medium","score":82.92,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-3.8-flash-low","score":77.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-sol-max","score":89.58,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-sol-xhigh","score":78.06,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-sol-high","score":68.89,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-sol-medium","score":57.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-sol-low","score":31.53,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6-sol-none","score":1.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"glm-5.3-flash-max","score":65.83,"metric":"percent"},{"benchmark":"arc-agi-2","model":"glm-5.3-flash-high","score":50.14,"metric":"percent"},{"benchmark":"arc-agi-2","model":"glm-5.3-flash-low","score":27.92,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6.1-sol-max","score":94.17,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6.1-sol-xhigh","score":91.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6.1-sol-high","score":91.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6.1-sol-medium","score":86.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gpt-6.1-sol-low","score":76.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"qwen3.8-27b-xhigh","score":42.36,"metric":"percent"},{"benchmark":"arc-agi-2","model":"qwen3.8-27b-medium","score":13.19,"metric":"percent"},{"benchmark":"arc-agi-2","model":"qwen3.8-27b-low","score":22.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"qwen3.8-27b-none","score":1.53,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4.1-flash-max","score":72.92,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4.1-flash-high","score":67.5,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4.1-flash-low","score":60.56,"metric":"percent"},{"benchmark":"arc-agi-2","model":"deepseek-v4.1-flash-none","score":1.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.7-xhigh","score":61.39,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.7-high","score":58.33,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.7-medium","score":58.75,"metric":"percent"},{"benchmark":"arc-agi-2","model":"grok-4.7-low","score":16.67,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-haiku-5.5-xhigh","score":61.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-haiku-5.5-high","score":30.69,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-haiku-5.5-medium","score":9.44,"metric":"percent"},{"benchmark":"arc-agi-2","model":"claude-haiku-5.5-low","score":2.78,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-4-argon-high","score":91.25,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-4-argon-medium","score":87.08,"metric":"percent"},{"benchmark":"arc-agi-2","model":"gemini-4-argon-low","score":42.08,"metric":"percent"},{"benchmark":"hle","model":"gemini-3-pro","score":38.3,"metric":"percent"},{"benchmark":"hle","model":"gpt-5","score":25.3,"metric":"percent"},{"benchmark":"hle","model":"o1","score":8,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"aletheia","score":91.9,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gpt-5.5-pro-xhigh","score":88.1,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gemini-3-deep-think","score":76.7,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gpt-5.5-xhigh","score":71.9,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gpt-5.2-high","score":35.7,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gemini-3-pro","score":30,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gpt-5-pro","score":28.6,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"claude-opus-4.5","score":23.8,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"grok-4.1-fast-thinking","score":18.6,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gpt-5.1","score":7.1,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"gemini-2.5-pro-huang-yang","score":24.8,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"grok-4-heavy","score":23.3,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"o3","score":20.5,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"o4-mini-high","score":11.4,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"kimi-k2-instruct","score":7.1,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"deepseek-v3","score":4.3,"metric":"percent"},{"benchmark":"proofbench-advanced","model":"claude-opus-4","score":2.9,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4.6","score":96.28,"metric":"percent"},{"benchmark":"mask","model":"claude-4.5-sonnet-thinking","score":96.13,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4.5-thinking","score":92.53,"metric":"percent"},{"benchmark":"mask","model":"gpt-5.4-pro","score":91.73,"metric":"percent"},{"benchmark":"mask","model":"gpt-5.4-xhigh","score":89.67,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4.5","score":87.13,"metric":"percent"},{"benchmark":"mask","model":"gpt-5.2","score":86.67,"metric":"percent"},{"benchmark":"mask","model":"claude-sonnet-4.5","score":86.4,"metric":"percent"},{"benchmark":"mask","model":"gpt-5.1-thinking","score":86.33,"metric":"percent"},{"benchmark":"mask","model":"gpt-5-pro","score":85.99,"metric":"percent"},{"benchmark":"mask","model":"claude-opus-4.6-max","score":85.4,"metric":"percent"},{"benchmark":"mask","model":"kimi-k2.5","score":70.47,"metric":"percent"},{"benchmark":"mask","model":"gpt-5.1","score":63.33,"metric":"percent"},{"benchmark":"mask","model":"magistral-medium-2506","score":56.5,"metric":"percent"},{"benchmark":"mask","model":"qwen3-235b-a22b","score":56.4,"metric":"percent"},{"benchmark":"mask","model":"gemini-3.1-flash-lite","score":48.4,"metric":"percent"},{"benchmark":"mask","model":"gemini-3-pro-preview","score":42.6,"metric":"percent"},{"benchmark":"mask","model":"gemini-3.1-pro","score":42.4,"metric":"percent"},{"benchmark":"vct","model":"gemini-2.5-pro","score":37.6,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5.5-max","score":38.16,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra-max","score":34.21,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-sol-max","score":31.58,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra-xhigh","score":32.24,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra-high","score":31.58,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra-medium","score":32.24,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-sol-xhigh","score":32.24,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5-high","score":32.24,"metric":"percent"},{"benchmark":"agents-last-exam","model":"muse-spark-1.3-xhigh","score":32.24,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5-xhigh","score":30.26,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-sol-high","score":31.58,"metric":"percent"},{"benchmark":"agents-last-exam","model":"muse-spark-1.3-max","score":29.61,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra-none","score":28.29,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-sol-medium","score":28.95,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol-xhigh","score":30.59,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-astra-low","score":29.61,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5-medium","score":28.95,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol-max","score":29.61,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5-max","score":30.92,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.8-max-xhigh","score":26.97,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-sol-low","score":27.63,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol-high","score":30.59,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol-medium","score":29.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-5-low","score":27.63,"metric":"percent"},{"benchmark":"agents-last-exam","model":"kimi-k3-max","score":28.29,"metric":"percent"},{"benchmark":"agents-last-exam","model":"grok-4.5-high","score":26.97,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-luna-max","score":25,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-terra-max","score":27.96,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-luna-max","score":28.95,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-sol-none","score":23.68,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-luna-xhigh","score":30.26,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-fable-5-xhigh","score":25.66,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-terra-xhigh","score":27.63,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.5-xhigh","score":26.64,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-luna-xhigh","score":24.34,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-luna-medium","score":20.39,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-terra-high","score":25.99,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-luna-high","score":24.34,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.5","score":24.45,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.8-max","score":26.97,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol-low","score":23.9,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-luna-high","score":21.05,"metric":"percent"},{"benchmark":"agents-last-exam","model":"agnes-2.5-pro-beta","score":21.71,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-terra-medium","score":22.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.7-high","score":21.05,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.8-xhigh","score":22.37,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-fable-5","score":22.37,"metric":"percent"},{"benchmark":"agents-last-exam","model":"ark-0614c","score":19.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"glm-5.2-max","score":20.39,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.8-high","score":22.37,"metric":"percent"},{"benchmark":"agents-last-exam","model":"claude-opus-4.7","score":18.42,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-terra-low","score":20.39,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.5-medium","score":18.42,"metric":"percent"},{"benchmark":"agents-last-exam","model":"composer-2.5","score":20.39,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-luna-medium","score":17.11,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.4","score":20.5,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.5-low","score":17.11,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-luna-low","score":16.45,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-6-luna-none","score":13.82,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gemini-3.1-pro","score":16.45,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.7-max","score":11.84,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-luna-low","score":11.84,"metric":"percent"},{"benchmark":"agents-last-exam","model":"glm-5.1","score":11.51,"metric":"percent"},{"benchmark":"agents-last-exam","model":"deepseek-v4-pro","score":12.39,"metric":"percent"},{"benchmark":"agents-last-exam","model":"qwen3.6-plus","score":8.55,"metric":"percent"},{"benchmark":"agents-last-exam","model":"mimo-v2.5","score":8.55,"metric":"percent"},{"benchmark":"agents-last-exam","model":"kimi-k2.6","score":9.21,"metric":"percent"},{"benchmark":"agents-last-exam","model":"grok-4.3","score":7.24,"metric":"percent"},{"benchmark":"agents-last-exam","model":"minimax-m2.7","score":5.92,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-5.5-max","score":63.71,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-astra-max","score":61.44,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-sol-max","score":59.49,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-sol-xhigh","score":59.38,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-astra-medium","score":59.15,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-astra-xhigh","score":58.96,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-astra-high","score":58.9,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-sol-high","score":58.84,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-sol-medium","score":57.73,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"muse-spark-1.3-xhigh","score":57.46,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"muse-spark-1.3-max","score":57.29,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-5-high","score":57.27,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-5-xhigh","score":56.15,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-astra-low","score":56.15,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-sol-low","score":55.21,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-5-medium","score":54.82,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-astra-none","score":54.82,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-sol-xhigh","score":53.64,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-5-max","score":53.37,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-sol-medium","score":53.14,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-sol-none","score":53.02,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"kimi-k3-max","score":52.79,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-luna-max","score":52.39,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-5-low","score":52.33,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-luna-max","score":51.93,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-sol-high","score":51.22,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"qwen3.8-max-xhigh","score":51.12,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-sol-max","score":50.95,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-luna-xhigh","score":50.73,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"grok-4.5-high","score":50.59,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"agnes-2.5-pro-beta","score":50.2,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-terra-max","score":50.12,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-luna-medium","score":49.58,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-terra-xhigh","score":49.36,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.5-xhigh","score":49.24,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-fable-5-xhigh","score":48.45,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.5","score":48.08,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-luna-high","score":47.76,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-luna-xhigh","score":47.62,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-terra-high","score":46.89,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-sol-low","score":46.82,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-luna-high","score":46.3,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-fable-5","score":45.76,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-4.7-high","score":45.68,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-4.8-high","score":44.6,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"glm-5.2-max","score":44.16,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-4.8-max","score":44.06,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-terra-medium","score":43.91,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-4.7","score":43.27,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-terra-low","score":42.52,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"composer-2.5","score":42.21,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"ark-0614c","score":42.2,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-opus-4.8-xhigh","score":42.14,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.4","score":41.85,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-luna-low","score":41.32,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-luna-medium","score":41.19,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-6-luna-none","score":39.48,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.5-medium","score":39.45,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.5-low","score":39.41,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gemini-3.1-pro","score":37.17,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"qwen3.7-max","score":34.64,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"gpt-5.6-luna-low","score":33.61,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"claude-sonnet-4.6","score":32.04,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"deepseek-v4-pro","score":30.84,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"glm-5.1","score":30.78,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"qwen3.6-plus","score":28.96,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"mimo-v2.5","score":26.47,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"grok-4.3","score":25.87,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"kimi-k2.6","score":21.24,"metric":"percent"},{"benchmark":"agents-last-exam-score","model":"minimax-m2.7","score":14.65,"metric":"percent"},{"benchmark":"mmlu","model":"claude-haiku-5.5","score":90.94,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-4-argon","score":95.25,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-6.1-sol","score":93.83,"metric":"percent"},{"benchmark":"mmlu","model":"grok-4.6","score":93.97,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-6-sol","score":93.94,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-3.8-flash","score":94.42,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-3.7-flash","score":94.52,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-5","score":94.16,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-3.6-flash","score":94.17,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-3.5-flash-lite","score":91.25,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-235b-a22b-instruct-2507","score":88.92,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-5.6-luna","score":91.89,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-5.6-terra","score":93.3,"metric":"percent"},{"benchmark":"mmlu","model":"grok-4.5","score":94.54,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-4-31b-it","score":91.82,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-3.5-flash","score":93.6,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-4.8","score":93.01,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-3-pro-preview","score":93.86,"metric":"percent"},{"benchmark":"mmlu","model":"granite-4.0-h-small","score":77.72,"metric":"percent"},{"benchmark":"mmlu","model":"grok-4-0709","score":91.65,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3.1","score":89.62,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-4.1-20250805","score":93.39,"metric":"percent"},{"benchmark":"mmlu","model":"qwen3-235b-a22b-thinking-2507","score":66.74,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-5-2025-08-07","score":93.48,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-120b","score":87.73,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-oss-20b","score":82.21,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-3b-2410","score":57.61,"metric":"percent"},{"benchmark":"mmlu","model":"open-mixtral-8x22b-2404","score":77.49,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-large-2411","score":85.13,"metric":"percent"},{"benchmark":"mmlu","model":"codestral-2501","score":67.59,"metric":"percent"},{"benchmark":"mmlu","model":"ministral-8b-2410","score":57.28,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-r1-0528","score":90.31,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-2.0-flash-001","score":87.69,"metric":"percent"},{"benchmark":"mmlu","model":"grok-3-mini","score":89.16,"metric":"percent"},{"benchmark":"mmlu","model":"claude-sonnet-4-20250514","score":91.39,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-12b-it","score":77.13,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4.1-2025-04-14","score":90.31,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3.7-sonnet-20250219","score":90.17,"metric":"percent"},{"benchmark":"mmlu","model":"grok-2-1212","score":88.01,"metric":"percent"},{"benchmark":"mmlu","model":"grok-3","score":90.11,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3.5-sonnet-20241022","score":89.48,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3.5-haiku-20241022","score":80.98,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3","score":89.51,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4o-mini-2024-07-18","score":81.38,"metric":"percent"},{"benchmark":"mmlu","model":"o3-2025-04-16","score":92.27,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-2.5-pro-preview-06-05","score":92.36,"metric":"percent"},{"benchmark":"mmlu","model":"o1-2024-12-17","score":91.92,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-1.5-pro","score":86.9,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-1.5-flash-8b-001","score":75.01,"metric":"percent"},{"benchmark":"mmlu","model":"o3-mini-2025-01-31","score":85.88,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-4b-it","score":62.75,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4o-2024-08-06","score":88.09,"metric":"percent"},{"benchmark":"mmlu","model":"o1-mini-2024-09-12","score":83.96,"metric":"percent"},{"benchmark":"mmlu","model":"o4-mini-2025-04-16","score":90.04,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-3-27b-it","score":81.51,"metric":"percent"},{"benchmark":"mmlu","model":"claude-opus-4-20250514","score":92.83,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-haiku-5.5","score":93.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-4-argon","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-6.1-sol","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4.7","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-5.5","score":96.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-6-sol","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-5.5","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-6-luna","score":96.67,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4.6","score":96.55,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-6-astra","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3.8-flash","score":93.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3.7-flash","score":93.1,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-5","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3.6-flash","score":93.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3.5-flash-lite","score":40,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4.5","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.6-terra","score":93.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.6-sol","score":96.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.6-luna","score":86.67,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-5","score":86.67,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.8","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5.5","score":100,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-31b-it","score":86.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-4-26b-a4b-it","score":63.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3.5-flash","score":96.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-3-pro-preview","score":95.83,"metric":"percent"},{"benchmark":"aime-2025","model":"granite-4.0-h-small","score":5,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-4-0709","score":93.33,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-v3.1","score":31.67,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4.1-20250805","score":33.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-5-2025-08-07","score":90.76,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-20b","score":11.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-oss-120b","score":78.33,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3-235b-a22b-thinking-2507","score":1.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.0-flash-001","score":29.17,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-3b-2410","score":0.83,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-sonnet-4-20250514","score":33.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4.1-2025-04-14","score":36.67,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-3.7-sonnet-20250219","score":20.83,"metric":"percent"},{"benchmark":"aime-2025","model":"mistral-large-2411","score":4.17,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-2-1212","score":10.83,"metric":"percent"},{"benchmark":"aime-2025","model":"grok-3","score":53.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4o-mini-2024-07-18","score":8.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-pro-preview-06-05","score":78.33,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-1.5-pro","score":12.5,"metric":"percent"},{"benchmark":"aime-2025","model":"deepseek-r1-0528","score":84.17,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-4b-it","score":10.83,"metric":"percent"},{"benchmark":"aime-2025","model":"gpt-4o-2024-08-06","score":5.83,"metric":"percent"},{"benchmark":"aime-2025","model":"gemini-2.5-flash-preview-05-20","score":75.83,"metric":"percent"},{"benchmark":"aime-2025","model":"o1-mini-2024-09-12","score":51.67,"metric":"percent"},{"benchmark":"aime-2025","model":"gemma-3-27b-it","score":25.83,"metric":"percent"},{"benchmark":"aime-2025","model":"ministral-8b-2410","score":0.83,"metric":"percent"},{"benchmark":"aime-2025","model":"claude-opus-4-20250514","score":35.83,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-6.1-sol","score":82.42,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-4-argon","score":78.63,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-haiku-5.5","score":65.83,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-6-sol","score":85.22,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-opus-5.5","score":68.46,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-6-astra","score":81.98,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-3.8-flash","score":73.09,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-3.7-flash","score":75.54,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-5.6-sol","score":68.75,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-3.5-flash-lite","score":71.2,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-3.6-flash","score":72.51,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-5.6-terra","score":71.21,"metric":"percent"},{"benchmark":"facts-grounding","model":"grok-4.5","score":74.52,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-opus-4.8","score":69.68,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-3.5-flash","score":73.24,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-4-26b-a4b-it","score":80.88,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-4-31b-it","score":80.67,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-5.5","score":76.19,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-opus-4.7","score":61.73,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-5.4","score":70.29,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-3-flash-preview","score":58.98,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-3.1-flash-lite","score":66.55,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-5.2","score":76.2,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-opus-4.6","score":54.91,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-sonnet-4.6","score":56.24,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-3.1-pro","score":65.67,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-opus-4.5","score":62.07,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-4.5-sonnet-thinking","score":61.77,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-sonnet-4.5","score":58.73,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-5.1","score":50.03,"metric":"percent"},{"benchmark":"facts-grounding","model":"grok-4-fast-thinking","score":43.15,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-5-mini","score":58.3,"metric":"percent"},{"benchmark":"facts-grounding","model":"mistral-small-3.1-24b-instruct-2503","score":43.3,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-opus-4.1-20250805","score":54.77,"metric":"percent"},{"benchmark":"facts-grounding","model":"claude-sonnet-4-20250514","score":56.08,"metric":"percent"},{"benchmark":"facts-grounding","model":"llama-3-glm-v2","score":71.76,"metric":"percent"},{"benchmark":"facts-grounding","model":"deepseek-r1-0528","score":55.99,"metric":"percent"},{"benchmark":"facts-grounding","model":"deepseek-v3.1","score":57.42,"metric":"percent"},{"benchmark":"facts-grounding","model":"deepseek-v3","score":33.39,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-2.5-flash","score":69.98,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemini-2.5-pro","score":74.29,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-4b-it","score":38.43,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-12b-it","score":58.33,"metric":"percent"},{"benchmark":"facts-grounding","model":"gemma-3-27b-it","score":56.37,"metric":"percent"},{"benchmark":"facts-grounding","model":"mistral-large-2411","score":49.74,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-4.1-2025-04-14","score":45.64,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-5-2025-08-07","score":69.63,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-oss-20b","score":23.09,"metric":"percent"},{"benchmark":"facts-grounding","model":"gpt-oss-120b","score":30.72,"metric":"percent"},{"benchmark":"facts-grounding","model":"o3-2025-04-16","score":36.21,"metric":"percent"},{"benchmark":"facts-grounding","model":"o4-mini-2025-04-16","score":29.35,"metric":"percent"},{"benchmark":"facts-grounding","model":"qwen3-235b-a22b-instruct-2507","score":40.81,"metric":"percent"},{"benchmark":"facts-grounding","model":"qwen3-235b-a22b-thinking-2507","score":48.23,"metric":"percent"},{"benchmark":"facts-grounding","model":"grok-3-mini","score":45.61,"metric":"percent"},{"benchmark":"facts-grounding","model":"grok-4-0709","score":54.74,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-3.5-sonnet","score":60.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-3.5-sonnet","score":84.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4o-2024-05-13","score":47.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4o-2024-05-13","score":84.45,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-1.5-pro","score":43.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-1.5-pro","score":71.97,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4v","score":37.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4v","score":79.92,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-3-sonnet","score":32.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-3-sonnet","score":73.65,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-3-haiku","score":31.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-3-haiku","score":65.08,"metric":"percent"},{"benchmark":"charxiv-rq","model":"phi-3-vision-4b","score":31.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"phi-3-vision-4b","score":60.48,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-3-opus","score":30.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-3-opus","score":71.55,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl-chat-v1.5","score":29.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl-chat-v1.5","score":58.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"reka-core","score":28.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"reka-core","score":55.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"reka-flash","score":26.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"reka-flash","score":56.45,"metric":"percent"},{"benchmark":"charxiv-rq","model":"mini-gemini-hd-34b","score":25,"metric":"percent"},{"benchmark":"charxiv-dq","model":"mini-gemini-hd-34b","score":52.68,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internlm-xcomposer2-4khd-7b","score":25,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internlm-xcomposer2-4khd-7b","score":54.65,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-llama3-v2.5","score":24.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"minicpm-llama3-v2.5","score":59.27,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen-vl-max","score":24.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen-vl-max","score":41.48,"metric":"percent"},{"benchmark":"charxiv-rq","model":"vila1.5-40b","score":24,"metric":"percent"},{"benchmark":"charxiv-dq","model":"vila1.5-40b","score":38.67,"metric":"percent"},{"benchmark":"charxiv-rq","model":"reka-edge","score":23.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"reka-edge","score":33.65,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-1.0-pro","score":22.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-1.0-pro","score":54.37,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llava-next-34b","score":22.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llava-next-34b","score":51.05,"metric":"percent"},{"benchmark":"charxiv-rq","model":"mini-gemini-hd-8b","score":19,"metric":"percent"},{"benchmark":"charxiv-dq","model":"mini-gemini-hd-8b","score":44.42,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internlm-xcomposer2-vl-7b","score":18.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internlm-xcomposer2-vl-7b","score":38.75,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-v-2.0-3b","score":18.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"minicpm-v-2.0-3b","score":35.77,"metric":"percent"},{"benchmark":"charxiv-rq","model":"idefics2-8b","score":18.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"idefics2-8b","score":32.77,"metric":"percent"},{"benchmark":"charxiv-rq","model":"idefics2-8b-chatty","score":17.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"idefics2-8b-chatty","score":41.55,"metric":"percent"},{"benchmark":"charxiv-rq","model":"moai","score":17.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"moai","score":28.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"deepseek-vl-7b","score":17.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"deepseek-vl-7b","score":45.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"sphinx-v2","score":16.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"sphinx-v2","score":30.25,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen-vl-plus","score":16,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen-vl-plus","score":28.93,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llava-1.6-mistral-7b","score":13.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llava-1.6-mistral-7b","score":35.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"cambrian-34b","score":27.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"cambrian-34b","score":59.73,"metric":"percent"},{"benchmark":"charxiv-rq","model":"chartgemma","score":12.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"chartgemma","score":21.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2-26b","score":33.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-26b","score":62.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2-llama-3-76b","score":38.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-llama-3-76b","score":75.17,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4o-mini","score":34.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4o-mini","score":74.92,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gemini-1.5-flash","score":33.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2-pro","score":39.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-pro","score":76.83,"metric":"percent"},{"benchmark":"charxiv-rq","model":"ovis1.5-gemma2-9b","score":28.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"ovis1.5-gemma2-9b","score":62.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"ovis1.5-llama3-8b","score":28.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"ovis1.5-llama3-8b","score":60.15,"metric":"percent"},{"benchmark":"charxiv-rq","model":"glm-4v-9b","score":29.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"glm-4v-9b","score":57.62,"metric":"percent"},{"benchmark":"charxiv-rq","model":"cogagent-18b","score":18.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"cogagent-18b","score":36.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"docowl-1.5-chat","score":17,"metric":"percent"},{"benchmark":"charxiv-dq","model":"docowl-1.5-chat","score":37.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"docowl-1.5-omni","score":9.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"docowl-1.5-omni","score":25.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"ureader","score":14.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"ureader","score":18.98,"metric":"percent"},{"benchmark":"charxiv-rq","model":"textmonkey","score":3.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"textmonkey","score":12.45,"metric":"percent"},{"benchmark":"charxiv-rq","model":"chartllama","score":14.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"chartllama","score":19.23,"metric":"percent"},{"benchmark":"charxiv-rq","model":"chartassistant","score":11.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"chartassistant","score":16.93,"metric":"percent"},{"benchmark":"charxiv-rq","model":"chartinstruct-flant5","score":11.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"chartinstruct-flant5","score":15.47,"metric":"percent"},{"benchmark":"charxiv-rq","model":"chartinstruct-llama2","score":8.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"chartinstruct-llama2","score":21.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"tinychart","score":8.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"tinychart","score":16.15,"metric":"percent"},{"benchmark":"charxiv-rq","model":"unichart-chartqa","score":5.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"unichart-chartqa","score":19.32,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-v-2_6","score":27.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"minicpm-v-2_6","score":61.62,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2.5-78b","score":42.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2.5-78b","score":82.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2.5-38b","score":42.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2.5-38b","score":79.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2.5-26b","score":35.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2.5-26b","score":73.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2.5-8b","score":32.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2.5-8b","score":68.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2.5-4b","score":24.9,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2.5-4b","score":61.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2.5-2b","score":21.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2.5-2b","score":49.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2.5-1b","score":19,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2.5-1b","score":38.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"o1","score":52.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"o1","score":87.45,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llama-3.2v-11b-instruct","score":31.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llama-3.2v-11b-instruct","score":59.35,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llama-3.2v-90b-instruct","score":37.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llama-3.2v-90b-instruct","score":68.42,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llava-onevision-0.5b","score":15.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llava-onevision-0.5b","score":32.77,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llava-onevision-7b","score":23.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llava-onevision-7b","score":48.73,"metric":"percent"},{"benchmark":"charxiv-rq","model":"llava-onevision-72b","score":36.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"llava-onevision-72b","score":71.83,"metric":"percent"},{"benchmark":"charxiv-rq","model":"molmo-7b-d","score":26.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"molmo-7b-d","score":52.73,"metric":"percent"},{"benchmark":"charxiv-rq","model":"molmo-7b-o","score":24.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"molmo-7b-o","score":45.67,"metric":"percent"},{"benchmark":"charxiv-rq","model":"molmo-72b","score":36.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"molmo-72b","score":75.45,"metric":"percent"},{"benchmark":"charxiv-rq","model":"molmoe-1b","score":18,"metric":"percent"},{"benchmark":"charxiv-dq","model":"molmoe-1b","score":40.8,"metric":"percent"},{"benchmark":"charxiv-rq","model":"nvlm-d-72b","score":36.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"nvlm-d-72b","score":63.92,"metric":"percent"},{"benchmark":"charxiv-rq","model":"phi-3.5-vision-instruct","score":32.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"phi-3.5-vision-instruct","score":55.02,"metric":"percent"},{"benchmark":"charxiv-rq","model":"pixtral-12b","score":42.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"pixtral-12b","score":68.12,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2-vl-2b","score":24.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2-vl-2b","score":44.55,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2-vl-7b","score":34.6,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2-vl-7b","score":58,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2-vl-72b","score":43,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2-vl-72b","score":81.35,"metric":"percent"},{"benchmark":"charxiv-rq","model":"doubao-1.5-vision-pro","score":54.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"doubao-1.5-vision-pro","score":84.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4o-2024-11-20","score":50.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"qwen2.5-vl-3b","score":31.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"qwen2.5-vl-3b","score":58.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3-1b","score":21,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3-1b","score":47.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3-8b","score":73.6,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3-9b","score":38,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3-9b","score":72.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3-14b","score":43.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3-14b","score":82.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3-38b","score":46.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3-38b","score":87.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl3-78b","score":46,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl3-78b","score":85.1,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4.1","score":56.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4.1","score":87.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4.5","score":55.4,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4.5","score":90,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4.1-mini","score":56.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4.1-mini","score":88.4,"metric":"percent"},{"benchmark":"charxiv-rq","model":"gpt-4.1-nano","score":40.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4.1-nano","score":73.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"o1-2024-12-17-high","score":55.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"o1-2024-12-17-high","score":88.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"o4-mini-high","score":72,"metric":"percent"},{"benchmark":"charxiv-dq","model":"o4-mini-high","score":94.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-3.7-sonnet","score":64.2,"metric":"percent"},{"benchmark":"chartmuseum","model":"internvl3-2b","score":16,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen2.5-vl-3b","score":21,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen2.5-vl-7b","score":26.8,"metric":"percent"},{"benchmark":"chartmuseum","model":"internvl3-8b","score":28.2,"metric":"percent"},{"benchmark":"chartmuseum","model":"bespoke-minichart-7b","score":34,"metric":"percent"},{"benchmark":"chartmuseum","model":"internvl3-38b","score":32.1,"metric":"percent"},{"benchmark":"chartmuseum","model":"internvl3-78b","score":35.2,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen2.5-vl-32b-instruct","score":38.1,"metric":"percent"},{"benchmark":"chartmuseum","model":"pixtral-large-2411","score":38.5,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen2.5-vl-72b-instruct","score":38.5,"metric":"percent"},{"benchmark":"chartmuseum","model":"gemini-1.5-flash","score":31.1,"metric":"percent"},{"benchmark":"chartmuseum","model":"gemini-1.5-pro","score":41.3,"metric":"percent"},{"benchmark":"chartmuseum","model":"gpt-4o","score":42.2,"metric":"percent"},{"benchmark":"chartmuseum","model":"gpt-4.1","score":48.4,"metric":"percent"},{"benchmark":"chartmuseum","model":"gpt-4.1-mini","score":52.7,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-3.5-sonnet","score":54.4,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-3.7-sonnet","score":60.3,"metric":"percent"},{"benchmark":"chartmuseum","model":"o3-high","score":60.9,"metric":"percent"},{"benchmark":"chartmuseum","model":"o4-mini-high","score":61.5,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-3.7-sonnet-thinking","score":61.7,"metric":"percent"},{"benchmark":"chartmuseum","model":"gemini-2.5-pro","score":63,"metric":"percent"},{"benchmark":"chartmuseum","model":"gpt-5-mini-high","score":63.3,"metric":"percent"},{"benchmark":"chartmuseum","model":"gpt-5-high","score":62.9,"metric":"percent"},{"benchmark":"chartmuseum","model":"gpt-5.2-high","score":77,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-sonnet-4","score":52.6,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-opus-4.1","score":59.1,"metric":"percent"},{"benchmark":"chartmuseum","model":"claude-opus-4.5","score":60.7,"metric":"percent"},{"benchmark":"chartmuseum","model":"glm-4.5v","score":40.6,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen3-vl-30b-a3b-thinking","score":49.7,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen3-vl-30b-a3b-instruct","score":40.2,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen3-vl-8b-thinking","score":44.4,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen3-vl-8b-instruct","score":40,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen3-vl-4b-thinking","score":36.1,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen3-vl-2b-thinking","score":30.1,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen3-vl-2b-instruct","score":22.7,"metric":"percent"},{"benchmark":"chartmuseum","model":"qwen3-vl-4b-instruct","score":37.7,"metric":"percent"},{"benchmark":"chartmuseum","model":"gemini-3-flash","score":78.6,"metric":"percent"},{"benchmark":"chartmuseum","model":"gemini-3.1-pro","score":80.7,"metric":"percent"},{"benchmark":"chartmuseum","model":"gemma-4-26b-a4b-it","score":70.6,"metric":"percent"},{"benchmark":"chartmuseum","model":"gemma-4-31b-it","score":71.1,"metric":"percent"},{"benchmark":"dynamath","model":"claude-3.5-sonnet","score":64.8,"metric":"percent"},{"benchmark":"dynamath","model":"gemini-1.5-pro","score":60.5,"metric":"percent"},{"benchmark":"dynamath","model":"qwen2-vl-72b","score":55.1,"metric":"percent"},{"benchmark":"dynamath","model":"qwen2-vl-7b","score":42.1,"metric":"percent"},{"benchmark":"dynamath","model":"internvl2-llama-3-76b","score":54,"metric":"percent"},{"benchmark":"dynamath","model":"internvl2-40b","score":41.8,"metric":"percent"},{"benchmark":"dynamath","model":"internvl2-26b","score":41,"metric":"percent"},{"benchmark":"dynamath","model":"internvl2-8b","score":39.7,"metric":"percent"},{"benchmark":"dynamath","model":"llama-3.2v-90b-instruct","score":44,"metric":"percent"},{"benchmark":"dynamath","model":"deepseek-vl-7b","score":21.5,"metric":"percent"},{"benchmark":"dynamath","model":"llava-next-34b","score":27.1,"metric":"percent"},{"benchmark":"dynamath","model":"llava-1.6-13b","score":19.8,"metric":"percent"},{"benchmark":"dynamath","model":"llava-1.5-7b","score":16.6,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"gpt-5.4-thinking-xhigh","score":96.1,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5.4-thinking-xhigh","score":92,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-3-flash","score":90.6,"metric":"percent"},{"benchmark":"mathvision-with-tools","model":"claude-opus-4.6-max","score":84.6,"metric":"percent"},{"benchmark":"mathvision","model":"seed1.6-thinking","score":77.2,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.5","score":77.1,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-5","score":72,"metric":"percent"},{"benchmark":"mathvision","model":"claude-opus-4.6-max","score":71.2,"metric":"percent"},{"benchmark":"mathvision","model":"qwen3-vl-235b-a22b-instruct","score":66,"metric":"percent"},{"benchmark":"mathvision","model":"claude-4.1-opus-thinking","score":66,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3.5-241b","score":63.9,"metric":"percent"},{"benchmark":"mathvision","model":"mimo-vl-7b-rl","score":60.4,"metric":"percent"},{"benchmark":"mathvision","model":"o1","score":60.3,"metric":"percent"},{"benchmark":"mathvision","model":"claude-3.7-sonnet","score":58.6,"metric":"percent"},{"benchmark":"mathvision","model":"o4-mini","score":58,"metric":"percent"},{"benchmark":"mathvision","model":"mimo-vl-7b-sft","score":57.9,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-vl-a3b-thinking-2506","score":56.9,"metric":"percent"},{"benchmark":"mathvision","model":"step-r1-v-mini","score":56.6,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3.5-30b-a3b","score":55.7,"metric":"percent"},{"benchmark":"mathvision","model":"sensenova-v6-reasoner","score":55.39,"metric":"percent"},{"benchmark":"mathvision","model":"glm-4.1v-9b-thinking","score":54.4,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3.5-38b","score":54,"metric":"percent"},{"benchmark":"mathvision","model":"ovis2.5-9b","score":53.9,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-k1.6-preview","score":53.29,"metric":"percent"},{"benchmark":"mathvision","model":"skywork-r1v3-38b","score":52.6,"metric":"percent"},{"benchmark":"mathvision","model":"open-vision-reasoner-7b","score":51.8,"metric":"percent"},{"benchmark":"mathvision","model":"qianfan-vl-70b","score":50.29,"metric":"percent"},{"benchmark":"mathvision","model":"skywork-r1v2-38b","score":49.7,"metric":"percent"},{"benchmark":"mathvision","model":"doubao-1.5-vision-pro","score":48.62,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.0-pro","score":48.1,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-4.5","score":47.3,"metric":"percent"},{"benchmark":"mathvision","model":"keye-vl-8b","score":46,"metric":"percent"},{"benchmark":"mathvision","model":"vl-rethinker-72b","score":44.93,"metric":"percent"},{"benchmark":"mathvision","model":"llava-critic-r1-7b","score":44.1,"metric":"percent"},{"benchmark":"mathvision","model":"vision-r1-7b","score":43.9,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3-78b","score":43.1,"metric":"percent"},{"benchmark":"mathvision","model":"skywork-r1v2-38b-awq","score":42.9,"metric":"percent"},{"benchmark":"mathvision","model":"infrl-qwen2.5-vl-72b-preview","score":42.73,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-2.0-flash","score":41.3,"metric":"percent"},{"benchmark":"mathvision","model":"vl-rethinker-32b","score":40.5,"metric":"percent"},{"benchmark":"mathvision","model":"vicrit-rl-72b","score":40.1,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3.5-4b","score":40,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-k1.5","score":38.6,"metric":"percent"},{"benchmark":"mathvision","model":"virgo-72b","score":38.4,"metric":"percent"},{"benchmark":"mathvision","model":"claude-3.5-sonnet","score":37.99,"metric":"percent"},{"benchmark":"mathvision","model":"ovis2.5-2b","score":37.4,"metric":"percent"},{"benchmark":"mathvision","model":"avar-thinker-7b","score":37.4,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3-14b","score":37,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-vl-a3b-thinking","score":36.8,"metric":"percent"},{"benchmark":"mathvision","model":"qvq-72b","score":35.9,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3-38b","score":34.5,"metric":"percent"},{"benchmark":"mathvision","model":"thinklite-vl-7b","score":32.9,"metric":"percent"},{"benchmark":"mathvision","model":"qianfan-vl-8b","score":32.82,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2.5-78b","score":32.2,"metric":"percent"},{"benchmark":"mathvision","model":"ovis2-34b","score":31.9,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2.5-38b","score":31.8,"metric":"percent"},{"benchmark":"mathvision","model":"ursa-8b-ps-grpo","score":31.5,"metric":"percent"},{"benchmark":"mathvision","model":"tbac-vlr1-7b","score":31.4,"metric":"percent"},{"benchmark":"mathvision","model":"llava-critic-r1-11b","score":30.9,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-4o","score":30.39,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-4-turbo","score":30.26,"metric":"percent"},{"benchmark":"mathvision","model":"mmr1-math-v0-7b","score":30.2,"metric":"percent"},{"benchmark":"mathvision","model":"dualmindvlm-7b","score":30.2,"metric":"percent"},{"benchmark":"mathvision","model":"ovis2-16b","score":30.1,"metric":"percent"},{"benchmark":"mathvision","model":"r1-onevision-7b","score":29.9,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3-8b","score":29,"metric":"percent"},{"benchmark":"mathvision","model":"vold-3b","score":28,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3-9b","score":27.6,"metric":"percent"},{"benchmark":"mathvision","model":"claude-3-opus","score":27.13,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2.5-vl-dp-7b","score":26.9,"metric":"percent"},{"benchmark":"mathvision","model":"mm-eureka-qwen-7b","score":26.9,"metric":"percent"},{"benchmark":"mathvision","model":"vision-sr1-7b","score":26.7,"metric":"percent"},{"benchmark":"mathvision","model":"mathglm-vision-32b","score":26.5,"metric":"percent"},{"benchmark":"mathvision","model":"vlaa-thinker-qwen2.5vl-7b","score":26.4,"metric":"percent"},{"benchmark":"mathvision","model":"mathcoder-vl-8b","score":26.1,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2-vl-72b","score":25.9,"metric":"percent"},{"benchmark":"mathvision","model":"openvlthinker-7b","score":25.9,"metric":"percent"},{"benchmark":"mathvision","model":"llava-onevision-72b","score":25.3,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2.5-vl-7b","score":25.1,"metric":"percent"},{"benchmark":"mathvision","model":"tbac-vlr1-3b-preview","score":25,"metric":"percent"},{"benchmark":"mathvision","model":"r1-vl-7b","score":24.7,"metric":"percent"},{"benchmark":"mathvision","model":"x-reasoner-3b","score":24.4,"metric":"percent"},{"benchmark":"mathvision","model":"r1-onevision-3b","score":23.6,"metric":"percent"},{"benchmark":"mathvision","model":"minicpm-v-2_6","score":23.4,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2.5-26b","score":23.1,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-4v","score":22.76,"metric":"percent"},{"benchmark":"mathvision","model":"mathcoder-vl-2b","score":21.7,"metric":"percent"},{"benchmark":"mathvision","model":"minicpm-o-2.6","score":21.7,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3-2b","score":21.7,"metric":"percent"},{"benchmark":"mathvision","model":"kimi-vl-a3b-instruct","score":21.4,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2.5-vl-3b","score":21.2,"metric":"percent"},{"benchmark":"mathvision","model":"multimath-7b","score":20.7,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2.5-8b","score":19.7,"metric":"percent"},{"benchmark":"mathvision","model":"mulberry-qwen2vl-7b","score":19.5,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-1.5-pro","score":19.24,"metric":"percent"},{"benchmark":"mathvision","model":"internvl3-1b","score":18.8,"metric":"percent"},{"benchmark":"mathvision","model":"ovis1.6-gemma2-9b","score":18.78,"metric":"percent"},{"benchmark":"mathvision","model":"mavis-7b","score":18.6,"metric":"percent"},{"benchmark":"mathvision","model":"aquila-vl-2b","score":17.9,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2-vl-dp-7b","score":17.7,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-pro","score":17.66,"metric":"percent"},{"benchmark":"mathvision","model":"internvl-chat-v1.2-plus","score":16.97,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2-vl-7b","score":16.3,"metric":"percent"},{"benchmark":"mathvision","model":"math-llava-13b","score":15.69,"metric":"percent"},{"benchmark":"mathvision","model":"qwen-vl-max","score":15.59,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2.5-2b","score":14.7,"metric":"percent"},{"benchmark":"mathvision","model":"internlm-xcomposer2-vl-7b","score":14.54,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2.5-1b","score":14.4,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2-vl-2b","score":12.4,"metric":"percent"},{"benchmark":"mathvision","model":"sharegpt4v-13b","score":11.88,"metric":"percent"},{"benchmark":"mathvision","model":"llava-1.5-13b","score":11.12,"metric":"percent"},{"benchmark":"mathvision","model":"qwen-vl-plus","score":10.72,"metric":"percent"},{"benchmark":"mathvision","model":"sharegpt4v-7b","score":10.53,"metric":"percent"},{"benchmark":"mathvision","model":"sphinx-v2","score":9.7,"metric":"percent"},{"benchmark":"mathvision","model":"llava-1.5-7b","score":8.52,"metric":"percent"},{"benchmark":"visulogic","model":"perea-1.0","score":52.8,"metric":"percent"},{"benchmark":"visulogic","model":"seed2.0-pro","score":47.4,"metric":"percent"},{"benchmark":"visulogic","model":"gemini-2.0-pro-exp-02-05","score":28,"metric":"percent"},{"benchmark":"visulogic","model":"internvl2.5-78b","score":27.3,"metric":"percent"},{"benchmark":"visulogic","model":"internvl3-38b","score":27.1,"metric":"percent"},{"benchmark":"visulogic","model":"gpt-4o","score":26.3,"metric":"percent"},{"benchmark":"visulogic","model":"qwen2.5-vl-72b-instruct","score":26.2,"metric":"percent"},{"benchmark":"visulogic","model":"ernie-4.5-vl-28b-a3b","score":26,"metric":"percent"},{"benchmark":"visulogic","model":"qwen2.5-vl-7b","score":26,"metric":"percent"},{"benchmark":"visulogic","model":"kimi-latest","score":25.9,"metric":"percent"},{"benchmark":"visulogic","model":"keye-vl-8b","score":25.6,"metric":"percent"},{"benchmark":"visulogic","model":"ovis2-8b","score":25.6,"metric":"percent"},{"benchmark":"visulogic","model":"internvl2.5-38b","score":25.5,"metric":"percent"},{"benchmark":"visulogic","model":"llava-onevision-7b-si","score":25.3,"metric":"percent"},{"benchmark":"visulogic","model":"minicpm-o-2.6","score":25.3,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"gpt-6-astra","score":84.1,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"pixtral-12b","score":12.15,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"pixtral-large-2411","score":13.6,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"qwen2.5-vl-7b","score":16.62,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"qwen2.5-vl-72b-instruct","score":13.87,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"moondream2","score":33.27,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"molmo-7b-d","score":38.39,"metric":"percent"},{"benchmark":"vlms-are-biased","model":"molmo-72b","score":36.39,"metric":"percent"},{"benchmark":"screenspot-pro","model":"indeed-ui-8b","score":73.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"indeed-ui-32b","score":73.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"huzzleworld-2b","score":61.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"duvo-eye-1","score":72.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"adazoom-gui-4b","score":61.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"kv-ground-qwen3vl-4b","score":63.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"kv-ground-guiowl1.5-8b-0315","score":73.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"kv-ground-guiowl1.5-4b-0228","score":67,"metric":"percent"},{"benchmark":"screenspot-pro","model":"mai-ui-8b","score":65.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"bami-7b","score":57.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-aima-3b","score":59.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-agile-3b","score":45,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-agile-7b","score":47.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gta1-7b","score":55.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-spotlight","score":52.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-g1","score":35.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5-high","score":6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gpt-5-minimal","score":18.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-arp-7b","score":60.8,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo1.5-3b","score":51.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo1.5-7b","score":57.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"holo1.5-72b","score":63.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"v2p-7b","score":52.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"di-gui-3b","score":31.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"zonui-3b","score":28.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-actor-3b-qwen2.5-vl","score":42.2,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-actor-7b-qwen2-vl","score":40.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gui-actor-2b-qwen2-vl","score":36.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gta1-qwen2.5vl-7b","score":50.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gta1-qwen2.5vl-32b","score":53.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"gta1-qwen2.5vl-72b","score":58.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"se-gui-3b","score":35.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2.5-vl-32b-instruct","score":48,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2.5-vl-3b","score":16.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2-vl-72b","score":1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"ui-tars-2b","score":27.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"aguvis-7b","score":22.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"uground-v1-7b","score":31.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"uground-v1-2b","score":26.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"aria-ui","score":11.3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"minicpm-v-2_6","score":3,"metric":"percent"},{"benchmark":"screenspot-pro","model":"showui-2b","score":7.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"seeclick","score":1.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"os-atlas-7b","score":18.9,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen-vl","score":0.1,"metric":"percent"},{"benchmark":"screenspot-pro","model":"qwen2-vl-7b","score":1.6,"metric":"percent"},{"benchmark":"screenspot-pro","model":"uground-7b","score":16.5,"metric":"percent"},{"benchmark":"screenspot-pro","model":"cogagent-18b","score":7.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"os-atlas-4b","score":3.7,"metric":"percent"},{"benchmark":"screenspot-pro","model":"huzzleworld-3b","score":66.4,"metric":"percent"},{"benchmark":"screenspot-pro","model":"huzzleworld-1b","score":55.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen-vl","score":41.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen-vl-chat","score":60.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"pandagpt-13b","score":39.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"openflamingo-v2","score":2.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sharegpt4v-7b","score":64.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sharegpt4v-13b","score":67.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"transcore-m","score":67.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"instructblip-7b","score":38.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"visualglm","score":36.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mplug-owl2","score":63.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cogvlm-17b-chat","score":63.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sharecaptioner","score":63.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"monkey","score":57.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"monkey-chat","score":69.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minigpt-4-v2","score":5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minigpt-4-v1-7b","score":30.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"emu2-chat","score":61.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"yi-vl-6b","score":65.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"yi-vl-34b","score":68.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mmalaya","score":55.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"omnilmm-12b","score":69.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-v","score":61.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-v-2.0-3b","score":67,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"deepseek-vl-1.3b","score":65.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"deepseek-vl-7b","score":71.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"xverse-v-13b","score":72.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"360vl-70b","score":76,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-llama3-v2.5","score":74,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"phi-3-vision-4b","score":70.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cogvlm2-llama3-chat-19b","score":72.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"wemm","score":77.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"idefics-9b-instruct","score":35.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"idefics-80b-instruct","score":11.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"idefics2-8b","score":72.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internlm-xcomposer","score":6.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internlm-xcomposer2-vl-7b","score":78.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internlm-xcomposer2-1.8b","score":70.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internlm-xcomposer2-4khd-7b","score":77,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl-chat-v1.5","score":80.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-v1-7b","score":41.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-internlm-7b-qlora","score":66,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-v1.5-7b-qlora","score":64.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-v1.5-13b-qlora","score":67,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-llama-3-8b","score":68.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-internlm2-7b-qlora","score":71.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-internlm2-20b-qlora","score":72.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-1.6-7b","score":66.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-1.6-mistral-7b","score":66.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-1.6-13b","score":67.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-next-34b","score":78.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"paligemma-mix-3b","score":68.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4-1106-vision-preview","score":65.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4-turbo-2024-04-09","score":80,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o-2024-05-13","score":83,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-1.0-pro","score":70.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen-vl-plus","score":64.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen-vl-max","score":75.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3-haiku","score":58,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3-sonnet","score":64.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3-opus","score":60.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"reka-flash","score":74.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"reka-edge","score":63.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4v","score":79.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mini-internvl-chat-2b-v1.5","score":67.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mini-internvl-chat-4b-v1.5","score":72.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-1.5-pro","score":74.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4v-9b","score":68.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3.5-sonnet","score":77.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"congrong","score":80.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bumblebee-7b-v1.6","score":73.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llama-3-mixsense","score":73.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-pro","score":86.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-1b","score":61.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-2b","score":70.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-4b","score":75.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-8b","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-26b","score":81.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-40b","score":85.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cambrian-1-8b","score":71.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internlm-xcomposer2.5","score":80.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bumblebee-7b-v2.0","score":75.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"xinyuan-vl","score":76.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cambrian-34b","score":78.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bunny-llama3-8b","score":74.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-llama-3-76b","score":85.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o-mini-2024-07-18","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis1.5-llama3-8b","score":78.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"chameleon-7b","score":19.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"chameleon-30b","score":37.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cambrian-13b","score":71.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"yi-vision","score":76.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis1.5-gemma2-9b","score":78.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-next-llama3","score":72.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-next-interleave-7b-dpo","score":71.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-next-interleave-7b","score":72.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-next-qwen-32b","score":76.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mantis-8b-clip-llama3","score":63.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mantis-8b-siglip-llama3","score":66.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mantis-8b-idefics2","score":73.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-v-2_6","score":79,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o-2024-08-06","score":81.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llama-3-mixsense-v1.1","score":73.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"omchat-v2.0-13b","score":79.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"parrot-7b","score":68.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"vila1.5-3b","score":63.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llama-3-vila1.5-8b","score":57.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"vila1.5-13b","score":71.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"vila1.5-40b","score":79.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mmalaya2","score":80.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"idefics3-8b-llama3","score":75,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"phi-3.5-vision-instruct","score":72.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mirage-12b-v2.0","score":78.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-1.5-7b","score":62.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-1.5-13b","score":65.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"xgen-mm-interleave-4b","score":75.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"xgen-mm-instruct-dpo-v1.5","score":75.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-7b","score":81.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-2b","score":73.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mantis-8b-fuyu","score":44.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"slime-7b","score":63.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"slime-8b","score":69,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"slime-13b","score":62.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"pixtral-12b","score":75.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-1.5-flash","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-onevision-0.5b","score":59.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-onevision-7b","score":80.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-onevision-0.5b-si","score":53,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-onevision-7b-si","score":77.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen-vl-plus-0809","score":81.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-onevision-72b-si","score":83.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-onevision-72b","score":85,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis1.6-gemma2-9b","score":81.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"eagle-x5-7b","score":67.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"eagle-x5-13b","score":70,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"moondream1","score":59.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minimonkey","score":69.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"xinyuan-vl-2b-instruct","score":76.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llama-3.2v-11b-instruct","score":67.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"step-1.5v","score":80.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"points-yi-1.5-9b","score":79,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"points-qwen2.5-7b","score":79,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"kosmos2","score":1.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llama-3.2v-90b-instruct","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"nvlm-d-72b","score":79,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"moondream2","score":67.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"molmo-7b-d","score":70.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"molmo-7b-o","score":69.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"molmoe-1b","score":60.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"janus-1.3b","score":50.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"vintern-3b-beta","score":67,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis1.6-llama3.2-3b","score":76.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"aquila-vl-2b","score":76.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"molmo-72b","score":79.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-72b","score":86.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bumblebee-7b-v2.2","score":78.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bluelm-v-3b","score":83.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"falcon2-vlm-11b","score":68.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"h2ovl-800m","score":53.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"h2ovl-2b","score":68.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen-vl-max-0809","score":86,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3.5-sonnet-20241022","score":80.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bailingmm-mini","score":82.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"vintern-1b-v2","score":54.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"rbdash-v1.5","score":82.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"awaker2.5-vl","score":82.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-8b-mpo","score":76.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-8b-mpo-cot","score":75.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"eagle-x5-34b-chat","score":77.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis1.6-gemma2-27b","score":82.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-1.5-pro-002","score":84.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-1.5-flash-002","score":81.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o-2024-11-20","score":84.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"aria","score":78.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"points1.5-qwen2.5-7b","score":81.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bailingmm-lite-1203","score":83.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4v-plus","score":79.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"step-1.5v-mini","score":79.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"abab6.5s","score":57.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"abab7-preview","score":83.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sensenova","score":86.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"taiyi","score":84.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-1b","score":68.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-2b","score":72.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-4b","score":78.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-8b","score":83.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-26b","score":84.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-38b","score":85.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-78b","score":87.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sail-vl-2b","score":75.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-1b-mpo","score":67.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-2b-mpo","score":71.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-4b-mpo","score":78.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-8b-mpo","score":82.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-26b-mpo","score":84.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-38b-mpo","score":85.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"valley-eagle","score":81.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-78b-mpo","score":87.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"telemm","score":81.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"deepseek-vl2-tiny","score":71.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"deepseek-vl2-small","score":80.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"varco-vision-14b","score":82.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.0-flash","score":70.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-cot","score":74.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"step-1o","score":87.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"hunyuan-standard-vision-2024-12-31","score":83.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ross-qwen2-7b","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"vita-1.5","score":77.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"vita","score":70.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-o-2.6","score":81.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bailingmm-pro-0120","score":87.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"doubao-1.5-vision-pro","score":80.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4v-plus-0111","score":87.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"emu3-chat","score":59.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"smolvlm-instruct","score":64.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"smolvlm-instruct-dpo","score":62.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"smolvlm-synthetic","score":51,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"smolvlm-256m","score":39.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"smolvlm-500m","score":50,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"janus-pro-7b","score":60,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ola-7b","score":85.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis2-1b","score":70.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis2-2b","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis2-4b","score":81.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis2-8b","score":83.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis2-16b","score":85.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis2-34b","score":86.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2.5-vl-3b","score":77,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2.5-vl-7b","score":82.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2.5-vl-72b-instruct","score":88.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.0-pro","score":82.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3.7-sonnet","score":79.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"moonshot-v1-8k","score":76.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"grok-2-vision-1212","score":83.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"deepseek-vl2","score":82.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"smolvlm2-2.2b","score":69.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"smolvlm2-0.256b","score":11,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"smolvlm2-0.5b","score":49.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"phi-4-multimodal-instruct","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mug-u-7b","score":81.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemma-3-4b-it","score":66.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemma-3-12b-it","score":74.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemma-3-27b-it","score":79.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"aki-4b","score":65.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4.5","score":83.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ristretto-3b","score":81.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"chatgpt-4o","score":86.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-2.5-pro","score":88.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"kimi-vl-a3b-instruct","score":80.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3-1b","score":69.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3-2b","score":79,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3-8b","score":82.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3-9b","score":81.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3-14b","score":83.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3-38b","score":87,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl3-78b","score":87.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4.1-2025-04-14","score":86.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4.1-mini-2025-04-14","score":83.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4.1-nano-2025-04-14","score":64.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"kimi-vl-a3b-thinking","score":72.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sail-vl-1.5-2b","score":79.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sail-vl-1.5-8b","score":82.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sail-vl-1.6-8b","score":84.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sensenova-v6-pro","score":88.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qtunevl1-2b","score":72.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"congrong-v2.0","score":87.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"wethink-qwen2.5vl-7b","score":82.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"valley2","score":81.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"valley2-dpo","score":82.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"flash-vl-2b-dynamic-iss","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"seed-1.5-vl","score":89,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"long-vita-16k","score":76.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"hawkvl-2b","score":65.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"granite-vision-3.1-2b-preview","score":74.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"granite-vision-3.2-2b","score":75.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"granite-vision-3.3-2b","score":71.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"mimo-vl-7b-rl","score":81.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2.5-vl-32b-instruct","score":84.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"kimi-vl-a3b-thinking-2506","score":80.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bluelm-2.5-3b","score":73.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"ovis-u1-3b","score":78.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"varco-vision-2.0-1.7b","score":74.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"varco-vision-2.0-14b","score":84.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"jt-vl-chat-v3.0","score":88.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qtunevl1.5-2b","score":78.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qtunevl1.5-3b","score":77.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"r-4b","score":83.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-5-2025-08-07","score":86.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-5-nano","score":78.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-5-mini-2025-08","score":86.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sensenova-v6-5-pro","score":87.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"bluelm-2.5-3b-0909","score":86.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sail-vl2-2b","score":80.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"sail-vl2-8b","score":84.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"jt-vl-chat-mini","score":87.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"jt-vl-chat-2b","score":86.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"rbdashmm3-dpo-38b","score":87.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"valley3","score":83.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-v-4","score":79.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-v-4.5-8b","score":84.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen-vl","score":24.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen-vl-chat","score":57.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"pandagpt-13b","score":29.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"openflamingo-v2","score":13.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sharegpt4v-7b","score":58.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sharegpt4v-13b","score":63,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"transcore-m","score":67.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"instructblip-7b","score":18.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"visualglm","score":34.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mplug-owl2","score":58,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"cogvlm-17b-chat","score":54,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sharecaptioner","score":57.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"monkey","score":52.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"monkey-chat","score":65.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minigpt-4-v2","score":1.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minigpt-4-v1-7b","score":10.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"emu2-chat","score":44.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"yi-vl-6b","score":63.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"yi-vl-34b","score":66.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mmalaya","score":56.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"omnilmm-12b","score":59.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-v","score":59.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-v-2.0-3b","score":64.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"deepseek-vl-1.3b","score":61.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"deepseek-vl-7b","score":69.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"xverse-v-13b","score":60.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"360vl-70b","score":73.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-llama3-v2.5","score":70.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"phi-3-vision-4b","score":59.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"cogvlm2-llama3-chat-19b","score":68.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"wemm","score":73.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"idefics-9b-instruct","score":19.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"idefics-80b-instruct","score":44.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"idefics2-8b","score":65.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internlm-xcomposer","score":45.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internlm-xcomposer2-vl-7b","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internlm-xcomposer2-1.8b","score":66.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internlm-xcomposer2-4khd-7b","score":76.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl-chat-v1.5","score":79.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-v1-7b","score":35.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-internlm-7b-qlora","score":64.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-v1.5-7b-qlora","score":59.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-v1.5-13b-qlora","score":62.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-llama-3-8b","score":60.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-internlm2-7b-qlora","score":70,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-internlm2-20b-qlora","score":70.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-1.6-7b","score":59.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-1.6-mistral-7b","score":59.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-1.6-13b","score":65.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-next-34b","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"paligemma-mix-3b","score":62.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4-1106-vision-preview","score":65.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4-turbo-2024-04-09","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4o-2024-05-13","score":81.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-1.0-pro","score":69.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen-vl-plus","score":68.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen-vl-max","score":73.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"claude-3-haiku","score":56.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"claude-3-sonnet","score":63.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"claude-3-opus","score":58.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"reka-flash","score":71.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"reka-edge","score":56.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"glm-4v","score":78,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mini-internvl-chat-2b-v1.5","score":63,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mini-internvl-chat-4b-v1.5","score":66.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-1.5-pro","score":73.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"glm-4v-9b","score":67.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"claude-3.5-sonnet","score":79.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"congrong","score":80.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bumblebee-7b-v1.6","score":73.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llama-3-mixsense","score":67.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-pro","score":85.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-1b","score":57.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-2b","score":68.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-4b","score":71.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-8b","score":79.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-26b","score":80.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-40b","score":84.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"cambrian-1-8b","score":64.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internlm-xcomposer2.5","score":78.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bumblebee-7b-v2.0","score":76.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"xinyuan-vl","score":74.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"cambrian-34b","score":77.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bunny-llama3-8b","score":71.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-llama-3-76b","score":85.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4o-mini-2024-07-18","score":75,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis1.5-llama3-8b","score":75.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"chameleon-7b","score":19.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"chameleon-30b","score":27.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"cambrian-13b","score":63.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"yi-vision","score":76.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis1.5-gemma2-9b","score":76.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-next-llama3","score":67.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-next-interleave-7b-dpo","score":70.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-next-interleave-7b","score":69.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-next-qwen-32b","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mantis-8b-clip-llama3","score":61.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mantis-8b-siglip-llama3","score":63.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mantis-8b-idefics2","score":65.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-v-2_6","score":76.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4o-2024-08-06","score":79.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llama-3-mixsense-v1.1","score":70.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"omchat-v2.0-13b","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"parrot-7b","score":69.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"vila1.5-3b","score":54.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llama-3-vila1.5-8b","score":57.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"vila1.5-13b","score":65.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"vila1.5-40b","score":79.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mmalaya2","score":79.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"idefics3-8b-llama3","score":71.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"phi-3.5-vision-instruct","score":62.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mirage-12b-v2.0","score":77.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-1.5-7b","score":43.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-1.5-13b","score":55.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"xgen-mm-interleave-4b","score":64.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"xgen-mm-instruct-dpo-v1.5","score":65.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2-vl-7b","score":80.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2-vl-2b","score":71.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mantis-8b-fuyu","score":31.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"slime-7b","score":54.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"slime-8b","score":63.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"slime-13b","score":56.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"pixtral-12b","score":70.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-1.5-flash","score":76.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-onevision-0.5b","score":53.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-onevision-7b","score":80.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-onevision-0.5b-si","score":47.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-onevision-7b-si","score":75.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen-vl-plus-0809","score":68.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-onevision-72b-si","score":81.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-onevision-72b","score":83.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis1.6-gemma2-9b","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"eagle-x5-7b","score":60.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"eagle-x5-13b","score":65.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"moondream1","score":18.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minimonkey","score":68.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"xinyuan-vl-2b-instruct","score":74.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llama-3.2v-11b-instruct","score":64.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"step-1.5v","score":83.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"points-yi-1.5-9b","score":77.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"points-qwen2.5-7b","score":76.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"kosmos2","score":0.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llama-3.2v-90b-instruct","score":75.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"nvlm-d-72b","score":78,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"moondream2","score":28.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"molmo-7b-d","score":71.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"molmo-7b-o","score":56.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"molmoe-1b","score":44.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"janus-1.3b","score":50.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"vintern-3b-beta","score":66.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis1.6-llama3.2-3b","score":71.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"aquila-vl-2b","score":74.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"molmo-72b","score":79.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2-vl-72b","score":85.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bumblebee-7b-v2.2","score":78,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bluelm-v-3b","score":82.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"falcon2-vlm-11b","score":65.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"h2ovl-800m","score":41.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"h2ovl-2b","score":61,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen-vl-max-0809","score":85.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"claude-3.5-sonnet-20241022","score":82.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bailingmm-mini","score":82.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"vintern-1b-v2","score":52.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"rbdash-v1.5","score":80.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"awaker2.5-vl","score":81.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-8b-mpo","score":76.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2-8b-mpo-cot","score":75.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"eagle-x5-34b-chat","score":73.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis1.6-gemma2-27b","score":81.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-1.5-pro-002","score":81.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-1.5-flash-002","score":81,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4o-2024-11-20","score":83.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"aria","score":76.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"points1.5-qwen2.5-7b","score":80.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bailingmm-lite-1203","score":82.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"glm-4v-plus","score":81,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"step-1.5v-mini","score":79.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"abab6.5s","score":57.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"abab7-preview","score":80.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sensenova","score":85.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"taiyi","score":85,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-1b","score":64.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-2b","score":69.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-4b","score":77.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-8b","score":81.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-26b","score":84.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-38b","score":85.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-78b","score":87.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sail-vl-2b","score":71.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-1b-mpo","score":64.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-2b-mpo","score":69.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-4b-mpo","score":76.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-8b-mpo","score":81.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-26b-mpo","score":84.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-38b-mpo","score":85.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"valley-eagle","score":79.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl2.5-78b-mpo","score":87.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"telemm","score":78.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"deepseek-vl2-tiny","score":70.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"deepseek-vl2-small","score":79.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"varco-vision-14b","score":80.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.0-flash","score":71.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"llava-cot","score":71.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"step-1o","score":87,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"hunyuan-standard-vision-2024-12-31","score":83.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ross-qwen2-7b","score":73.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"vita-1.5","score":76.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"vita","score":68.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-o-2.6","score":79.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bailingmm-pro-0120","score":86.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"doubao-1.5-vision-pro","score":83.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"glm-4v-plus-0111","score":84.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"emu3-chat","score":46.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"smolvlm-instruct","score":50.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"smolvlm-instruct-dpo","score":48.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"smolvlm-synthetic","score":35.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"smolvlm-256m","score":14.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"smolvlm-500m","score":33.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"janus-pro-7b","score":58.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ola-7b","score":83.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis2-1b","score":66.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis2-2b","score":76.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis2-4b","score":81,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis2-8b","score":83.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis2-16b","score":85.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis2-34b","score":86.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2.5-vl-3b","score":76.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2.5-vl-7b","score":82.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2.5-vl-72b-instruct","score":87.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.0-pro","score":83.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"claude-3.7-sonnet","score":79.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"moonshot-v1-8k","score":76.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"grok-2-vision-1212","score":82.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"deepseek-vl2","score":80.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"smolvlm2-2.2b","score":53.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"smolvlm2-0.256b","score":1.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"smolvlm2-0.5b","score":33.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"phi-4-multimodal-instruct","score":74.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mug-u-7b","score":81.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemma-3-4b-it","score":66.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemma-3-12b-it","score":74.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemma-3-27b-it","score":78.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"aki-4b","score":45.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4.5","score":83.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ristretto-3b","score":79.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"chatgpt-4o","score":85.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gemini-2.5-pro","score":88.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"kimi-vl-a3b-instruct","score":80.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl3-1b","score":66.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl3-2b","score":77,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl3-8b","score":81.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl3-9b","score":82.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl3-14b","score":83.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl3-38b","score":86.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"internvl3-78b","score":87.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4.1-2025-04-14","score":86.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4.1-mini-2025-04-14","score":78.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-4.1-nano-2025-04-14","score":60.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"kimi-vl-a3b-thinking","score":64.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sail-vl-1.5-2b","score":77.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sail-vl-1.5-8b","score":81.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sail-vl-1.6-8b","score":83.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sensenova-v6-pro","score":87.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qtunevl1-2b","score":69.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"congrong-v2.0","score":88.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"wethink-qwen2.5vl-7b","score":81.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"valley2","score":80.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"valley2-dpo","score":81.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"flash-vl-2b-dynamic-iss","score":74.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"seed-1.5-vl","score":89,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"long-vita-16k","score":75.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"hawkvl-2b","score":63.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"granite-vision-3.1-2b-preview","score":64.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"granite-vision-3.2-2b","score":65.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"granite-vision-3.3-2b","score":65,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"mimo-vl-7b-rl","score":79.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qwen2.5-vl-32b-instruct","score":83.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"kimi-vl-a3b-thinking-2506","score":79.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bluelm-2.5-3b","score":75.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"ovis-u1-3b","score":77.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"varco-vision-2.0-1.7b","score":70.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"varco-vision-2.0-14b","score":83,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"jt-vl-chat-v3.0","score":86.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qtunevl1.5-2b","score":76.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"qtunevl1.5-3b","score":77.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"r-4b","score":81.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-5-2025-08-07","score":86.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-5-nano","score":79.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"gpt-5-mini-2025-08","score":86.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sensenova-v6-5-pro","score":87,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"bluelm-2.5-3b-0909","score":86.4,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sail-vl2-2b","score":79.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"sail-vl2-8b","score":84.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"jt-vl-chat-mini","score":83,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"jt-vl-chat-2b","score":78.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"rbdashmm3-dpo-38b","score":87.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"valley3","score":82.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-v-4","score":79.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-cn","model":"minicpm-v-4.5-8b","score":84.1,"metric":"percent"},{"benchmark":"buzzbench","model":"llama-3.1-405b","score":45.94,"metric":"percent"},{"benchmark":"buzzbench","model":"llama-3.2-1b-instruct","score":9.51,"metric":"percent"},{"benchmark":"buzzbench","model":"llama-3.2-3b-instruct","score":26.55,"metric":"percent"},{"benchmark":"buzzbench","model":"chatgpt-4o","score":59.48,"metric":"percent"},{"benchmark":"buzzbench","model":"deepseek-v3","score":51.63,"metric":"percent"},{"benchmark":"buzzbench","model":"o1-mini","score":46.18,"metric":"percent"},{"benchmark":"buzzbench","model":"llama-3.3-70b-instruct","score":45.7,"metric":"percent"},{"benchmark":"buzzbench","model":"gpt-3.5-turbo-0613","score":39,"metric":"percent"},{"benchmark":"buzzbench","model":"qwen2.5-7b-instruct","score":31.42,"metric":"percent"},{"benchmark":"buzzbench","model":"mistral-large-2411","score":47.48,"metric":"percent"},{"benchmark":"buzzbench","model":"ministral-8b-2410","score":32.3,"metric":"percent"},{"benchmark":"buzzbench","model":"llama-3.1-8b-instruct","score":32.88,"metric":"percent"},{"benchmark":"buzzbench","model":"qwen2.5-72b-instruct","score":45.89,"metric":"percent"},{"benchmark":"buzzbench","model":"grok-2-1212","score":51.76,"metric":"percent"},{"benchmark":"buzzbench","model":"phi-4","score":38.67,"metric":"percent"},{"benchmark":"buzzbench","model":"quasar-alpha","score":67.85,"metric":"percent"},{"benchmark":"buzzbench","model":"chatgpt-4o-latest-20250326","score":69.11,"metric":"percent"},{"benchmark":"buzzbench","model":"gemini-2.5-pro-preview-03-25","score":71.09,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"mistral-small-3.2-24b-instruct","score":50.21,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3-235b-a22b-instruct-2507","score":59.69,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5-mini-minimal","score":74.49,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5-nano-minimal","score":52.2,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-oss-120b","score":54.78,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-oss-20b","score":42.8,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5-minimal","score":81.2,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3-30b-a3b-instruct-2507","score":34.58,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gemini-2.5-flash-lite","score":55.99,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-4.1-mini","score":57.26,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"mistral-medium-3","score":58.53,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3-235b-a22b","score":56.18,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"o4-mini","score":56.1,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"llama-3.1-8b-instruct","score":19.18,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"claude-sonnet-4.5","score":84.56,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"claude-4.5-haiku","score":79.72,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gemini-3-pro-preview","score":86.58,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"grok-4.1-fast","score":75.82,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"deepseek-v3.2","score":66.28,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"mistral-large-3","score":68.2,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5.2","score":82.01,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gemini-3-flash-preview","score":85.38,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"glm-4.7-flash","score":66.18,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"glm-4.7","score":77.48,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"claude-sonnet-4.6","score":94.08,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"claude-opus-4.6","score":92.93,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"glm-5","score":85.58,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3.5-397b-a17b","score":85.45,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"minimax-m2.5","score":64.46,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3.5-27b","score":84.31,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3.5-122b-a10b","score":81.03,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3.5-35b-a3b","score":81.39,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gemini-3.1-flash-lite","score":80.92,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5.4","score":84.98,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3.5-flash","score":81.85,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"qwen3.5-9b","score":74.99,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"mistral-small-4","score":51.6,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5.4-nano","score":64.47,"metric":"percent"},{"benchmark":"judgemark-v2-1","model":"gpt-5.4-mini","score":81.14,"metric":"percent"},{"benchmark":"eqbench","model":"internlm2-chat-7b","score":62.61,"metric":"percent"},{"benchmark":"eqbench","model":"nous-hermes-2-yi-34b","score":72.68,"metric":"percent"},{"benchmark":"eqbench","model":"lmcocktail-10.7b-v1","score":73.67,"metric":"percent"},{"benchmark":"eqbench","model":"yi-34b-chat","score":71.62,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-7b-openorca","score":66.55,"metric":"percent"},{"benchmark":"eqbench","model":"una-cybertron-7b-v2","score":62.83,"metric":"percent"},{"benchmark":"eqbench","model":"neural-chat-7b-v3-1","score":64.77,"metric":"percent"},{"benchmark":"eqbench","model":"marcoroni-neural-chat-7b-v2","score":68.54,"metric":"percent"},{"benchmark":"eqbench","model":"zephyr-7b-beta","score":58.33,"metric":"percent"},{"benchmark":"eqbench","model":"marcoroni-7b-v3","score":71.68,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-7b-instruct-v0.1","score":52.15,"metric":"percent"},{"benchmark":"eqbench","model":"sauerkrautlm-una-solar-instruct","score":73.56,"metric":"percent"},{"benchmark":"eqbench","model":"zephyr-7b-alpha","score":56.82,"metric":"percent"},{"benchmark":"eqbench","model":"llama-2-13b-chat","score":49.12,"metric":"percent"},{"benchmark":"eqbench","model":"gml-mistral-merged-v1","score":74.01,"metric":"percent"},{"benchmark":"eqbench","model":"solar-10.7b-instruct-v1.0","score":73.53,"metric":"percent"},{"benchmark":"eqbench","model":"dolphin-2.2-yi-34b","score":75.52,"metric":"percent"},{"benchmark":"eqbench","model":"dolphin-2.2-70b","score":79.6,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4-0314","score":85.73,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4-0613","score":84.79,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4-1106-preview","score":86.05,"metric":"percent"},{"benchmark":"eqbench","model":"koala-7b","score":21.54,"metric":"percent"},{"benchmark":"eqbench","model":"llama-2-70b-chat","score":73.59,"metric":"percent"},{"benchmark":"eqbench","model":"vicuna-7b-v1.1","score":26.12,"metric":"percent"},{"benchmark":"eqbench","model":"nous-capybara-7b-v1","score":34.37,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-medium","score":82.57,"metric":"percent"},{"benchmark":"eqbench","model":"llama-2-7b-chat","score":36.32,"metric":"percent"},{"benchmark":"eqbench","model":"gemini-pro","score":75.08,"metric":"percent"},{"benchmark":"eqbench","model":"synthia-70b-v1.5","score":73.71,"metric":"percent"},{"benchmark":"eqbench","model":"openchat-3.5-1210","score":72.52,"metric":"percent"},{"benchmark":"eqbench","model":"openchat-3.5","score":72.18,"metric":"percent"},{"benchmark":"eqbench","model":"beagle14-7b","score":74.45,"metric":"percent"},{"benchmark":"eqbench","model":"neuralmarcoro14-7b","score":74.15,"metric":"percent"},{"benchmark":"eqbench","model":"firefly-mixtral-8x7b","score":64.36,"metric":"percent"},{"benchmark":"eqbench","model":"neuralhermes-2.5-mistral-7b","score":65.86,"metric":"percent"},{"benchmark":"eqbench","model":"mixtral-34bx2-moe-60b","score":72.69,"metric":"percent"},{"benchmark":"eqbench","model":"mixtral-8x7b-instruct-v0.1","score":72.37,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-7b-instruct-v0.2","score":68.18,"metric":"percent"},{"benchmark":"eqbench","model":"phi-2-dpo","score":54.42,"metric":"percent"},{"benchmark":"eqbench","model":"phi-2-orange","score":56.94,"metric":"percent"},{"benchmark":"eqbench","model":"phixtral-2x2.8","score":54.58,"metric":"percent"},{"benchmark":"eqbench","model":"phi-2","score":27.6,"metric":"percent"},{"benchmark":"eqbench","model":"beyonder-4x7b-v2","score":69.23,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-3.5-turbo-1106","score":71.74,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-3.5-turbo-0613","score":69.35,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-3.5-turbo-0301","score":70.67,"metric":"percent"},{"benchmark":"eqbench","model":"meow","score":73.94,"metric":"percent"},{"benchmark":"eqbench","model":"goliath-120b","score":76.09,"metric":"percent"},{"benchmark":"eqbench","model":"tess-xl-v1.0","score":78.46,"metric":"percent"},{"benchmark":"eqbench","model":"neuralbeagle14-7b","score":74.79,"metric":"percent"},{"benchmark":"eqbench","model":"nous-hermes-2-mixtral-8x7b-sft","score":72.91,"metric":"percent"},{"benchmark":"eqbench","model":"phi-2-psy","score":56.44,"metric":"percent"},{"benchmark":"eqbench","model":"stablelm-2-zephyr-1.6b","score":15.04,"metric":"percent"},{"benchmark":"eqbench","model":"megadolphin-120b","score":80.21,"metric":"percent"},{"benchmark":"eqbench","model":"orion-14b-chat","score":59.71,"metric":"percent"},{"benchmark":"eqbench","model":"laserxtral","score":71.96,"metric":"percent"},{"benchmark":"eqbench","model":"solar-10.7b-instruct-dpo","score":73.21,"metric":"percent"},{"benchmark":"eqbench","model":"falcon-180b-chat","score":56.82,"metric":"percent"},{"benchmark":"eqbench","model":"qwen-1.8b-chat","score":30,"metric":"percent"},{"benchmark":"eqbench","model":"qwen-14b-chat","score":63.47,"metric":"percent"},{"benchmark":"eqbench","model":"qwen-7b-chat","score":50.11,"metric":"percent"},{"benchmark":"eqbench","model":"yi-6b-chat","score":61.79,"metric":"percent"},{"benchmark":"eqbench","model":"miqu-1-70b","score":82.91,"metric":"percent"},{"benchmark":"eqbench","model":"discolm-120b","score":78.48,"metric":"percent"},{"benchmark":"eqbench","model":"qwen-72b-chat","score":80.7,"metric":"percent"},{"benchmark":"eqbench","model":"wizardlm-70b","score":71.28,"metric":"percent"},{"benchmark":"eqbench","model":"vicuna-13b-v1.5","score":67.39,"metric":"percent"},{"benchmark":"eqbench","model":"tulu-2-dpo-70b","score":76.63,"metric":"percent"},{"benchmark":"eqbench","model":"wizardlm-13b-v1.2","score":63.71,"metric":"percent"},{"benchmark":"eqbench","model":"dolphin-2.2.1-mistral-7b","score":69.92,"metric":"percent"},{"benchmark":"eqbench","model":"guanaco-33b","score":36.11,"metric":"percent"},{"benchmark":"eqbench","model":"openhermes-2.5-mistral-7b","score":66.89,"metric":"percent"},{"benchmark":"eqbench","model":"starling-lm-7b-alpha","score":73.9,"metric":"percent"},{"benchmark":"eqbench","model":"vicuna-33b-v1.3","score":67.07,"metric":"percent"},{"benchmark":"eqbench","model":"sparsetral-16x7b-v2","score":59.9,"metric":"percent"},{"benchmark":"eqbench","model":"qwen1.5-14b-chat","score":74.99,"metric":"percent"},{"benchmark":"eqbench","model":"qwen1.5-4b-chat","score":28.75,"metric":"percent"},{"benchmark":"eqbench","model":"qwen1.5-1.8b-chat","score":24.12,"metric":"percent"},{"benchmark":"eqbench","model":"qwen1.5-72b-chat","score":82.81,"metric":"percent"},{"benchmark":"eqbench","model":"qwen1.5-7b-chat","score":54.41,"metric":"percent"},{"benchmark":"eqbench","model":"quyen-pro-max-v0.1","score":77.16,"metric":"percent"},{"benchmark":"eqbench","model":"senku-70b-full","score":84.89,"metric":"percent"},{"benchmark":"eqbench","model":"claude-instant-1.2","score":69.04,"metric":"percent"},{"benchmark":"eqbench","model":"claude-2.1","score":73.96,"metric":"percent"},{"benchmark":"eqbench","model":"claude","score":76.83,"metric":"percent"},{"benchmark":"eqbench","model":"claude-2","score":72.89,"metric":"percent"},{"benchmark":"eqbench","model":"pplx-70b-online","score":62.79,"metric":"percent"},{"benchmark":"eqbench","model":"pplx-7b-online","score":48.91,"metric":"percent"},{"benchmark":"eqbench","model":"snorkel-mistral-pairrm-dpo","score":65.83,"metric":"percent"},{"benchmark":"eqbench","model":"miquella-120b","score":82.15,"metric":"percent"},{"benchmark":"eqbench","model":"miquliz-120b-v2.0","score":82.21,"metric":"percent"},{"benchmark":"eqbench","model":"tess-72b-v1.5b","score":81.78,"metric":"percent"},{"benchmark":"eqbench","model":"quyen-pro-v0.1","score":70.75,"metric":"percent"},{"benchmark":"eqbench","model":"monarch-7b","score":75.8,"metric":"percent"},{"benchmark":"eqbench","model":"neuralmonarch-7b","score":76.26,"metric":"percent"},{"benchmark":"eqbench","model":"alphamonarch-7b","score":76.08,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-3.5-turbo-0125","score":64.97,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4-0125-preview","score":83.87,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-7b-it","score":61.72,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-2b-it","score":23.26,"metric":"percent"},{"benchmark":"eqbench","model":"westlake-7b-v2","score":78.7,"metric":"percent"},{"benchmark":"eqbench","model":"smaug-72b-v0.1","score":79.75,"metric":"percent"},{"benchmark":"eqbench","model":"theprofessor-155b","score":78.82,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-small-2402","score":80.36,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-large-2402","score":85.17,"metric":"percent"},{"benchmark":"eqbench","model":"experiment26-7b","score":77.21,"metric":"percent"},{"benchmark":"eqbench","model":"samantha-120b","score":76.44,"metric":"percent"},{"benchmark":"eqbench","model":"midnight-miqu-70b-v1.0","score":75.9,"metric":"percent"},{"benchmark":"eqbench","model":"claude-3-sonnet","score":80.45,"metric":"percent"},{"benchmark":"eqbench","model":"claude-3-opus","score":82.19,"metric":"percent"},{"benchmark":"eqbench","model":"miiqu-f16","score":83.17,"metric":"percent"},{"benchmark":"eqbench","model":"beyonder-4x7b-v3","score":77.01,"metric":"percent"},{"benchmark":"eqbench","model":"starling-lm-7b-beta","score":73.82,"metric":"percent"},{"benchmark":"eqbench","model":"qwen1.5-moe-a2.7b-chat","score":58.07,"metric":"percent"},{"benchmark":"eqbench","model":"databricks-dbrx-instruct","score":76.82,"metric":"percent"},{"benchmark":"eqbench","model":"command-r","score":56.05,"metric":"percent"},{"benchmark":"eqbench","model":"claude-3-haiku","score":63.65,"metric":"percent"},{"benchmark":"eqbench","model":"qwen1.5-32b-chat","score":75.59,"metric":"percent"},{"benchmark":"eqbench","model":"command-r-plus","score":76.11,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-1.1-7b-it","score":59.17,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4-turbo-2024-04-09","score":86.35,"metric":"percent"},{"benchmark":"eqbench","model":"wizardlm-2-7b","score":69.31,"metric":"percent"},{"benchmark":"eqbench","model":"wizardlm-2-8x22b","score":77.91,"metric":"percent"},{"benchmark":"eqbench","model":"mixtral-8x22b-instruct-v0.1","score":78.79,"metric":"percent"},{"benchmark":"eqbench","model":"meta-llama-3-8b-instruct","score":68.88,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3-70b-instruct","score":82.13,"metric":"percent"},{"benchmark":"eqbench","model":"ece-tw3-jrgl-v1","score":83.07,"metric":"percent"},{"benchmark":"eqbench","model":"nanbeige2-8b-chat","score":65.17,"metric":"percent"},{"benchmark":"eqbench","model":"phi-3-mini-4k-instruct","score":58.15,"metric":"percent"},{"benchmark":"eqbench","model":"qwen1.5-110b-chat","score":83.68,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4o","score":83.51,"metric":"percent"},{"benchmark":"eqbench","model":"yi-1.5-34b-chat","score":72.93,"metric":"percent"},{"benchmark":"eqbench","model":"yi-1.5-9b-chat","score":70.37,"metric":"percent"},{"benchmark":"eqbench","model":"yi-1.5-6b-chat","score":59.45,"metric":"percent"},{"benchmark":"eqbench","model":"smaug-llama-3-70b-instruct","score":80.69,"metric":"percent"},{"benchmark":"eqbench","model":"phi-3-medium-4k-instruct","score":76.34,"metric":"percent"},{"benchmark":"eqbench","model":"phi-3-small-8k-instruct","score":73.49,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-7b-instruct-v0.3","score":63.15,"metric":"percent"},{"benchmark":"eqbench","model":"qwen2-72b-instruct","score":81.35,"metric":"percent"},{"benchmark":"eqbench","model":"claude-3.5-sonnet-20240620","score":86.36,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-2-9b-it","score":80.46,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-2-27b-it","score":80.55,"metric":"percent"},{"benchmark":"eqbench","model":"gpt-4o-mini","score":76.93,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-nemo-instruct-2407","score":77.13,"metric":"percent"},{"benchmark":"eqbench","model":"deepseek-v2-chat-0628","score":83.18,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-large-2407","score":85.05,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.1-405b","score":83,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-2-2b-it","score":60.86,"metric":"percent"},{"benchmark":"eqbench","model":"rys-xlarge","score":84.55,"metric":"percent"},{"benchmark":"eqbench","model":"rys-xlarge-base","score":85.05,"metric":"percent"},{"benchmark":"eqbench","model":"exaone-3.0-7.8b-instruct","score":66.72,"metric":"percent"},{"benchmark":"eqbench","model":"phi-3.5-mini-instruct","score":54.74,"metric":"percent"},{"benchmark":"eqbench","model":"phi-3.5-moe-instruct","score":76.97,"metric":"percent"},{"benchmark":"eqbench","model":"trillama-8b","score":66.63,"metric":"percent"},{"benchmark":"eqbench","model":"solar-pro-preview","score":78.52,"metric":"percent"},{"benchmark":"eqbench","model":"gemma-2-ifable-9b","score":79.93,"metric":"percent"},{"benchmark":"eqbench","model":"o1-preview-2024-09-12","score":80.51,"metric":"percent"},{"benchmark":"eqbench","model":"o1-mini-2024-09-12","score":71.97,"metric":"percent"},{"benchmark":"eqbench","model":"hermes-3-llama-3.1-405b","score":82.79,"metric":"percent"},{"benchmark":"eqbench","model":"deepseek-v2.5","score":81.96,"metric":"percent"},{"benchmark":"eqbench","model":"chatgpt-4o-latest-20240903","score":82.45,"metric":"percent"},{"benchmark":"eqbench","model":"mistral-small-instruct-2409","score":80.86,"metric":"percent"},{"benchmark":"eqbench","model":"qwen2.5-3b","score":49.76,"metric":"percent"},{"benchmark":"eqbench","model":"qwen2.5-7b-instruct","score":69.18,"metric":"percent"},{"benchmark":"eqbench","model":"qwen2.5-14b-instruct","score":79.23,"metric":"percent"},{"benchmark":"eqbench","model":"qwen2.5-32b-instruct","score":79.89,"metric":"percent"},{"benchmark":"eqbench","model":"qwen2.5-72b-instruct","score":79.05,"metric":"percent"},{"benchmark":"eqbench","model":"gemini-1.5-pro-002","score":83.52,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.2-1b-instruct","score":22.65,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.2-3b-instruct","score":61.06,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.2-vision-11b-instruct","score":67.88,"metric":"percent"},{"benchmark":"eqbench","model":"llama-3.2-90b-vision","score":81.98,"metric":"percent"},{"benchmark":"creative-writing-v3","model":"gpt-6-astra","score":2173.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-fable-5.1","score":2162,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-opus-5","score":2132.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-6-sol","score":2124.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"kimi-k3","score":2082.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-5.3","score":2075,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-opus-5.5","score":2050.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"grok-4.7","score":2006.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"ox-alpha","score":1971.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5.6-sol","score":1971.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-fable-5","score":1943.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"aion-3.5","score":1929.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"muse-spark-1.1","score":1927.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-opus-4.7","score":1914.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"hemmingway-1","score":1906.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"muse-spark-1.3","score":1905.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5.6-terra","score":1854.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5.5","score":1843.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"qwen3.8-2.4t-a95b","score":1842.5,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"muse-spark-1.2","score":1840.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-opus-4.8","score":1839.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5.4","score":1839.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5.6-luna","score":1828.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-sonnet-4.6","score":1810.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-opus-4.6","score":1809.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"muse-glimmer-30b","score":1798.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-sonnet-5","score":1794,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"space-bunny-alpha","score":1784.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-5.2","score":1756.5,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-3.8-flash","score":1747.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"kimi-k2.6","score":1724.5,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-3.7-flash","score":1723.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5.2","score":1702.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"nemotron-3-ultra","score":1692.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5.3-instant","score":1689.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-opus-4.5","score":1686.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-sonnet-4.5","score":1677.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"o3","score":1675.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"qwen3.8-27b","score":1671.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"kimi-k2-instruct","score":1665.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5.4-mini","score":1665,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"kimi-k2-thinking","score":1630.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"horizon-beta","score":1627.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5","score":1626.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"horizon-alpha","score":1622.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"pony-alpha","score":1616.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"inkling","score":1610.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-3.6-flash","score":1603.5,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-5","score":1600.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-5.1","score":1592.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-opus-4","score":1579.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"grok-4.5","score":1578.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"kimi-k2.5","score":1578.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"grok-4.2","score":1573.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v4-flash","score":1559.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-3.5-flash-lite","score":1559.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v4-pro","score":1553.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v4.1-flash","score":1540.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-3-pro-preview","score":1524.5,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v3.2","score":1515,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"chatgpt-4o-latest-20250326","score":1501.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mimo-v2.5-pro","score":1493.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"inkling-small","score":1491.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-3.1-pro","score":1491.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"hunter-alpha","score":1483.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-sonnet-4","score":1482.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"qwen3.5-397b-a17b","score":1478.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-medium-3.1","score":1475.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v3-0324","score":1472.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-3.5-sonnet-20241022","score":1450.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v4-flash-0731","score":1441.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v3.1","score":1435.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-2.5-pro-preview-06-05","score":1421.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-r1-0528","score":1421.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"hermes-4-405b","score":1420.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-4.1","score":1419.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"optimus-alpha","score":1417.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-4.7","score":1413.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-large-3","score":1412.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-3.7-sonnet","score":1411.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-4.6","score":1411.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-2.5-pro-exp-03.25","score":1396.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-small-creative","score":1369.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-4-31b-it","score":1368.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"qwen-3-235b-a22b-thinking","score":1365.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"minimax-m2.5","score":1361,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"quasar-alpha","score":1351,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"chatgpt-4o-latest-20250129","score":1346.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-4.5","score":1343.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"sherlock-dash-alpha","score":1332.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"grok-4.1-fast","score":1327.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5-mini","score":1313,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-4-26b-a4b-it","score":1304.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-4-12b-it","score":1288.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"nemotron-3.5-lightning-30b-a3b","score":1280.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"deepseek-v3.2-speciale","score":1276.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-3-27b-it","score":1265.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-4.5","score":1258,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"qwq-32b","score":1257.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-small-3.2-24b-instruct","score":1255.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"reka-flash-3","score":1227.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"grok-3-beta","score":1185.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-4.1-mini","score":1147,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-3.5-haiku","score":1145.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"command-a","score":1145.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-2.5-flash-preview-04-17","score":1136.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemini-2.0-flash","score":1127.5,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-3-12b-it","score":1125.5,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-4.7-flash","score":1124.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-3-glitter-12b","score":1118.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"darkest-muse-v1","score":1104.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"glm-4-32b","score":1068.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-3-4b-it","score":1068,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-2-ifable-9b","score":1002.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"pixtral-large-2411","score":987.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-large-2411","score":984.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-oss-120b","score":961,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-4.1-nano","score":945.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-3-starshine-12b","score":885.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-nemo-instruct-2407","score":880.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-4o-mini","score":872.8,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"llama-3.1-405b","score":870.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"llama-4-maverick","score":860.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gemma-2-9b-it","score":841.4,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"nanbeige4-3b-thinking-2511","score":841.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"llama-3.1-70b-instruct","score":783.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"llama-4-scout-17b-16e","score":783.1,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"cypher-alpha","score":776.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-small-3.1-24b-instruct","score":760.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-4-0314","score":752.2,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"lfm-7b","score":751.7,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"claude-3-haiku","score":717.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"llama-3.1-8b-instruct","score":713,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"mistral-small-24b-instruct-2501","score":706.5,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-5-nano","score":704.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-oss-20b","score":665.6,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"llama-3.2-3b-instruct","score":595.3,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"gpt-3.5-turbo-0613","score":450.9,"metric":"ELO"},{"benchmark":"creative-writing-v3","model":"llama-3.2-1b-instruct","score":200,"metric":"ELO"},{"benchmark":"creative-writing-longform","model":"claude-sonnet-4.6","score":79.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-opus-4.6","score":77.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"kimi-k2.5","score":74.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-opus-4.5","score":73.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5-high","score":73.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5","score":72.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.2","score":71.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-sonnet-4.5","score":71.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"horizon-alpha","score":71.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-5","score":70.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-opus-4.1","score":70.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"kimi-k2-thinking","score":69,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-3-pro-preview","score":68.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3.5-397b-a17b","score":68.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"kimi-k2-instruct","score":68.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v3.2","score":66.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5-chat","score":66.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3-max","score":66.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-4.7","score":66,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"minimax-m2.5","score":65.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-4.5-haiku","score":65,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"kimi-k2-0905","score":63.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"o3","score":62.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v3.1","score":62.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v3.2-exp","score":60.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"chatgpt-4o-latest-20250326","score":60.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v3-0324","score":60.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-r1","score":59.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-tng-r1t-chimera-20250427","score":59.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-r1-0528","score":59.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-2.5-pro-preview-03-25","score":58.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-sonnet-4","score":58.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-3.5-sonnet","score":58.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"minimax-m2.1","score":57.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-3.7-sonnet","score":57.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3-235b-a22b-instruct-2507","score":57.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-4.6","score":57.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"ling-1t","score":56.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5-mini","score":56.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-3-flash-preview","score":55.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-4.5","score":55.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-2.5-pro-preview-06-05","score":53.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mimo-v2-flash","score":53.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"hermes-4-405b","score":51.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3-max-instruct-preview","score":50.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v3.2-speciale","score":48.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-2.5-flash-preview-05-20","score":48.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mistral-large-3","score":48.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-4.7-flash","score":47.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"seed1.6","score":47.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"sherlock-dash-alpha","score":47.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"olmo-3.1-think-32b","score":47,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"minimax-m2","score":46.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"bert-nebulon-alpha","score":46.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mistral-medium-3.1","score":46.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"grok-4","score":45.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemma-3-27b-it-antislop","score":45.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"sonoma-sky","score":42.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemma-3-27b-it","score":41.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemma-3-12b-it","score":41.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mistral-small-3.2-24b-instruct","score":41.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"reka-flash-3","score":41.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3-32b","score":40.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"grok-4.1-fast","score":40.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"ftpo-exp501","score":39.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"nova-2-lite","score":38.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwq-32b","score":36.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3-14b","score":35.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-oss-120b","score":35.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3-30b-a3b","score":35.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"longcat-flash-chat","score":35.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"trinity-large-preview","score":35,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"minimax-m2-her","score":34.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemma-3-4b-it","score":34.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"nemotron-3-nano-30b-a3b","score":32.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mistral-small-creative","score":32.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-4.1-nano","score":32.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"ministral-3-14b-instruct","score":31.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"llama-4-maverick","score":31.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"nanbeige4-3b-thinking-2511","score":31.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3-next-80b-a3b-instruct","score":31.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"llama-4-scout-17b-16e","score":31.1,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"aurora-alpha","score":29.4,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mistral-nemo-instruct-2407","score":28.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5-nano","score":28,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"solar-pro-3","score":27,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"phi-4-multimodal-instruct","score":22.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-oss-20b","score":21.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3-4b","score":17,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-3.1-pro","score":68.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3.5-122b-a10b","score":54.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3.5-27b","score":59,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3.5-35b-a3b","score":44.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-3.1-flash-lite","score":49,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.3-instant","score":62.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.4","score":78.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"hunter-alpha","score":62.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"healer-alpha","score":51,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"grok-4.2","score":68.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mistral-small-4","score":43.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.4-mini","score":73,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.4-nano","score":57.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mimo-v2-pro","score":70.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemma-4-31b-it","score":56.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemma-4-26b-a4b-it","score":50.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-5.1","score":73.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-opus-4.7","score":81.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v4-pro","score":75.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.5","score":78.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v4-flash","score":66,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"kimi-k2.6","score":78.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-opus-4.8","score":80.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-fable-5","score":83,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-3.5-flash","score":71.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-5.2","score":77.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemma-4-12b-it","score":48.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-sonnet-5","score":78.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.6-terra","score":78,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.6-sol","score":81.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-5.6-luna","score":75.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"muse-spark-1.1","score":70.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"inkling","score":72.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"kimi-k3","score":79.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-opus-5","score":86.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"mimo-v2.5-pro","score":73.7,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v4-flash-0731","score":61.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"muse-spark-1.2","score":81.5,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"qwen3.8-27b","score":53.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"ox-alpha","score":79.9,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"glm-5.3","score":81.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-6-astra","score":82.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gemini-3.8-flash","score":76.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"muse-spark-1.3","score":82.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-fable-5.1","score":85.3,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"hemmingway-1","score":74.2,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"grok-4.7","score":83,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"deepseek-v4.1-flash","score":74,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"claude-opus-5.5","score":84.6,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"gpt-6-sol","score":82.8,"metric":"percent"},{"benchmark":"creative-writing-longform","model":"aion-3.5","score":82.1,"metric":"percent"},{"benchmark":"eqbench-3","model":"claude-fable-5","score":2049.7,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-opus-4.8","score":2029.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-opus-4.7","score":1884.3,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-opus-4.6","score":1717.4,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-sonnet-4.6","score":1714.1,"metric":"ELO"},{"benchmark":"eqbench-3","model":"hivemind-32b-preview","score":1618.1,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-5.5","score":1576.9,"metric":"ELO"},{"benchmark":"eqbench-3","model":"glm-5.2","score":1575.1,"metric":"ELO"},{"benchmark":"eqbench-3","model":"deepseek-v4-pro","score":1570.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"glm-5.1","score":1566.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-5.4","score":1562.9,"metric":"ELO"},{"benchmark":"eqbench-3","model":"kimi-k2-instruct","score":1562.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"kimi-k2.6","score":1561.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemini-3-pro-preview","score":1559.4,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-5.2","score":1558.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"horizon-alpha","score":1554.4,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-5.1","score":1551,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-opus-4.5","score":1545.7,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemini-2.5-pro-preview-06-05","score":1545,"metric":"ELO"},{"benchmark":"eqbench-3","model":"kimi-k2.5","score":1544.7,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemini-3.1-pro","score":1537.7,"metric":"ELO"},{"benchmark":"eqbench-3","model":"glm-5","score":1526,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-sonnet-4.5","score":1511,"metric":"ELO"},{"benchmark":"eqbench-3","model":"deepseek-v4-flash","score":1491.3,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-5-chat","score":1488.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemma-4-31b-it","score":1434.1,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemma-4-26b-a4b-it","score":1430.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"glm-4.7","score":1428.3,"metric":"ELO"},{"benchmark":"eqbench-3","model":"qwen3.5-397b-a17b","score":1413.1,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-opus-4","score":1399.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemini-2.5-pro-preview-03-25","score":1393.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-5.3-instant","score":1393,"metric":"ELO"},{"benchmark":"eqbench-3","model":"chatgpt-4o-latest-20250425","score":1389.9,"metric":"ELO"},{"benchmark":"eqbench-3","model":"chatgpt-4o-latest-20250326","score":1386.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"hermes-4-405b","score":1361.4,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemma-4-12b-it","score":1361.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"glm-4.5","score":1276.3,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-sonnet-4","score":1242.9,"metric":"ELO"},{"benchmark":"eqbench-3","model":"o4-mini","score":1232.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"deepseek-r1","score":1230.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"qwen3-235b-a22b","score":1213.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemini-2.5-pro-preview-05-06","score":1208.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"grok-4.1-fast","score":1184.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-4.1","score":1179.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"qwq-32b","score":1167.7,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemini-2.5-flash-preview-04-17","score":1164.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"grok-3-beta","score":1149.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"grok-4","score":1147.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-3.7-sonnet","score":1111.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-4.1-mini","score":1099.3,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemma-3-27b-it","score":1093.9,"metric":"ELO"},{"benchmark":"eqbench-3","model":"glm-4.7-flash","score":1083,"metric":"ELO"},{"benchmark":"eqbench-3","model":"deepseek-v3-0324","score":1082.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"claude-3.5-sonnet-20241022","score":1080.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-oss-120b","score":1075.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"mistral-small-3.2-24b-instruct","score":1071.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"grok-3-mini-beta","score":1064.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-4.5","score":1053.3,"metric":"ELO"},{"benchmark":"eqbench-3","model":"qwen3-32b","score":1047.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"llama-3.1-nemotron-ultra-253b-v1","score":1043.3,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-4.1-nano","score":1029.4,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemma-3-4b-it","score":977.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-oss-20b","score":956,"metric":"ELO"},{"benchmark":"eqbench-3","model":"mistral-large-2411","score":950.7,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemini-2.0-flash","score":910.9,"metric":"ELO"},{"benchmark":"eqbench-3","model":"qwen3-30b-a3b","score":868.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"qwen3-8b","score":865.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"grok-4.2","score":851.5,"metric":"ELO"},{"benchmark":"eqbench-3","model":"qwen2.5-72b-instruct","score":845.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"llama-4-maverick","score":806.8,"metric":"ELO"},{"benchmark":"eqbench-3","model":"mistral-small-24b-instruct-2501","score":801.7,"metric":"ELO"},{"benchmark":"eqbench-3","model":"llama-3.1-405b","score":799,"metric":"ELO"},{"benchmark":"eqbench-3","model":"mistral-small-3.1-24b-instruct","score":783.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"nanbeige4-3b-thinking-2511","score":675,"metric":"ELO"},{"benchmark":"eqbench-3","model":"llama-4-scout-17b-16e","score":608.2,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gpt-4-0314","score":577.6,"metric":"ELO"},{"benchmark":"eqbench-3","model":"gemma-2-9b-it","score":554.3,"metric":"ELO"},{"benchmark":"eqbench-3","model":"llama-3.2-1b-instruct","score":200,"metric":"ELO"},{"benchmark":"spiral-bench","model":"chatgpt-4o","score":25.2,"metric":"percent"},{"benchmark":"spiral-bench","model":"claude-3.5-sonnet","score":42.6,"metric":"percent"},{"benchmark":"spiral-bench","model":"claude-sonnet-4.5","score":70.3,"metric":"percent"},{"benchmark":"spiral-bench","model":"claude-sonnet-4","score":32.1,"metric":"percent"},{"benchmark":"spiral-bench","model":"deepseek-r1-0528","score":14.2,"metric":"percent"},{"benchmark":"spiral-bench","model":"gemini-2.5-flash","score":36.5,"metric":"percent"},{"benchmark":"spiral-bench","model":"gemini-2.5-pro","score":28.3,"metric":"percent"},{"benchmark":"spiral-bench","model":"glm-4.6","score":30.8,"metric":"percent"},{"benchmark":"spiral-bench","model":"gpt-5","score":57.4,"metric":"percent"},{"benchmark":"spiral-bench","model":"gpt-5-chat-2025-10-03","score":70.8,"metric":"percent"},{"benchmark":"spiral-bench","model":"gpt-5-chat","score":36.6,"metric":"percent"},{"benchmark":"spiral-bench","model":"gpt-oss-120b","score":57.5,"metric":"percent"},{"benchmark":"spiral-bench","model":"grok-4-fast","score":37.5,"metric":"percent"},{"benchmark":"spiral-bench","model":"kimi-k2","score":57.2,"metric":"percent"},{"benchmark":"spiral-bench","model":"llama-4-maverick","score":38.2,"metric":"percent"},{"benchmark":"spiral-bench","model":"mistral-medium-3.1","score":15,"metric":"percent"},{"benchmark":"spiral-bench","model":"o3","score":63.4,"metric":"percent"},{"benchmark":"spiral-bench","model":"o4-mini","score":53.6,"metric":"percent"},{"benchmark":"spiral-bench","model":"qwen3-235b-a22b-instruct-2507","score":20.4,"metric":"percent"},{"benchmark":"spiral-bench","model":"grok-4.1-fast","score":25.3,"metric":"percent"},{"benchmark":"spiral-bench","model":"gemini-3-pro-preview","score":38.7,"metric":"percent"},{"benchmark":"spiral-bench","model":"gpt-5.2","score":70.2,"metric":"percent"},{"benchmark":"spiral-bench","model":"gemma-3-27b-it","score":25.2,"metric":"percent"},{"benchmark":"creative-story-writing-v3","model":"kimi-k2-instruct-0905","score":8.729,"metric":"score"},{"benchmark":"creative-story-writing-v3","model":"grok-4-fast-thinking","score":8.114,"metric":"score"},{"benchmark":"faix-overall","model":"qwen3.8-max","score":51.74,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-fable-5","score":36,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-3-pro","score":30.73,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-3.1-pro","score":29.25,"metric":"percent"},{"benchmark":"faix-overall","model":"seed2.1-pro","score":28.91,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-3-pro-preview","score":28.17,"metric":"percent"},{"benchmark":"faix-overall","model":"kimi-k3","score":25.33,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-5.5","score":24.96,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.8-flash-next","score":24.77,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-5","score":23.62,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-5.6-sol","score":22.42,"metric":"percent"},{"benchmark":"faix-overall","model":"seed2.1-turbo","score":21.29,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3.1-405b","score":20.76,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-397b-a17b","score":20.16,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-opus-4","score":20,"metric":"percent"},{"benchmark":"faix-overall","model":"ovis2.6-80b-a3b","score":19.83,"metric":"percent"},{"benchmark":"faix-overall","model":"o1","score":19.74,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-o3","score":18.92,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.6-plus","score":18.64,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v4-pro","score":18.51,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-opus-4.6","score":17.38,"metric":"percent"},{"benchmark":"faix-overall","model":"grok-4","score":17.36,"metric":"percent"},{"benchmark":"faix-overall","model":"llada2.0-flash","score":16.89,"metric":"percent"},{"benchmark":"faix-overall","model":"llada2.1-flash","score":16.86,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-2.5-pro","score":16.66,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-235b-a22b","score":16.05,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-opus-4.5","score":16.04,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-opus-4.8","score":15.91,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.7-plus","score":15.9,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-omni-plus","score":15.56,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-32b-thinking","score":14.86,"metric":"percent"},{"benchmark":"faix-overall","model":"ovis2.6-30b-a3b","score":14.58,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-2.0-flash","score":14.46,"metric":"percent"},{"benchmark":"faix-overall","model":"o1-mini","score":14.09,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-4o-mini","score":13.91,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-5.2","score":13.84,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-3-flash","score":13.48,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-3.7-sonnet-20250219","score":13.11,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.7-max","score":12.83,"metric":"percent"},{"benchmark":"faix-overall","model":"seed-1.5-vl","score":12.7,"metric":"percent"},{"benchmark":"faix-overall","model":"ernie-5.0","score":12.57,"metric":"percent"},{"benchmark":"faix-overall","model":"kimi-k2.5","score":12.51,"metric":"percent"},{"benchmark":"faix-overall","model":"o4-mini","score":12.24,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-sonnet-4","score":12.22,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-vl-72b","score":12.12,"metric":"percent"},{"benchmark":"faix-overall","model":"dots-vlm1","score":12,"metric":"percent"},{"benchmark":"faix-overall","model":"ernie-4.5","score":11.84,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-3.5-sonnet-20240620","score":11.83,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3.1-70b","score":11.79,"metric":"percent"},{"benchmark":"faix-overall","model":"seed2.0-pro","score":11.78,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v4-flash","score":11.61,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-r1","score":11.54,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.6-27b","score":11.53,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-sonnet-4.5","score":11.48,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.8-27b","score":11.3,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-5.4","score":11.07,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-2.0-pro","score":10.92,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-coder-480b-a35b-instruct","score":10.81,"metric":"percent"},{"benchmark":"faix-overall","model":"seed2.0-lite","score":10.63,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-30b-a3b","score":10.6,"metric":"percent"},{"benchmark":"faix-overall","model":"seed1.8","score":10.58,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.5v","score":10.55,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-4.5","score":10.48,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-235b-a22b","score":10.41,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-4.1","score":10.4,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3-super-120b-a12b-base","score":10.35,"metric":"percent"},{"benchmark":"faix-overall","model":"mistral-medium-3","score":10.29,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-opus-4.1-20250805","score":10.21,"metric":"percent"},{"benchmark":"faix-overall","model":"kimi-k2-base","score":10.19,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v4-pro-base","score":10.1,"metric":"percent"},{"benchmark":"faix-overall","model":"qwq-32b","score":10,"metric":"percent"},{"benchmark":"faix-overall","model":"ling-flash-2.0","score":9.95,"metric":"percent"},{"benchmark":"faix-overall","model":"mimo-vl","score":9.91,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-sonnet-4.6","score":9.78,"metric":"percent"},{"benchmark":"faix-overall","model":"ling-2.6-1t-base","score":9.71,"metric":"percent"},{"benchmark":"faix-overall","model":"minicpm-v-4.7-35b-a3b","score":9.64,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-32b-instruct","score":9.62,"metric":"percent"},{"benchmark":"faix-overall","model":"kimi-k2","score":9.6,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-next-80b-a3b-instruct","score":9.31,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-oss-120b","score":9.22,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.6v","score":9.02,"metric":"percent"},{"benchmark":"faix-overall","model":"kimi-k2-thinking","score":8.94,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-122b-a10b","score":8.94,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-5.3-flash","score":8.93,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-5.2","score":8.8,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-3.1-think-32b","score":8.77,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3-70b","score":8.62,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-5.1","score":8.11,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-3-think-32b-dpo","score":8,"metric":"percent"},{"benchmark":"faix-overall","model":"chatgpt-4o","score":7.91,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v3.1","score":7.87,"metric":"percent"},{"benchmark":"faix-overall","model":"seed2.0-mini","score":7.83,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-27b","score":7.82,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-3-think-32b","score":7.71,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.6-35b-a3b","score":7.67,"metric":"percent"},{"benchmark":"faix-overall","model":"step-3","score":7.57,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-max","score":7.49,"metric":"percent"},{"benchmark":"faix-overall","model":"mistral-small-3.2-24b-instruct","score":7.4,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v3.2","score":7.39,"metric":"percent"},{"benchmark":"faix-overall","model":"kanana-2-30b-a3b-base","score":7.27,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v4-flash-base","score":7.2,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-opus-4.7","score":7.14,"metric":"percent"},{"benchmark":"faix-overall","model":"molmopoint-8b","score":6.96,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3.5-super-vl-120b-a12b-base","score":6.91,"metric":"percent"},{"benchmark":"faix-overall","model":"o3-mini","score":6.87,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3.3-70b","score":6.83,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-3.3-8b-base","score":6.8,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-5.4-mini","score":6.62,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-4.1-30b","score":6.56,"metric":"percent"},{"benchmark":"faix-overall","model":"mistral-large-3-base","score":6.43,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-1.5-pro","score":6.35,"metric":"percent"},{"benchmark":"faix-overall","model":"molmo2-4b","score":6.34,"metric":"percent"},{"benchmark":"faix-overall","model":"ling-1t-base","score":6.29,"metric":"percent"},{"benchmark":"faix-overall","model":"kimi-k2.6","score":6.26,"metric":"percent"},{"benchmark":"faix-overall","model":"marin-8b-base","score":6.25,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v3.1-terminus","score":6.24,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-2.5-flash","score":6.21,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v3.2-exp-base","score":6.14,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-2-9b","score":6.06,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-32b","score":5.92,"metric":"percent"},{"benchmark":"faix-overall","model":"ministral-3-14b-base","score":5.91,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-8b","score":5.91,"metric":"percent"},{"benchmark":"faix-overall","model":"lfm2-vl-3b","score":5.83,"metric":"percent"},{"benchmark":"faix-overall","model":"eagle2.5-8b","score":5.8,"metric":"percent"},{"benchmark":"faix-overall","model":"mimo-v2-flash-base","score":5.73,"metric":"percent"},{"benchmark":"faix-overall","model":"step-3.5-flash-base","score":5.6,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-4.5-haiku","score":5.56,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-3","score":5.46,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-4b","score":5.33,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-32b-instruct","score":5.25,"metric":"percent"},{"benchmark":"faix-overall","model":"claude-3-haiku","score":5,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-5.1","score":5,"metric":"percent"},{"benchmark":"faix-overall","model":"molmo2-o-7b","score":5,"metric":"percent"},{"benchmark":"faix-overall","model":"phi-3.5-vision-instruct","score":5,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-1.5-flash","score":4.94,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3-super-120b-a12b","score":4.89,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v3.2-exp","score":4.78,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-8b-thinking","score":4.67,"metric":"percent"},{"benchmark":"faix-overall","model":"ministral-3-8b-base","score":4.57,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.5","score":4.46,"metric":"percent"},{"benchmark":"faix-overall","model":"minimax-m2.7","score":4.44,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-4-12b-it","score":4.43,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-chat-v3","score":4.41,"metric":"percent"},{"benchmark":"faix-overall","model":"keye-vl-1.5-8b","score":4.35,"metric":"percent"},{"benchmark":"faix-overall","model":"molmo2-8b","score":4.35,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3.5-super-vl-120b-a12b","score":4.16,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.5-air","score":4.11,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-v3.2-base","score":4,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon-h1-34b-instruct","score":4,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3.1-8b","score":4,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-30b-a3b-thinking","score":4,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-35b-a3b","score":4,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-oss-20b","score":3.93,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-7b","score":3.89,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-8b-instruct","score":3.87,"metric":"percent"},{"benchmark":"faix-overall","model":"step3-vl-10b","score":3.85,"metric":"percent"},{"benchmark":"faix-overall","model":"minimax-m2","score":3.71,"metric":"percent"},{"benchmark":"faix-overall","model":"lfm2.5-vl-3b","score":3.68,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.7","score":3.67,"metric":"percent"},{"benchmark":"faix-overall","model":"grok-3","score":3.6,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-3-7b","score":3.58,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.6","score":3.57,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-4-31b-it","score":3.56,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-9b","score":3.56,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.6v-flash","score":3.52,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-4.0-h-small","score":3.48,"metric":"percent"},{"benchmark":"faix-overall","model":"joyai-llm-flash","score":3.43,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3-ultra","score":3.3,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-4b","score":3.24,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-30b-a3b-instruct","score":3.2,"metric":"percent"},{"benchmark":"faix-overall","model":"gemini-2.5-flash-lite","score":3.08,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-2-1124-7b","score":3.06,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-4-e4b","score":3.04,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-4b-instruct","score":3.02,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-3-think-32b-sft","score":3,"metric":"percent"},{"benchmark":"faix-overall","model":"openpangu-vl-7b","score":2.93,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen-2.5-72b","score":2.91,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-4.1-8b","score":2.88,"metric":"percent"},{"benchmark":"faix-overall","model":"youtu-vl-4b-instruct","score":2.86,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","score":2.8,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-2-0325-32b-instruct","score":2.75,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.1v","score":2.74,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-3-12b","score":2.67,"metric":"percent"},{"benchmark":"faix-overall","model":"k2-high-70b","score":2.67,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-vl-7b","score":2.67,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-14b","score":2.67,"metric":"percent"},{"benchmark":"faix-overall","model":"ling-mini-2.0","score":2.53,"metric":"percent"},{"benchmark":"faix-overall","model":"moonlight-base","score":2.48,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-omni-30b-a3b","score":2.46,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-4.1-3b","score":2.4,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3-8b","score":2.33,"metric":"percent"},{"benchmark":"faix-overall","model":"ling-flash-base-2.0","score":2.29,"metric":"percent"},{"benchmark":"faix-overall","model":"smollm3-3b","score":2.24,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-4-maverick","score":2.16,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-4.0-micro","score":2.15,"metric":"percent"},{"benchmark":"faix-overall","model":"llada2.1-mini","score":2.12,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-5","score":2.11,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.5-air-base","score":2.08,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-4-26b-a4b","score":2.07,"metric":"percent"},{"benchmark":"faix-overall","model":"kimi-linear-base","score":2,"metric":"percent"},{"benchmark":"faix-overall","model":"plm-8b","score":2,"metric":"percent"},{"benchmark":"faix-overall","model":"internvl-8b","score":1.95,"metric":"percent"},{"benchmark":"faix-overall","model":"ling-2.6-flash-base","score":1.9,"metric":"percent"},{"benchmark":"faix-overall","model":"llada2.0-mini","score":1.85,"metric":"percent"},{"benchmark":"faix-overall","model":"openreasoning-nemotron-7b","score":1.74,"metric":"percent"},{"benchmark":"faix-overall","model":"minicpm-o-4.5","score":1.71,"metric":"percent"},{"benchmark":"faix-overall","model":"exaone-4.5-33b","score":1.67,"metric":"percent"},{"benchmark":"faix-overall","model":"gpt-5-nano","score":1.58,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-4.0-h-micro","score":1.57,"metric":"percent"},{"benchmark":"faix-overall","model":"internvl3.5-4b","score":1.57,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-3.1-instruct-32b","score":1.54,"metric":"percent"},{"benchmark":"faix-overall","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","score":1.52,"metric":"percent"},{"benchmark":"faix-overall","model":"mimo-embodied-7b","score":1.4,"metric":"percent"},{"benchmark":"faix-overall","model":"nvidia-nemotron-nano-9b-v2","score":1.33,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-omni-flash","score":1.33,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3-nano-30b-a3b","score":1.22,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3-nano-4b","score":1.09,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-2b-instruct","score":1.05,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-r1-distill-qwen-32b","score":1,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3-nano-30b-a3b-base","score":1,"metric":"percent"},{"benchmark":"faix-overall","model":"internvl3.5-2b","score":0.91,"metric":"percent"},{"benchmark":"faix-overall","model":"apertus-8b","score":0.9,"metric":"percent"},{"benchmark":"faix-overall","model":"kimi-vl-a3b-a2b-thinking-2506","score":0.9,"metric":"percent"},{"benchmark":"faix-overall","model":"apriel-1.6-15b-thinker","score":0.89,"metric":"percent"},{"benchmark":"faix-overall","model":"inkling-small","score":0.89,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen-1.7b-thinking","score":0.88,"metric":"percent"},{"benchmark":"faix-overall","model":"internvl3.5-8b","score":0.87,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-4b-thinking","score":0.78,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-4.0-h-tiny","score":0.7,"metric":"percent"},{"benchmark":"faix-overall","model":"comet-60b-a12b","score":0.6,"metric":"percent"},{"benchmark":"faix-overall","model":"grok-4-fast","score":0.59,"metric":"percent"},{"benchmark":"faix-overall","model":"ministral-3-3b-base","score":0.59,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-3-think-7b","score":0.59,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-3-27b-vl","score":0.57,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-3-4b","score":0.54,"metric":"percent"},{"benchmark":"faix-overall","model":"hy3-preview-base","score":0.53,"metric":"percent"},{"benchmark":"faix-overall","model":"apriel-1.5-15b-thinker","score":0.5,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-vl-3b","score":0.46,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-4-e2b","score":0.42,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-4-scout-17b","score":0.39,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-3-1b","score":0.35,"metric":"percent"},{"benchmark":"faix-overall","model":"apertus-v1.5-70b","score":0.33,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-2b","score":0.32,"metric":"percent"},{"benchmark":"faix-overall","model":"t5gemma-2-4b-4b","score":0.26,"metric":"percent"},{"benchmark":"faix-overall","model":"comet-60b-a12b-nvfp4","score":0.2,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon-h1-7b","score":0.17,"metric":"percent"},{"benchmark":"faix-overall","model":"cosmos-reason2-8b","score":0.16,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-7b-instruct","score":0.15,"metric":"percent"},{"benchmark":"faix-overall","model":"apertus-70b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"apertus-v1.5-8b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"comet-60b-a12b-fp8","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-r1-distill-llama-8b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-r1-distill-qwen-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"deepseek-r1-distill-qwen-7b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"eurollm-22b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon-3-1b-base","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon-h1-0.5b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon-h1-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon-h1-3b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon3-10b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon3-3b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"falcon3-7b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-2-27b-it","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-2-2b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-3-270m-it","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"gemma-3n-e2b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.1v-9b-thinking","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"glm-4.7-flash","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"granite-4.2-3b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"lfm2-8b-a1b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"lfm2.5-vl-1.6b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3.2-1.24b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3.2-1b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"llama-3.2-3b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"longcat-next","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"mimo-v2.5-base","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"minicpm-v-4.5-8b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"minicpm-v-4.6","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"mobilellm-p1","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"motif-2-12.7b-base","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"nemotron-3.5-lightning-30b-a3b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-2-0425-1b-base","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"olmo-3-instruct-7b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"olmoe-1b-7b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"phi-4-multimodal-instruct","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"phi-4-reasoning-vision-15b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"plm-3b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen-2.5-3b-instruct","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-0.6b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-0.5b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-1.5b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-coder-7b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen2.5-omni-7b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-0.8b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3-vl-2b-thinking","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"qwen3.5-0.8b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"seed-coder-8b-base","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"smollm2-1.7b-base","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"smollm2-360m-base","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"smolvlm2-2.2b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"solar-open-100b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"t5gemma-2-1b-1b","score":0,"metric":"percent"},{"benchmark":"faix-overall","model":"t5gemma-2-270m-270m","score":0,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b","score":75.6,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-llm-7b-base","score":75.4,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-70b","score":84,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-llm-67b-base","score":84,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-7b","score":78,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-llm-7b-base","score":79.2,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-70b","score":82,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-llm-67b-base","score":83.6,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-7b","score":69.6,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-llm-7b-base","score":70.5,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-llm-67b-base","score":79.8,"metric":"percent"},{"benchmark":"race-middle","model":"llama-2-7b","score":60.7,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-llm-7b-base","score":63.2,"metric":"percent"},{"benchmark":"race-middle","model":"llama-2-70b","score":70.1,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-llm-67b-base","score":69.9,"metric":"percent"},{"benchmark":"race-high","model":"llama-2-7b","score":45.8,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-llm-7b-base","score":46.5,"metric":"percent"},{"benchmark":"race-high","model":"llama-2-70b","score":54.3,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-llm-67b-base","score":50.7,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-llm-7b-base","score":59.7,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-70b","score":79.5,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-llm-67b-base","score":78.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b","score":25.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-llm-7b-base","score":22.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-70b","score":36.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-llm-67b-base","score":36.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b","score":45.8,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-llm-7b-base","score":48.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b","score":69,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-llm-67b-base","score":71.3,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-7b","score":69.1,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-7b-base","score":67.9,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-70b","score":76.5,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-67b-base","score":76.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-7b","score":49,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-7b-base","score":48.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-70b","score":59.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-67b-base","score":59,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-7b","score":57.4,"metric":"percent"},{"benchmark":"openbookqa","model":"deepseek-llm-7b-base","score":55.8,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-70b","score":60.4,"metric":"percent"},{"benchmark":"openbookqa","model":"deepseek-llm-67b-base","score":60.2,"metric":"percent"},{"benchmark":"drop","model":"llama-2-7b","score":39.8,"metric":"percent"},{"benchmark":"drop","model":"deepseek-llm-7b-base","score":41,"metric":"percent"},{"benchmark":"drop","model":"llama-2-70b","score":69.2,"metric":"percent"},{"benchmark":"drop","model":"deepseek-llm-67b-base","score":67.9,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b","score":2.5,"metric":"percent"},{"benchmark":"math","model":"deepseek-llm-7b-base","score":6,"metric":"percent"},{"benchmark":"math","model":"llama-2-70b","score":13.5,"metric":"percent"},{"benchmark":"math","model":"deepseek-llm-67b-base","score":18.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b","score":15.5,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-llm-7b-base","score":17.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b","score":58.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-llm-67b-base","score":63.4,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b","score":14.6,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-llm-7b-base","score":26.2,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":28.7,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-llm-67b-base","score":42.7,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b","score":21.8,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-llm-7b-base","score":39,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-70b","score":45.6,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-llm-67b-base","score":57.4,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-7b","score":38.5,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-llm-7b-base","score":39.5,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-70b","score":62.9,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-llm-67b-base","score":68.7,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-7b","score":22.8,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-llm-7b-base","score":26.4,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-70b","score":37.2,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-llm-67b-base","score":41.3,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-2-7b","score":64,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-llm-7b-base","score":73.1,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-2-70b","score":76.5,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-llm-67b-base","score":81,"metric":"percent"},{"benchmark":"chid","model":"llama-2-7b","score":37.9,"metric":"percent"},{"benchmark":"chid","model":"deepseek-llm-7b-base","score":89.3,"metric":"percent"},{"benchmark":"chid","model":"llama-2-70b","score":55.5,"metric":"percent"},{"benchmark":"chid","model":"deepseek-llm-67b-base","score":92.1,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b","score":33.9,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-llm-7b-base","score":45,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b","score":51.4,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-llm-67b-base","score":66.1,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b","score":32.6,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-llm-7b-base","score":47.2,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-70b","score":53.1,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-llm-67b-base","score":70.8,"metric":"percent"},{"benchmark":"cmath","model":"llama-2-7b","score":25.1,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-llm-7b-base","score":34.5,"metric":"percent"},{"benchmark":"cmath","model":"llama-2-70b","score":53.9,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-llm-67b-base","score":63,"metric":"percent"},{"benchmark":"c3","model":"llama-2-7b","score":47.4,"metric":"percent"},{"benchmark":"c3","model":"deepseek-llm-7b-base","score":65.4,"metric":"percent"},{"benchmark":"c3","model":"llama-2-70b","score":61.7,"metric":"percent"},{"benchmark":"c3","model":"deepseek-llm-67b-base","score":75.3,"metric":"percent"},{"benchmark":"ccpm","model":"llama-2-7b","score":60.7,"metric":"percent"},{"benchmark":"ccpm","model":"deepseek-llm-7b-base","score":76.9,"metric":"percent"},{"benchmark":"ccpm","model":"llama-2-70b","score":66.2,"metric":"percent"},{"benchmark":"ccpm","model":"deepseek-llm-67b-base","score":88.5,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-llm-7b-chat","score":68.5,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-llm-67b-chat","score":75.7,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-llm-7b-chat","score":77.6,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-llm-67b-chat","score":82.6,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-llm-7b-chat","score":66.9,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-llm-67b-chat","score":76,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-llm-7b-chat","score":65.2,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-llm-67b-chat","score":70.9,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-llm-7b-chat","score":50.8,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-llm-67b-chat","score":56,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-llm-7b-chat","score":57.9,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-llm-67b-chat","score":81.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-llm-7b-chat","score":32.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-llm-67b-chat","score":47,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-llm-7b-chat","score":49.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-llm-67b-chat","score":71.1,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-7b-chat","score":71,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-67b-chat","score":81.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-7b-chat","score":49.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-67b-chat","score":64.1,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-llm-7b-chat","score":63,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-llm-67b-chat","score":84.1,"metric":"percent"},{"benchmark":"math","model":"deepseek-llm-7b-chat","score":15.8,"metric":"percent"},{"benchmark":"math","model":"deepseek-llm-67b-chat","score":32.6,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-llm-7b-chat","score":48.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-llm-67b-chat","score":73.8,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-llm-7b-chat","score":35.2,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-llm-67b-chat","score":61.4,"metric":"percent"},{"benchmark":"drop","model":"deepseek-llm-7b-chat","score":49.1,"metric":"percent"},{"benchmark":"drop","model":"deepseek-llm-67b-chat","score":71.9,"metric":"percent"},{"benchmark":"openbookqa","model":"deepseek-llm-7b-chat","score":54.8,"metric":"percent"},{"benchmark":"openbookqa","model":"deepseek-llm-67b-chat","score":63.2,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-llm-7b-chat","score":42.3,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-llm-67b-chat","score":71.7,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-llm-7b-chat","score":19.3,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-llm-67b-chat","score":46.4,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-llm-7b-chat","score":71.9,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-llm-67b-chat","score":60,"metric":"percent"},{"benchmark":"chid","model":"deepseek-llm-7b-chat","score":64.9,"metric":"percent"},{"benchmark":"chid","model":"deepseek-llm-67b-chat","score":72.6,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-llm-7b-chat","score":47,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-llm-67b-chat","score":65.2,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-llm-7b-chat","score":49.7,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-llm-67b-chat","score":67.8,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-llm-7b-chat","score":68.4,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-llm-67b-chat","score":80.3,"metric":"percent"},{"benchmark":"c3","model":"deepseek-llm-7b-chat","score":66.4,"metric":"percent"},{"benchmark":"c3","model":"deepseek-llm-67b-chat","score":77,"metric":"percent"},{"benchmark":"ccpm","model":"deepseek-llm-7b-chat","score":76.5,"metric":"percent"},{"benchmark":"ccpm","model":"deepseek-llm-67b-chat","score":84.9,"metric":"percent"},{"benchmark":"alignbench","model":"gpt-4-1106-preview","score":8.01,"metric":"score"},{"benchmark":"alignbench","model":"gpt-4-0613","score":7.53,"metric":"score"},{"benchmark":"alignbench","model":"deepseek-llm-67b-chat","score":6.43,"metric":"score"},{"benchmark":"alignbench","model":"chatglm-turbo","score":6.24,"metric":"score"},{"benchmark":"alignbench","model":"ernie-bot-3.5","score":6.14,"metric":"score"},{"benchmark":"alignbench","model":"gpt-3.5-turbo-0613","score":6.08,"metric":"score"},{"benchmark":"alignbench","model":"chatglm-pro","score":5.83,"metric":"score"},{"benchmark":"alignbench","model":"sparkdesk-v2","score":5.74,"metric":"score"},{"benchmark":"alignbench","model":"qwen-14b-chat","score":5.72,"metric":"score"},{"benchmark":"alignbench","model":"baichuan2-13b-chat","score":5.25,"metric":"score"},{"benchmark":"alignbench","model":"chatglm3-6b","score":4.97,"metric":"score"},{"benchmark":"alignbench","model":"baichuan2-7b-chat","score":4.97,"metric":"score"},{"benchmark":"alignbench","model":"internlm-chat-20b","score":4.96,"metric":"score"},{"benchmark":"alignbench","model":"qwen-7b-chat","score":4.91,"metric":"score"},{"benchmark":"alignbench","model":"chatglm2-6b","score":4.48,"metric":"score"},{"benchmark":"alignbench","model":"internlm-chat-7b","score":3.65,"metric":"score"},{"benchmark":"alignbench","model":"chinese-llama-2-7b-chat","score":3.57,"metric":"score"},{"benchmark":"alignbench","model":"llama-2-13b-chinese-chat","score":3.35,"metric":"score"},{"benchmark":"mt-bench","model":"gpt-4-1106-preview","score":9.26,"metric":"percent"},{"benchmark":"mt-bench","model":"gpt-3.5-turbo-0613","score":8.39,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-2-7b-chat","score":6.27,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-2-13b-chat","score":6.65,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-2-70b-chat","score":6.86,"metric":"percent"},{"benchmark":"mt-bench","model":"zephyr-7b-beta","score":7.35,"metric":"percent"},{"benchmark":"mt-bench","model":"xwin-lm-70b-v0.1","score":7.53,"metric":"percent"},{"benchmark":"mt-bench","model":"xwin-lm-13b-v0.2","score":7.01,"metric":"percent"},{"benchmark":"mt-bench","model":"tulu-2-dpo-70b","score":7.89,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-llm-67b-chat","score":8.35,"metric":"percent"},{"benchmark":"leetcode-contest","model":"gpt-4","score":48.4,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"gpt-4","score":68,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4","score":79.3,"metric":"percent"},{"benchmark":"leetcode-contest","model":"chatglm3-6b","score":2.4,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"chatglm3-6b","score":32,"metric":"percent"},{"benchmark":"ifeval","model":"chatglm3-6b","score":29.7,"metric":"percent"},{"benchmark":"leetcode-contest","model":"deepseek-llm-7b-chat","score":4.7,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"deepseek-llm-7b-chat","score":28.5,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-llm-7b-chat","score":41.2,"metric":"percent"},{"benchmark":"leetcode-contest","model":"baichuan2-13b-chat","score":1.6,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"baichuan2-13b-chat","score":19.5,"metric":"percent"},{"benchmark":"ifeval","model":"baichuan2-13b-chat","score":44.5,"metric":"percent"},{"benchmark":"leetcode-contest","model":"yi-34b-chat","score":7.9,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"yi-34b-chat","score":39,"metric":"percent"},{"benchmark":"ifeval","model":"yi-34b-chat","score":48.4,"metric":"percent"},{"benchmark":"leetcode-contest","model":"qwen-72b-chat","score":12.7,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"qwen-72b-chat","score":52,"metric":"percent"},{"benchmark":"ifeval","model":"qwen-72b-chat","score":50.8,"metric":"percent"},{"benchmark":"leetcode-contest","model":"deepseek-llm-67b-chat","score":17.5,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"deepseek-llm-67b-chat","score":58,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-llm-67b-chat","score":55.5,"metric":"percent"},{"benchmark":"do-not-answer","model":"llama-2-7b-chat","score":99.4,"metric":"percent"},{"benchmark":"do-not-answer","model":"claude","score":98.3,"metric":"percent"},{"benchmark":"do-not-answer","model":"deepseek-llm-67b-chat","score":97.8,"metric":"percent"},{"benchmark":"do-not-answer","model":"gpt-3.5-turbo","score":97.7,"metric":"percent"},{"benchmark":"do-not-answer","model":"gpt-4","score":96.5,"metric":"percent"},{"benchmark":"do-not-answer","model":"vicuna-7b","score":94.9,"metric":"percent"},{"benchmark":"do-not-answer","model":"chatglm2-6b","score":92.9,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-llm-7b-chat","score":7.15,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-moe-16b-base","score":77.1,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-moe-16b-base","score":80.2,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-moe-16b-base","score":68.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-moe-16b-base","score":49.8,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-moe-16b-base","score":61.9,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-moe-16b-base","score":46.4,"metric":"percent"},{"benchmark":"drop","model":"deepseek-llm-7b-base","score":34.9,"metric":"percent"},{"benchmark":"drop","model":"deepseek-moe-16b-base","score":32.9,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-moe-16b-base","score":18.8,"metric":"percent"},{"benchmark":"math","model":"deepseek-llm-7b-base","score":3.3,"metric":"percent"},{"benchmark":"math","model":"deepseek-moe-16b-base","score":4.3,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-moe-16b-base","score":26.8,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-moe-16b-base","score":39.2,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-moe-16b-base","score":64.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-moe-16b-base","score":25.5,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-moe-16b-base","score":45,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-moe-16b-base","score":70.2,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-moe-16b-base","score":72.1,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-moe-16b-base","score":40.6,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-moe-16b-base","score":42.5,"metric":"percent"},{"benchmark":"chid","model":"deepseek-moe-16b-base","score":89.4,"metric":"percent"},{"benchmark":"drop","model":"llama-2-7b","score":34,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b","score":2.6,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-llm-7b-chat","score":71,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-moe-16b-chat","score":72.2,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-llm-7b-chat","score":78.4,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-moe-16b-chat","score":79.7,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-7b-chat","score":70.2,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-moe-16b-chat","score":69.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-7b-chat","score":50.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-moe-16b-chat","score":50,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-llm-7b-chat","score":43.1,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-moe-16b-chat","score":42.2,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-llm-7b-chat","score":66.1,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-moe-16b-chat","score":64.8,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-moe-16b-chat","score":50.6,"metric":"percent"},{"benchmark":"drop","model":"deepseek-llm-7b-chat","score":41.7,"metric":"percent"},{"benchmark":"drop","model":"deepseek-moe-16b-chat","score":33.8,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-llm-7b-chat","score":62.6,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-moe-16b-chat","score":62.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-llm-7b-chat","score":14.7,"metric":"percent"},{"benchmark":"math","model":"deepseek-moe-16b-chat","score":15.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-llm-7b-chat","score":45.1,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-moe-16b-chat","score":45.7,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-llm-7b-chat","score":39,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-moe-16b-chat","score":46.2,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-llm-7b-chat","score":59.5,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-moe-16b-chat","score":63.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-llm-7b-chat","score":32.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-moe-16b-chat","score":35.1,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-llm-7b-chat","score":49.7,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-moe-16b-chat","score":47.2,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-llm-7b-chat","score":68.4,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-moe-16b-chat","score":69,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-llm-7b-chat","score":66.2,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-moe-16b-chat","score":68.2,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-llm-7b-chat","score":44.7,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-moe-16b-chat","score":40,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-llm-7b-chat","score":51.2,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-moe-16b-chat","score":49.3,"metric":"percent"},{"benchmark":"humaneval","model":"code-cushman-001","score":33.5,"metric":"percent"},{"benchmark":"humaneval","model":"codegeex2-6b","score":36,"metric":"percent"},{"benchmark":"humaneval-x","model":"codegeex2-6b","score":24.5,"metric":"percent"},{"benchmark":"mbpp","model":"codegeex2-6b","score":36.2,"metric":"percent"},{"benchmark":"humaneval","model":"starcoderbase-16b","score":31.7,"metric":"percent"},{"benchmark":"humaneval-x","model":"starcoderbase-16b","score":28,"metric":"percent"},{"benchmark":"mbpp","model":"starcoderbase-16b","score":42.8,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-7b","score":31.7,"metric":"percent"},{"benchmark":"humaneval-x","model":"codellama-7b","score":29.2,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b","score":38.6,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-13b","score":36,"metric":"percent"},{"benchmark":"humaneval-x","model":"codellama-13b","score":35.4,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-13b","score":48.4,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-34b","score":48.2,"metric":"percent"},{"benchmark":"humaneval-x","model":"codellama-34b","score":41,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-34b","score":55.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-1.3b-base","score":34.8,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-coder-1.3b-base","score":28.3,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-1.3b-base","score":46.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-6.7b-base","score":49.4,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-coder-6.7b-base","score":44.7,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-6.7b-base","score":60.6,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-33b-base","score":56.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-coder-33b-base","score":50.3,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-33b-base","score":66,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5-turbo","score":76.2,"metric":"percent"},{"benchmark":"humaneval-x","model":"gpt-3.5-turbo","score":64.9,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-3.5-turbo","score":70.8,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4","score":84.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"gpt-4","score":76.5,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4","score":80,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-1.3b-instruct","score":65.2,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-coder-1.3b-instruct","score":48.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-1.3b-instruct","score":49.4,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-6.7b-instruct","score":78.6,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-coder-6.7b-instruct","score":66.1,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-6.7b-instruct","score":65.4,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-33b-instruct","score":79.3,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-coder-33b-instruct","score":69.2,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-33b-instruct","score":70,"metric":"percent"},{"benchmark":"ds-1000","model":"codegeex2-6b","score":22.9,"metric":"percent"},{"benchmark":"ds-1000","model":"starcoderbase-16b","score":24.6,"metric":"percent"},{"benchmark":"ds-1000","model":"codellama-7b","score":22.1,"metric":"percent"},{"benchmark":"ds-1000","model":"codellama-13b","score":26.8,"metric":"percent"},{"benchmark":"ds-1000","model":"codellama-34b","score":34.3,"metric":"percent"},{"benchmark":"ds-1000","model":"deepseek-coder-1.3b-base","score":16.2,"metric":"percent"},{"benchmark":"ds-1000","model":"deepseek-coder-6.7b-base","score":30.5,"metric":"percent"},{"benchmark":"ds-1000","model":"deepseek-coder-33b-base","score":40.2,"metric":"percent"},{"benchmark":"leetcode-contest","model":"wizardcoder-15b-v1.0","score":5,"metric":"percent"},{"benchmark":"leetcode-contest","model":"codellama-34b-instruct","score":9.4,"metric":"percent"},{"benchmark":"leetcode-contest","model":"phind-codellama-34b-v2","score":13.3,"metric":"percent"},{"benchmark":"leetcode-contest","model":"gpt-3.5-turbo","score":23.3,"metric":"percent"},{"benchmark":"leetcode-contest","model":"gpt-4-turbo","score":40.6,"metric":"percent"},{"benchmark":"leetcode-contest","model":"deepseek-coder-1.3b-instruct","score":7.2,"metric":"percent"},{"benchmark":"leetcode-contest","model":"deepseek-coder-6.7b-instruct","score":19.4,"metric":"percent"},{"benchmark":"leetcode-contest","model":"deepseek-coder-33b-instruct","score":27.8,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-6.7b-base","score":44.7,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-6.7b-base","score":43.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-6.7b-base","score":19.2,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-6.7b-base","score":36.6,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-coder-6.7b-base","score":44.3,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-6.7b-base","score":53.8,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-6.7b-base","score":57.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-6.7b-base","score":32.5,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-7b-base-v1.5","score":43.2,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-7b-base-v1.5","score":60.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-7b-base-v1.5","score":62.4,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-7b-base-v1.5","score":24.7,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-7b-base-v1.5","score":49.1,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-coder-7b-base-v1.5","score":55.2,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-7b-base-v1.5","score":69.9,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-7b-base-v1.5","score":63.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-7b-base-v1.5","score":47.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-6.7b-instruct","score":66.1,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-6.7b-instruct","score":62.8,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-6.7b-instruct","score":28.6,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-6.7b-instruct","score":37.2,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-coder-6.7b-instruct","score":46.9,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-6.7b-instruct","score":55,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-6.7b-instruct","score":57.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-6.7b-instruct","score":37.4,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-7b-instruct-v1.5","score":64.1,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-7b-instruct-v1.5","score":64.6,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-7b-instruct-v1.5","score":72.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-7b-instruct-v1.5","score":34.1,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-7b-instruct-v1.5","score":49.5,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-coder-7b-instruct-v1.5","score":53.3,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-7b-instruct-v1.5","score":72.2,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-7b-instruct-v1.5","score":63.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-7b-instruct-v1.5","score":48.1,"metric":"percent"},{"benchmark":"gsm8k","model":"minerva-8b","score":16.2,"metric":"percent"},{"benchmark":"math","model":"minerva-8b","score":14.1,"metric":"percent"},{"benchmark":"ocw-courses","model":"minerva-8b","score":7.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"minerva-8b","score":35.6,"metric":"percent"},{"benchmark":"gsm8k","model":"minerva-62b","score":52.4,"metric":"percent"},{"benchmark":"math","model":"minerva-62b","score":27.6,"metric":"percent"},{"benchmark":"ocw-courses","model":"minerva-62b","score":12,"metric":"percent"},{"benchmark":"mmlu-stem","model":"minerva-62b","score":53.9,"metric":"percent"},{"benchmark":"gsm8k","model":"minerva-540b","score":58.8,"metric":"percent"},{"benchmark":"math","model":"minerva-540b","score":33.6,"metric":"percent"},{"benchmark":"ocw-courses","model":"minerva-540b","score":17.6,"metric":"percent"},{"benchmark":"mmlu-stem","model":"minerva-540b","score":63.9,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.1","score":40.3,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-v0.1","score":14.3,"metric":"percent"},{"benchmark":"ocw-courses","model":"mistral-7b-v0.1","score":9.2,"metric":"percent"},{"benchmark":"sat-math","model":"mistral-7b-v0.1","score":71.9,"metric":"percent"},{"benchmark":"mmlu-stem","model":"mistral-7b-v0.1","score":51.1,"metric":"percent"},{"benchmark":"cmath","model":"mistral-7b-v0.1","score":44.9,"metric":"percent"},{"benchmark":"gaokao-mathcloze","model":"mistral-7b-v0.1","score":5.1,"metric":"percent"},{"benchmark":"gaokao-mathqa","model":"mistral-7b-v0.1","score":23.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llemma-7b","score":37.4,"metric":"percent"},{"benchmark":"math","model":"llemma-7b","score":18.1,"metric":"percent"},{"benchmark":"ocw-courses","model":"llemma-7b","score":6.3,"metric":"percent"},{"benchmark":"sat-math","model":"llemma-7b","score":59.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llemma-7b","score":43.1,"metric":"percent"},{"benchmark":"cmath","model":"llemma-7b","score":43.4,"metric":"percent"},{"benchmark":"gaokao-mathcloze","model":"llemma-7b","score":11.9,"metric":"percent"},{"benchmark":"gaokao-mathqa","model":"llemma-7b","score":23.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llemma-34b","score":54,"metric":"percent"},{"benchmark":"math","model":"llemma-34b","score":25.3,"metric":"percent"},{"benchmark":"ocw-courses","model":"llemma-34b","score":10.3,"metric":"percent"},{"benchmark":"sat-math","model":"llemma-34b","score":71.9,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llemma-34b","score":52.9,"metric":"percent"},{"benchmark":"cmath","model":"llemma-34b","score":56.1,"metric":"percent"},{"benchmark":"gaokao-mathcloze","model":"llemma-34b","score":11.9,"metric":"percent"},{"benchmark":"gaokao-mathqa","model":"llemma-34b","score":26.2,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-math-7b","score":64.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-math-7b","score":36.2,"metric":"percent"},{"benchmark":"ocw-courses","model":"deepseek-math-7b","score":15.4,"metric":"percent"},{"benchmark":"sat-math","model":"deepseek-math-7b","score":84.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-math-7b","score":56.5,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-math-7b","score":71.7,"metric":"percent"},{"benchmark":"gaokao-mathcloze","model":"deepseek-math-7b","score":20.3,"metric":"percent"},{"benchmark":"gaokao-mathqa","model":"deepseek-math-7b","score":35.3,"metric":"percent"},{"benchmark":"minif2f-test","model":"mistral-7b-v0.1","score":18,"metric":"percent"},{"benchmark":"minif2f-test","model":"codellama-7b","score":17.6,"metric":"percent"},{"benchmark":"minif2f-test","model":"codellama-34b","score":18,"metric":"percent"},{"benchmark":"minif2f-test","model":"llemma-7b","score":22.1,"metric":"percent"},{"benchmark":"minif2f-test","model":"llemma-34b","score":21.3,"metric":"percent"},{"benchmark":"minif2f-test","model":"deepseek-math-7b","score":24.6,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-v0.1","score":62.4,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b-v0.1","score":55.7,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-v0.1","score":28,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-v0.1","score":41.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-math-7b","score":54.9,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-math-7b","score":59.5,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-math-7b","score":40.9,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-math-7b","score":52.6,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-1.0-ultra","score":94.4,"metric":"percent"},{"benchmark":"math","model":"gemini-1.0-ultra","score":53.2,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4","score":92,"metric":"percent"},{"benchmark":"math","model":"gpt-4","score":52.9,"metric":"percent"},{"benchmark":"cmath","model":"gpt-4","score":86,"metric":"percent"},{"benchmark":"gsm8k","model":"inflection-2","score":81.4,"metric":"percent"},{"benchmark":"math","model":"inflection-2","score":34.8,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5","score":80.8,"metric":"percent"},{"benchmark":"math","model":"gpt-3.5","score":34.1,"metric":"percent"},{"benchmark":"cmath","model":"gpt-3.5","score":73.8,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-pro","score":86.5,"metric":"percent"},{"benchmark":"math","model":"gemini-pro","score":32.6,"metric":"percent"},{"benchmark":"gsm8k","model":"grok-1","score":62.9,"metric":"percent"},{"benchmark":"math","model":"grok-1","score":23.9,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan-3","score":88.2,"metric":"percent"},{"benchmark":"math","model":"baichuan-3","score":49.2,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4-0116","score":87.6,"metric":"percent"},{"benchmark":"math","model":"glm-4-0116","score":47.9,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-20b","score":82.6,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-20b","score":37.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-72b-chat","score":78.9,"metric":"percent"},{"benchmark":"math","model":"qwen-72b-chat","score":35.2,"metric":"percent"},{"benchmark":"gsm8k","model":"math-shepherd-mistral-7b","score":84.1,"metric":"percent"},{"benchmark":"math","model":"math-shepherd-mistral-7b","score":33,"metric":"percent"},{"benchmark":"gsm8k","model":"wizardmath-7b-v1.1","score":83.2,"metric":"percent"},{"benchmark":"math","model":"wizardmath-7b-v1.1","score":33,"metric":"percent"},{"benchmark":"gsm8k","model":"metamath-70b","score":82.3,"metric":"percent"},{"benchmark":"math","model":"metamath-70b","score":26.6,"metric":"percent"},{"benchmark":"cmath","model":"metamath-70b","score":70.9,"metric":"percent"},{"benchmark":"gsm8k","model":"seallm-7b-v2","score":78.2,"metric":"percent"},{"benchmark":"math","model":"seallm-7b-v2","score":27.5,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm3-6b","score":72.3,"metric":"percent"},{"benchmark":"math","model":"chatglm3-6b","score":25.7,"metric":"percent"},{"benchmark":"gsm8k","model":"wizardmath-70b-v1.0","score":81.6,"metric":"percent"},{"benchmark":"math","model":"wizardmath-70b-v1.0","score":22.7,"metric":"percent"},{"benchmark":"cmath","model":"wizardmath-70b-v1.0","score":65.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-math-7b-instruct","score":82.9,"metric":"percent"},{"benchmark":"math","model":"deepseek-math-7b-instruct","score":46.8,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-math-7b-instruct","score":84.6,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-math-7b-rl","score":88.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-math-7b-rl","score":51.7,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-math-7b-rl","score":88.8,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-pro","score":48.9,"metric":"percent"},{"benchmark":"mmbench","model":"gemini-pro","score":75.2,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"gemini-pro","score":74,"metric":"percent"},{"benchmark":"seedbench","model":"gemini-pro","score":70.7,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-pro","score":65.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-pro","score":45.2,"metric":"percent"},{"benchmark":"mmvet","model":"gemini-pro","score":59.2,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4v","score":56.8,"metric":"percent"},{"benchmark":"cmmmu","model":"gpt-4v","score":42.5,"metric":"percent"},{"benchmark":"mmbench","model":"gpt-4v","score":75,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"gpt-4v","score":74.7,"metric":"percent"},{"benchmark":"seedbench","model":"gpt-4v","score":71.6,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4v","score":65.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4v","score":47.8,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4v","score":49.9,"metric":"percent"},{"benchmark":"mmmu","model":"qwen-vl-plus","score":45.2,"metric":"percent"},{"benchmark":"cmmmu","model":"qwen-vl-plus","score":39.5,"metric":"percent"},{"benchmark":"mmbench","model":"qwen-vl-plus","score":66.2,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"qwen-vl-plus","score":69.6,"metric":"percent"},{"benchmark":"seedbench","model":"qwen-vl-plus","score":72.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen-vl-plus","score":43.3,"metric":"percent"},{"benchmark":"mmvet","model":"qwen-vl-plus","score":55.7,"metric":"percent"},{"benchmark":"mmmu","model":"qwen-vl-max","score":51.4,"metric":"percent"},{"benchmark":"mmbench","model":"qwen-vl-max","score":78.1,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"qwen-vl-max","score":76.4,"metric":"percent"},{"benchmark":"seedbench","model":"qwen-vl-max","score":72.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen-vl-max","score":51,"metric":"percent"},{"benchmark":"mmvet","model":"qwen-vl-max","score":61.8,"metric":"percent"},{"benchmark":"mmmu","model":"llava-1.5-13b","score":36.4,"metric":"percent"},{"benchmark":"mmbench","model":"llava-1.5-13b","score":68.2,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"llava-1.5-13b","score":61.9,"metric":"percent"},{"benchmark":"seedbench","model":"llava-1.5-13b","score":68.2,"metric":"percent"},{"benchmark":"ocrbench","model":"llava-1.5-13b","score":33.1,"metric":"percent"},{"benchmark":"pope","model":"llava-1.5-13b","score":85.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-1.5-13b","score":26.4,"metric":"percent"},{"benchmark":"mmvet","model":"llava-1.5-13b","score":38.3,"metric":"percent"},{"benchmark":"mmbench","model":"vila-13b","score":70.3,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"vila-13b","score":64.3,"metric":"percent"},{"benchmark":"pope","model":"vila-13b","score":84.2,"metric":"percent"},{"benchmark":"mmvet","model":"vila-13b","score":38.8,"metric":"percent"},{"benchmark":"mmmu","model":"llava-1.6-13b","score":36.2,"metric":"percent"},{"benchmark":"mmbench","model":"llava-1.6-13b","score":70,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"llava-1.6-13b","score":64.4,"metric":"percent"},{"benchmark":"seedbench","model":"llava-1.6-13b","score":71.9,"metric":"percent"},{"benchmark":"pope","model":"llava-1.6-13b","score":86.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-1.6-13b","score":35.3,"metric":"percent"},{"benchmark":"mmvet","model":"llava-1.6-13b","score":48.4,"metric":"percent"},{"benchmark":"mmmu","model":"emu2-chat","score":36.3,"metric":"percent"},{"benchmark":"cmmmu","model":"emu2-chat","score":23.8,"metric":"percent"},{"benchmark":"mmbench","model":"emu2-chat","score":63.6,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"emu2-chat","score":45.9,"metric":"percent"},{"benchmark":"seedbench","model":"emu2-chat","score":68.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"emu2-chat","score":30,"metric":"percent"},{"benchmark":"mmvet","model":"emu2-chat","score":31,"metric":"percent"},{"benchmark":"mmmu","model":"qwen-vl-chat","score":37,"metric":"percent"},{"benchmark":"mmbench","model":"qwen-vl-chat","score":60.6,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"qwen-vl-chat","score":56.7,"metric":"percent"},{"benchmark":"seedbench","model":"qwen-vl-chat","score":64.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen-vl-chat","score":33.8,"metric":"percent"},{"benchmark":"mmvet","model":"qwen-vl-chat","score":47.3,"metric":"percent"},{"benchmark":"mmmu","model":"cogvlm-17b-chat","score":37.3,"metric":"percent"},{"benchmark":"cmmmu","model":"cogvlm-17b-chat","score":24.8,"metric":"percent"},{"benchmark":"mmbench","model":"cogvlm-17b-chat","score":63.7,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"cogvlm-17b-chat","score":53.8,"metric":"percent"},{"benchmark":"seedbench","model":"cogvlm-17b-chat","score":68.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"cogvlm-17b-chat","score":34.7,"metric":"percent"},{"benchmark":"mmvet","model":"cogvlm-17b-chat","score":54.5,"metric":"percent"},{"benchmark":"mmmu","model":"llava-next-7b","score":35.8,"metric":"percent"},{"benchmark":"mmbench","model":"llava-next-7b","score":67.4,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"llava-next-7b","score":60,"metric":"percent"},{"benchmark":"seedbench","model":"llava-next-7b","score":70.2,"metric":"percent"},{"benchmark":"pope","model":"llava-next-7b","score":86.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-next-7b","score":34.6,"metric":"percent"},{"benchmark":"mmvet","model":"llava-next-7b","score":43.9,"metric":"percent"},{"benchmark":"mmmu","model":"yi-vl-6b","score":37.8,"metric":"percent"},{"benchmark":"cmmmu","model":"yi-vl-6b","score":35.8,"metric":"percent"},{"benchmark":"mmbench","model":"yi-vl-6b","score":68.2,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"yi-vl-6b","score":68.9,"metric":"percent"},{"benchmark":"seedbench","model":"yi-vl-6b","score":67.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"yi-vl-6b","score":28,"metric":"percent"},{"benchmark":"mmvet","model":"yi-vl-6b","score":31.1,"metric":"percent"},{"benchmark":"mmmu","model":"deepseek-vl-7b","score":36.6,"metric":"percent"},{"benchmark":"cmmmu","model":"deepseek-vl-7b","score":37.9,"metric":"percent"},{"benchmark":"mmbench","model":"deepseek-vl-7b","score":73.2,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"deepseek-vl-7b","score":72.8,"metric":"percent"},{"benchmark":"seedbench","model":"deepseek-vl-7b","score":70.4,"metric":"percent"},{"benchmark":"ocrbench","model":"deepseek-vl-7b","score":45.6,"metric":"percent"},{"benchmark":"pope","model":"deepseek-vl-7b","score":88.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"deepseek-vl-7b","score":36.1,"metric":"percent"},{"benchmark":"mmvet","model":"deepseek-vl-7b","score":41.5,"metric":"percent"},{"benchmark":"mmbench","model":"mobilevlm-1.7b","score":53.2,"metric":"percent"},{"benchmark":"pope","model":"mobilevlm-1.7b","score":84.5,"metric":"percent"},{"benchmark":"mmbench","model":"mobilevlm-3b","score":59.6,"metric":"percent"},{"benchmark":"pope","model":"mobilevlm-3b","score":84.9,"metric":"percent"},{"benchmark":"mmbench","model":"mobilevlm-v2-1.7b","score":59.6,"metric":"percent"},{"benchmark":"pope","model":"mobilevlm-v2-1.7b","score":84.3,"metric":"percent"},{"benchmark":"mmbench","model":"mobilevlm-v2-3b","score":63.2,"metric":"percent"},{"benchmark":"pope","model":"mobilevlm-v2-3b","score":84.7,"metric":"percent"},{"benchmark":"mmbench","model":"llava-phi","score":59.5,"metric":"percent"},{"benchmark":"pope","model":"llava-phi","score":85,"metric":"percent"},{"benchmark":"mmvet","model":"llava-phi","score":28.9,"metric":"percent"},{"benchmark":"mmmu","model":"deepseek-vl-1.3b","score":32.2,"metric":"percent"},{"benchmark":"cmmmu","model":"deepseek-vl-1.3b","score":27.4,"metric":"percent"},{"benchmark":"mmbench","model":"deepseek-vl-1.3b","score":64.6,"metric":"percent"},{"benchmark":"mmc-benchmark","model":"deepseek-vl-1.3b","score":61.3,"metric":"percent"},{"benchmark":"seedbench","model":"deepseek-vl-1.3b","score":66.7,"metric":"percent"},{"benchmark":"ocrbench","model":"deepseek-vl-1.3b","score":40.9,"metric":"percent"},{"benchmark":"pope","model":"deepseek-vl-1.3b","score":87.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"deepseek-vl-1.3b","score":31.1,"metric":"percent"},{"benchmark":"mmvet","model":"deepseek-vl-1.3b","score":34.8,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-vl-1.3b","score":56,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-vl-7b","score":68.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-vl-1.3b","score":32.5,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-vl-7b","score":52.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-vl-1.3b","score":18,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-vl-7b","score":55,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-vl-1.3b","score":10,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-vl-7b","score":35.2,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-vl-1.3b","score":14,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-vl-7b","score":27.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-72b","score":59.9,"metric":"percent"},{"benchmark":"bbh","model":"mixtral-8x22b","score":78.9,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-70b-base","score":81,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2","score":78.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-72b","score":77.2,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x22b","score":77.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-70b-base","score":78.9,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2","score":78.5,"metric":"percent"},{"benchmark":"drop","model":"deepseek-llm-67b-base","score":69.7,"metric":"percent"},{"benchmark":"drop","model":"qwen1.5-72b","score":71.5,"metric":"percent"},{"benchmark":"drop","model":"mixtral-8x22b","score":80.4,"metric":"percent"},{"benchmark":"drop","model":"llama-3-70b-base","score":82.5,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v2","score":80.1,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-67b-base","score":95.3,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen1.5-72b","score":97.1,"metric":"percent"},{"benchmark":"arc-easy","model":"mixtral-8x22b","score":97.3,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-3-70b-base","score":97.9,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-v2","score":97.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-67b-base","score":86.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-72b","score":92.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"mixtral-8x22b","score":91.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-70b-base","score":93.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2","score":92.4,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-llm-67b-base","score":86.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-72b","score":85.8,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x22b","score":86.6,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3-70b-base","score":87.9,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v2","score":84.2,"metric":"percent"},{"benchmark":"piqa","model":"qwen1.5-72b","score":83.3,"metric":"percent"},{"benchmark":"piqa","model":"mixtral-8x22b","score":83.6,"metric":"percent"},{"benchmark":"piqa","model":"llama-3-70b-base","score":85,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-v2","score":83.7,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-llm-67b-base","score":84.9,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-72b","score":82.4,"metric":"percent"},{"benchmark":"winogrande","model":"mixtral-8x22b","score":83.7,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3-70b-base","score":85.7,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v2","score":84.9,"metric":"percent"},{"benchmark":"race-middle","model":"qwen1.5-72b","score":63.4,"metric":"percent"},{"benchmark":"race-middle","model":"mixtral-8x22b","score":73.3,"metric":"percent"},{"benchmark":"race-middle","model":"llama-3-70b-base","score":73.3,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-v2","score":73.1,"metric":"percent"},{"benchmark":"race-high","model":"qwen1.5-72b","score":47,"metric":"percent"},{"benchmark":"race-high","model":"mixtral-8x22b","score":56.7,"metric":"percent"},{"benchmark":"race-high","model":"llama-3-70b-base","score":57.9,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-v2","score":52.7,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen1.5-72b","score":73.1,"metric":"percent"},{"benchmark":"triviaqa","model":"mixtral-8x22b","score":82.1,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-3-70b-base","score":81.6,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v2","score":79.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen1.5-72b","score":35.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"mixtral-8x22b","score":39.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-3-70b-base","score":40.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-v2","score":38.7,"metric":"percent"},{"benchmark":"agieval","model":"qwen1.5-72b","score":64.4,"metric":"percent"},{"benchmark":"agieval","model":"mixtral-8x22b","score":43.4,"metric":"percent"},{"benchmark":"agieval","model":"llama-3-70b-base","score":49.8,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v2","score":51.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-llm-67b-base","score":45.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-72b","score":43.9,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x22b","score":53.1,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b-base","score":48.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2","score":48.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-72b","score":53.6,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x22b","score":64.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-70b-base","score":68.6,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2","score":66.6,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-llm-67b-base","score":42.5,"metric":"percent"},{"benchmark":"crux-i","model":"qwen1.5-72b","score":44.3,"metric":"percent"},{"benchmark":"crux-i","model":"mixtral-8x22b","score":52.4,"metric":"percent"},{"benchmark":"crux-i","model":"llama-3-70b-base","score":49.4,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v2","score":52.8,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-llm-67b-base","score":41,"metric":"percent"},{"benchmark":"crux-o","model":"qwen1.5-72b","score":42.3,"metric":"percent"},{"benchmark":"crux-o","model":"mixtral-8x22b","score":52.8,"metric":"percent"},{"benchmark":"crux-o","model":"llama-3-70b-base","score":54.3,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v2","score":49.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-72b","score":77.9,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b","score":80.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b-base","score":83,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2","score":79.2,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-72b","score":41.4,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x22b","score":42.5,"metric":"percent"},{"benchmark":"math","model":"llama-3-70b-base","score":42.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2","score":43.6,"metric":"percent"},{"benchmark":"cmath","model":"qwen1.5-72b","score":77.8,"metric":"percent"},{"benchmark":"cmath","model":"mixtral-8x22b","score":72.3,"metric":"percent"},{"benchmark":"cmath","model":"llama-3-70b-base","score":73.9,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v2","score":78.7,"metric":"percent"},{"benchmark":"cluewsc","model":"qwen1.5-72b","score":80.5,"metric":"percent"},{"benchmark":"cluewsc","model":"mixtral-8x22b","score":77.5,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-3-70b-base","score":78.3,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v2","score":82.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-72b","score":83.7,"metric":"percent"},{"benchmark":"c-eval","model":"mixtral-8x22b","score":59.6,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-70b-base","score":67.5,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v2","score":81.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-72b","score":84.3,"metric":"percent"},{"benchmark":"cmmlu","model":"mixtral-8x22b","score":60,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-70b-base","score":69.3,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v2","score":84,"metric":"percent"},{"benchmark":"cmrc2018","model":"deepseek-llm-67b-base","score":73.4,"metric":"percent"},{"benchmark":"cmrc2018","model":"qwen1.5-72b","score":66.6,"metric":"percent"},{"benchmark":"cmrc2018","model":"mixtral-8x22b","score":73.1,"metric":"percent"},{"benchmark":"cmrc2018","model":"llama-3-70b-base","score":73.3,"metric":"percent"},{"benchmark":"cmrc2018","model":"deepseek-v2","score":77.5,"metric":"percent"},{"benchmark":"c3","model":"qwen1.5-72b","score":78.2,"metric":"percent"},{"benchmark":"c3","model":"mixtral-8x22b","score":71.4,"metric":"percent"},{"benchmark":"c3","model":"llama-3-70b-base","score":74,"metric":"percent"},{"benchmark":"c3","model":"deepseek-v2","score":77.4,"metric":"percent"},{"benchmark":"chid","model":"mixtral-8x22b","score":57,"metric":"percent"},{"benchmark":"chid","model":"llama-3-70b-base","score":83.2,"metric":"percent"},{"benchmark":"chid","model":"deepseek-v2","score":92.7,"metric":"percent"},{"benchmark":"ccpm","model":"qwen1.5-72b","score":88.1,"metric":"percent"},{"benchmark":"ccpm","model":"mixtral-8x22b","score":61,"metric":"percent"},{"benchmark":"ccpm","model":"llama-3-70b-base","score":68.1,"metric":"percent"},{"benchmark":"ccpm","model":"deepseek-v2","score":93.1,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen1.5-72b-chat","score":79.6,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-3-70b-instruct","score":69.1,"metric":"percent"},{"benchmark":"triviaqa","model":"mixtral-8x22b-instruct-v0.1","score":80,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v2-chat-sft","score":85.4,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v2-chat","score":86.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen1.5-72b-chat","score":46.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-3-70b-instruct","score":44.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"mixtral-8x22b-instruct-v0.1","score":54.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-v2-chat-sft","score":51.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-v2-chat","score":53.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-72b-chat","score":76.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-70b-instruct","score":80.3,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x22b-instruct-v0.1","score":77.8,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2-chat-sft","score":78.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2-chat","score":77.8,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-67b-chat","score":96.6,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen1.5-72b-chat","score":96.8,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-3-70b-instruct","score":96.9,"metric":"percent"},{"benchmark":"arc-easy","model":"mixtral-8x22b-instruct-v0.1","score":97.1,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-v2-chat-sft","score":97.6,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-v2-chat","score":98.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-67b-chat","score":88.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-72b-chat","score":91.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-70b-instruct","score":92.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"mixtral-8x22b-instruct-v0.1","score":90,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2-chat-sft","score":92.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2-chat","score":92.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-72b-chat","score":65.9,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-70b-instruct","score":80.1,"metric":"percent"},{"benchmark":"bbh","model":"mixtral-8x22b-instruct-v0.1","score":78.4,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2-chat-sft","score":81.3,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2-chat","score":79.7,"metric":"percent"},{"benchmark":"agieval","model":"qwen1.5-72b-chat","score":62.8,"metric":"percent"},{"benchmark":"agieval","model":"llama-3-70b-instruct","score":56.6,"metric":"percent"},{"benchmark":"agieval","model":"mixtral-8x22b-instruct-v0.1","score":41.4,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v2-chat-sft","score":63.2,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v2-chat","score":61.4,"metric":"percent"},{"benchmark":"ifeval","model":"qwen1.5-72b-chat","score":57.3,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3-70b-instruct","score":79.7,"metric":"percent"},{"benchmark":"ifeval","model":"mixtral-8x22b-instruct-v0.1","score":72.1,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v2-chat-sft","score":64.1,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v2-chat","score":63.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-72b-chat","score":68.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b-instruct","score":76.2,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x22b-instruct-v0.1","score":75,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2-chat-sft","score":76.8,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2-chat","score":81.1,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-72b-chat","score":52.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-70b-instruct","score":69.8,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x22b-instruct-v0.1","score":64.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2-chat-sft","score":70.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2-chat","score":72,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-llm-67b-chat","score":49.1,"metric":"percent"},{"benchmark":"crux-i","model":"qwen1.5-72b-chat","score":51.4,"metric":"percent"},{"benchmark":"crux-i","model":"llama-3-70b-instruct","score":61.1,"metric":"percent"},{"benchmark":"crux-i","model":"mixtral-8x22b-instruct-v0.1","score":59.4,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v2-chat-sft","score":59.5,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v2-chat","score":61.5,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-llm-67b-chat","score":50.9,"metric":"percent"},{"benchmark":"crux-o","model":"qwen1.5-72b-chat","score":56.5,"metric":"percent"},{"benchmark":"crux-o","model":"llama-3-70b-instruct","score":63.6,"metric":"percent"},{"benchmark":"crux-o","model":"mixtral-8x22b-instruct-v0.1","score":63.6,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v2-chat-sft","score":60.7,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v2-chat","score":63,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-llm-67b-chat","score":18.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen1.5-72b-chat","score":18.8,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3-70b-instruct","score":30.5,"metric":"percent"},{"benchmark":"livecodebench","model":"mixtral-8x22b-instruct-v0.1","score":25,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2-chat-sft","score":28.7,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2-chat","score":32.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-72b-chat","score":81.9,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b-instruct","score":93.2,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b-instruct-v0.1","score":87.9,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2-chat-sft","score":90.8,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2-chat","score":92.2,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-72b-chat","score":40.6,"metric":"percent"},{"benchmark":"math","model":"llama-3-70b-instruct","score":48.5,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x22b-instruct-v0.1","score":49.8,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2-chat-sft","score":52.7,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2-chat","score":53.9,"metric":"percent"},{"benchmark":"cmath","model":"qwen1.5-72b-chat","score":82.8,"metric":"percent"},{"benchmark":"cmath","model":"llama-3-70b-instruct","score":79.2,"metric":"percent"},{"benchmark":"cmath","model":"mixtral-8x22b-instruct-v0.1","score":75.1,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v2-chat-sft","score":82,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v2-chat","score":81.9,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-llm-67b-chat","score":78.5,"metric":"percent"},{"benchmark":"cluewsc","model":"qwen1.5-72b-chat","score":90.1,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-3-70b-instruct","score":85.4,"metric":"percent"},{"benchmark":"cluewsc","model":"mixtral-8x22b-instruct-v0.1","score":75.8,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v2-chat-sft","score":88.6,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v2-chat","score":89.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-72b-chat","score":82.2,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-70b-instruct","score":67.9,"metric":"percent"},{"benchmark":"c-eval","model":"mixtral-8x22b-instruct-v0.1","score":60,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v2-chat-sft","score":80.9,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v2-chat","score":78,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-72b-chat","score":82.9,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-70b-instruct","score":70.7,"metric":"percent"},{"benchmark":"cmmlu","model":"mixtral-8x22b-instruct-v0.1","score":61,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v2-chat-sft","score":82.4,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v2-chat","score":81.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-llm-67b-chat","score":16.6,"metric":"percent"},{"benchmark":"mt-bench","model":"mixtral-8x22b-instruct-v0.1","score":8.66,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"mixtral-8x22b-instruct-v0.1","score":30.9,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen1.5-72b-chat","score":8.61,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen1.5-72b-chat","score":36.6,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3-70b-instruct","score":8.95,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3-70b-instruct","score":34.4,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-v2-chat-sft","score":8.62,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-v2-chat-sft","score":30,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-v2-chat","score":8.97,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-v2-chat","score":38.9,"metric":"percent"},{"benchmark":"alignbench","model":"deepseek-v2-chat","score":7.91,"metric":"score"},{"benchmark":"alignbench","model":"ernie-bot-4.0-202404","score":7.89,"metric":"score"},{"benchmark":"alignbench","model":"deepseek-v2-chat-sft","score":7.74,"metric":"score"},{"benchmark":"alignbench","model":"ernie-bot-4.0-202312","score":7.36,"metric":"score"},{"benchmark":"alignbench","model":"moonshot-v1-32k-202404","score":7.22,"metric":"score"},{"benchmark":"alignbench","model":"qwen1.5-72b-chat","score":7.19,"metric":"score"},{"benchmark":"alignbench","model":"yi-34b-chat","score":6.12,"metric":"score"},{"benchmark":"mmlu","model":"deepseek-v2-lite","score":58.3,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-moe-16b-base","score":38.9,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2-lite","score":44.1,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v2-lite","score":64.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-v2-lite","score":26,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-v2-lite","score":70.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2-lite","score":51.2,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-moe-16b-base","score":17.4,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v2-lite","score":33.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2-lite","score":29.9,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2-lite","score":43.2,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2-lite","score":41.1,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2-lite","score":17.1,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-moe-16b-base","score":40.4,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v2-lite","score":58.4,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v2-lite","score":74.3,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v2-lite","score":60.3,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v2-lite","score":64.3,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2-lite-chat","score":55.7,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2-lite-chat","score":48.1,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v2-lite-chat","score":65.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-v2-lite-chat","score":35.5,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-v2-lite-chat","score":74.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2-lite-chat","score":51.5,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-llm-7b-chat","score":17.6,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-moe-16b-chat","score":19.7,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v2-lite-chat","score":42.8,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2-lite-chat","score":57.3,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2-lite-chat","score":45.8,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2-lite-chat","score":72,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2-lite-chat","score":27.9,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-llm-7b-chat","score":66.4,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-moe-16b-chat","score":67.9,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v2-lite-chat","score":71.7,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v2-lite-chat","score":80,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v2-lite-chat","score":60.1,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v2-lite-chat","score":62.5,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-1.5-pro","score":83.5,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3-opus-20240229","score":84.2,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4-1106-preview","score":87.8,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4-turbo-2024-04-09","score":88.2,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-2024-05-13","score":91,"metric":"percent"},{"benchmark":"humaneval","model":"codestral-22b","score":78.1,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b-instruct","score":81.1,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-v2-instruct","score":90.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3-opus-20240229","score":72,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4-1106-preview","score":69.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4-turbo-2024-04-09","score":72.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4o-2024-05-13","score":73.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codestral-22b","score":68.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-70b-instruct","score":68.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-v2-lite-instruct","score":68.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-v2-instruct","score":76.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemini-1.5-pro","score":34.1,"metric":"percent"},{"benchmark":"usaco","model":"gemini-1.5-pro","score":4.9,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3-opus-20240229","score":34.6,"metric":"percent"},{"benchmark":"usaco","model":"claude-3-opus-20240229","score":7.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4-1106-preview","score":37.1,"metric":"percent"},{"benchmark":"usaco","model":"gpt-4-1106-preview","score":11.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4-turbo-2024-04-09","score":45.7,"metric":"percent"},{"benchmark":"usaco","model":"gpt-4-turbo-2024-04-09","score":12.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o-2024-05-13","score":43.4,"metric":"percent"},{"benchmark":"usaco","model":"gpt-4o-2024-05-13","score":18.8,"metric":"percent"},{"benchmark":"livecodebench","model":"codestral-22b","score":31,"metric":"percent"},{"benchmark":"usaco","model":"codestral-22b","score":4.6,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-coder-33b-instruct","score":22.5,"metric":"percent"},{"benchmark":"usaco","model":"deepseek-coder-33b-instruct","score":4.2,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3-70b-instruct","score":28.7,"metric":"percent"},{"benchmark":"usaco","model":"llama-3-70b-instruct","score":3.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-coder-v2-lite-instruct","score":24.3,"metric":"percent"},{"benchmark":"usaco","model":"deepseek-coder-v2-lite-instruct","score":6.5,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-coder-v2-instruct","score":43.4,"metric":"percent"},{"benchmark":"usaco","model":"deepseek-coder-v2-instruct","score":12.1,"metric":"percent"},{"benchmark":"defects4j","model":"gemini-1.5-pro","score":18.6,"metric":"percent"},{"benchmark":"swe-bench","model":"gemini-1.5-pro","score":19.3,"metric":"percent"},{"benchmark":"aider-code-editing","model":"gemini-1.5-pro","score":57.1,"metric":"percent"},{"benchmark":"defects4j","model":"claude-3-opus-20240229","score":25.5,"metric":"percent"},{"benchmark":"swe-bench","model":"claude-3-opus-20240229","score":11.7,"metric":"percent"},{"benchmark":"aider-code-editing","model":"claude-3-opus-20240229","score":68.4,"metric":"percent"},{"benchmark":"defects4j","model":"gpt-4-1106-preview","score":22.8,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-4-1106-preview","score":22.7,"metric":"percent"},{"benchmark":"aider-code-editing","model":"gpt-4-1106-preview","score":65.4,"metric":"percent"},{"benchmark":"defects4j","model":"gpt-4-turbo-2024-04-09","score":24.3,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-4-turbo-2024-04-09","score":18.3,"metric":"percent"},{"benchmark":"aider-code-editing","model":"gpt-4-turbo-2024-04-09","score":63.9,"metric":"percent"},{"benchmark":"defects4j","model":"gpt-4o-2024-05-13","score":26.1,"metric":"percent"},{"benchmark":"swe-bench","model":"gpt-4o-2024-05-13","score":26.7,"metric":"percent"},{"benchmark":"aider-code-editing","model":"gpt-4o-2024-05-13","score":72.9,"metric":"percent"},{"benchmark":"defects4j","model":"codestral-22b","score":17.8,"metric":"percent"},{"benchmark":"swe-bench","model":"codestral-22b","score":2.7,"metric":"percent"},{"benchmark":"aider-code-editing","model":"codestral-22b","score":51.1,"metric":"percent"},{"benchmark":"defects4j","model":"deepseek-coder-33b-instruct","score":11.3,"metric":"percent"},{"benchmark":"swe-bench","model":"deepseek-coder-33b-instruct","score":0,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-coder-33b-instruct","score":54.5,"metric":"percent"},{"benchmark":"defects4j","model":"llama-3-70b-instruct","score":16.2,"metric":"percent"},{"benchmark":"aider-code-editing","model":"llama-3-70b-instruct","score":49.2,"metric":"percent"},{"benchmark":"defects4j","model":"deepseek-coder-v2-lite-instruct","score":9.2,"metric":"percent"},{"benchmark":"swe-bench","model":"deepseek-coder-v2-lite-instruct","score":0,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-coder-v2-lite-instruct","score":44.4,"metric":"percent"},{"benchmark":"defects4j","model":"deepseek-coder-v2-instruct","score":21,"metric":"percent"},{"benchmark":"swe-bench","model":"deepseek-coder-v2-instruct","score":12.7,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-coder-v2-instruct","score":73.7,"metric":"percent"},{"benchmark":"crux-i","model":"gemini-1.5-pro","score":67,"metric":"percent"},{"benchmark":"crux-o","model":"gemini-1.5-pro","score":77.5,"metric":"percent"},{"benchmark":"crux-i","model":"claude-3-opus-20240229","score":73.4,"metric":"percent"},{"benchmark":"crux-o","model":"claude-3-opus-20240229","score":82,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4-1106-preview","score":75.5,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-4-1106-preview","score":77.1,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4-turbo-2024-04-09","score":75.7,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-4-turbo-2024-04-09","score":82,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4o-2024-05-13","score":77.4,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-4o-2024-05-13","score":88.7,"metric":"percent"},{"benchmark":"crux-i","model":"codestral-22b","score":48,"metric":"percent"},{"benchmark":"crux-o","model":"codestral-22b","score":60.6,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-33b-instruct","score":47.3,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-33b-instruct","score":50.6,"metric":"percent"},{"benchmark":"crux-o","model":"llama-3-70b-instruct","score":64.3,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-v2-lite-instruct","score":53,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-v2-lite-instruct","score":52.9,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-v2-instruct","score":70,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-v2-instruct","score":75.1,"metric":"percent"},{"benchmark":"math","model":"gemini-1.5-pro","score":67.7,"metric":"percent"},{"benchmark":"aime-2024","model":"gemini-1.5-pro","score":6.7,"metric":"percent"},{"benchmark":"odyssey-math","model":"gemini-1.5-pro","score":45,"metric":"percent"},{"benchmark":"math","model":"claude-3-opus-20240229","score":60.1,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-3-opus-20240229","score":6.7,"metric":"percent"},{"benchmark":"odyssey-math","model":"claude-3-opus-20240229","score":40.6,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4-1106-preview","score":91.4,"metric":"percent"},{"benchmark":"math","model":"gpt-4-1106-preview","score":64.3,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4-1106-preview","score":3.3,"metric":"percent"},{"benchmark":"odyssey-math","model":"gpt-4-1106-preview","score":49.1,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4-turbo-2024-04-09","score":93.7,"metric":"percent"},{"benchmark":"math","model":"gpt-4-turbo-2024-04-09","score":73.4,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4-turbo-2024-04-09","score":10,"metric":"percent"},{"benchmark":"odyssey-math","model":"gpt-4-turbo-2024-04-09","score":46.8,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4o-2024-05-13","score":95.8,"metric":"percent"},{"benchmark":"math","model":"gpt-4o-2024-05-13","score":76.6,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4o-2024-05-13","score":6.7,"metric":"percent"},{"benchmark":"odyssey-math","model":"gpt-4o-2024-05-13","score":53.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b-instruct","score":93,"metric":"percent"},{"benchmark":"math","model":"llama-3-70b-instruct","score":50.4,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3-70b-instruct","score":3.3,"metric":"percent"},{"benchmark":"odyssey-math","model":"llama-3-70b-instruct","score":27.9,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-lite-instruct","score":86.4,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-v2-lite-instruct","score":61.8,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-coder-v2-lite-instruct","score":0,"metric":"percent"},{"benchmark":"odyssey-math","model":"deepseek-coder-v2-lite-instruct","score":44.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-instruct","score":94.9,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-v2-instruct","score":75.7,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-coder-v2-instruct","score":13.3,"metric":"percent"},{"benchmark":"odyssey-math","model":"deepseek-coder-v2-instruct","score":53.7,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-coder-v2-lite-instruct","score":61.2,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-coder-v2-instruct","score":83.9,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-v2-lite-instruct","score":60.1,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2-chat","score":78.1,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-v2-instruct","score":79.2,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-v2-lite-chat","score":86.1,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-coder-v2-lite-instruct","score":88.9,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-coder-v2-instruct","score":97.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2-lite-chat","score":73.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-v2-lite-instruct","score":77.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-v2-instruct","score":92.8,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-coder-v2-lite-instruct","score":59.5,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-coder-v2-instruct","score":82.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-coder-v2-lite-instruct","score":30.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-coder-v2-instruct","score":47.5,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-coder-v2-lite-instruct","score":28.7,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-coder-v2-instruct","score":60,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-coder-v2-lite-instruct","score":76.5,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-coder-v2-instruct","score":85.9,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-coder-v2-lite-instruct","score":61.6,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-coder-v2-instruct","score":79.4,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-coder-v2-lite-instruct","score":62.7,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-coder-v2-instruct","score":80.9,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-v2-lite-chat","score":11.4,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-coder-v2-lite-instruct","score":38.1,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-v2-chat","score":41.6,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-coder-v2-instruct","score":65,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-v2-lite-chat","score":16.85,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-coder-v2-lite-instruct","score":17.74,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-coder-v2-instruct","score":36.92,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-v2-lite-chat","score":7.37,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-coder-v2-lite-instruct","score":7.81,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-coder-v2-instruct","score":8.77,"metric":"percent"},{"benchmark":"alignbench","model":"deepseek-v2-lite-chat","score":6.02,"metric":"score"},{"benchmark":"alignbench","model":"deepseek-coder-v2-lite-instruct","score":6.83,"metric":"score"},{"benchmark":"alignbench","model":"deepseek-coder-v2-instruct","score":7.84,"metric":"score"},{"benchmark":"infovqa","model":"gpt-4v","score":75.1,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4v","score":64.5,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-4o","score":79.2,"metric":"percent"},{"benchmark":"docvqa","model":"claude-3.5-sonnet-20240620","score":95.2,"metric":"percent"},{"benchmark":"chartqa","model":"claude-3.5-sonnet-20240620","score":90.8,"metric":"percent"},{"benchmark":"infovqa","model":"claude-3.5-sonnet-20240620","score":74.1,"metric":"percent"},{"benchmark":"textvqa","model":"claude-3.5-sonnet-20240620","score":74.1,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-3.5-sonnet-20240620","score":78.8,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-1.5-pro","score":80.1,"metric":"percent"},{"benchmark":"docvqa","model":"llava-onevision-0.5b","score":70,"metric":"percent"},{"benchmark":"chartqa","model":"llava-onevision-0.5b","score":61.4,"metric":"percent"},{"benchmark":"infovqa","model":"llava-onevision-0.5b","score":41.8,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2-1b","score":81.7,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2-1b","score":72.9,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2-1b","score":50.9,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2-1b","score":70.5,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2-1b","score":75.4,"metric":"percent"},{"benchmark":"docvqa","model":"mm1.5-1b","score":81,"metric":"percent"},{"benchmark":"chartqa","model":"mm1.5-1b","score":67.2,"metric":"percent"},{"benchmark":"infovqa","model":"mm1.5-1b","score":50.5,"metric":"percent"},{"benchmark":"textvqa","model":"mm1.5-1b","score":72.5,"metric":"percent"},{"benchmark":"ocrbench","model":"mm1.5-1b","score":60.5,"metric":"percent"},{"benchmark":"docvqa","model":"deepseek-vl2-tiny","score":88.9,"metric":"percent"},{"benchmark":"chartqa","model":"deepseek-vl2-tiny","score":81,"metric":"percent"},{"benchmark":"infovqa","model":"deepseek-vl2-tiny","score":66.1,"metric":"percent"},{"benchmark":"textvqa","model":"deepseek-vl2-tiny","score":80.7,"metric":"percent"},{"benchmark":"ocrbench","model":"deepseek-vl2-tiny","score":80.9,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2-2b","score":86.9,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2-2b","score":76.2,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2-2b","score":58.9,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2-2b","score":73.4,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2-2b","score":78.4,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2-vl-2b","score":90.1,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2-vl-2b","score":65.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2-vl-2b","score":79.4,"metric":"percent"},{"benchmark":"docvqa","model":"deepseek-vl2-small","score":92.3,"metric":"percent"},{"benchmark":"chartqa","model":"deepseek-vl2-small","score":84.5,"metric":"percent"},{"benchmark":"infovqa","model":"deepseek-vl2-small","score":75.8,"metric":"percent"},{"benchmark":"textvqa","model":"deepseek-vl2-small","score":83.4,"metric":"percent"},{"benchmark":"ocrbench","model":"deepseek-vl2-small","score":83.4,"metric":"percent"},{"benchmark":"docvqa","model":"phi-3.5-vision-instruct","score":69.3,"metric":"percent"},{"benchmark":"chartqa","model":"phi-3.5-vision-instruct","score":81.8,"metric":"percent"},{"benchmark":"infovqa","model":"phi-3.5-vision-instruct","score":36.6,"metric":"percent"},{"benchmark":"textvqa","model":"phi-3.5-vision-instruct","score":72,"metric":"percent"},{"benchmark":"ocrbench","model":"phi-3.5-vision-instruct","score":59.9,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2-4b","score":89.2,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2-4b","score":81.5,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2-4b","score":67,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2-4b","score":74.4,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2-4b","score":78.8,"metric":"percent"},{"benchmark":"docvqa","model":"aria","score":92.6,"metric":"percent"},{"benchmark":"chartqa","model":"aria","score":86.4,"metric":"percent"},{"benchmark":"textvqa","model":"aria","score":81.1,"metric":"percent"},{"benchmark":"docvqa","model":"mm1.5-7b","score":88.1,"metric":"percent"},{"benchmark":"chartqa","model":"mm1.5-7b","score":78.6,"metric":"percent"},{"benchmark":"infovqa","model":"mm1.5-7b","score":59.5,"metric":"percent"},{"benchmark":"textvqa","model":"mm1.5-7b","score":76.5,"metric":"percent"},{"benchmark":"ocrbench","model":"mm1.5-7b","score":63.5,"metric":"percent"},{"benchmark":"infovqa","model":"llava-onevision-7b","score":68.8,"metric":"percent"},{"benchmark":"infovqa","model":"molmo-7b-o","score":70,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-v-2_6","score":90.8,"metric":"percent"},{"benchmark":"chartqa","model":"minicpm-v-2_6","score":82.4,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-v-2_6","score":80.1,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2-8b","score":74.8,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2-8b","score":79.4,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2-vl-7b","score":76.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2-vl-7b","score":84.5,"metric":"percent"},{"benchmark":"infovqa","model":"pixtral-12b","score":50.8,"metric":"percent"},{"benchmark":"docvqa","model":"deepseek-vl2","score":93.3,"metric":"percent"},{"benchmark":"chartqa","model":"deepseek-vl2","score":86,"metric":"percent"},{"benchmark":"infovqa","model":"deepseek-vl2","score":78.1,"metric":"percent"},{"benchmark":"textvqa","model":"deepseek-vl2","score":84.2,"metric":"percent"},{"benchmark":"ocrbench","model":"deepseek-vl2","score":81.1,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4v","score":56,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4v","score":1927,"metric":"points"},{"benchmark":"mmbench","model":"gpt-4v","score":81,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gpt-4v","score":80.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4v","score":80,"metric":"percent"},{"benchmark":"mmt-bench","model":"gpt-4v","score":64.3,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4o","score":63.9,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4o","score":94.2,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4o","score":69.1,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4o","score":2329,"metric":"points"},{"benchmark":"mmbench","model":"gpt-4o","score":83.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gpt-4o","score":82.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o","score":82.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"gpt-4o","score":65.5,"metric":"percent"},{"benchmark":"mmstar","model":"claude-3.5-sonnet-20240620","score":62.2,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3.5-sonnet-20240620","score":94.7,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3.5-sonnet-20240620","score":68.3,"metric":"percent"},{"benchmark":"mme-elo","model":"claude-3.5-sonnet-20240620","score":1920,"metric":"points"},{"benchmark":"mmbench","model":"claude-3.5-sonnet-20240620","score":79.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"claude-3.5-sonnet-20240620","score":80.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3.5-sonnet-20240620","score":78.5,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-3.5-sonnet-20240620","score":60.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-3.5-sonnet-20240620","score":67.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"gemini-1.5-pro","score":64.5,"metric":"percent"},{"benchmark":"mmstar","model":"llava-onevision-0.5b","score":37.7,"metric":"percent"},{"benchmark":"ai2d","model":"llava-onevision-0.5b","score":57.1,"metric":"percent"},{"benchmark":"mmmu","model":"llava-onevision-0.5b","score":31.4,"metric":"percent"},{"benchmark":"mme-elo","model":"llava-onevision-0.5b","score":1478,"metric":"points"},{"benchmark":"mmbench","model":"llava-onevision-0.5b","score":61.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"llava-onevision-0.5b","score":55.5,"metric":"percent"},{"benchmark":"realworldqa","model":"llava-onevision-0.5b","score":55.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-onevision-0.5b","score":34.8,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-1b","score":45.7,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-1b","score":64.1,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-1b","score":35.4,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-1b","score":1794,"metric":"points"},{"benchmark":"mmbench","model":"internvl2-1b","score":65.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2-1b","score":60.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2-1b","score":49.5,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-1b","score":50.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2-1b","score":37.7,"metric":"percent"},{"benchmark":"ai2d","model":"mm1.5-1b","score":59.3,"metric":"percent"},{"benchmark":"mmmu","model":"mm1.5-1b","score":35.8,"metric":"percent"},{"benchmark":"mme-elo","model":"mm1.5-1b","score":1611,"metric":"points"},{"benchmark":"realworldqa","model":"mm1.5-1b","score":53.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"mm1.5-1b","score":37.2,"metric":"percent"},{"benchmark":"mmstar","model":"deepseek-vl2-tiny","score":45.9,"metric":"percent"},{"benchmark":"ai2d","model":"deepseek-vl2-tiny","score":71.6,"metric":"percent"},{"benchmark":"mmmu","model":"deepseek-vl2-tiny","score":40.7,"metric":"percent"},{"benchmark":"mme-elo","model":"deepseek-vl2-tiny","score":1915,"metric":"points"},{"benchmark":"mmbench","model":"deepseek-vl2-tiny","score":73.3,"metric":"percent"},{"benchmark":"mmbench-cn","model":"deepseek-vl2-tiny","score":69.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"deepseek-vl2-tiny","score":68.3,"metric":"percent"},{"benchmark":"mmt-bench","model":"deepseek-vl2-tiny","score":53.2,"metric":"percent"},{"benchmark":"realworldqa","model":"deepseek-vl2-tiny","score":64.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"deepseek-vl2-tiny","score":53.6,"metric":"percent"},{"benchmark":"mme-elo","model":"minicpm-v-2.0-3b","score":1809,"metric":"points"},{"benchmark":"mmbench","model":"minicpm-v-2.0-3b","score":69.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"minicpm-v-2.0-3b","score":68.1,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-2b","score":49.8,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-2b","score":74.1,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-2b","score":36.3,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-2b","score":1877,"metric":"points"},{"benchmark":"mmbench","model":"internvl2-2b","score":73.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2-2b","score":70.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-2b","score":69.6,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2-2b","score":50.4,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-2b","score":57.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2-2b","score":46.3,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2-vl-2b","score":48,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2-vl-2b","score":74.4,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2-vl-2b","score":41.1,"metric":"percent"},{"benchmark":"mme-elo","model":"qwen2-vl-2b","score":1872,"metric":"points"},{"benchmark":"mmbench","model":"qwen2-vl-2b","score":74.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen2-vl-2b","score":73.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-2b","score":72.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen2-vl-2b","score":54.5,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2-vl-2b","score":62.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2-vl-2b","score":47.8,"metric":"percent"},{"benchmark":"mme-elo","model":"mm1.5-3b","score":1798,"metric":"points"},{"benchmark":"mmstar","model":"deepseek-vl2-small","score":57,"metric":"percent"},{"benchmark":"ai2d","model":"deepseek-vl2-small","score":80,"metric":"percent"},{"benchmark":"mmmu","model":"deepseek-vl2-small","score":48,"metric":"percent"},{"benchmark":"mme-elo","model":"deepseek-vl2-small","score":2123,"metric":"points"},{"benchmark":"mmbench","model":"deepseek-vl2-small","score":82.3,"metric":"percent"},{"benchmark":"mmbench-cn","model":"deepseek-vl2-small","score":80.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"deepseek-vl2-small","score":79.3,"metric":"percent"},{"benchmark":"mmt-bench","model":"deepseek-vl2-small","score":62.9,"metric":"percent"},{"benchmark":"realworldqa","model":"deepseek-vl2-small","score":65.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"deepseek-vl2-small","score":60.7,"metric":"percent"},{"benchmark":"mmstar","model":"phi-3.5-vision-instruct","score":47.5,"metric":"percent"},{"benchmark":"ai2d","model":"phi-3.5-vision-instruct","score":78.1,"metric":"percent"},{"benchmark":"mmmu","model":"phi-3.5-vision-instruct","score":43,"metric":"percent"},{"benchmark":"mmbench","model":"phi-3.5-vision-instruct","score":76,"metric":"percent"},{"benchmark":"mmbench-cn","model":"phi-3.5-vision-instruct","score":66.1,"metric":"percent"},{"benchmark":"mmt-bench","model":"phi-3.5-vision-instruct","score":53.6,"metric":"percent"},{"benchmark":"realworldqa","model":"phi-3.5-vision-instruct","score":53.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"phi-3.5-vision-instruct","score":43.9,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-4b","score":54.3,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-4b","score":78.9,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-4b","score":47.9,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-4b","score":2060,"metric":"points"},{"benchmark":"mmbench","model":"internvl2-4b","score":78.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2-4b","score":73.9,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2-4b","score":55.7,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-4b","score":60.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2-4b","score":58.6,"metric":"percent"},{"benchmark":"mmmu","model":"aria","score":54.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"aria","score":66.1,"metric":"percent"},{"benchmark":"ai2d","model":"mm1.5-7b","score":72.2,"metric":"percent"},{"benchmark":"mmmu","model":"mm1.5-7b","score":41.8,"metric":"percent"},{"benchmark":"mme-elo","model":"mm1.5-7b","score":1861,"metric":"points"},{"benchmark":"realworldqa","model":"mm1.5-7b","score":62.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"mm1.5-7b","score":47.6,"metric":"percent"},{"benchmark":"mme-elo","model":"llava-onevision-7b","score":1998,"metric":"points"},{"benchmark":"mmbench","model":"llava-onevision-7b","score":80.8,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-v-2_6","score":57.5,"metric":"percent"},{"benchmark":"ai2d","model":"minicpm-v-2_6","score":82.1,"metric":"percent"},{"benchmark":"mmbench","model":"minicpm-v-2_6","score":81.5,"metric":"percent"},{"benchmark":"mmbench-cn","model":"minicpm-v-2_6","score":79.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-v-2_6","score":78,"metric":"percent"},{"benchmark":"mmt-bench","model":"minicpm-v-2_6","score":60.8,"metric":"percent"},{"benchmark":"realworldqa","model":"minicpm-v-2_6","score":65,"metric":"percent"},{"benchmark":"mathvista-mini","model":"minicpm-v-2_6","score":60.6,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-8b","score":61.5,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-8b","score":51.8,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-8b","score":2210,"metric":"points"},{"benchmark":"mmbench","model":"internvl2-8b","score":81.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2-8b","score":81.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2-8b","score":79.4,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2-8b","score":60,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-8b","score":64.4,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2-vl-7b","score":60.7,"metric":"percent"},{"benchmark":"mme-elo","model":"qwen2-vl-7b","score":2327,"metric":"points"},{"benchmark":"mmbench","model":"qwen2-vl-7b","score":83,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen2-vl-7b","score":80.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-7b","score":80.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen2-vl-7b","score":63.7,"metric":"percent"},{"benchmark":"mmstar","model":"deepseek-vl2","score":61.3,"metric":"percent"},{"benchmark":"ai2d","model":"deepseek-vl2","score":81.4,"metric":"percent"},{"benchmark":"mmmu","model":"deepseek-vl2","score":51.1,"metric":"percent"},{"benchmark":"mme-elo","model":"deepseek-vl2","score":2253,"metric":"points"},{"benchmark":"mmbench","model":"deepseek-vl2","score":83.1,"metric":"percent"},{"benchmark":"mmbench-cn","model":"deepseek-vl2","score":79.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"deepseek-vl2","score":79.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"deepseek-vl2","score":63.6,"metric":"percent"},{"benchmark":"realworldqa","model":"deepseek-vl2","score":68.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"deepseek-vl2","score":62.8,"metric":"percent"},{"benchmark":"refcoco","model":"internvl2-1b","score":83.6,"metric":"percent"},{"benchmark":"refcocoplus","model":"internvl2-1b","score":76,"metric":"percent"},{"benchmark":"refcocog","model":"internvl2-1b","score":80.2,"metric":"percent"},{"benchmark":"refcoco","model":"deepseek-vl2-tiny","score":84.7,"metric":"percent"},{"benchmark":"refcocoplus","model":"deepseek-vl2-tiny","score":75.9,"metric":"percent"},{"benchmark":"refcocog","model":"deepseek-vl2-tiny","score":73.8,"metric":"percent"},{"benchmark":"refcoco","model":"internvl2-2b","score":82.3,"metric":"percent"},{"benchmark":"refcocoplus","model":"internvl2-2b","score":73.5,"metric":"percent"},{"benchmark":"refcocog","model":"internvl2-2b","score":77.6,"metric":"percent"},{"benchmark":"refcoco","model":"deepseek-vl2-small","score":93.9,"metric":"percent"},{"benchmark":"refcocoplus","model":"deepseek-vl2-small","score":89.4,"metric":"percent"},{"benchmark":"refcocog","model":"deepseek-vl2-small","score":92.6,"metric":"percent"},{"benchmark":"refcoco","model":"shikra-7b","score":87,"metric":"percent"},{"benchmark":"refcocoplus","model":"shikra-7b","score":81.6,"metric":"percent"},{"benchmark":"refcocog","model":"shikra-7b","score":82.3,"metric":"percent"},{"benchmark":"refcoco","model":"texthawk2","score":91.9,"metric":"percent"},{"benchmark":"refcocoplus","model":"texthawk2","score":86.2,"metric":"percent"},{"benchmark":"refcocog","model":"texthawk2","score":88.2,"metric":"percent"},{"benchmark":"refcoco","model":"ferret-v2-7b","score":92.8,"metric":"percent"},{"benchmark":"refcocoplus","model":"ferret-v2-7b","score":87.4,"metric":"percent"},{"benchmark":"refcocog","model":"ferret-v2-7b","score":89.4,"metric":"percent"},{"benchmark":"refcoco","model":"internvl2-8b","score":87.1,"metric":"percent"},{"benchmark":"refcocoplus","model":"internvl2-8b","score":79.8,"metric":"percent"},{"benchmark":"refcocog","model":"internvl2-8b","score":82.7,"metric":"percent"},{"benchmark":"refcoco","model":"qwen2-vl-7b","score":91.7,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen2-vl-7b","score":85.8,"metric":"percent"},{"benchmark":"refcocog","model":"qwen2-vl-7b","score":87.3,"metric":"percent"},{"benchmark":"refcoco","model":"deepseek-vl2","score":95.1,"metric":"percent"},{"benchmark":"refcocoplus","model":"deepseek-vl2","score":91.2,"metric":"percent"},{"benchmark":"refcocog","model":"deepseek-vl2","score":92.8,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2","score":78.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen-2.5-72b","score":79.8,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-405b-base","score":82.9,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v3-base","score":87.5,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2","score":78.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-2.5-72b","score":85,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-405b-base","score":84.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3-base","score":87.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v2","score":75.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen-2.5-72b","score":83.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3.1-405b-base","score":81.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3-base","score":86.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v2","score":51.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen-2.5-72b","score":58.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-405b-base","score":52.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3-base","score":64.4,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v2","score":80.4,"metric":"percent"},{"benchmark":"drop","model":"qwen-2.5-72b","score":80.6,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-405b-base","score":86,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v3-base","score":89,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-2.5-72b","score":98.4,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-3.1-405b-base","score":98.4,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-v3-base","score":98.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2","score":92.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-2.5-72b","score":94.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-405b-base","score":95.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v3-base","score":95.3,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v2","score":87.1,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-2.5-72b","score":84.8,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3.1-405b-base","score":89.2,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v3-base","score":88.9,"metric":"percent"},{"benchmark":"piqa","model":"deepseek-v2","score":83.9,"metric":"percent"},{"benchmark":"piqa","model":"qwen-2.5-72b","score":82.6,"metric":"percent"},{"benchmark":"piqa","model":"llama-3.1-405b-base","score":85.9,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v2","score":86.3,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-2.5-72b","score":82.3,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.1-405b-base","score":85.2,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v3-base","score":84.9,"metric":"percent"},{"benchmark":"race-middle","model":"qwen-2.5-72b","score":68.1,"metric":"percent"},{"benchmark":"race-middle","model":"llama-3.1-405b-base","score":74.2,"metric":"percent"},{"benchmark":"race-middle","model":"deepseek-v3-base","score":67.1,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-v2","score":52.6,"metric":"percent"},{"benchmark":"race-high","model":"qwen-2.5-72b","score":50.3,"metric":"percent"},{"benchmark":"race-high","model":"llama-3.1-405b-base","score":56.8,"metric":"percent"},{"benchmark":"race-high","model":"deepseek-v3-base","score":51.3,"metric":"percent"},{"benchmark":"triviaqa","model":"deepseek-v2","score":80,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen-2.5-72b","score":71.9,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-3.1-405b-base","score":82.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-v2","score":38.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-2.5-72b","score":33.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-3.1-405b-base","score":41.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"deepseek-v3-base","score":40,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v2","score":57.5,"metric":"percent"},{"benchmark":"agieval","model":"qwen-2.5-72b","score":75.8,"metric":"percent"},{"benchmark":"agieval","model":"llama-3.1-405b-base","score":60.6,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-v3-base","score":79.6,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2","score":43.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-2.5-72b","score":53,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-405b-base","score":54.9,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v3-base","score":65.2,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2","score":65,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-2.5-72b","score":72.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-405b-base","score":68.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v3-base","score":75.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2","score":11.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen-2.5-72b","score":12.9,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-405b-base","score":15.5,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3-base","score":19.4,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v2","score":52.5,"metric":"percent"},{"benchmark":"crux-i","model":"qwen-2.5-72b","score":59.1,"metric":"percent"},{"benchmark":"crux-i","model":"llama-3.1-405b-base","score":58.5,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-v3-base","score":67.3,"metric":"percent"},{"benchmark":"crux-o","model":"qwen-2.5-72b","score":59.9,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-v3-base","score":69.8,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v2","score":81.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-2.5-72b","score":88.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-405b-base","score":83.5,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-v3-base","score":89.3,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2","score":43.4,"metric":"percent"},{"benchmark":"math","model":"qwen-2.5-72b","score":54.4,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-405b-base","score":49,"metric":"percent"},{"benchmark":"math","model":"deepseek-v3-base","score":61.6,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v2","score":63.6,"metric":"percent"},{"benchmark":"mgsm","model":"qwen-2.5-72b","score":76.2,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.1-405b-base","score":69.9,"metric":"percent"},{"benchmark":"mgsm","model":"deepseek-v3-base","score":79.8,"metric":"percent"},{"benchmark":"cmath","model":"qwen-2.5-72b","score":84.5,"metric":"percent"},{"benchmark":"cmath","model":"llama-3.1-405b-base","score":77.3,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-v3-base","score":90.7,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v2","score":82,"metric":"percent"},{"benchmark":"cluewsc","model":"qwen-2.5-72b","score":82.5,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-3.1-405b-base","score":83,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v2","score":81.4,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-2.5-72b","score":89.2,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-2.5-72b","score":89.5,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-v3-base","score":88.8,"metric":"percent"},{"benchmark":"cmrc2018","model":"deepseek-v2","score":77.4,"metric":"percent"},{"benchmark":"cmrc2018","model":"qwen-2.5-72b","score":75.8,"metric":"percent"},{"benchmark":"cmrc2018","model":"llama-3.1-405b-base","score":76,"metric":"percent"},{"benchmark":"cmrc2018","model":"deepseek-v3-base","score":76.3,"metric":"percent"},{"benchmark":"c3","model":"qwen-2.5-72b","score":76.7,"metric":"percent"},{"benchmark":"c3","model":"llama-3.1-405b-base","score":79.7,"metric":"percent"},{"benchmark":"c3","model":"deepseek-v3-base","score":78.6,"metric":"percent"},{"benchmark":"ccpm","model":"deepseek-v2","score":93,"metric":"percent"},{"benchmark":"ccpm","model":"qwen-2.5-72b","score":88.5,"metric":"percent"},{"benchmark":"ccpm","model":"llama-3.1-405b-base","score":78.6,"metric":"percent"},{"benchmark":"ccpm","model":"deepseek-v3-base","score":92,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v2","score":64,"metric":"percent"},{"benchmark":"mmmlu","model":"qwen-2.5-72b","score":74.8,"metric":"percent"},{"benchmark":"mmmlu","model":"llama-3.1-405b-base","score":73.8,"metric":"percent"},{"benchmark":"mmmlu","model":"deepseek-v3-base","score":79.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2-chat","score":78.2,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2.5","score":80.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-72b-instruct","score":85.3,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-405b-instruct","score":88.6,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3.5-sonnet-20241022","score":88.3,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4o-2024-05-13","score":87.2,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v3","score":88.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v2-chat","score":77.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v2.5","score":80.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-72b-instruct","score":85.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3.1-405b-instruct","score":86.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"claude-3.5-sonnet-20241022","score":88.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4o-2024-05-13","score":88,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v3","score":89.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v2-chat","score":58.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v2.5","score":66.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-72b-instruct","score":71.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4o-2024-05-13","score":72.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-v3","score":75.9,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v2-chat","score":83,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v2.5","score":87.8,"metric":"percent"},{"benchmark":"drop","model":"qwen2.5-72b-instruct","score":76.7,"metric":"percent"},{"benchmark":"drop","model":"llama-3.1-405b-instruct","score":88.7,"metric":"percent"},{"benchmark":"drop","model":"claude-3.5-sonnet-20241022","score":88.3,"metric":"percent"},{"benchmark":"drop","model":"gpt-4o-2024-05-13","score":83.7,"metric":"percent"},{"benchmark":"drop","model":"deepseek-v3","score":91.6,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v2-chat","score":57.7,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v2.5","score":80.6,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-405b-instruct","score":86,"metric":"percent"},{"benchmark":"ifeval","model":"claude-3.5-sonnet-20241022","score":86.5,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4o-2024-05-13","score":84.3,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v3","score":86.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v2-chat","score":35.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v2.5","score":41.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-405b-instruct","score":51.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-3.5-sonnet-20241022","score":65,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-4o-2024-05-13","score":49.9,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-v3","score":59.1,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v2-chat","score":9,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v2.5","score":10.2,"metric":"percent"},{"benchmark":"simpleqa","model":"qwen2.5-72b-instruct","score":9.1,"metric":"percent"},{"benchmark":"simpleqa","model":"llama-3.1-405b-instruct","score":17.1,"metric":"percent"},{"benchmark":"simpleqa","model":"claude-3.5-sonnet-20241022","score":28.4,"metric":"percent"},{"benchmark":"simpleqa","model":"gpt-4o-2024-05-13","score":38.2,"metric":"percent"},{"benchmark":"simpleqa","model":"deepseek-v3","score":24.9,"metric":"percent"},{"benchmark":"frames","model":"deepseek-v2-chat","score":66.9,"metric":"percent"},{"benchmark":"frames","model":"deepseek-v2.5","score":65.4,"metric":"percent"},{"benchmark":"frames","model":"qwen2.5-72b-instruct","score":69.8,"metric":"percent"},{"benchmark":"frames","model":"llama-3.1-405b-instruct","score":70,"metric":"percent"},{"benchmark":"frames","model":"claude-3.5-sonnet-20241022","score":72.5,"metric":"percent"},{"benchmark":"frames","model":"gpt-4o-2024-05-13","score":80.5,"metric":"percent"},{"benchmark":"frames","model":"deepseek-v3","score":73.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v2-chat","score":31.6,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v2.5","score":35.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"qwen2.5-72b-instruct","score":39.4,"metric":"percent"},{"benchmark":"longbench-v2","model":"llama-3.1-405b-instruct","score":36.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"claude-3.5-sonnet-20241022","score":41,"metric":"percent"},{"benchmark":"longbench-v2","model":"gpt-4o-2024-05-13","score":48.1,"metric":"percent"},{"benchmark":"longbench-v2","model":"deepseek-v3","score":48.7,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-v2-chat","score":69.3,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-v2.5","score":77.4,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen2.5-72b-instruct","score":77.3,"metric":"percent"},{"benchmark":"humaneval-x","model":"llama-3.1-405b-instruct","score":77.2,"metric":"percent"},{"benchmark":"humaneval-x","model":"claude-3.5-sonnet-20241022","score":81.7,"metric":"percent"},{"benchmark":"humaneval-x","model":"gpt-4o-2024-05-13","score":80.5,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-v3","score":82.6,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2-chat","score":18.8,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2.5","score":29.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-72b-instruct","score":31.1,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-405b-instruct","score":28.4,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.5-sonnet-20241022","score":36.3,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o-2024-05-13","score":33.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3","score":40.5,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2-chat","score":20.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2.5","score":28.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-72b-instruct","score":28.7,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-405b-instruct","score":30.1,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.5-sonnet-20241022","score":32.8,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o-2024-05-13","score":34.2,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v3","score":37.6,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"deepseek-v2-chat","score":17.5,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"deepseek-v2.5","score":35.6,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"qwen2.5-72b-instruct","score":24.8,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"llama-3.1-405b-instruct","score":25.3,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"claude-3.5-sonnet-20241022","score":20.3,"metric":"percent"},{"benchmark":"codeforces-percentile","model":"gpt-4o-2024-05-13","score":23.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v2.5","score":22.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen2.5-72b-instruct","score":23.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"llama-3.1-405b-instruct","score":24.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"claude-3.5-sonnet-20241022","score":50.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gpt-4o-2024-05-13","score":38.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v3","score":42,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-v2-chat","score":60.3,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-v2.5","score":71.6,"metric":"percent"},{"benchmark":"aider-code-editing","model":"qwen2.5-72b-instruct","score":65.4,"metric":"percent"},{"benchmark":"aider-code-editing","model":"llama-3.1-405b-instruct","score":63.9,"metric":"percent"},{"benchmark":"aider-code-editing","model":"claude-3.5-sonnet-20241022","score":84.2,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-v3","score":79.7,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v2.5","score":18.2,"metric":"percent"},{"benchmark":"aider-polyglot","model":"qwen2.5-72b-instruct","score":7.6,"metric":"percent"},{"benchmark":"aider-polyglot","model":"llama-3.1-405b-instruct","score":5.8,"metric":"percent"},{"benchmark":"aider-polyglot","model":"claude-3.5-sonnet-20241022","score":45.3,"metric":"percent"},{"benchmark":"aider-polyglot","model":"gpt-4o-2024-05-13","score":16,"metric":"percent"},{"benchmark":"aider-polyglot","model":"deepseek-v3","score":49.6,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v2-chat","score":4.6,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v2.5","score":16.7,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-72b-instruct","score":23.3,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.1-405b-instruct","score":23.3,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-3.5-sonnet-20241022","score":16,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4o-2024-05-13","score":9.3,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-v3","score":39.2,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v2-chat","score":56.3,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v2.5","score":74.7,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-72b-instruct","score":80,"metric":"percent"},{"benchmark":"math500","model":"llama-3.1-405b-instruct","score":73.8,"metric":"percent"},{"benchmark":"math500","model":"claude-3.5-sonnet-20241022","score":78.3,"metric":"percent"},{"benchmark":"math500","model":"gpt-4o-2024-05-13","score":74.6,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v3","score":90.2,"metric":"percent"},{"benchmark":"cnmo-2024","model":"deepseek-v2-chat","score":2.8,"metric":"percent"},{"benchmark":"cnmo-2024","model":"deepseek-v2.5","score":10.8,"metric":"percent"},{"benchmark":"cnmo-2024","model":"qwen2.5-72b-instruct","score":15.9,"metric":"percent"},{"benchmark":"cnmo-2024","model":"llama-3.1-405b-instruct","score":6.8,"metric":"percent"},{"benchmark":"cnmo-2024","model":"claude-3.5-sonnet-20241022","score":13.1,"metric":"percent"},{"benchmark":"cnmo-2024","model":"gpt-4o-2024-05-13","score":10.8,"metric":"percent"},{"benchmark":"cnmo-2024","model":"deepseek-v3","score":43.2,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v2.5","score":90.4,"metric":"percent"},{"benchmark":"cluewsc","model":"qwen2.5-72b-instruct","score":91.4,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-3.1-405b-instruct","score":84.7,"metric":"percent"},{"benchmark":"cluewsc","model":"claude-3.5-sonnet-20241022","score":85.4,"metric":"percent"},{"benchmark":"cluewsc","model":"gpt-4o-2024-05-13","score":87.9,"metric":"percent"},{"benchmark":"cluewsc","model":"deepseek-v3","score":90.9,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v2-chat","score":78.6,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v2.5","score":79.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2.5-72b-instruct","score":86.1,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3.1-405b-instruct","score":61.5,"metric":"percent"},{"benchmark":"c-eval","model":"claude-3.5-sonnet-20241022","score":76.7,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-4o-2024-05-13","score":76,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-v3","score":86.5,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v2-chat","score":48.5,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v2.5","score":54.1,"metric":"percent"},{"benchmark":"csimpleqa","model":"qwen2.5-72b-instruct","score":48.4,"metric":"percent"},{"benchmark":"csimpleqa","model":"llama-3.1-405b-instruct","score":50.4,"metric":"percent"},{"benchmark":"csimpleqa","model":"claude-3.5-sonnet-20241022","score":51.3,"metric":"percent"},{"benchmark":"csimpleqa","model":"gpt-4o-2024-05-13","score":59.3,"metric":"percent"},{"benchmark":"csimpleqa","model":"deepseek-v3","score":64.8,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-v2.5","score":76.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-v2.5","score":50.5,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2.5-72b-instruct","score":81.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen2.5-72b-instruct","score":49.1,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3.1-405b-instruct","score":69.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-405b-instruct","score":40.5,"metric":"percent"},{"benchmark":"arena-hard","model":"gpt-4o-2024-05-13","score":80.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"gpt-4o-2024-05-13","score":51.1,"metric":"percent"},{"benchmark":"arena-hard","model":"claude-3.5-sonnet-20241022","score":85.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"claude-3.5-sonnet-20241022","score":52,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-v3","score":85.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-v3","score":70,"metric":"percent"},{"benchmark":"rewardbench","model":"gpt-4o-2024-05-13","score":84.7,"metric":"percent"},{"benchmark":"rewardbench","model":"gpt-4o-2024-11-20","score":84.6,"metric":"percent"},{"benchmark":"rewardbench","model":"claude-3.5-sonnet-20241022","score":88.7,"metric":"percent"},{"benchmark":"rewardbench","model":"deepseek-v3","score":87,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-v2-chat-0628","score":46.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"deepseek-coder-v2-instruct-0724","score":44.5,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-v2-chat-0628","score":68.3,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-coder-v2-instruct-0724","score":66.3,"metric":"percent"},{"benchmark":"alignbench","model":"deepseek-v2-chat-0628","score":7.88,"metric":"score"},{"benchmark":"alignbench","model":"deepseek-coder-v2-instruct-0724","score":7.91,"metric":"score"},{"benchmark":"alignbench","model":"deepseek-v2.5","score":8.04,"metric":"score"},{"benchmark":"mt-bench","model":"deepseek-v2-chat-0628","score":8.85,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-coder-v2-instruct-0724","score":8.91,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-v2.5","score":9.02,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2-chat-0628","score":84.5,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-v2-instruct-0724","score":87.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2.5","score":89,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-v2-chat-0628","score":73.8,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-coder-v2-instruct-0724","score":74.8,"metric":"percent"},{"benchmark":"humaneval-x","model":"deepseek-v2.5","score":73.8,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2-chat-0628","score":36.6,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-coder-v2-instruct-0724","score":39.7,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2.5","score":41.8,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-v2-chat-0628","score":69.9,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-coder-v2-instruct-0724","score":72.9,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-v2.5","score":72.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-coder-v2-instruct-0724","score":19,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"deepseek-v2.5","score":16.8,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2-chat-0628","score":84.8,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2-chat-0628","score":71,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2-chat-0628","score":83.4,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v2-chat-0628","score":77.6,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v2.5","score":74.8,"metric":"percent"},{"benchmark":"math500","model":"deepseek-v2.5-1210","score":82.8,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2.5-1210","score":34.38,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-r1-lite-preview","score":52.5,"metric":"percent"},{"benchmark":"aime-2024","model":"o1-preview","score":44.6,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4o","score":9.3,"metric":"percent"},{"benchmark":"math","model":"deepseek-r1-lite-preview","score":91.6,"metric":"percent"},{"benchmark":"math","model":"o1-preview","score":85.5,"metric":"percent"},{"benchmark":"math","model":"gpt-4o","score":76.6,"metric":"percent"},{"benchmark":"math","model":"claude-3.5-sonnet-20241022","score":78.3,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-72b-instruct","score":83.1,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2.5","score":74.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"deepseek-r1-lite-preview","score":58.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o1-preview","score":73.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-4o","score":53.6,"metric":"percent"},{"benchmark":"codeforces","model":"deepseek-r1-lite-preview","score":1450,"metric":"ELO"},{"benchmark":"codeforces","model":"o1-preview","score":1428,"metric":"ELO"},{"benchmark":"codeforces","model":"gpt-4o","score":759,"metric":"ELO"},{"benchmark":"codeforces","model":"claude-3.5-sonnet-20241022","score":717,"metric":"ELO"},{"benchmark":"codeforces","model":"qwen2.5-72b-instruct","score":732,"metric":"ELO"},{"benchmark":"codeforces","model":"deepseek-v2.5","score":882,"metric":"ELO"},{"benchmark":"livecodebench","model":"deepseek-r1-lite-preview","score":51.6,"metric":"percent"},{"benchmark":"livecodebench","model":"o1-preview","score":53.6,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o","score":33.4,"metric":"percent"},{"benchmark":"zebralogic","model":"deepseek-r1-lite-preview","score":56.6,"metric":"percent"},{"benchmark":"zebralogic","model":"o1-preview","score":71.4,"metric":"percent"},{"benchmark":"zebralogic","model":"gpt-4o","score":28.2,"metric":"percent"},{"benchmark":"zebralogic","model":"claude-3.5-sonnet-20241022","score":33.4,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x22b","score":77.8,"metric":"percent"},{"benchmark":"mmlu","model":"hunyuan-large","score":88.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mixtral-8x22b","score":49.5,"metric":"percent"},{"benchmark":"bbh","model":"hunyuan-large","score":86.3,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x22b","score":88.7,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v2","score":87.8,"metric":"percent"},{"benchmark":"hellaswag","model":"hunyuan-large","score":86.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"mixtral-8x22b","score":82.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"hunyuan-large","score":92.9,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3.1-70b-base","score":85.3,"metric":"percent"},{"benchmark":"winogrande","model":"mixtral-8x22b","score":85,"metric":"percent"},{"benchmark":"winogrande","model":"hunyuan-large","score":88.7,"metric":"percent"},{"benchmark":"piqa","model":"hunyuan-large","score":88.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"hunyuan-large","score":52.8,"metric":"percent"},{"benchmark":"drop","model":"hunyuan-large","score":88.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"hunyuan-large","score":95,"metric":"percent"},{"benchmark":"triviaqa","model":"hunyuan-large","score":89.2,"metric":"percent"},{"benchmark":"cmmlu","model":"hunyuan-large","score":90.2,"metric":"percent"},{"benchmark":"c-eval","model":"hunyuan-large","score":91.9,"metric":"percent"},{"benchmark":"c3","model":"hunyuan-large","score":82.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b-base","score":83.7,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b","score":83.7,"metric":"percent"},{"benchmark":"gsm8k","model":"hunyuan-large","score":92.8,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-405b-base","score":53.8,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-70b-base","score":41.4,"metric":"percent"},{"benchmark":"math","model":"hunyuan-large","score":69.8,"metric":"percent"},{"benchmark":"cmath","model":"hunyuan-large","score":91.3,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-405b-base","score":61,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-70b-base","score":58.5,"metric":"percent"},{"benchmark":"humaneval","model":"hunyuan-large","score":71.4,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-405b-base","score":73.4,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-70b-base","score":68.6,"metric":"percent"},{"benchmark":"mbpp","model":"hunyuan-large","score":72.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-405b-instruct","score":87.3,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-70b-instruct","score":83.6,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-v2.5","score":80.4,"metric":"percent"},{"benchmark":"mmlu","model":"hunyuan-large-instruct","score":89.9,"metric":"percent"},{"benchmark":"cmmlu","model":"hunyuan-large-instruct","score":90.4,"metric":"percent"},{"benchmark":"c-eval","model":"hunyuan-large-instruct","score":88.6,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-v2.5","score":84.3,"metric":"percent"},{"benchmark":"bbh","model":"hunyuan-large-instruct","score":89.5,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x22b-instruct-v0.1","score":86,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-v2.5","score":90.3,"metric":"percent"},{"benchmark":"hellaswag","model":"hunyuan-large-instruct","score":88.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-405b-instruct","score":96.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3.1-70b-instruct","score":94.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"hunyuan-large-instruct","score":94.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"llama-3.1-70b-instruct","score":46.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"hunyuan-large-instruct","score":42.4,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-405b-instruct","score":73.8,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-70b-instruct","score":68,"metric":"percent"},{"benchmark":"math","model":"hunyuan-large-instruct","score":77.4,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-405b-instruct","score":89,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-70b-instruct","score":80.5,"metric":"percent"},{"benchmark":"humaneval","model":"hunyuan-large-instruct","score":90,"metric":"percent"},{"benchmark":"alignbench","model":"llama-3.1-405b-instruct","score":6,"metric":"score"},{"benchmark":"alignbench","model":"llama-3.1-70b-instruct","score":5.9,"metric":"score"},{"benchmark":"alignbench","model":"mixtral-8x22b-instruct-v0.1","score":6.2,"metric":"score"},{"benchmark":"alignbench","model":"deepseek-v2.5","score":8,"metric":"score"},{"benchmark":"alignbench","model":"hunyuan-large-instruct","score":8.3,"metric":"score"},{"benchmark":"mt-bench","model":"llama-3.1-405b-instruct","score":9.1,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.1-70b-instruct","score":8.8,"metric":"percent"},{"benchmark":"mt-bench","model":"mixtral-8x22b-instruct-v0.1","score":8.1,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-v2.5","score":9,"metric":"percent"},{"benchmark":"mt-bench","model":"hunyuan-large-instruct","score":9.4,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llama-3.1-405b-instruct","score":86,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llama-3.1-70b-instruct","score":83.6,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"mixtral-8x22b-instruct-v0.1","score":71.2,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"hunyuan-large-instruct","score":85,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3.1-70b-instruct","score":55.7,"metric":"percent"},{"benchmark":"arena-hard","model":"hunyuan-large-instruct","score":81.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-405b-instruct","score":39.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-3.1-70b-instruct","score":34.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"hunyuan-large-instruct","score":51.8,"metric":"percent"},{"benchmark":"penguinscrolls","model":"llama-3.1-70b-instruct","score":69.37,"metric":"percent"},{"benchmark":"penguinscrolls","model":"hunyuan-large-instruct","score":85.23,"metric":"percent"},{"benchmark":"c-eval","model":"open-llama-13b","score":27.1,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-13b","score":35.5,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b","score":36.5,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan-13b-base","score":52.4,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-base","score":58.1,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-13b","score":54.7,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-20b","score":58.8,"metric":"percent"},{"benchmark":"c-eval","model":"skywork-13b-base","score":60.6,"metric":"percent"},{"benchmark":"cmmlu","model":"open-llama-13b","score":26.7,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-1-13b","score":31.2,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b","score":36.6,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan-13b-base","score":55.3,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-base","score":62,"metric":"percent"},{"benchmark":"cmmlu","model":"skywork-13b-base","score":61.8,"metric":"percent"},{"benchmark":"mmlu","model":"open-llama-13b","score":42.7,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-13b","score":46.9,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan-13b-base","score":51.6,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-base","score":59.2,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-13b","score":55.1,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-20b","score":62,"metric":"percent"},{"benchmark":"mmlu","model":"skywork-13b-base","score":62.1,"metric":"percent"},{"benchmark":"gsm8k","model":"open-llama-13b","score":12.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-13b","score":17.8,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan-13b-base","score":26.6,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-base","score":52.8,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-20b","score":52.6,"metric":"percent"},{"benchmark":"gsm8k","model":"skywork-13b-base","score":55.8,"metric":"percent"},{"benchmark":"boolq","model":"open-llama-13b","score":77.6,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-13b","score":80.7,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-13b","score":83.3,"metric":"percent"},{"benchmark":"boolq","model":"baichuan-13b-base","score":78.8,"metric":"percent"},{"benchmark":"boolq","model":"baichuan2-13b-base","score":80.3,"metric":"percent"},{"benchmark":"boolq","model":"xverse-13b","score":79.8,"metric":"percent"},{"benchmark":"boolq","model":"skywork-13b-base","score":82.9,"metric":"percent"},{"benchmark":"piqa","model":"open-llama-13b","score":79.5,"metric":"percent"},{"benchmark":"piqa","model":"llama-1-13b","score":81,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-13b","score":81.7,"metric":"percent"},{"benchmark":"piqa","model":"baichuan-13b-base","score":77.2,"metric":"percent"},{"benchmark":"piqa","model":"baichuan2-13b-base","score":79.3,"metric":"percent"},{"benchmark":"piqa","model":"xverse-13b","score":80,"metric":"percent"},{"benchmark":"piqa","model":"skywork-13b-base","score":79.9,"metric":"percent"},{"benchmark":"winogrande","model":"open-llama-13b","score":72,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1-13b","score":76.2,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-13b","score":75.8,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan-13b-base","score":70.4,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan2-13b-base","score":72.1,"metric":"percent"},{"benchmark":"winogrande","model":"xverse-13b","score":71.1,"metric":"percent"},{"benchmark":"winogrande","model":"skywork-13b-base","score":72.2,"metric":"percent"},{"benchmark":"triviaqa","model":"open-llama-13b","score":60.2,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-1-13b","score":65,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-13b","score":68.2,"metric":"percent"},{"benchmark":"triviaqa","model":"baichuan-13b-base","score":51.6,"metric":"percent"},{"benchmark":"triviaqa","model":"baichuan2-13b-base","score":58,"metric":"percent"},{"benchmark":"triviaqa","model":"xverse-13b","score":53.3,"metric":"percent"},{"benchmark":"triviaqa","model":"skywork-13b-base","score":54,"metric":"percent"},{"benchmark":"race","model":"open-llama-13b","score":42.4,"metric":"percent"},{"benchmark":"race","model":"llama-1-13b","score":43.4,"metric":"percent"},{"benchmark":"race","model":"llama-2-13b","score":43.9,"metric":"percent"},{"benchmark":"race","model":"baichuan-13b-base","score":35.8,"metric":"percent"},{"benchmark":"race","model":"baichuan2-13b-base","score":25.2,"metric":"percent"},{"benchmark":"race","model":"xverse-13b","score":43.2,"metric":"percent"},{"benchmark":"race","model":"skywork-13b-base","score":45.2,"metric":"percent"},{"benchmark":"hellaswag","model":"open-llama-13b","score":76,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-1-13b","score":80.1,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-13b","score":81.5,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan-13b-base","score":74.2,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-13b-base","score":76.4,"metric":"percent"},{"benchmark":"hellaswag","model":"xverse-13b","score":77.2,"metric":"percent"},{"benchmark":"hellaswag","model":"skywork-13b-base","score":77.4,"metric":"percent"},{"benchmark":"arc-easy","model":"open-llama-13b","score":78.9,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-1-13b","score":82.1,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-13b","score":83.7,"metric":"percent"},{"benchmark":"arc-easy","model":"baichuan-13b-base","score":77.2,"metric":"percent"},{"benchmark":"arc-easy","model":"baichuan2-13b-base","score":81.1,"metric":"percent"},{"benchmark":"arc-easy","model":"xverse-13b","score":78.5,"metric":"percent"},{"benchmark":"arc-easy","model":"skywork-13b-base","score":78.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"open-llama-13b","score":48.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-1-13b","score":54.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-13b","score":57,"metric":"percent"},{"benchmark":"arc-challenge","model":"baichuan-13b-base","score":48.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"baichuan2-13b-base","score":53.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"xverse-13b","score":49.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"skywork-13b-base","score":50.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b","score":72.1,"metric":"percent"},{"benchmark":"c-eval","model":"aquila2-34b","score":63.1,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-14b","score":71,"metric":"percent"},{"benchmark":"cmmlu","model":"aquila2-34b","score":71.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b","score":66.3,"metric":"percent"},{"benchmark":"mmlu","model":"aquila2-34b","score":64.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b","score":61.3,"metric":"percent"},{"benchmark":"gsm8k","model":"aquila2-34b","score":58.4,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-base","score":52.3,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan-13b-base","score":26.76,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-base","score":52.77,"metric":"percent"},{"benchmark":"gsm8k","model":"wizardmath-13b-v1.0","score":63.9,"metric":"percent"},{"benchmark":"gsm8k","model":"gair-abel-13b","score":66.41,"metric":"percent"},{"benchmark":"gsm8k","model":"metamath-13b","score":72.3,"metric":"percent"},{"benchmark":"gsm8k","model":"skywork-13b-math","score":72.33,"metric":"percent"},{"benchmark":"math","model":"llama-1-13b","score":3.9,"metric":"percent"},{"benchmark":"math","model":"llama-2-13b","score":3.9,"metric":"percent"},{"benchmark":"math","model":"baichuan-13b-base","score":4.84,"metric":"percent"},{"benchmark":"math","model":"baichuan2-13b-base","score":10.08,"metric":"percent"},{"benchmark":"math","model":"wizardmath-13b-v1.0","score":14,"metric":"percent"},{"benchmark":"math","model":"gair-abel-13b","score":17.34,"metric":"percent"},{"benchmark":"math","model":"metamath-13b","score":22.4,"metric":"percent"},{"benchmark":"math","model":"skywork-13b-math","score":16.98,"metric":"percent"},{"benchmark":"cmath","model":"baichuan-13b-base","score":51.33,"metric":"percent"},{"benchmark":"cmath","model":"wizardmath-13b-v1.0","score":50.83,"metric":"percent"},{"benchmark":"cmath","model":"skywork-13b-math","score":77.27,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-72b","score":84.1,"metric":"percent"},{"benchmark":"c-eval","model":"skywork-13b-base","score":62.1,"metric":"percent"},{"benchmark":"c-eval","model":"skywork-moe-base","score":82.2,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-72b","score":83.5,"metric":"percent"},{"benchmark":"cmmlu","model":"skywork-13b-base","score":62.4,"metric":"percent"},{"benchmark":"cmmlu","model":"skywork-moe-base","score":79.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-72b","score":77.5,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-70b","score":78.8,"metric":"percent"},{"benchmark":"mmlu","model":"grok-1","score":73,"metric":"percent"},{"benchmark":"mmlu","model":"dbrx-instruct-preview","score":73.7,"metric":"percent"},{"benchmark":"mmlu","model":"skywork-13b-base","score":62.7,"metric":"percent"},{"benchmark":"mmlu","model":"skywork-moe-base","score":77.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-72b","score":79.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b","score":82.7,"metric":"percent"},{"benchmark":"gsm8k","model":"dbrx-instruct-preview","score":66.9,"metric":"percent"},{"benchmark":"gsm8k","model":"skywork-13b-base","score":60.2,"metric":"percent"},{"benchmark":"gsm8k","model":"skywork-moe-base","score":76.1,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-72b","score":34.1,"metric":"percent"},{"benchmark":"math","model":"llama-2-70b","score":13.6,"metric":"percent"},{"benchmark":"math","model":"llama-3-70b","score":36.7,"metric":"percent"},{"benchmark":"math","model":"skywork-13b-base","score":8.4,"metric":"percent"},{"benchmark":"math","model":"skywork-moe-base","score":31.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-72b","score":41.5,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b","score":39,"metric":"percent"},{"benchmark":"humaneval","model":"grok-1","score":63.2,"metric":"percent"},{"benchmark":"humaneval","model":"dbrx-instruct-preview","score":70.1,"metric":"percent"},{"benchmark":"humaneval","model":"skywork-13b-base","score":18.9,"metric":"percent"},{"benchmark":"humaneval","model":"skywork-moe-base","score":43.9,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b","score":41.4,"metric":"percent"},{"benchmark":"c-eval","model":"skywork-13b-base","score":59.1,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-base","score":59,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b","score":71.7,"metric":"percent"},{"benchmark":"c-eval","model":"orion-14b-base","score":72.9,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b","score":38.4,"metric":"percent"},{"benchmark":"cmmlu","model":"skywork-13b-base","score":61.4,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-base","score":61.3,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-14b","score":70.2,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm-20b","score":59,"metric":"percent"},{"benchmark":"cmmlu","model":"orion-14b-base","score":70.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b","score":55,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-base","score":59.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b","score":67.9,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-20b","score":62.1,"metric":"percent"},{"benchmark":"mmlu","model":"orion-14b-base","score":69.9,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-13b","score":30.9,"metric":"percent"},{"benchmark":"agieval","model":"skywork-13b-base","score":43.6,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-13b-base","score":37.4,"metric":"percent"},{"benchmark":"agieval","model":"qwen-14b","score":51.9,"metric":"percent"},{"benchmark":"agieval","model":"internlm-20b","score":44.6,"metric":"percent"},{"benchmark":"agieval","model":"orion-14b-base","score":54.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-13b","score":18.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"skywork-13b-base","score":56.1,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-13b-base","score":45.6,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-14b","score":62.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm-20b","score":45.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"orion-14b-base","score":62.1,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b","score":45.6,"metric":"percent"},{"benchmark":"bbh","model":"skywork-13b-base","score":48.3,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-base","score":49,"metric":"percent"},{"benchmark":"bbh","model":"qwen-14b","score":53.7,"metric":"percent"},{"benchmark":"bbh","model":"internlm-20b","score":52.5,"metric":"percent"},{"benchmark":"bbh","model":"orion-14b-base","score":56.5,"metric":"percent"},{"benchmark":"race-high","model":"llama-2-13b","score":58.9,"metric":"percent"},{"benchmark":"race-high","model":"skywork-13b-base","score":84.1,"metric":"percent"},{"benchmark":"race-high","model":"baichuan2-13b-base","score":67.2,"metric":"percent"},{"benchmark":"race-high","model":"qwen-14b","score":90.3,"metric":"percent"},{"benchmark":"race-high","model":"internlm-20b","score":83.3,"metric":"percent"},{"benchmark":"race-high","model":"orion-14b-base","score":91.3,"metric":"percent"},{"benchmark":"race-middle","model":"llama-2-13b","score":63,"metric":"percent"},{"benchmark":"race-middle","model":"skywork-13b-base","score":87.6,"metric":"percent"},{"benchmark":"race-middle","model":"baichuan2-13b-base","score":68.9,"metric":"percent"},{"benchmark":"race-middle","model":"qwen-14b","score":93,"metric":"percent"},{"benchmark":"race-middle","model":"internlm-20b","score":86.4,"metric":"percent"},{"benchmark":"race-middle","model":"orion-14b-base","score":93.2,"metric":"percent"},{"benchmark":"chid","model":"llama-2-13b","score":53,"metric":"percent"},{"benchmark":"chid","model":"skywork-13b-base","score":88.1,"metric":"percent"},{"benchmark":"chid","model":"baichuan2-13b-base","score":83.2,"metric":"percent"},{"benchmark":"chid","model":"qwen-14b","score":84.7,"metric":"percent"},{"benchmark":"chid","model":"internlm-20b","score":81.7,"metric":"percent"},{"benchmark":"chid","model":"orion-14b-base","score":90.1,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-13b","score":77.5,"metric":"percent"},{"benchmark":"hellaswag","model":"skywork-13b-base","score":73.7,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-13b-base","score":70.8,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-14b","score":80.2,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm-20b","score":78.1,"metric":"percent"},{"benchmark":"hellaswag","model":"orion-14b-base","score":78.5,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-13b","score":79.8,"metric":"percent"},{"benchmark":"piqa","model":"skywork-13b-base","score":78.3,"metric":"percent"},{"benchmark":"piqa","model":"baichuan2-13b-base","score":78.1,"metric":"percent"},{"benchmark":"piqa","model":"qwen-14b","score":79.8,"metric":"percent"},{"benchmark":"piqa","model":"internlm-20b","score":80.3,"metric":"percent"},{"benchmark":"piqa","model":"orion-14b-base","score":79.5,"metric":"percent"},{"benchmark":"lambada","model":"llama-2-13b","score":76.5,"metric":"percent"},{"benchmark":"lambada","model":"skywork-13b-base","score":71.8,"metric":"percent"},{"benchmark":"lambada","model":"baichuan2-13b-base","score":74.1,"metric":"percent"},{"benchmark":"lambada","model":"qwen-14b","score":71.4,"metric":"percent"},{"benchmark":"lambada","model":"internlm-20b","score":71.8,"metric":"percent"},{"benchmark":"lambada","model":"orion-14b-base","score":78.8,"metric":"percent"},{"benchmark":"wsc","model":"llama-2-13b","score":66.3,"metric":"percent"},{"benchmark":"wsc","model":"skywork-13b-base","score":66.3,"metric":"percent"},{"benchmark":"wsc","model":"baichuan2-13b-base","score":66.3,"metric":"percent"},{"benchmark":"wsc","model":"qwen-14b","score":66.3,"metric":"percent"},{"benchmark":"wsc","model":"internlm-20b","score":68.3,"metric":"percent"},{"benchmark":"wsc","model":"orion-14b-base","score":70.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-13b","score":60.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"skywork-13b-base","score":65.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"baichuan2-13b-base","score":38,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-14b","score":84.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"internlm-20b","score":81.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"orion-14b-base","score":80.7,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-13b","score":71.8,"metric":"percent"},{"benchmark":"arc-easy","model":"skywork-13b-base","score":79.5,"metric":"percent"},{"benchmark":"arc-easy","model":"baichuan2-13b-base","score":61.9,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-14b","score":90.1,"metric":"percent"},{"benchmark":"arc-easy","model":"internlm-20b","score":86.1,"metric":"percent"},{"benchmark":"arc-easy","model":"orion-14b-base","score":88.9,"metric":"percent"},{"benchmark":"tydiqa","model":"llama-2-13b","score":33.2,"metric":"percent"},{"benchmark":"tydiqa","model":"skywork-13b-base","score":27.9,"metric":"percent"},{"benchmark":"tydiqa","model":"baichuan2-13b-base","score":30.8,"metric":"percent"},{"benchmark":"tydiqa","model":"qwen-14b","score":39.8,"metric":"percent"},{"benchmark":"tydiqa","model":"internlm-20b","score":43.2,"metric":"percent"},{"benchmark":"tydiqa","model":"orion-14b-base","score":32.7,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-13b","score":82.4,"metric":"percent"},{"benchmark":"boolq","model":"skywork-13b-base","score":80.9,"metric":"percent"},{"benchmark":"boolq","model":"baichuan2-13b-base","score":67,"metric":"percent"},{"benchmark":"boolq","model":"qwen-14b","score":86.1,"metric":"percent"},{"benchmark":"boolq","model":"internlm-20b","score":87.5,"metric":"percent"},{"benchmark":"boolq","model":"orion-14b-base","score":84.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-2-13b","score":66.7,"metric":"percent"},{"benchmark":"commonsenseqa","model":"skywork-13b-base","score":64.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"baichuan2-13b-base","score":65.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen-14b","score":70.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"internlm-20b","score":70.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"orion-14b-base","score":65.7,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-13b","score":59.4,"metric":"percent"},{"benchmark":"triviaqa","model":"skywork-13b-base","score":48.1,"metric":"percent"},{"benchmark":"triviaqa","model":"baichuan2-13b-base","score":46.6,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen-14b","score":48.4,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm-20b","score":57.3,"metric":"percent"},{"benchmark":"triviaqa","model":"orion-14b-base","score":77.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-13b","score":24.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"skywork-13b-base","score":17.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"baichuan2-13b-base","score":16.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-14b","score":19.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm-20b","score":25.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"orion-14b-base","score":12.4,"metric":"percent"},{"benchmark":"c3","model":"llama-2-13b","score":46.1,"metric":"percent"},{"benchmark":"c3","model":"skywork-13b-base","score":64.9,"metric":"percent"},{"benchmark":"c3","model":"baichuan2-13b-base","score":65.6,"metric":"percent"},{"benchmark":"c3","model":"qwen-14b","score":90.8,"metric":"percent"},{"benchmark":"c3","model":"internlm-20b","score":73.7,"metric":"percent"},{"benchmark":"c3","model":"orion-14b-base","score":80.2,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-13b","score":65,"metric":"percent"},{"benchmark":"openbookqa","model":"skywork-13b-base","score":83.4,"metric":"percent"},{"benchmark":"openbookqa","model":"baichuan2-13b-base","score":65,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen-14b","score":94.8,"metric":"percent"},{"benchmark":"openbookqa","model":"internlm-20b","score":87.6,"metric":"percent"},{"benchmark":"openbookqa","model":"orion-14b-base","score":89.8,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-13b","score":34.1,"metric":"percent"},{"benchmark":"ocnli","model":"skywork-13b-base","score":30,"metric":"percent"},{"benchmark":"ocnli","model":"baichuan2-13b-base","score":30,"metric":"percent"},{"benchmark":"ocnli","model":"qwen-14b","score":58.2,"metric":"percent"},{"benchmark":"ocnli","model":"internlm-20b","score":42.5,"metric":"percent"},{"benchmark":"ocnli","model":"orion-14b-base","score":68.3,"metric":"percent"},{"benchmark":"copa","model":"llama-2-13b","score":70,"metric":"percent"},{"benchmark":"copa","model":"skywork-13b-base","score":72,"metric":"percent"},{"benchmark":"copa","model":"baichuan2-13b-base","score":71,"metric":"percent"},{"benchmark":"copa","model":"qwen-14b","score":93,"metric":"percent"},{"benchmark":"copa","model":"internlm-20b","score":83,"metric":"percent"},{"benchmark":"copa","model":"orion-14b-base","score":82,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-13b","score":54.8,"metric":"percent"},{"benchmark":"siqa","model":"skywork-13b-base","score":70.4,"metric":"percent"},{"benchmark":"siqa","model":"baichuan2-13b-base","score":44.3,"metric":"percent"},{"benchmark":"siqa","model":"qwen-14b","score":78.1,"metric":"percent"},{"benchmark":"siqa","model":"internlm-20b","score":72.8,"metric":"percent"},{"benchmark":"siqa","model":"orion-14b-base","score":69.4,"metric":"percent"},{"benchmark":"math","model":"llama-2-13b","score":5,"metric":"percent"},{"benchmark":"math","model":"skywork-13b-base","score":9.8,"metric":"percent"},{"benchmark":"math","model":"baichuan2-13b-base","score":10.1,"metric":"percent"},{"benchmark":"math","model":"qwen-14b","score":25.2,"metric":"percent"},{"benchmark":"math","model":"internlm-20b","score":7.9,"metric":"percent"},{"benchmark":"math","model":"orion-14b-base","score":7.78,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b","score":29.6,"metric":"percent"},{"benchmark":"gsm8k","model":"skywork-13b-base","score":54.3,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-base","score":52.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b","score":61.6,"metric":"percent"},{"benchmark":"gsm8k","model":"orion-14b-base","score":51.9,"metric":"percent"},{"benchmark":"drop","model":"llama-2-13b","score":46.4,"metric":"percent"},{"benchmark":"drop","model":"skywork-13b-base","score":41.7,"metric":"percent"},{"benchmark":"drop","model":"baichuan2-13b-base","score":45,"metric":"percent"},{"benchmark":"drop","model":"qwen-14b","score":53.6,"metric":"percent"},{"benchmark":"drop","model":"internlm-20b","score":46,"metric":"percent"},{"benchmark":"drop","model":"orion-14b-base","score":40.8,"metric":"percent"},{"benchmark":"humaneval","model":"skywork-13b-base","score":15.9,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-13b-base","score":17.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-14b","score":32.3,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-20b","score":25.6,"metric":"percent"},{"benchmark":"humaneval","model":"orion-14b-base","score":20.7,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-13b","score":26.8,"metric":"percent"},{"benchmark":"mbpp","model":"skywork-13b-base","score":25.4,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-13b-base","score":30.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-14b","score":39.8,"metric":"percent"},{"benchmark":"mbpp","model":"internlm-20b","score":35.6,"metric":"percent"},{"benchmark":"mbpp","model":"orion-14b-base","score":29,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-4","score":69.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-72b","score":83.3,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b","score":81.8,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-4","score":71,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-72b","score":61.8,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-34b","score":82.6,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4","score":83,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-72b","score":77.3,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b","score":76.3,"metric":"percent"},{"benchmark":"lambada","model":"gpt-4","score":65.5,"metric":"percent"},{"benchmark":"lambada","model":"qwen-72b","score":76.1,"metric":"percent"},{"benchmark":"lambada","model":"yi-34b","score":73.1,"metric":"percent"},{"benchmark":"hellaswag","model":"gpt-4","score":91.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-72b","score":85.4,"metric":"percent"},{"benchmark":"hellaswag","model":"yi-34b","score":82,"metric":"percent"},{"benchmark":"c-eval","model":"orion-14b-base","score":72.8,"metric":"percent"},{"benchmark":"mmlu","model":"orion-14b-base","score":70,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-chat","score":58.4,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-14b-chat","score":70,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b-chat","score":38.7,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm-chat-20b","score":52.2,"metric":"percent"},{"benchmark":"cmmlu","model":"orion-14b-chat","score":63.9,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-chat","score":57,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b-chat","score":66.4,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b-chat","score":54.6,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-chat-20b","score":52.5,"metric":"percent"},{"benchmark":"mmlu","model":"orion-14b-chat","score":61.7,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-chat","score":49.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen-14b-chat","score":58,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b-chat","score":40.2,"metric":"percent"},{"benchmark":"bbh","model":"internlm-chat-20b","score":35.3,"metric":"percent"},{"benchmark":"bbh","model":"orion-14b-chat","score":49.1,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-13b-chat","score":66.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-14b-chat","score":65.2,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-13b-chat","score":78.2,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm-chat-20b","score":69.2,"metric":"percent"},{"benchmark":"hellaswag","model":"orion-14b-chat","score":76.7,"metric":"percent"},{"benchmark":"piqa","model":"baichuan2-13b-chat","score":77.6,"metric":"percent"},{"benchmark":"piqa","model":"qwen-14b-chat","score":74,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-13b-chat","score":78.8,"metric":"percent"},{"benchmark":"piqa","model":"internlm-chat-20b","score":76.7,"metric":"percent"},{"benchmark":"piqa","model":"orion-14b-chat","score":78.4,"metric":"percent"},{"benchmark":"wsc","model":"baichuan2-13b-chat","score":71.2,"metric":"percent"},{"benchmark":"wsc","model":"qwen-14b-chat","score":66.3,"metric":"percent"},{"benchmark":"wsc","model":"llama-2-13b-chat","score":68.3,"metric":"percent"},{"benchmark":"wsc","model":"internlm-chat-20b","score":61.5,"metric":"percent"},{"benchmark":"wsc","model":"orion-14b-chat","score":71.2,"metric":"percent"},{"benchmark":"mt-bench","model":"baichuan2-13b-chat","score":6.76,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen-14b-chat","score":6.96,"metric":"percent"},{"benchmark":"mt-bench","model":"internlm-chat-20b","score":6.48,"metric":"percent"},{"benchmark":"mt-bench","model":"orion-14b-chat","score":7.37,"metric":"percent"},{"benchmark":"alignbench","model":"llama-2-13b-chat","score":4.7,"metric":"score"},{"benchmark":"alignbench","model":"orion-14b-chat","score":5.51,"metric":"score"},{"benchmark":"mmlu","model":"llama-2-7b-chat","score":46.2,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b","score":45.9,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm3-6b","score":51.9,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-chat-7b","score":52,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-chat","score":52.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b-chat","score":56.6,"metric":"percent"},{"benchmark":"mmlu","model":"telechat-7b","score":54.4,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b-chat","score":31.9,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b-chat","score":36.2,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm2-6b","score":52.6,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm3-6b","score":53.8,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-chat-7b","score":54.1,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-chat","score":55.6,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-chat","score":56.7,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b-chat","score":59.3,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b-chat","score":71.7,"metric":"percent"},{"benchmark":"c-eval","model":"telechat-7b","score":63.1,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b-chat","score":31.5,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm2-6b","score":49.3,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm3-6b","score":54,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm-chat-7b","score":52.6,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-chat","score":54,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-7b-chat","score":59.5,"metric":"percent"},{"benchmark":"cmmlu","model":"telechat-7b","score":64.3,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-7b-chat","score":28.5,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-13b-chat","score":32.3,"metric":"percent"},{"benchmark":"agieval","model":"chatglm2-6b","score":39,"metric":"percent"},{"benchmark":"agieval","model":"chatglm3-6b","score":38.9,"metric":"percent"},{"benchmark":"agieval","model":"internlm-chat-7b","score":43.7,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-7b-chat","score":35.3,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-13b-chat","score":40,"metric":"percent"},{"benchmark":"agieval","model":"qwen-7b-chat","score":41.3,"metric":"percent"},{"benchmark":"agieval","model":"qwen-14b-chat","score":47.3,"metric":"percent"},{"benchmark":"agieval","model":"telechat-7b","score":46.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-7b-chat","score":16.1,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-13b-chat","score":18.6,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm2-6b","score":46.4,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm3-6b","score":49.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm-chat-7b","score":45.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-7b-chat","score":39.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-13b-chat","score":51.4,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-7b-chat","score":63.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-14b-chat","score":76.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"telechat-7b","score":57.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b-chat","score":26.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b-chat","score":29.6,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b","score":28.8,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm3-6b","score":56.7,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-chat-7b","score":34.6,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-7b-chat","score":32.8,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-chat","score":55.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b-chat","score":52.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b-chat","score":61,"metric":"percent"},{"benchmark":"gsm8k","model":"telechat-7b","score":36.7,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b-chat","score":3.9,"metric":"percent"},{"benchmark":"math","model":"llama-2-13b-chat","score":5,"metric":"percent"},{"benchmark":"math","model":"chatglm2-6b","score":6.5,"metric":"percent"},{"benchmark":"math","model":"chatglm3-6b","score":18.7,"metric":"percent"},{"benchmark":"math","model":"internlm-chat-7b","score":5.6,"metric":"percent"},{"benchmark":"math","model":"baichuan2-7b-chat","score":6,"metric":"percent"},{"benchmark":"math","model":"baichuan2-13b-chat","score":8.6,"metric":"percent"},{"benchmark":"math","model":"qwen-7b-chat","score":10.3,"metric":"percent"},{"benchmark":"math","model":"qwen-14b-chat","score":26.8,"metric":"percent"},{"benchmark":"math","model":"telechat-7b","score":10.3,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b-chat","score":12.2,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b-chat","score":18.9,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm2-6b","score":11,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm3-6b","score":61,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-chat-7b","score":12.8,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-7b-chat","score":13.4,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-13b-chat","score":17.7,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b-chat","score":26.2,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-14b-chat","score":36.6,"metric":"percent"},{"benchmark":"humaneval","model":"telechat-7b","score":14.6,"metric":"percent"},{"benchmark":"chid","model":"llama-2-7b-chat","score":44.1,"metric":"percent"},{"benchmark":"chid","model":"llama-2-13b-chat","score":48,"metric":"percent"},{"benchmark":"chid","model":"chatglm2-6b","score":57.9,"metric":"percent"},{"benchmark":"chid","model":"chatglm3-6b","score":63.4,"metric":"percent"},{"benchmark":"chid","model":"internlm-chat-7b","score":79.7,"metric":"percent"},{"benchmark":"chid","model":"baichuan2-7b-chat","score":75.2,"metric":"percent"},{"benchmark":"chid","model":"baichuan2-13b-chat","score":78.2,"metric":"percent"},{"benchmark":"chid","model":"qwen-7b-chat","score":72.3,"metric":"percent"},{"benchmark":"chid","model":"qwen-14b-chat","score":72.3,"metric":"percent"},{"benchmark":"chid","model":"telechat-7b","score":88,"metric":"percent"},{"benchmark":"mmlu","model":"telechat-1b","score":36.5,"metric":"percent"},{"benchmark":"mmlu","model":"telechat-7b","score":60.5,"metric":"percent"},{"benchmark":"mmlu","model":"telechat-12b","score":73.3,"metric":"percent"},{"benchmark":"c-eval","model":"telechat-1b","score":53.3,"metric":"percent"},{"benchmark":"c-eval","model":"telechat-7b","score":64.6,"metric":"percent"},{"benchmark":"c-eval","model":"telechat-12b","score":66.6,"metric":"percent"},{"benchmark":"cmmlu","model":"telechat-1b","score":42.1,"metric":"percent"},{"benchmark":"cmmlu","model":"telechat-12b","score":74.2,"metric":"percent"},{"benchmark":"agieval","model":"telechat-1b","score":32.1,"metric":"percent"},{"benchmark":"agieval","model":"telechat-12b","score":51.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"telechat-1b","score":34.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"telechat-7b","score":59,"metric":"percent"},{"benchmark":"gaokao-bench","model":"telechat-12b","score":53.1,"metric":"percent"},{"benchmark":"gsm8k","model":"telechat-1b","score":36.8,"metric":"percent"},{"benchmark":"gsm8k","model":"telechat-12b","score":57.2,"metric":"percent"},{"benchmark":"math","model":"telechat-1b","score":7.2,"metric":"percent"},{"benchmark":"math","model":"telechat-12b","score":16,"metric":"percent"},{"benchmark":"humaneval","model":"telechat-1b","score":12.8,"metric":"percent"},{"benchmark":"humaneval","model":"telechat-7b","score":20.1,"metric":"percent"},{"benchmark":"humaneval","model":"telechat-12b","score":22,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-7b-chat","score":35.6,"metric":"percent"},{"benchmark":"bbh","model":"chatglm2-6b","score":32.7,"metric":"percent"},{"benchmark":"bbh","model":"chatglm3-6b","score":44.6,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-7b-chat","score":35.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen-7b-chat","score":46.9,"metric":"percent"},{"benchmark":"bbh","model":"telechat-1b","score":37.4,"metric":"percent"},{"benchmark":"bbh","model":"telechat-7b","score":19.5,"metric":"percent"},{"benchmark":"bbh","model":"telechat-12b","score":52.2,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b-chat","score":74.1,"metric":"percent"},{"benchmark":"hellaswag","model":"chatglm2-6b","score":57,"metric":"percent"},{"benchmark":"hellaswag","model":"chatglm3-6b","score":62.7,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-7b-chat","score":61.6,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-7b-chat","score":59.9,"metric":"percent"},{"benchmark":"hellaswag","model":"telechat-1b","score":29.6,"metric":"percent"},{"benchmark":"hellaswag","model":"telechat-7b","score":36.7,"metric":"percent"},{"benchmark":"hellaswag","model":"telechat-12b","score":71.5,"metric":"percent"},{"benchmark":"chid","model":"telechat-1b","score":69.8,"metric":"percent"},{"benchmark":"chid","model":"telechat-12b","score":83.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-72b-instruct","score":83.8,"metric":"percent"},{"benchmark":"c-eval","model":"telechat2-115b","score":86.9,"metric":"percent"},{"benchmark":"c-eval","model":"telechat2-35b","score":85,"metric":"percent"},{"benchmark":"c-eval","model":"telechat2-7b","score":82,"metric":"percent"},{"benchmark":"c-eval","model":"telechat2-3b","score":75,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-70b-instruct","score":86,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-110b-chat","score":80.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-72b-instruct","score":82.3,"metric":"percent"},{"benchmark":"mmlu","model":"telechat2-115b","score":80.9,"metric":"percent"},{"benchmark":"mmlu","model":"telechat2-35b","score":82,"metric":"percent"},{"benchmark":"mmlu","model":"telechat2-7b","score":79.6,"metric":"percent"},{"benchmark":"mmlu","model":"telechat2-3b","score":72.9,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3.1-70b-instruct","score":69.01,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-110b-chat","score":87.64,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2-72b-instruct","score":87.47,"metric":"percent"},{"benchmark":"cmmlu","model":"telechat2-115b","score":89.94,"metric":"percent"},{"benchmark":"cmmlu","model":"telechat2-35b","score":90.18,"metric":"percent"},{"benchmark":"cmmlu","model":"telechat2-7b","score":84.6,"metric":"percent"},{"benchmark":"cmmlu","model":"telechat2-3b","score":73,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-110b-chat","score":74.8,"metric":"percent"},{"benchmark":"bbh","model":"telechat2-115b","score":89.04,"metric":"percent"},{"benchmark":"bbh","model":"telechat2-35b","score":88.6,"metric":"percent"},{"benchmark":"bbh","model":"telechat2-7b","score":77.3,"metric":"percent"},{"benchmark":"bbh","model":"telechat2-3b","score":65.99,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b-instruct","score":95.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-110b-chat","score":85.4,"metric":"percent"},{"benchmark":"gsm8k","model":"telechat2-115b","score":92.2,"metric":"percent"},{"benchmark":"gsm8k","model":"telechat2-35b","score":91,"metric":"percent"},{"benchmark":"gsm8k","model":"telechat2-7b","score":86.8,"metric":"percent"},{"benchmark":"gsm8k","model":"telechat2-3b","score":64.7,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-110b-chat","score":52.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-72b-instruct","score":86,"metric":"percent"},{"benchmark":"humaneval","model":"telechat2-115b","score":75,"metric":"percent"},{"benchmark":"humaneval","model":"telechat2-35b","score":73,"metric":"percent"},{"benchmark":"humaneval","model":"telechat2-7b","score":56,"metric":"percent"},{"benchmark":"humaneval","model":"telechat2-3b","score":38,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-70b-instruct","score":86,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-110b-chat","score":58.1,"metric":"percent"},{"benchmark":"mbpp","model":"telechat2-115b","score":78,"metric":"percent"},{"benchmark":"mbpp","model":"telechat2-35b","score":75,"metric":"percent"},{"benchmark":"mbpp","model":"telechat2-7b","score":62.6,"metric":"percent"},{"benchmark":"mbpp","model":"telechat2-3b","score":47,"metric":"percent"},{"benchmark":"alignbench","model":"qwen1.5-110b-chat","score":7.86,"metric":"score"},{"benchmark":"alignbench","model":"qwen2-72b-instruct","score":8.27,"metric":"score"},{"benchmark":"alignbench","model":"telechat2-115b","score":8.03,"metric":"score"},{"benchmark":"alignbench","model":"telechat2-35b","score":7.88,"metric":"score"},{"benchmark":"alignbench","model":"telechat2-7b","score":6.96,"metric":"score"},{"benchmark":"alignbench","model":"telechat2-3b","score":5.74,"metric":"score"},{"benchmark":"mt-bench","model":"llama-3.1-70b-instruct","score":8.79,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen1.5-110b-chat","score":8.88,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2-72b-instruct","score":9.12,"metric":"percent"},{"benchmark":"mt-bench","model":"telechat2-115b","score":8.89,"metric":"percent"},{"benchmark":"mt-bench","model":"telechat2-35b","score":8.2,"metric":"percent"},{"benchmark":"mt-bench","model":"telechat2-7b","score":7.2,"metric":"percent"},{"benchmark":"mt-bench","model":"telechat2-3b","score":5.72,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-70b-instruct","score":87.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2-72b-instruct","score":77.6,"metric":"percent"},{"benchmark":"ifeval","model":"telechat2-115b","score":82.81,"metric":"percent"},{"benchmark":"ifeval","model":"telechat2-35b","score":79.63,"metric":"percent"},{"benchmark":"ifeval","model":"telechat2-7b","score":73.1,"metric":"percent"},{"benchmark":"ifeval","model":"telechat2-3b","score":61.29,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b","score":32.42,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b","score":58.96,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-llm-7b-base","score":42.82,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b-v0.1","score":46.12,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-7b","score":42.57,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b","score":37.32,"metric":"percent"},{"benchmark":"c-eval","model":"mpt-30b","score":29.34,"metric":"percent"},{"benchmark":"c-eval","model":"falcon-40b","score":40.29,"metric":"percent"},{"benchmark":"c-eval","model":"tinyllama-1.1b","score":25.02,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-1.8b","score":49.81,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-1.8b","score":55,"metric":"percent"},{"benchmark":"c-eval","model":"stablelm-zephyr-3b","score":30.34,"metric":"percent"},{"benchmark":"c-eval","model":"phi-2","score":23.37,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-2b","score":29.26,"metric":"percent"},{"benchmark":"c-eval","model":"minicpm-1b-sft","score":49.14,"metric":"percent"},{"benchmark":"c-eval","model":"minicpm-2b-sft","score":51.13,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b","score":31.11,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-7b","score":60.35,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-llm-7b-base","score":44.45,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b-v0.1","score":42.96,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-7b","score":44.2,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b","score":37.06,"metric":"percent"},{"benchmark":"cmmlu","model":"mpt-30b","score":32.09,"metric":"percent"},{"benchmark":"cmmlu","model":"falcon-40b","score":41.57,"metric":"percent"},{"benchmark":"cmmlu","model":"tinyllama-1.1b","score":24.03,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-1.8b","score":45.32,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-1.8b","score":50.85,"metric":"percent"},{"benchmark":"cmmlu","model":"stablelm-zephyr-3b","score":30.89,"metric":"percent"},{"benchmark":"cmmlu","model":"phi-2","score":24.18,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-2b","score":28.56,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-1b-sft","score":46.81,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-2b-sft","score":51.07,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b","score":44.32,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b","score":57.65,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-llm-7b-base","score":47.82,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-v0.1","score":62.69,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-7b","score":60.83,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b","score":54.71,"metric":"percent"},{"benchmark":"mmlu","model":"mpt-30b","score":46.56,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-40b","score":53.53,"metric":"percent"},{"benchmark":"mmlu","model":"tinyllama-1.1b","score":24.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-1.8b","score":43.37,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-1.8b","score":43.81,"metric":"percent"},{"benchmark":"mmlu","model":"stablelm-zephyr-3b","score":45.9,"metric":"percent"},{"benchmark":"mmlu","model":"phi-2","score":52.66,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2b","score":38.49,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm-1b-sft","score":49.63,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm-2b-sft","score":53.46,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b","score":12.2,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b","score":17.07,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-llm-7b-base","score":20.12,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-v0.1","score":27.44,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-7b","score":38.41,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b","score":17.07,"metric":"percent"},{"benchmark":"humaneval","model":"mpt-30b","score":21.95,"metric":"percent"},{"benchmark":"humaneval","model":"falcon-40b","score":24.39,"metric":"percent"},{"benchmark":"humaneval","model":"tinyllama-1.1b","score":6.71,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-1.8b","score":7.93,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-1.8b","score":5.49,"metric":"percent"},{"benchmark":"humaneval","model":"stablelm-zephyr-3b","score":35.37,"metric":"percent"},{"benchmark":"humaneval","model":"phi-2","score":47.56,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2b","score":24.39,"metric":"percent"},{"benchmark":"humaneval","model":"minicpm-1b-sft","score":44.51,"metric":"percent"},{"benchmark":"humaneval","model":"minicpm-2b-sft","score":50,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b","score":27.17,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-7b","score":42.15,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-llm-7b-base","score":41.45,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-v0.1","score":45.2,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-7b","score":50.12,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-13b","score":32.55,"metric":"percent"},{"benchmark":"mbpp","model":"mpt-30b","score":35.36,"metric":"percent"},{"benchmark":"mbpp","model":"falcon-40b","score":36.53,"metric":"percent"},{"benchmark":"mbpp","model":"tinyllama-1.1b","score":19.91,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-1.8b","score":17.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-1.8b","score":24.82,"metric":"percent"},{"benchmark":"mbpp","model":"gemini-nano-2","score":27.2,"metric":"percent"},{"benchmark":"mbpp","model":"stablelm-zephyr-3b","score":31.85,"metric":"percent"},{"benchmark":"mbpp","model":"phi-2","score":55.04,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2b","score":29.74,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm-1b-sft","score":32.75,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm-2b-sft","score":47.31,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b","score":13.57,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b","score":41.24,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-llm-7b-base","score":15.85,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.1","score":33.13,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-7b","score":47.31,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b","score":21.15,"metric":"percent"},{"benchmark":"gsm8k","model":"mpt-30b","score":10.31,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-40b","score":22.44,"metric":"percent"},{"benchmark":"gsm8k","model":"tinyllama-1.1b","score":2.27,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-1.8b","score":19.26,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-1.8b","score":26.16,"metric":"percent"},{"benchmark":"gsm8k","model":"gemini-nano-2","score":22.8,"metric":"percent"},{"benchmark":"gsm8k","model":"stablelm-zephyr-3b","score":52.54,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-2","score":57.16,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2b","score":16.83,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm-1b-sft","score":31.77,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm-2b-sft","score":53.83,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b","score":1.8,"metric":"percent"},{"benchmark":"math","model":"qwen-7b","score":5.34,"metric":"percent"},{"benchmark":"math","model":"deepseek-llm-7b-base","score":1.53,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-v0.1","score":5,"metric":"percent"},{"benchmark":"math","model":"gemma-7b","score":6.18,"metric":"percent"},{"benchmark":"math","model":"llama-2-13b","score":2.25,"metric":"percent"},{"benchmark":"math","model":"mpt-30b","score":1.56,"metric":"percent"},{"benchmark":"math","model":"falcon-40b","score":1.92,"metric":"percent"},{"benchmark":"math","model":"tinyllama-1.1b","score":0.74,"metric":"percent"},{"benchmark":"math","model":"qwen-1.8b","score":2.42,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-1.8b","score":3.25,"metric":"percent"},{"benchmark":"math","model":"stablelm-zephyr-3b","score":12.12,"metric":"percent"},{"benchmark":"math","model":"phi-2","score":3.5,"metric":"percent"},{"benchmark":"math","model":"gemma-2b","score":3.34,"metric":"percent"},{"benchmark":"math","model":"minicpm-1b-sft","score":10.6,"metric":"percent"},{"benchmark":"math","model":"minicpm-2b-sft","score":10.24,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-7b","score":33.23,"metric":"percent"},{"benchmark":"bbh","model":"qwen-7b","score":37.75,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-llm-7b-base","score":33.38,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b-v0.1","score":41.06,"metric":"percent"},{"benchmark":"bbh","model":"gemma-7b","score":39.19,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b","score":37.92,"metric":"percent"},{"benchmark":"bbh","model":"mpt-30b","score":38.22,"metric":"percent"},{"benchmark":"bbh","model":"falcon-40b","score":36.24,"metric":"percent"},{"benchmark":"bbh","model":"tinyllama-1.1b","score":28.78,"metric":"percent"},{"benchmark":"bbh","model":"qwen-1.8b","score":29.07,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-1.8b","score":28.82,"metric":"percent"},{"benchmark":"bbh","model":"gemini-nano-2","score":42.4,"metric":"percent"},{"benchmark":"bbh","model":"stablelm-zephyr-3b","score":37.68,"metric":"percent"},{"benchmark":"bbh","model":"phi-2","score":43.39,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2b","score":30.93,"metric":"percent"},{"benchmark":"bbh","model":"minicpm-1b-sft","score":34.7,"metric":"percent"},{"benchmark":"bbh","model":"minicpm-2b-sft","score":36.87,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-7b","score":75.25,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-7b","score":83.42,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-7b-base","score":74.58,"metric":"percent"},{"benchmark":"arc-easy","model":"mistral-7b-v0.1","score":83.92,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-7b","score":89.35,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-13b","score":78.87,"metric":"percent"},{"benchmark":"arc-easy","model":"mpt-30b","score":78.66,"metric":"percent"},{"benchmark":"arc-easy","model":"falcon-40b","score":81.94,"metric":"percent"},{"benchmark":"arc-easy","model":"tinyllama-1.1b","score":60.77,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-1.8b","score":63.97,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen1.5-1.8b","score":64.86,"metric":"percent"},{"benchmark":"arc-easy","model":"stablelm-zephyr-3b","score":73.78,"metric":"percent"},{"benchmark":"arc-easy","model":"phi-2","score":86.11,"metric":"percent"},{"benchmark":"arc-easy","model":"gemma-2b","score":74.33,"metric":"percent"},{"benchmark":"arc-easy","model":"minicpm-1b-sft","score":80.93,"metric":"percent"},{"benchmark":"arc-easy","model":"minicpm-2b-sft","score":85.44,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-7b","score":42.75,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-7b","score":64.76,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-7b-base","score":42.15,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-v0.1","score":70.73,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-7b","score":76.79,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-13b","score":58.19,"metric":"percent"},{"benchmark":"arc-challenge","model":"mpt-30b","score":46.08,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon-40b","score":57.68,"metric":"percent"},{"benchmark":"arc-challenge","model":"tinyllama-1.1b","score":28.15,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-1.8b","score":43.69,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-1.8b","score":45.56,"metric":"percent"},{"benchmark":"arc-challenge","model":"stablelm-zephyr-3b","score":55.38,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-2","score":71.25,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2b","score":40.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"minicpm-1b-sft","score":66.81,"metric":"percent"},{"benchmark":"arc-challenge","model":"minicpm-2b-sft","score":68,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b","score":75.62,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-7b","score":75.32,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-llm-7b-base","score":75.45,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-v0.1","score":80.43,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-7b","score":79.47,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-13b","score":79.23,"metric":"percent"},{"benchmark":"hellaswag","model":"mpt-30b","score":79.72,"metric":"percent"},{"benchmark":"hellaswag","model":"falcon-40b","score":83.26,"metric":"percent"},{"benchmark":"hellaswag","model":"tinyllama-1.1b","score":58.33,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-1.8b","score":59.28,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-1.8b","score":59.39,"metric":"percent"},{"benchmark":"hellaswag","model":"stablelm-zephyr-3b","score":71.87,"metric":"percent"},{"benchmark":"hellaswag","model":"phi-2","score":73.07,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2b","score":69.51,"metric":"percent"},{"benchmark":"hellaswag","model":"minicpm-1b-sft","score":54.72,"metric":"percent"},{"benchmark":"hellaswag","model":"minicpm-2b-sft","score":68.25,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm2-6b","score":52.05,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b-instruct-v0.1","score":38.06,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b-instruct-v0.2","score":42.55,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b-chat","score":58.57,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b-chat","score":70.88,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-chat","score":53.28,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-llm-7b-chat","score":46.95,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b-chat","score":34.54,"metric":"percent"},{"benchmark":"c-eval","model":"minicpm-2b-dpo-fp32","score":48.64,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm2-6b","score":49.21,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b-instruct-v0.1","score":36.96,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b-instruct-v0.2","score":41.92,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-7b-chat","score":57.23,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b-chat","score":71.11,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-chat","score":53.5,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-llm-7b-chat","score":49.72,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b-chat","score":32.64,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-2b-dpo-fp32","score":48.37,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b","score":45.77,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-instruct-v0.1","score":53.56,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-instruct-v0.2","score":60.51,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b-chat","score":56.03,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b-chat","score":62.95,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-chat","score":53,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-llm-7b-chat","score":51.67,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b-chat","score":47.64,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm-2b-dpo-fp32","score":53.05,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm2-6b","score":10.37,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-instruct-v0.1","score":29.27,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-instruct-v0.2","score":36.59,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b-chat","score":15.85,"metric":"percent"},{"benchmark":"humaneval","model":"yi-6b-chat","score":14.02,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-7b-chat","score":21.34,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-llm-7b-chat","score":40.85,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b-chat","score":14.02,"metric":"percent"},{"benchmark":"humaneval","model":"minicpm-2b-dpo-fp32","score":51.22,"metric":"percent"},{"benchmark":"mbpp","model":"chatglm2-6b","score":9.38,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-instruct-v0.1","score":39.34,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-instruct-v0.2","score":48.95,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-7b-chat","score":40.52,"metric":"percent"},{"benchmark":"mbpp","model":"yi-6b-chat","score":28.34,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-7b-chat","score":32.32,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-llm-7b-chat","score":48.48,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b-chat","score":27.4,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm-2b-dpo-fp32","score":48.01,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b","score":22.74,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-instruct-v0.1","score":28.73,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-instruct-v0.2","score":40.49,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b-chat","score":42.23,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-6b-chat","score":36.54,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-7b-chat","score":25.25,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-llm-7b-chat","score":48.52,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b-chat","score":21.15,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm-2b-dpo-fp32","score":53.37,"metric":"percent"},{"benchmark":"math","model":"chatglm2-6b","score":5.96,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-instruct-v0.1","score":3.48,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-instruct-v0.2","score":4.95,"metric":"percent"},{"benchmark":"math","model":"qwen-7b-chat","score":8.3,"metric":"percent"},{"benchmark":"math","model":"yi-6b-chat","score":3.88,"metric":"percent"},{"benchmark":"math","model":"baichuan2-7b-chat","score":6.32,"metric":"percent"},{"benchmark":"math","model":"deepseek-llm-7b-chat","score":4.26,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b-chat","score":2.08,"metric":"percent"},{"benchmark":"math","model":"minicpm-2b-dpo-fp32","score":9.86,"metric":"percent"},{"benchmark":"bbh","model":"chatglm2-6b","score":32.6,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b-instruct-v0.1","score":39.52,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b-instruct-v0.2","score":39.81,"metric":"percent"},{"benchmark":"bbh","model":"qwen-7b-chat","score":37.34,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b-chat","score":37.43,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-7b-chat","score":37.46,"metric":"percent"},{"benchmark":"bbh","model":"deepseek-llm-7b-chat","score":35.7,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-7b-chat","score":35.54,"metric":"percent"},{"benchmark":"bbh","model":"minicpm-2b-dpo-fp32","score":36.22,"metric":"percent"},{"benchmark":"arc-easy","model":"chatglm2-6b","score":74.45,"metric":"percent"},{"benchmark":"arc-easy","model":"mistral-7b-instruct-v0.1","score":81.61,"metric":"percent"},{"benchmark":"arc-easy","model":"mistral-7b-instruct-v0.2","score":86.28,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-7b-chat","score":64.44,"metric":"percent"},{"benchmark":"arc-easy","model":"yi-6b-chat","score":84.89,"metric":"percent"},{"benchmark":"arc-easy","model":"baichuan2-7b-chat","score":79.63,"metric":"percent"},{"benchmark":"arc-easy","model":"deepseek-llm-7b-chat","score":76.85,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-7b-chat","score":74.28,"metric":"percent"},{"benchmark":"arc-easy","model":"minicpm-2b-dpo-fp32","score":85.02,"metric":"percent"},{"benchmark":"arc-challenge","model":"chatglm2-6b","score":56.82,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-instruct-v0.1","score":63.99,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-instruct-v0.2","score":73.38,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-7b-chat","score":39.25,"metric":"percent"},{"benchmark":"arc-challenge","model":"yi-6b-chat","score":70.39,"metric":"percent"},{"benchmark":"arc-challenge","model":"baichuan2-7b-chat","score":60.15,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-llm-7b-chat","score":63.05,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-7b-chat","score":54.78,"metric":"percent"},{"benchmark":"arc-challenge","model":"minicpm-2b-dpo-fp32","score":68.17,"metric":"percent"},{"benchmark":"hellaswag","model":"chatglm2-6b","score":58.48,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-instruct-v0.1","score":73.47,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-instruct-v0.2","score":84.55,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-7b-chat","score":74.52,"metric":"percent"},{"benchmark":"hellaswag","model":"yi-6b-chat","score":74.6,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-7b-chat","score":69.23,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-llm-7b-chat","score":76.68,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b-chat","score":75.65,"metric":"percent"},{"benchmark":"hellaswag","model":"minicpm-2b-dpo-fp32","score":65.67,"metric":"percent"},{"benchmark":"c-eval","model":"minicpm-moe-8x2b","score":58.11,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-moe-8x2b","score":58.8,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-34b","score":62.6,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm-moe-8x2b","score":58.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-34b","score":22.6,"metric":"percent"},{"benchmark":"humaneval","model":"minicpm-moe-8x2b","score":56.71,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-34b","score":33,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm-moe-8x2b","score":51.05,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-34b","score":42.2,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm-moe-8x2b","score":61.56,"metric":"percent"},{"benchmark":"math","model":"llama-2-34b","score":6.24,"metric":"percent"},{"benchmark":"math","model":"minicpm-moe-8x2b","score":10.52,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-34b","score":44.1,"metric":"percent"},{"benchmark":"bbh","model":"minicpm-moe-8x2b","score":39.22,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-7b-instruct","score":70.5,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4-9b-chat","score":72.4,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-9b-it","score":72.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3.1-8b-instruct","score":69.4,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-3.5-turbo-0125","score":69.2,"metric":"percent"},{"benchmark":"mmlu","model":"phi-3.5-mini-instruct","score":68.4,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm3-4b","score":67.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-7b-instruct","score":64.9,"metric":"percent"},{"benchmark":"bbh","model":"glm-4-9b-chat","score":76.3,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-9b-it","score":65.2,"metric":"percent"},{"benchmark":"bbh","model":"llama-3.1-8b-instruct","score":67.8,"metric":"percent"},{"benchmark":"bbh","model":"gpt-3.5-turbo-0125","score":70.3,"metric":"percent"},{"benchmark":"bbh","model":"phi-3.5-mini-instruct","score":68.6,"metric":"percent"},{"benchmark":"bbh","model":"minicpm3-4b","score":70.2,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2-7b-instruct","score":8.41,"metric":"percent"},{"benchmark":"mt-bench","model":"glm-4-9b-chat","score":8.35,"metric":"percent"},{"benchmark":"mt-bench","model":"gemma-2-9b-it","score":7.88,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.1-8b-instruct","score":8.28,"metric":"percent"},{"benchmark":"mt-bench","model":"gpt-3.5-turbo-0125","score":8.17,"metric":"percent"},{"benchmark":"mt-bench","model":"phi-3.5-mini-instruct","score":8.6,"metric":"percent"},{"benchmark":"mt-bench","model":"minicpm3-4b","score":8.41,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2-7b-instruct","score":51,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"glm-4-9b-chat","score":64.5,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"gemma-2-9b-it","score":71.9,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llama-3.1-8b-instruct","score":71.5,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"gpt-3.5-turbo-0125","score":58.8,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"phi-3.5-mini-instruct","score":49.4,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"minicpm3-4b","score":68.4,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2-7b-instruct","score":80.9,"metric":"percent"},{"benchmark":"cmmlu","model":"glm-4-9b-chat","score":71.5,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-2-9b-it","score":59.5,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3.1-8b-instruct","score":55.8,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-3.5-turbo-0125","score":54.5,"metric":"percent"},{"benchmark":"cmmlu","model":"phi-3.5-mini-instruct","score":46.9,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm3-4b","score":73.3,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-7b-instruct","score":77.2,"metric":"percent"},{"benchmark":"c-eval","model":"glm-4-9b-chat","score":75.6,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-2-9b-it","score":56.7,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3.1-8b-instruct","score":55.2,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-3.5-turbo-0125","score":52.8,"metric":"percent"},{"benchmark":"c-eval","model":"phi-3.5-mini-instruct","score":46.1,"metric":"percent"},{"benchmark":"c-eval","model":"minicpm3-4b","score":73.6,"metric":"percent"},{"benchmark":"alignbench","model":"qwen2-7b-instruct","score":7.1,"metric":"score"},{"benchmark":"alignbench","model":"glm-4-9b-chat","score":6.61,"metric":"score"},{"benchmark":"alignbench","model":"gemma-2-9b-it","score":7.1,"metric":"score"},{"benchmark":"alignbench","model":"llama-3.1-8b-instruct","score":5.68,"metric":"score"},{"benchmark":"alignbench","model":"gpt-3.5-turbo-0125","score":5.82,"metric":"score"},{"benchmark":"alignbench","model":"phi-3.5-mini-instruct","score":5.73,"metric":"score"},{"benchmark":"alignbench","model":"minicpm3-4b","score":6.74,"metric":"score"},{"benchmark":"math","model":"qwen2-7b-instruct","score":49.6,"metric":"percent"},{"benchmark":"math","model":"glm-4-9b-chat","score":50.6,"metric":"percent"},{"benchmark":"math","model":"gemma-2-9b-it","score":46,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-8b-instruct","score":51.9,"metric":"percent"},{"benchmark":"math","model":"gpt-3.5-turbo-0125","score":41.8,"metric":"percent"},{"benchmark":"math","model":"phi-3.5-mini-instruct","score":46.4,"metric":"percent"},{"benchmark":"math","model":"minicpm3-4b","score":46.6,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4-9b-chat","score":79.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b-instruct","score":84.5,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5-turbo-0125","score":76.4,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3.5-mini-instruct","score":82.7,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm3-4b","score":81.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2-7b-instruct","score":70.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"glm-4-9b-chat","score":67.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-2-9b-it","score":61.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-3.5-turbo-0125","score":66.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"phi-3.5-mini-instruct","score":68.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"minicpm3-4b","score":68.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2-7b-instruct","score":57.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"glm-4-9b-chat","score":62.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-2-9b-it","score":64.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.1-8b-instruct","score":55.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-3.5-turbo-0125","score":71.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"phi-3.5-mini-instruct","score":55.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"minicpm3-4b","score":63.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"qwen2-7b-instruct","score":22.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"glm-4-9b-chat","score":20.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"gemma-2-9b-it","score":19.2,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"llama-3.1-8b-instruct","score":20.4,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"gpt-3.5-turbo-0125","score":24,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"phi-3.5-mini-instruct","score":19.6,"metric":"percent"},{"benchmark":"livecodebench-v3","model":"minicpm3-4b","score":22.6,"metric":"percent"},{"benchmark":"bfcl-v2","model":"qwen2-7b-instruct","score":71.6,"metric":"percent"},{"benchmark":"bfcl-v2","model":"glm-4-9b-chat","score":70.1,"metric":"percent"},{"benchmark":"bfcl-v2","model":"gemma-2-9b-it","score":19.2,"metric":"percent"},{"benchmark":"bfcl-v2","model":"llama-3.1-8b-instruct","score":73.3,"metric":"percent"},{"benchmark":"bfcl-v2","model":"gpt-3.5-turbo-0125","score":75.4,"metric":"percent"},{"benchmark":"bfcl-v2","model":"phi-3.5-mini-instruct","score":48.4,"metric":"percent"},{"benchmark":"bfcl-v2","model":"minicpm3-4b","score":76,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4-1106-vision-preview","score":1771.5,"metric":"points"},{"benchmark":"mme-elo","model":"gemini-1.0-pro","score":2148.9,"metric":"points"},{"benchmark":"mme-elo","model":"claude-3-opus","score":1586.8,"metric":"points"},{"benchmark":"mme-elo","model":"deepseek-vl-1.3b","score":1531.6,"metric":"points"},{"benchmark":"mme-elo","model":"mini-gemini-2b","score":1653,"metric":"points"},{"benchmark":"mme-elo","model":"yi-vl-6b","score":1915.1,"metric":"points"},{"benchmark":"mme-elo","model":"qwen-vl-chat","score":1860,"metric":"points"},{"benchmark":"mme-elo","model":"yi-vl-34b","score":2050.2,"metric":"points"},{"benchmark":"mme-elo","model":"llava-llama-3-8b","score":1818,"metric":"points"},{"benchmark":"mme-elo","model":"cogvlm-17b-chat","score":1736.6,"metric":"points"},{"benchmark":"mme-elo","model":"bunny-llama3-8b","score":1920.3,"metric":"points"},{"benchmark":"mme-elo","model":"deepseek-vl-7b","score":1765.4,"metric":"points"},{"benchmark":"mme-elo","model":"llava-next-llama3","score":1971.5,"metric":"points"},{"benchmark":"mme-elo","model":"idefics2-8b","score":1847.6,"metric":"points"},{"benchmark":"mme-elo","model":"cambrian-1-8b","score":1802.9,"metric":"points"},{"benchmark":"mme-elo","model":"cogvlm2-llama3-chat-19b","score":1869.5,"metric":"points"},{"benchmark":"mme-elo","model":"llava-next-34b","score":2006.5,"metric":"points"},{"benchmark":"mme-elo","model":"cambrian-1-34b","score":2049.9,"metric":"points"},{"benchmark":"mme-elo","model":"minicpm-v","score":1650.2,"metric":"points"},{"benchmark":"mme-elo","model":"minicpm-v-2.0-3b","score":1808.6,"metric":"points"},{"benchmark":"mme-elo","model":"minicpm-llama3-v2.5","score":2024.6,"metric":"points"},{"benchmark":"mmbench","model":"gpt-4-1106-vision-preview","score":77,"metric":"percent"},{"benchmark":"mmbench","model":"gemini-1.0-pro","score":73.6,"metric":"percent"},{"benchmark":"mmbench","model":"claude-3-opus","score":63.3,"metric":"percent"},{"benchmark":"mmbench","model":"deepseek-vl-1.3b","score":66.4,"metric":"percent"},{"benchmark":"mmbench","model":"yi-vl-6b","score":68.4,"metric":"percent"},{"benchmark":"mmbench","model":"qwen-vl-chat","score":61.8,"metric":"percent"},{"benchmark":"mmbench","model":"yi-vl-34b","score":72.4,"metric":"percent"},{"benchmark":"mmbench","model":"llava-llama-3-8b","score":71.7,"metric":"percent"},{"benchmark":"mmbench","model":"cogvlm-17b-chat","score":65.8,"metric":"percent"},{"benchmark":"mmbench","model":"bunny-llama3-8b","score":77,"metric":"percent"},{"benchmark":"mmbench","model":"deepseek-vl-7b","score":73.8,"metric":"percent"},{"benchmark":"mmbench","model":"idefics2-8b","score":75.7,"metric":"percent"},{"benchmark":"mmbench","model":"cambrian-1-8b","score":74.6,"metric":"percent"},{"benchmark":"mmbench","model":"cogvlm2-llama3-chat-19b","score":73.9,"metric":"percent"},{"benchmark":"mmbench","model":"llava-next-34b","score":81.1,"metric":"percent"},{"benchmark":"mmbench","model":"cambrian-1-34b","score":80.4,"metric":"percent"},{"benchmark":"mmbench","model":"minicpm-v","score":64.1,"metric":"percent"},{"benchmark":"mmbench","model":"minicpm-v-2.0-3b","score":69.1,"metric":"percent"},{"benchmark":"mmbench","model":"minicpm-llama3-v2.5","score":77.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gpt-4-1106-vision-preview","score":74.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gemini-1.0-pro","score":74.3,"metric":"percent"},{"benchmark":"mmbench-cn","model":"claude-3-opus","score":59.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"deepseek-vl-1.3b","score":62.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"yi-vl-6b","score":66.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen-vl-chat","score":56.3,"metric":"percent"},{"benchmark":"mmbench-cn","model":"yi-vl-34b","score":70.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"llava-llama-3-8b","score":63.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"cogvlm-17b-chat","score":55.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"bunny-llama3-8b","score":73.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"deepseek-vl-7b","score":71.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"idefics2-8b","score":68.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"cambrian-1-8b","score":67.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"cogvlm2-llama3-chat-19b","score":69.8,"metric":"percent"},{"benchmark":"mmbench-cn","model":"llava-next-34b","score":79,"metric":"percent"},{"benchmark":"mmbench-cn","model":"cambrian-1-34b","score":79.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"minicpm-v","score":62.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"minicpm-v-2.0-3b","score":66.5,"metric":"percent"},{"benchmark":"mmbench-cn","model":"minicpm-llama3-v2.5","score":74.2,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4-1106-vision-preview","score":53.8,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.0-pro","score":48.9,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3-opus","score":54.9,"metric":"percent"},{"benchmark":"mmmu","model":"deepseek-vl-1.3b","score":33.8,"metric":"percent"},{"benchmark":"mmmu","model":"mini-gemini-2b","score":31.7,"metric":"percent"},{"benchmark":"mmmu","model":"yi-vl-6b","score":40.3,"metric":"percent"},{"benchmark":"mmmu","model":"yi-vl-34b","score":45.1,"metric":"percent"},{"benchmark":"mmmu","model":"phi-3-vision-128k-instruct","score":40.4,"metric":"percent"},{"benchmark":"mmmu","model":"llava-llama-3-8b","score":39.2,"metric":"percent"},{"benchmark":"mmmu","model":"bunny-llama3-8b","score":41.3,"metric":"percent"},{"benchmark":"mmmu","model":"deepseek-vl-7b","score":38.3,"metric":"percent"},{"benchmark":"mmmu","model":"llava-next-llama3","score":41.7,"metric":"percent"},{"benchmark":"mmmu","model":"idefics2-8b","score":45.2,"metric":"percent"},{"benchmark":"mmmu","model":"cambrian-1-8b","score":41.8,"metric":"percent"},{"benchmark":"mmmu","model":"cogvlm2-llama3-chat-19b","score":42.6,"metric":"percent"},{"benchmark":"mmmu","model":"llava-next-34b","score":48.8,"metric":"percent"},{"benchmark":"mmmu","model":"cambrian-1-34b","score":50.4,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v","score":38.3,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-llama3-v2.5","score":45.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4-1106-vision-preview","score":47.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-1.0-pro","score":45.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-3-opus","score":45.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"deepseek-vl-1.3b","score":29.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"yi-vl-6b","score":28.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"yi-vl-34b","score":30.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"phi-3-vision-128k-instruct","score":44.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-llama-3-8b","score":40,"metric":"percent"},{"benchmark":"mathvista-mini","model":"bunny-llama3-8b","score":31.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"deepseek-vl-7b","score":36.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"idefics2-8b","score":52.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"cambrian-1-8b","score":47,"metric":"percent"},{"benchmark":"mathvista-mini","model":"cogvlm2-llama3-chat-19b","score":38.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-next-34b","score":40.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"cambrian-1-34b","score":50.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"minicpm-v","score":28.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"minicpm-llama3-v2.5","score":54.3,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"gpt-4-1106-vision-preview","score":93.1,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"gemini-1.0-pro","score":79.9,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"claude-3-opus","score":73.9,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"deepseek-vl-1.3b","score":51.1,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"yi-vl-6b","score":51.9,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"qwen-vl-chat","score":67.7,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"yi-vl-34b","score":62.3,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"phi-3-vision-128k-instruct","score":64.2,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"llava-llama-3-8b","score":69.2,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"cogvlm-17b-chat","score":73.9,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"bunny-llama3-8b","score":61.2,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"deepseek-vl-7b","score":77.8,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"llava-next-llama3","score":80.1,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"idefics2-8b","score":49.1,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"cambrian-1-8b","score":71,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"cogvlm2-llama3-chat-19b","score":83,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"llava-next-34b","score":81.8,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"cambrian-1-34b","score":82,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"minicpm-v","score":51.3,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"minicpm-v-2.0-3b","score":69.2,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"minicpm-llama3-v2.5","score":86.7,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-4-1106-vision-preview","score":63,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-1.0-pro","score":60.4,"metric":"percent"},{"benchmark":"realworldqa","model":"claude-3-opus","score":48.4,"metric":"percent"},{"benchmark":"realworldqa","model":"deepseek-vl-1.3b","score":49.7,"metric":"percent"},{"benchmark":"realworldqa","model":"yi-vl-6b","score":53.5,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen-vl-chat","score":49.3,"metric":"percent"},{"benchmark":"realworldqa","model":"yi-vl-34b","score":54.8,"metric":"percent"},{"benchmark":"realworldqa","model":"phi-3-vision-128k-instruct","score":58.8,"metric":"percent"},{"benchmark":"realworldqa","model":"cogvlm-17b-chat","score":60.3,"metric":"percent"},{"benchmark":"realworldqa","model":"bunny-llama3-8b","score":58.8,"metric":"percent"},{"benchmark":"realworldqa","model":"deepseek-vl-7b","score":54.2,"metric":"percent"},{"benchmark":"realworldqa","model":"llava-next-llama3","score":60,"metric":"percent"},{"benchmark":"realworldqa","model":"idefics2-8b","score":60.7,"metric":"percent"},{"benchmark":"realworldqa","model":"cambrian-1-8b","score":60,"metric":"percent"},{"benchmark":"realworldqa","model":"cogvlm2-llama3-chat-19b","score":62.9,"metric":"percent"},{"benchmark":"realworldqa","model":"llava-next-34b","score":66,"metric":"percent"},{"benchmark":"realworldqa","model":"cambrian-1-34b","score":67.1,"metric":"percent"},{"benchmark":"realworldqa","model":"minicpm-v","score":51.2,"metric":"percent"},{"benchmark":"realworldqa","model":"minicpm-llama3-v2.5","score":63.5,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-1.0-pro","score":68,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4-1106-vision-preview","score":64.5,"metric":"percent"},{"benchmark":"ocrbench","model":"yi-vl-6b","score":29,"metric":"percent"},{"benchmark":"ocrbench","model":"yi-vl-34b","score":29,"metric":"percent"},{"benchmark":"ocrbench","model":"deepseek-vl-1.3b","score":41.3,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen-vl-chat","score":48.8,"metric":"percent"},{"benchmark":"ocrbench","model":"deepseek-vl-7b","score":43.5,"metric":"percent"},{"benchmark":"ocrbench","model":"cogvlm-17b-chat","score":59,"metric":"percent"},{"benchmark":"ocrbench","model":"textmonkey","score":55.8,"metric":"percent"},{"benchmark":"ocrbench","model":"phi-3-vision-128k-instruct","score":63.9,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-v","score":36.6,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-llama3-v2.5","score":72.5,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-1.0-pro","score":74.6,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-4-1106-vision-preview","score":78,"metric":"percent"},{"benchmark":"textvqa","model":"yi-vl-6b","score":45.5,"metric":"percent"},{"benchmark":"textvqa","model":"yi-vl-34b","score":43.4,"metric":"percent"},{"benchmark":"textvqa","model":"mini-gemini-2b","score":56.2,"metric":"percent"},{"benchmark":"textvqa","model":"mobilevlm-v2-3b","score":57.5,"metric":"percent"},{"benchmark":"textvqa","model":"deepseek-vl-1.3b","score":58.4,"metric":"percent"},{"benchmark":"textvqa","model":"qwen-vl-chat","score":61.5,"metric":"percent"},{"benchmark":"textvqa","model":"deepseek-vl-7b","score":64.7,"metric":"percent"},{"benchmark":"textvqa","model":"cogvlm-17b-chat","score":70.4,"metric":"percent"},{"benchmark":"textvqa","model":"textmonkey","score":64.3,"metric":"percent"},{"benchmark":"textvqa","model":"idefics2-8b","score":73,"metric":"percent"},{"benchmark":"textvqa","model":"phi-3-vision-128k-instruct","score":70.9,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-v","score":60.6,"metric":"percent"},{"benchmark":"textvqa","model":"minicpm-llama3-v2.5","score":76.6,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-1.0-pro","score":88.1,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4-1106-vision-preview","score":88.4,"metric":"percent"},{"benchmark":"docvqa","model":"yi-vl-6b","score":17.1,"metric":"percent"},{"benchmark":"docvqa","model":"yi-vl-34b","score":16.9,"metric":"percent"},{"benchmark":"docvqa","model":"mini-gemini-2b","score":34.2,"metric":"percent"},{"benchmark":"docvqa","model":"mobilevlm-v2-3b","score":19.4,"metric":"percent"},{"benchmark":"docvqa","model":"deepseek-vl-1.3b","score":37.9,"metric":"percent"},{"benchmark":"docvqa","model":"qwen-vl-chat","score":62.6,"metric":"percent"},{"benchmark":"docvqa","model":"deepseek-vl-7b","score":47,"metric":"percent"},{"benchmark":"docvqa","model":"cogvlm-17b-chat","score":33.3,"metric":"percent"},{"benchmark":"docvqa","model":"textmonkey","score":66.7,"metric":"percent"},{"benchmark":"docvqa","model":"idefics2-8b","score":74,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-v","score":38.2,"metric":"percent"},{"benchmark":"docvqa","model":"minicpm-llama3-v2.5","score":84.8,"metric":"percent"},{"benchmark":"docvqa","model":"llava-next-llama3","score":78.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-next-llama3","score":37.5,"metric":"percent"},{"benchmark":"mme-elo","model":"phi-3-vision-128k-instruct","score":1537.5,"metric":"points"},{"benchmark":"mmmu","model":"qwen-vl-chat","score":35.9,"metric":"percent"},{"benchmark":"mmmu","model":"cogvlm-17b-chat","score":32.1,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v","score":37.2,"metric":"percent"},{"benchmark":"cmmmu","model":"qwen-vl-chat","score":30.7,"metric":"percent"},{"benchmark":"cmmmu","model":"minicpm-v","score":32.1,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4o-2024-05-13","score":2328.7,"metric":"points"},{"benchmark":"mme-elo","model":"gemini-1.5-pro","score":2110.6,"metric":"points"},{"benchmark":"mme-elo","model":"gpt-4o-mini-2024-07-18","score":2003.4,"metric":"points"},{"benchmark":"mme-elo","model":"gpt-4-1106-vision-preview","score":2070.2,"metric":"points"},{"benchmark":"mme-elo","model":"step-1v-32k","score":2206.4,"metric":"points"},{"benchmark":"mme-elo","model":"qwen-vl-max","score":2281.7,"metric":"points"},{"benchmark":"mme-elo","model":"mini-gemini-hd-34b","score":2141,"metric":"points"},{"benchmark":"mme-elo","model":"glm-4v-9b","score":2018.8,"metric":"points"},{"benchmark":"mme-elo","model":"internvl2-8b","score":2215.1,"metric":"points"},{"benchmark":"mme-elo","model":"minicpm-v-2_6","score":2348.4,"metric":"points"},{"benchmark":"mmvet","model":"gpt-4o-2024-05-13","score":69.1,"metric":"percent"},{"benchmark":"mmvet","model":"claude-3.5-sonnet-20240620","score":66,"metric":"percent"},{"benchmark":"mmvet","model":"gemini-1.5-pro","score":64,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4o-mini-2024-07-18","score":66.9,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4-1106-vision-preview","score":67.5,"metric":"percent"},{"benchmark":"mmvet","model":"step-1v-32k","score":63.3,"metric":"percent"},{"benchmark":"mmvet","model":"llava-next-34b","score":50.7,"metric":"percent"},{"benchmark":"mmvet","model":"mini-gemini-hd-34b","score":59.3,"metric":"percent"},{"benchmark":"mmvet","model":"cambrian-1-34b","score":53.2,"metric":"percent"},{"benchmark":"mmvet","model":"glm-4v-9b","score":58,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2-8b","score":54.3,"metric":"percent"},{"benchmark":"mmvet","model":"minicpm-llama3-v2.5","score":52.8,"metric":"percent"},{"benchmark":"mmvet","model":"minicpm-v-2_6","score":60,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4o-2024-05-13","score":73.6,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4o-mini-2024-07-18","score":78.5,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4-1106-vision-preview","score":65.6,"metric":"percent"},{"benchmark":"ocrbench","model":"step-1v-32k","score":62.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen-vl-max","score":68.4,"metric":"percent"},{"benchmark":"ocrbench","model":"llava-next-34b","score":57.4,"metric":"percent"},{"benchmark":"ocrbench","model":"mini-gemini-hd-34b","score":51.8,"metric":"percent"},{"benchmark":"ocrbench","model":"cambrian-1-34b","score":59.1,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4v-9b","score":77.6,"metric":"percent"},{"benchmark":"ocrbench","model":"minicpm-v-2_6","score":85.2,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4o-2024-05-13","score":69.2,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3.5-sonnet-20240620","score":65.9,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4o-mini-2024-07-18","score":60,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4-1106-vision-preview","score":61.7,"metric":"percent"},{"benchmark":"mmmu","model":"step-1v-32k","score":49.9,"metric":"percent"},{"benchmark":"mmmu","model":"qwen-vl-max","score":52,"metric":"percent"},{"benchmark":"mmmu","model":"mini-gemini-hd-34b","score":48,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4v-9b","score":46.9,"metric":"percent"},{"benchmark":"mmmu","model":"minicpm-v-2_6","score":49.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4o-2024-05-13","score":61.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-3.5-sonnet-20240620","score":61.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4o-mini-2024-07-18","score":52.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4-1106-vision-preview","score":54.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"step-1v-32k","score":44.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen-vl-max","score":43.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"mini-gemini-hd-34b","score":43.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"glm-4v-9b","score":51.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o-2024-05-13","score":82.2,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-1.5-pro","score":73.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o-mini-2024-07-18","score":76,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4-1106-vision-preview","score":79.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"step-1v-32k","score":78,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen-vl-max","score":74.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"llava-next-34b","score":77.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"cambrian-1-34b","score":77.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"glm-4v-9b","score":67.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"minicpm-llama3-v2.5","score":72,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4o-2024-05-13","score":84.6,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3.5-sonnet-20240620","score":80.2,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4o-mini-2024-07-18","score":77.8,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4-1106-vision-preview","score":78.6,"metric":"percent"},{"benchmark":"ai2d","model":"step-1v-32k","score":79.2,"metric":"percent"},{"benchmark":"ai2d","model":"qwen-vl-max","score":75.7,"metric":"percent"},{"benchmark":"ai2d","model":"llava-next-34b","score":78.9,"metric":"percent"},{"benchmark":"ai2d","model":"mini-gemini-hd-34b","score":80.5,"metric":"percent"},{"benchmark":"ai2d","model":"cambrian-1-34b","score":79.5,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4v-9b","score":71.2,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-8b","score":83.6,"metric":"percent"},{"benchmark":"ai2d","model":"minicpm-llama3-v2.5","score":78.4,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-1.5-pro","score":73.5,"metric":"percent"},{"benchmark":"textvqa","model":"step-1v-32k","score":71.6,"metric":"percent"},{"benchmark":"textvqa","model":"qwen-vl-max","score":79.5,"metric":"percent"},{"benchmark":"textvqa","model":"llava-next-34b","score":69.3,"metric":"percent"},{"benchmark":"textvqa","model":"mini-gemini-hd-34b","score":74.1,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4o-2024-05-13","score":92.8,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-1.5-pro","score":86.5,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4-1106-vision-preview","score":87.2,"metric":"percent"},{"benchmark":"docvqa","model":"qwen-vl-max","score":93.1,"metric":"percent"},{"benchmark":"docvqa","model":"mini-gemini-hd-34b","score":78.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4o-2024-05-13","score":55,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-3.5-sonnet-20240620","score":49.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-1.5-pro","score":45.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4o-mini-2024-07-18","score":46.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4-1106-vision-preview","score":43.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"step-1v-32k","score":48.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen-vl-max","score":41.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"llava-next-34b","score":34.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"cambrian-1-34b","score":41.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"glm-4v-9b","score":45,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2-8b","score":45,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-llama3-v2.5","score":42.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-v-2_6","score":48.1,"metric":"percent"},{"benchmark":"mantis","model":"gpt-4-1106-vision-preview","score":62.7,"metric":"percent"},{"benchmark":"mantis","model":"llava-next-interleave-14b","score":66.4,"metric":"percent"},{"benchmark":"mantis","model":"emu2-chat","score":37.8,"metric":"percent"},{"benchmark":"mantis","model":"cogvlm-17b-chat","score":45.2,"metric":"percent"},{"benchmark":"mantis","model":"vpg-c-7b","score":52.4,"metric":"percent"},{"benchmark":"mantis","model":"llama-3-vila1.5-8b","score":51.2,"metric":"percent"},{"benchmark":"mantis","model":"internlm-xcomposer2.5","score":53.1,"metric":"percent"},{"benchmark":"mantis","model":"internvl2-8b","score":59,"metric":"percent"},{"benchmark":"mantis","model":"minicpm-v-2_6","score":69.1,"metric":"percent"},{"benchmark":"blink","model":"gpt-4-1106-vision-preview","score":54.6,"metric":"percent"},{"benchmark":"blink","model":"llava-next-interleave-14b","score":52.6,"metric":"percent"},{"benchmark":"blink","model":"emu2-chat","score":36.2,"metric":"percent"},{"benchmark":"blink","model":"cogvlm-17b-chat","score":41.1,"metric":"percent"},{"benchmark":"blink","model":"vpg-c-7b","score":43.1,"metric":"percent"},{"benchmark":"blink","model":"llama-3-vila1.5-8b","score":39.3,"metric":"percent"},{"benchmark":"blink","model":"internlm-xcomposer2.5","score":48.9,"metric":"percent"},{"benchmark":"blink","model":"internvl2-8b","score":50.9,"metric":"percent"},{"benchmark":"blink","model":"minicpm-v-2_6","score":53,"metric":"percent"},{"benchmark":"mirb","model":"gpt-4-1106-vision-preview","score":53.1,"metric":"percent"},{"benchmark":"mirb","model":"internlm-xcomposer2.5","score":42.5,"metric":"percent"},{"benchmark":"mirb","model":"internvl2-8b","score":56.9,"metric":"percent"},{"benchmark":"mirb","model":"minicpm-v-2_6","score":53.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"claude-3.5-sonnet-20240620","score":60,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-4-1106-vision-preview","score":59.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"longva-7b","score":52.4,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2-8b","score":54,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internlm-xcomposer2.5","score":55.8,"metric":"percent"},{"benchmark":"videomme-nosub","model":"llava-next-video-32b","score":60.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"minicpm-v-2_6","score":60.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"claude-3.5-sonnet-20240620","score":62.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-4-1106-vision-preview","score":63.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"longva-7b","score":54.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2-8b","score":56.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"llava-next-video-32b","score":63,"metric":"percent"},{"benchmark":"videomme-sub","model":"minicpm-v-2_6","score":63.6,"metric":"percent"},{"benchmark":"boolq","model":"llama-3-8b","score":66.82,"metric":"percent"},{"benchmark":"boolq","model":"mistral-7b-v0.1","score":64.1,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-7b","score":70.67,"metric":"percent"},{"benchmark":"boolq","model":"amber-7b","score":63.52,"metric":"percent"},{"benchmark":"boolq","model":"olmo-7b","score":68.41,"metric":"percent"},{"benchmark":"boolq","model":"olmo-1.7-7b","score":70.49,"metric":"percent"},{"benchmark":"boolq","model":"pythia-6.9b","score":62.45,"metric":"percent"},{"benchmark":"boolq","model":"pythia-12b","score":61.07,"metric":"percent"},{"benchmark":"boolq","model":"map-neo-7b","score":81.07,"metric":"percent"},{"benchmark":"piqa","model":"llama-3-8b","score":81.12,"metric":"percent"},{"benchmark":"piqa","model":"mistral-7b-v0.1","score":81.18,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-7b","score":78.18,"metric":"percent"},{"benchmark":"piqa","model":"amber-7b","score":76.82,"metric":"percent"},{"benchmark":"piqa","model":"olmo-7b","score":79,"metric":"percent"},{"benchmark":"piqa","model":"olmo-1.7-7b","score":80.25,"metric":"percent"},{"benchmark":"piqa","model":"pythia-6.9b","score":75.52,"metric":"percent"},{"benchmark":"piqa","model":"pythia-12b","score":76.17,"metric":"percent"},{"benchmark":"piqa","model":"map-neo-7b","score":76.55,"metric":"percent"},{"benchmark":"siqa","model":"llama-3-8b","score":47.34,"metric":"percent"},{"benchmark":"siqa","model":"mistral-7b-v0.1","score":47.13,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-7b","score":45.5,"metric":"percent"},{"benchmark":"siqa","model":"amber-7b","score":42.89,"metric":"percent"},{"benchmark":"siqa","model":"olmo-7b","score":44.11,"metric":"percent"},{"benchmark":"siqa","model":"olmo-1.7-7b","score":54.71,"metric":"percent"},{"benchmark":"siqa","model":"pythia-6.9b","score":42.32,"metric":"percent"},{"benchmark":"siqa","model":"pythia-12b","score":44.32,"metric":"percent"},{"benchmark":"siqa","model":"map-neo-7b","score":68.22,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3-8b","score":74.52,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-v0.1","score":76.49,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b","score":71.27,"metric":"percent"},{"benchmark":"hellaswag","model":"amber-7b","score":66.76,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-7b","score":70.32,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-1.7-7b","score":72.37,"metric":"percent"},{"benchmark":"hellaswag","model":"pythia-6.9b","score":59.6,"metric":"percent"},{"benchmark":"hellaswag","model":"pythia-12b","score":63.04,"metric":"percent"},{"benchmark":"hellaswag","model":"map-neo-7b","score":70.74,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3-8b","score":72.38,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b-v0.1","score":75.3,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-7b","score":69.53,"metric":"percent"},{"benchmark":"winogrande","model":"amber-7b","score":64.64,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-7b","score":66.54,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-1.7-7b","score":69.22,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-6.9b","score":60.85,"metric":"percent"},{"benchmark":"winogrande","model":"pythia-12b","score":63.69,"metric":"percent"},{"benchmark":"winogrande","model":"map-neo-7b","score":59.83,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-8b","score":79.66,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-v0.1","score":71.53,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-7b","score":35.93,"metric":"percent"},{"benchmark":"arc-challenge","model":"amber-7b","score":24.41,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-7b","score":24.07,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-1.7-7b","score":49.83,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-6.9b","score":22.71,"metric":"percent"},{"benchmark":"arc-challenge","model":"pythia-12b","score":25.08,"metric":"percent"},{"benchmark":"arc-challenge","model":"map-neo-7b","score":68.14,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-3-8b","score":69,"metric":"percent"},{"benchmark":"openbookqa","model":"mistral-7b-v0.1","score":81,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-7b","score":42.6,"metric":"percent"},{"benchmark":"openbookqa","model":"amber-7b","score":26.6,"metric":"percent"},{"benchmark":"openbookqa","model":"olmo-7b","score":24.6,"metric":"percent"},{"benchmark":"openbookqa","model":"olmo-1.7-7b","score":64.4,"metric":"percent"},{"benchmark":"openbookqa","model":"pythia-6.9b","score":25,"metric":"percent"},{"benchmark":"openbookqa","model":"pythia-12b","score":28.6,"metric":"percent"},{"benchmark":"openbookqa","model":"map-neo-7b","score":82,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-3-8b","score":69.7,"metric":"percent"},{"benchmark":"commonsenseqa","model":"mistral-7b-v0.1","score":67.57,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-2-7b","score":66.5,"metric":"percent"},{"benchmark":"commonsenseqa","model":"amber-7b","score":57,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-7b","score":60.44,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-1.7-7b","score":69.04,"metric":"percent"},{"benchmark":"commonsenseqa","model":"pythia-6.9b","score":55.45,"metric":"percent"},{"benchmark":"commonsenseqa","model":"pythia-12b","score":54.79,"metric":"percent"},{"benchmark":"commonsenseqa","model":"map-neo-7b","score":69.94,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-8b","score":66.52,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-v0.1","score":64.04,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b","score":46.8,"metric":"percent"},{"benchmark":"mmlu","model":"amber-7b","score":28.07,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-7b","score":28.51,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-1.7-7b","score":53.52,"metric":"percent"},{"benchmark":"mmlu","model":"pythia-6.9b","score":26.39,"metric":"percent"},{"benchmark":"mmlu","model":"pythia-12b","score":27.06,"metric":"percent"},{"benchmark":"mmlu","model":"map-neo-7b","score":58.14,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-8b","score":33.5,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b","score":13.4,"metric":"percent"},{"benchmark":"humaneval","model":"amber-7b","score":13.4,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-7b","score":11.6,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-1.7-7b","score":17.1,"metric":"percent"},{"benchmark":"humaneval","model":"pythia-6.9b","score":9.1,"metric":"percent"},{"benchmark":"humaneval","model":"pythia-12b","score":8.5,"metric":"percent"},{"benchmark":"humaneval","model":"map-neo-7b","score":23.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3-8b","score":29.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-7b-v0.1","score":23.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-2-7b","score":11.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"amber-7b","score":12.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-7b","score":9.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-1.7-7b","score":15.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"pythia-6.9b","score":8.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"pythia-12b","score":7.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"map-neo-7b","score":20.1,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b","score":61.4,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-v0.1","score":46.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b","score":29.1,"metric":"percent"},{"benchmark":"mbpp","model":"amber-7b","score":22.8,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-7b","score":27,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-1.7-7b","score":32.3,"metric":"percent"},{"benchmark":"mbpp","model":"pythia-6.9b","score":16.1,"metric":"percent"},{"benchmark":"mbpp","model":"pythia-12b","score":15.6,"metric":"percent"},{"benchmark":"mbpp","model":"map-neo-7b","score":34.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-8b","score":51.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistral-7b-v0.1","score":38.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-2-7b","score":22.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"amber-7b","score":18.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-7b","score":21.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-1.7-7b","score":25.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"pythia-6.9b","score":13.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"pythia-12b","score":11.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"map-neo-7b","score":29.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-3-8b","score":10.14,"metric":"percent"},{"benchmark":"naturalquestions","model":"mistral-7b-v0.1","score":9.31,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b","score":5.07,"metric":"percent"},{"benchmark":"naturalquestions","model":"amber-7b","score":3.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"olmo-7b","score":0.66,"metric":"percent"},{"benchmark":"naturalquestions","model":"olmo-1.7-7b","score":1.02,"metric":"percent"},{"benchmark":"naturalquestions","model":"pythia-6.9b","score":0.86,"metric":"percent"},{"benchmark":"naturalquestions","model":"pythia-12b","score":1.83,"metric":"percent"},{"benchmark":"naturalquestions","model":"map-neo-7b","score":9.97,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-3-8b","score":51.94,"metric":"percent"},{"benchmark":"triviaqa","model":"mistral-7b-v0.1","score":56.47,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-7b","score":52.44,"metric":"percent"},{"benchmark":"triviaqa","model":"amber-7b","score":26.65,"metric":"percent"},{"benchmark":"triviaqa","model":"olmo-7b","score":31.97,"metric":"percent"},{"benchmark":"triviaqa","model":"olmo-1.7-7b","score":45.16,"metric":"percent"},{"benchmark":"triviaqa","model":"pythia-6.9b","score":16.97,"metric":"percent"},{"benchmark":"triviaqa","model":"pythia-12b","score":24.31,"metric":"percent"},{"benchmark":"triviaqa","model":"map-neo-7b","score":42.36,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llama-3-8b","score":40.88,"metric":"percent"},{"benchmark":"squad-v2.0","model":"mistral-7b-v0.1","score":12.53,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llama-2-7b","score":41.32,"metric":"percent"},{"benchmark":"squad-v2.0","model":"amber-7b","score":31.15,"metric":"percent"},{"benchmark":"squad-v2.0","model":"olmo-7b","score":27.05,"metric":"percent"},{"benchmark":"squad-v2.0","model":"olmo-1.7-7b","score":30.43,"metric":"percent"},{"benchmark":"squad-v2.0","model":"pythia-6.9b","score":22.54,"metric":"percent"},{"benchmark":"squad-v2.0","model":"pythia-12b","score":23.11,"metric":"percent"},{"benchmark":"squad-v2.0","model":"map-neo-7b","score":30.98,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b","score":20.76,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-v0.1","score":15.74,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b","score":6.14,"metric":"percent"},{"benchmark":"math","model":"amber-7b","score":3.88,"metric":"percent"},{"benchmark":"math","model":"olmo-7b","score":1.6,"metric":"percent"},{"benchmark":"math","model":"olmo-1.7-7b","score":4.86,"metric":"percent"},{"benchmark":"math","model":"pythia-6.9b","score":3.82,"metric":"percent"},{"benchmark":"math","model":"pythia-12b","score":4.54,"metric":"percent"},{"benchmark":"math","model":"map-neo-7b","score":20.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b","score":54.74,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.1","score":47.46,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b","score":16.22,"metric":"percent"},{"benchmark":"gsm8k","model":"amber-7b","score":3.64,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-7b","score":5.84,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-1.7-7b","score":28.43,"metric":"percent"},{"benchmark":"gsm8k","model":"pythia-6.9b","score":3.41,"metric":"percent"},{"benchmark":"gsm8k","model":"pythia-12b","score":3.94,"metric":"percent"},{"benchmark":"gsm8k","model":"map-neo-7b","score":53.68,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-8b","score":49.83,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b-v0.1","score":47.54,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b","score":32.37,"metric":"percent"},{"benchmark":"c-eval","model":"amber-7b","score":23.82,"metric":"percent"},{"benchmark":"c-eval","model":"olmo-7b","score":27.39,"metric":"percent"},{"benchmark":"c-eval","model":"olmo-1.7-7b","score":35.21,"metric":"percent"},{"benchmark":"c-eval","model":"pythia-6.9b","score":24.64,"metric":"percent"},{"benchmark":"c-eval","model":"pythia-12b","score":24.82,"metric":"percent"},{"benchmark":"c-eval","model":"map-neo-7b","score":57.68,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-8b","score":50.72,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b-v0.1","score":44.63,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b","score":31.85,"metric":"percent"},{"benchmark":"cmmlu","model":"amber-7b","score":25.77,"metric":"percent"},{"benchmark":"cmmlu","model":"olmo-7b","score":25.53,"metric":"percent"},{"benchmark":"cmmlu","model":"olmo-1.7-7b","score":36.74,"metric":"percent"},{"benchmark":"cmmlu","model":"pythia-6.9b","score":25.34,"metric":"percent"},{"benchmark":"cmmlu","model":"pythia-12b","score":24.88,"metric":"percent"},{"benchmark":"cmmlu","model":"map-neo-7b","score":55.1,"metric":"percent"},{"benchmark":"alignbench","model":"llama-3-8b-instruct","score":6.17,"metric":"score"},{"benchmark":"alignbench","model":"mistral-7b-instruct-v0.2","score":5.27,"metric":"score"},{"benchmark":"alignbench","model":"llama-2-7b-chat","score":4.33,"metric":"score"},{"benchmark":"alignbench","model":"amberchat","score":2.85,"metric":"score"},{"benchmark":"alignbench","model":"olmo-7b-instruct","score":3.2,"metric":"score"},{"benchmark":"alignbench","model":"map-neo-7b-sft","score":4.63,"metric":"score"},{"benchmark":"alignbench","model":"map-neo-7b-instruct","score":5.04,"metric":"score"},{"benchmark":"alpacaeval-2.0","model":"llama-3-8b-instruct","score":22.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"mistral-7b-instruct-v0.2","score":17.1,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-2-7b-chat","score":5.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"amberchat","score":1.21,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"olmo-7b-instruct","score":3.64,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"map-neo-7b-sft","score":9.77,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"map-neo-7b-instruct","score":16.65,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3-8b-instruct","score":20.6,"metric":"percent"},{"benchmark":"arena-hard","model":"mistral-7b-instruct-v0.2","score":12.6,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-2-7b-chat","score":4.6,"metric":"percent"},{"benchmark":"arena-hard","model":"amberchat","score":1.2,"metric":"percent"},{"benchmark":"arena-hard","model":"olmo-7b-instruct","score":1.7,"metric":"percent"},{"benchmark":"arena-hard","model":"map-neo-7b-sft","score":10,"metric":"percent"},{"benchmark":"arena-hard","model":"map-neo-7b-instruct","score":11.5,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3-8b-instruct","score":8.1,"metric":"percent"},{"benchmark":"mt-bench","model":"mistral-7b-instruct-v0.2","score":7.5,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-2-7b-chat","score":6.6,"metric":"percent"},{"benchmark":"mt-bench","model":"amberchat","score":5.2,"metric":"percent"},{"benchmark":"mt-bench","model":"olmo-7b-instruct","score":5.3,"metric":"percent"},{"benchmark":"mt-bench","model":"map-neo-7b-sft","score":7.1,"metric":"percent"},{"benchmark":"mt-bench","model":"map-neo-7b-instruct","score":7.1,"metric":"percent"},{"benchmark":"boolq","model":"llama-3-8b-instruct","score":75.05,"metric":"percent"},{"benchmark":"boolq","model":"mistral-7b-instruct-v0.2","score":82.87,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-7b-chat","score":74.77,"metric":"percent"},{"benchmark":"boolq","model":"amberchat","score":66.51,"metric":"percent"},{"benchmark":"boolq","model":"olmo-7b-instruct","score":72.2,"metric":"percent"},{"benchmark":"boolq","model":"map-neo-7b-sft","score":84.59,"metric":"percent"},{"benchmark":"boolq","model":"map-neo-7b-instruct","score":81.28,"metric":"percent"},{"benchmark":"piqa","model":"llama-3-8b-instruct","score":80.09,"metric":"percent"},{"benchmark":"piqa","model":"mistral-7b-instruct-v0.2","score":82.43,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-7b-chat","score":76.01,"metric":"percent"},{"benchmark":"piqa","model":"amberchat","score":77.48,"metric":"percent"},{"benchmark":"piqa","model":"olmo-7b-instruct","score":75.3,"metric":"percent"},{"benchmark":"piqa","model":"map-neo-7b-sft","score":76.06,"metric":"percent"},{"benchmark":"piqa","model":"map-neo-7b-instruct","score":75.24,"metric":"percent"},{"benchmark":"siqa","model":"llama-3-8b-instruct","score":51.23,"metric":"percent"},{"benchmark":"siqa","model":"mistral-7b-instruct-v0.2","score":50.41,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-7b-chat","score":48.72,"metric":"percent"},{"benchmark":"siqa","model":"amberchat","score":44.88,"metric":"percent"},{"benchmark":"siqa","model":"olmo-7b-instruct","score":48.41,"metric":"percent"},{"benchmark":"siqa","model":"map-neo-7b-sft","score":51.69,"metric":"percent"},{"benchmark":"siqa","model":"map-neo-7b-instruct","score":52.25,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3-8b-instruct","score":71.39,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-instruct-v0.2","score":80.11,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b-chat","score":71.32,"metric":"percent"},{"benchmark":"hellaswag","model":"amberchat","score":67.84,"metric":"percent"},{"benchmark":"hellaswag","model":"olmo-7b-instruct","score":75.18,"metric":"percent"},{"benchmark":"hellaswag","model":"map-neo-7b-sft","score":68.5,"metric":"percent"},{"benchmark":"hellaswag","model":"map-neo-7b-instruct","score":68.7,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3-8b-instruct","score":71.9,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b-instruct-v0.2","score":73.4,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-7b-chat","score":68.35,"metric":"percent"},{"benchmark":"winogrande","model":"amberchat","score":64.96,"metric":"percent"},{"benchmark":"winogrande","model":"olmo-7b-instruct","score":66.69,"metric":"percent"},{"benchmark":"winogrande","model":"map-neo-7b-sft","score":65.19,"metric":"percent"},{"benchmark":"winogrande","model":"map-neo-7b-instruct","score":66.06,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-8b-instruct","score":81.36,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-instruct-v0.2","score":73.56,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-7b-chat","score":55.59,"metric":"percent"},{"benchmark":"arc-challenge","model":"amberchat","score":37.29,"metric":"percent"},{"benchmark":"arc-challenge","model":"olmo-7b-instruct","score":57.63,"metric":"percent"},{"benchmark":"arc-challenge","model":"map-neo-7b-sft","score":80,"metric":"percent"},{"benchmark":"arc-challenge","model":"map-neo-7b-instruct","score":80,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-3-8b-instruct","score":87,"metric":"percent"},{"benchmark":"openbookqa","model":"mistral-7b-instruct-v0.2","score":85.4,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-7b-chat","score":74.4,"metric":"percent"},{"benchmark":"openbookqa","model":"amberchat","score":36.6,"metric":"percent"},{"benchmark":"openbookqa","model":"olmo-7b-instruct","score":74,"metric":"percent"},{"benchmark":"openbookqa","model":"map-neo-7b-sft","score":85.4,"metric":"percent"},{"benchmark":"openbookqa","model":"map-neo-7b-instruct","score":85.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-3-8b-instruct","score":73.55,"metric":"percent"},{"benchmark":"commonsenseqa","model":"mistral-7b-instruct-v0.2","score":75.84,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-2-7b-chat","score":70.11,"metric":"percent"},{"benchmark":"commonsenseqa","model":"amberchat","score":60.28,"metric":"percent"},{"benchmark":"commonsenseqa","model":"olmo-7b-instruct","score":63.47,"metric":"percent"},{"benchmark":"commonsenseqa","model":"map-neo-7b-sft","score":68.39,"metric":"percent"},{"benchmark":"commonsenseqa","model":"map-neo-7b-instruct","score":70.35,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-8b-instruct","score":38.12,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-7b-instruct-v0.2","score":30.86,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-2-7b-chat","score":21.61,"metric":"percent"},{"benchmark":"mmlu-pro","model":"amberchat","score":14.65,"metric":"percent"},{"benchmark":"mmlu-pro","model":"olmo-7b-instruct","score":16.27,"metric":"percent"},{"benchmark":"mmlu-pro","model":"map-neo-7b-sft","score":28.08,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-8b-instruct","score":67.1,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-instruct-v0.2","score":60.81,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b-chat","score":48.22,"metric":"percent"},{"benchmark":"mmlu","model":"amberchat","score":38.8,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-7b-instruct","score":47.47,"metric":"percent"},{"benchmark":"mmlu","model":"map-neo-7b-sft","score":58.28,"metric":"percent"},{"benchmark":"mmlu","model":"map-neo-7b-instruct","score":58.28,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-8b-instruct","score":48.8,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b-chat","score":14,"metric":"percent"},{"benchmark":"humaneval","model":"amberchat","score":17.7,"metric":"percent"},{"benchmark":"humaneval","model":"olmo-7b-instruct","score":14.63,"metric":"percent"},{"benchmark":"humaneval","model":"map-neo-7b-sft","score":34.1,"metric":"percent"},{"benchmark":"humaneval","model":"map-neo-7b-instruct","score":45.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3-8b-instruct","score":44.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-2-7b-chat","score":12.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"amberchat","score":14,"metric":"percent"},{"benchmark":"humaneval-plus","model":"olmo-7b-instruct","score":12.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"map-neo-7b-sft","score":31.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"map-neo-7b-instruct","score":37.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b-instruct","score":70.1,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-instruct-v0.2","score":39.7,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b-chat","score":29.1,"metric":"percent"},{"benchmark":"mbpp","model":"amberchat","score":28,"metric":"percent"},{"benchmark":"mbpp","model":"olmo-7b-instruct","score":20.1,"metric":"percent"},{"benchmark":"mbpp","model":"map-neo-7b-sft","score":44.4,"metric":"percent"},{"benchmark":"mbpp","model":"map-neo-7b-instruct","score":44.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-8b-instruct","score":59.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistral-7b-instruct-v0.2","score":33.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-2-7b-chat","score":22.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"amberchat","score":23.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"olmo-7b-instruct","score":16.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"map-neo-7b-sft","score":38.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"map-neo-7b-instruct","score":36,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-3-8b-instruct","score":8.25,"metric":"percent"},{"benchmark":"naturalquestions","model":"mistral-7b-instruct-v0.2","score":1.14,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b-chat","score":1.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"amberchat","score":3.02,"metric":"percent"},{"benchmark":"naturalquestions","model":"olmo-7b-instruct","score":0.53,"metric":"percent"},{"benchmark":"naturalquestions","model":"map-neo-7b-sft","score":3.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"map-neo-7b-instruct","score":2.41,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-3-8b-instruct","score":56.32,"metric":"percent"},{"benchmark":"triviaqa","model":"mistral-7b-instruct-v0.2","score":45.06,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-7b-chat","score":46.79,"metric":"percent"},{"benchmark":"triviaqa","model":"amberchat","score":30.95,"metric":"percent"},{"benchmark":"triviaqa","model":"olmo-7b-instruct","score":27.91,"metric":"percent"},{"benchmark":"triviaqa","model":"map-neo-7b-sft","score":38.77,"metric":"percent"},{"benchmark":"triviaqa","model":"map-neo-7b-instruct","score":27.09,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llama-3-8b-instruct","score":66.99,"metric":"percent"},{"benchmark":"squad-v2.0","model":"mistral-7b-instruct-v0.2","score":15.01,"metric":"percent"},{"benchmark":"squad-v2.0","model":"llama-2-7b-chat","score":19.61,"metric":"percent"},{"benchmark":"squad-v2.0","model":"amberchat","score":13.12,"metric":"percent"},{"benchmark":"squad-v2.0","model":"olmo-7b-instruct","score":42.13,"metric":"percent"},{"benchmark":"squad-v2.0","model":"map-neo-7b-sft","score":44.58,"metric":"percent"},{"benchmark":"squad-v2.0","model":"map-neo-7b-instruct","score":25.2,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b-instruct","score":29.28,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-instruct-v0.2","score":13.14,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b-chat","score":6.9,"metric":"percent"},{"benchmark":"math","model":"amberchat","score":4.2,"metric":"percent"},{"benchmark":"math","model":"olmo-7b-instruct","score":1.8,"metric":"percent"},{"benchmark":"math","model":"map-neo-7b-sft","score":35.36,"metric":"percent"},{"benchmark":"math","model":"map-neo-7b-instruct","score":35.58,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b-instruct","score":79.23,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-instruct-v0.2","score":49.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b-chat","score":26,"metric":"percent"},{"benchmark":"gsm8k","model":"amberchat","score":7.59,"metric":"percent"},{"benchmark":"gsm8k","model":"olmo-7b-instruct","score":13.5,"metric":"percent"},{"benchmark":"gsm8k","model":"map-neo-7b-sft","score":72.02,"metric":"percent"},{"benchmark":"gsm8k","model":"map-neo-7b-instruct","score":73.16,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-8b-instruct","score":50.76,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b-instruct-v0.2","score":43.72,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b-chat","score":35.67,"metric":"percent"},{"benchmark":"c-eval","model":"amberchat","score":26.29,"metric":"percent"},{"benchmark":"c-eval","model":"olmo-7b-instruct","score":35.18,"metric":"percent"},{"benchmark":"c-eval","model":"map-neo-7b-sft","score":55.42,"metric":"percent"},{"benchmark":"c-eval","model":"map-neo-7b-instruct","score":56.97,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-8b-instruct","score":51.68,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b-instruct-v0.2","score":42.67,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b-chat","score":33.9,"metric":"percent"},{"benchmark":"cmmlu","model":"amberchat","score":30.09,"metric":"percent"},{"benchmark":"cmmlu","model":"olmo-7b-instruct","score":35.55,"metric":"percent"},{"benchmark":"cmmlu","model":"map-neo-7b-sft","score":55.27,"metric":"percent"},{"benchmark":"cmmlu","model":"map-neo-7b-instruct","score":55.01,"metric":"percent"},{"benchmark":"humaneval","model":"code-davinci-002","score":47,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5-turbo","score":66.5,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4","score":86.6,"metric":"percent"},{"benchmark":"humaneval","model":"palm-coder-540b","score":35.9,"metric":"percent"},{"benchmark":"humaneval","model":"palm-2-s","score":37.6,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":30.5,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-34b-unnatural","score":62.2,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-python-34b","score":53.7,"metric":"percent"},{"benchmark":"humaneval","model":"codet5plus-16b","score":30.9,"metric":"percent"},{"benchmark":"humaneval","model":"instructcodet5plus-16b","score":35,"metric":"percent"},{"benchmark":"humaneval","model":"wizardcoder-15b-v1.0","score":57.3,"metric":"percent"},{"benchmark":"humaneval","model":"yuan2.0-2b","score":54.9,"metric":"percent"},{"benchmark":"humaneval","model":"yuan2.0-51b","score":66.5,"metric":"percent"},{"benchmark":"humaneval","model":"yuan2.0-102b","score":67.1,"metric":"percent"},{"benchmark":"gsm8k","model":"palm-2","score":91,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5-turbo","score":68.6,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5","score":57.1,"metric":"percent"},{"benchmark":"gsm8k","model":"palm-540b","score":56.5,"metric":"percent"},{"benchmark":"gsm8k","model":"chinchilla-70b","score":43.7,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3","score":34,"metric":"percent"},{"benchmark":"gsm8k","model":"yuan2.0-2b","score":66.6,"metric":"percent"},{"benchmark":"gsm8k","model":"yuan2.0-51b","score":76.3,"metric":"percent"},{"benchmark":"gsm8k","model":"yuan2.0-102b","score":76.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"gpt-4","score":59,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-2-13b-chat","score":54,"metric":"percent"},{"benchmark":"truthfulqa","model":"gpt-3.5-turbo","score":34,"metric":"percent"},{"benchmark":"truthfulqa","model":"gopher-280b","score":29.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"gpt-3","score":21,"metric":"percent"},{"benchmark":"truthfulqa","model":"opt-175b","score":21,"metric":"percent"},{"benchmark":"truthfulqa","model":"yuan2.0-102b","score":58,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b-instruct","score":81.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-8b-instruct","score":62.2,"metric":"percent"},{"benchmark":"humaneval","model":"phi-3-medium-4k-instruct","score":62.2,"metric":"percent"},{"benchmark":"humaneval","model":"phi-3-small-8k-instruct","score":61,"metric":"percent"},{"benchmark":"humaneval","model":"phi-3-mini-4k-instruct","score":58.5,"metric":"percent"},{"benchmark":"humaneval","model":"yuan2.0-m32","score":74.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b-instruct","score":79.6,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3-medium-4k-instruct","score":91,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3-small-8k-instruct","score":89.6,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-3-mini-4k-instruct","score":82.5,"metric":"percent"},{"benchmark":"gsm8k","model":"yuan2.0-m32","score":92.7,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b-instruct","score":30,"metric":"percent"},{"benchmark":"math","model":"yuan2.0-m32","score":55.9,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-8b-instruct","score":68.4,"metric":"percent"},{"benchmark":"mmlu","model":"phi-3-medium-4k-instruct","score":78,"metric":"percent"},{"benchmark":"mmlu","model":"phi-3-small-8k-instruct","score":75.7,"metric":"percent"},{"benchmark":"mmlu","model":"phi-3-mini-4k-instruct","score":68.8,"metric":"percent"},{"benchmark":"mmlu","model":"yuan2.0-m32","score":72.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-70b-instruct","score":93.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-8b-instruct","score":78.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-3-medium-4k-instruct","score":91.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-3-small-8k-instruct","score":90.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-3-mini-4k-instruct","score":84.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"yuan2.0-m32","score":95.8,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x7b","score":70.86,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-13b-2","score":63.5,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-13b","score":28.8,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b","score":35.6,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-13b-2","score":66.2,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-13b","score":59.1,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-1-13b","score":31.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-13b-2","score":67.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-13b","score":53.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-13b-base","score":54.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-13b","score":26.4,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-13b","score":35.4,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-13b-2","score":61.2,"metric":"percent"},{"benchmark":"agieval","model":"xverse-13b-2","score":54.5,"metric":"percent"},{"benchmark":"agieval","model":"xverse-13b","score":41.4,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-13b-base","score":48.2,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-13b","score":27.3,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-13b","score":33.4,"metric":"percent"},{"benchmark":"race-middle","model":"xverse-13b-2","score":84.6,"metric":"percent"},{"benchmark":"race-middle","model":"xverse-13b","score":74.2,"metric":"percent"},{"benchmark":"race-middle","model":"llama-1-13b","score":61.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"xverse-13b-2","score":74,"metric":"percent"},{"benchmark":"commonsenseqa","model":"xverse-13b","score":69.5,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-1-13b","score":62,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-2-13b","score":67.3,"metric":"percent"},{"benchmark":"piqa","model":"xverse-13b-2","score":80.8,"metric":"percent"},{"benchmark":"piqa","model":"xverse-13b","score":79,"metric":"percent"},{"benchmark":"piqa","model":"baichuan2-13b-base","score":78.5,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-13b","score":80.5,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-13b-2","score":54.9,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-13b","score":18.4,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-base","score":52.7,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-13b-2","score":39.6,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-13b","score":15.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-13b","score":15.8,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-13b-chat","score":60.2,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-7b-chat","score":63.7,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-65b-2","score":72.4,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-65b","score":68.6,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-65b","score":38.8,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b","score":49.9,"metric":"percent"},{"benchmark":"c-eval","model":"falcon-180b","score":54.2,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-3.5","score":54.4,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-4","score":68.7,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-65b-2","score":75.1,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-65b","score":72.6,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-1-65b","score":40.6,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-70b","score":53.6,"metric":"percent"},{"benchmark":"cmmlu","model":"falcon-180b","score":57.2,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-3.5","score":53.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-65b-2","score":76.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-65b","score":73.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-65b","score":38.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-70b","score":51.4,"metric":"percent"},{"benchmark":"gaokao-bench","model":"falcon-180b","score":50.5,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-65b-2","score":74.4,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-65b","score":70.8,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-180b","score":70.5,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-3.5","score":70,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4","score":86.4,"metric":"percent"},{"benchmark":"agieval","model":"xverse-65b-2","score":66.2,"metric":"percent"},{"benchmark":"agieval","model":"xverse-65b","score":61.8,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-65b","score":42.4,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-70b","score":51.4,"metric":"percent"},{"benchmark":"agieval","model":"falcon-180b","score":51.3,"metric":"percent"},{"benchmark":"race-middle","model":"xverse-65b-2","score":90.7,"metric":"percent"},{"benchmark":"race-middle","model":"xverse-65b","score":90.6,"metric":"percent"},{"benchmark":"race-middle","model":"llama-1-65b","score":67.9,"metric":"percent"},{"benchmark":"race-middle","model":"llama-2-70b","score":81.5,"metric":"percent"},{"benchmark":"race-middle","model":"falcon-180b","score":87.6,"metric":"percent"},{"benchmark":"race-middle","model":"gpt-3.5","score":85.6,"metric":"percent"},{"benchmark":"race-middle","model":"gpt-4","score":93.7,"metric":"percent"},{"benchmark":"commonsenseqa","model":"xverse-65b-2","score":81.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"xverse-65b","score":79.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-1-65b","score":74,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-2-70b","score":78.5,"metric":"percent"},{"benchmark":"commonsenseqa","model":"falcon-180b","score":82.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"gpt-3.5","score":80.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"gpt-4","score":88.3,"metric":"percent"},{"benchmark":"piqa","model":"xverse-65b-2","score":79.4,"metric":"percent"},{"benchmark":"piqa","model":"xverse-65b","score":80.4,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-70b","score":82.8,"metric":"percent"},{"benchmark":"piqa","model":"falcon-180b","score":85.3,"metric":"percent"},{"benchmark":"piqa","model":"gpt-3.5","score":81.7,"metric":"percent"},{"benchmark":"piqa","model":"gpt-4","score":89.2,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-65b-2","score":72.6,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-65b","score":60.3,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-180b","score":62.6,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-65b-2","score":37.8,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-65b","score":26.8,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5","score":48.1,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4","score":67,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan-7b","score":42.3,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-base","score":54.2,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-chat","score":53.2,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b","score":45.5,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-7b","score":27.8,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-7b","score":51,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-chat-7b","score":50.8,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-7b","score":35.1,"metric":"percent"},{"benchmark":"mmlu","model":"mpt-7b","score":29.6,"metric":"percent"},{"benchmark":"mmlu","model":"vicuna-7b-v1.5","score":49.8,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-7b","score":56.6,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan-7b","score":42.8,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-base","score":54,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-chat","score":52.2,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm2-6b","score":50.1,"metric":"percent"},{"benchmark":"c-eval","model":"falcon-7b","score":25.8,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-7b","score":52.4,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-chat-7b","score":52.8,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-7b","score":27,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b","score":28.9,"metric":"percent"},{"benchmark":"c-eval","model":"mpt-7b","score":27.8,"metric":"percent"},{"benchmark":"c-eval","model":"vicuna-7b-v1.5","score":22.9,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-7b","score":57.1,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-7b-chat","score":55.4,"metric":"percent"},{"benchmark":"agieval","model":"baichuan-7b","score":34.4,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-7b-base","score":42.7,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-7b-chat","score":41.3,"metric":"percent"},{"benchmark":"agieval","model":"chatglm2-6b","score":42.6,"metric":"percent"},{"benchmark":"agieval","model":"falcon-7b","score":26.2,"metric":"percent"},{"benchmark":"agieval","model":"internlm-7b","score":34.1,"metric":"percent"},{"benchmark":"agieval","model":"internlm-chat-7b","score":39,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-7b","score":27.4,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-7b","score":27,"metric":"percent"},{"benchmark":"agieval","model":"mpt-7b","score":24.2,"metric":"percent"},{"benchmark":"agieval","model":"vicuna-7b-v1.5","score":26.7,"metric":"percent"},{"benchmark":"agieval","model":"xverse-7b","score":46.9,"metric":"percent"},{"benchmark":"agieval","model":"xverse-7b-chat","score":48.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan-7b","score":36.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-7b-base","score":47.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-7b-chat","score":49.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm2-6b","score":54.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"falcon-7b","score":26.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm-7b","score":53.6,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm-chat-7b","score":67.4,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-7b","score":26,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-7b","score":27.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"mpt-7b","score":25.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"vicuna-7b-v1.5","score":24.4,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-7b","score":61.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-7b-chat","score":57.5,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-moe-a4.2b","score":60.5,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-13b-2","score":62,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b-v0.1","score":45.1,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-7b","score":50,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-moe-a4.2b","score":64.5,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-13b-2","score":65.4,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-7b","score":61.3,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b-v0.1","score":44.9,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-7b","score":50.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-moe-a4.2b","score":60.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-13b-2","score":65.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"deepseek-llm-7b-base","score":35.4,"metric":"percent"},{"benchmark":"gaokao-bench","model":"mistral-7b-v0.1","score":40.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"gemma-7b","score":42.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"deepseek-moe-16b-base","score":29.1,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-moe-a4.2b","score":60.2,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-13b-2","score":60,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-v0.1","score":62.5,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-7b","score":64.3,"metric":"percent"},{"benchmark":"agieval","model":"xverse-moe-a4.2b","score":48,"metric":"percent"},{"benchmark":"agieval","model":"xverse-13b-2","score":52.4,"metric":"percent"},{"benchmark":"agieval","model":"mistral-7b-v0.1","score":41.2,"metric":"percent"},{"benchmark":"agieval","model":"gemma-7b","score":41.7,"metric":"percent"},{"benchmark":"agieval","model":"deepseek-moe-16b-base","score":31.7,"metric":"percent"},{"benchmark":"race-middle","model":"xverse-moe-a4.2b","score":75.4,"metric":"percent"},{"benchmark":"race-middle","model":"xverse-13b-2","score":82.4,"metric":"percent"},{"benchmark":"race-middle","model":"xverse-7b","score":79,"metric":"percent"},{"benchmark":"race-middle","model":"mistral-7b-v0.1","score":67.5,"metric":"percent"},{"benchmark":"race-middle","model":"gemma-7b","score":80.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"xverse-moe-a4.2b","score":70,"metric":"percent"},{"benchmark":"commonsenseqa","model":"xverse-13b-2","score":68,"metric":"percent"},{"benchmark":"commonsenseqa","model":"xverse-7b","score":64.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"deepseek-llm-7b-base","score":56.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"mistral-7b-v0.1","score":68.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"gemma-7b","score":74,"metric":"percent"},{"benchmark":"commonsenseqa","model":"deepseek-moe-16b-base","score":54.8,"metric":"percent"},{"benchmark":"piqa","model":"xverse-moe-a4.2b","score":81.4,"metric":"percent"},{"benchmark":"piqa","model":"xverse-13b-2","score":79.8,"metric":"percent"},{"benchmark":"piqa","model":"xverse-7b","score":76.7,"metric":"percent"},{"benchmark":"piqa","model":"mistral-7b-v0.1","score":82.2,"metric":"percent"},{"benchmark":"piqa","model":"gemma-7b","score":81.2,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-moe-a4.2b","score":51.2,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-13b-2","score":52.7,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-7b","score":19.3,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.1","score":35.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-7b","score":46.4,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-moe-a4.2b","score":29.9,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-13b-2","score":32.3,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-7b","score":10.4,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-v0.1","score":26.2,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-7b","score":32.3,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-moe-a36b","score":80.8,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-moe-a36b","score":79.5,"metric":"percent"},{"benchmark":"c-eval","model":"mixtral-8x22b","score":56.8,"metric":"percent"},{"benchmark":"c-eval","model":"dbrx-instruct-preview","score":44.9,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-moe-a36b","score":81.7,"metric":"percent"},{"benchmark":"cmmlu","model":"mixtral-8x22b","score":59.9,"metric":"percent"},{"benchmark":"cmmlu","model":"dbrx-instruct-preview","score":61.3,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-moe-a36b","score":89.5,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b","score":82.3,"metric":"percent"},{"benchmark":"gsm8k","model":"dbrx-instruct-preview","score":70.7,"metric":"percent"},{"benchmark":"math","model":"xverse-moe-a36b","score":53.3,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x22b","score":34.1,"metric":"percent"},{"benchmark":"math","model":"dbrx-instruct-preview","score":25.6,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-moe-a36b","score":51.8,"metric":"percent"},{"benchmark":"humaneval","model":"dbrx-instruct-preview","score":46.3,"metric":"percent"},{"benchmark":"mbpp","model":"xverse-moe-a36b","score":59.8,"metric":"percent"},{"benchmark":"mbpp","model":"dbrx-instruct-preview","score":58,"metric":"percent"},{"benchmark":"piqa","model":"xverse-moe-a36b","score":84.8,"metric":"percent"},{"benchmark":"piqa","model":"mixtral-8x22b","score":84.1,"metric":"percent"},{"benchmark":"piqa","model":"dbrx-instruct-preview","score":84.5,"metric":"percent"},{"benchmark":"race-middle","model":"xverse-moe-a36b","score":88.4,"metric":"percent"},{"benchmark":"race-middle","model":"mixtral-8x22b","score":85.7,"metric":"percent"},{"benchmark":"race-middle","model":"dbrx-instruct-preview","score":55.9,"metric":"percent"},{"benchmark":"mmlu","model":"nemotron-4-340b-base","score":81.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-110b","score":80.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-72b","score":84.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-110b","score":89.1,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-72b","score":91,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-110b","score":88.3,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2-72b","score":90.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-110b","score":85.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-72b","score":89.5,"metric":"percent"},{"benchmark":"math","model":"xverse-65b-2","score":20.8,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-110b","score":49.6,"metric":"percent"},{"benchmark":"math","model":"qwen2-72b","score":51.1,"metric":"percent"},{"benchmark":"humaneval","model":"nemotron-4-340b-base","score":57.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-110b","score":54.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-72b","score":64.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-72b","score":46.3,"metric":"percent"},{"benchmark":"mbpp","model":"xverse-65b-2","score":40.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-110b","score":70.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-72b","score":76.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-72b","score":66.9,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-70b-base","score":66.2,"metric":"percent"},{"benchmark":"piqa","model":"llama-3.1-405b-base","score":85.6,"metric":"percent"},{"benchmark":"piqa","model":"llama-3.1-70b-base","score":83.8,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4o-2024-05-13","score":88.7,"metric":"percent"},{"benchmark":"mmlu","model":"abab6.5","score":78.7,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan-3","score":81.7,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4-0520","score":83.3,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan-3","score":78.1,"metric":"percent"},{"benchmark":"gsm8k","model":"abab6.5","score":91.7,"metric":"percent"},{"benchmark":"gsm8k","model":"step-2","score":94,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4-0520","score":93.3,"metric":"percent"},{"benchmark":"math","model":"abab6.5","score":51.3,"metric":"percent"},{"benchmark":"math","model":"step-2","score":68.4,"metric":"percent"},{"benchmark":"math","model":"glm-4-0520","score":61.3,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-2024-05-13","score":90.2,"metric":"percent"},{"benchmark":"humaneval","model":"abab6.5","score":78,"metric":"percent"},{"benchmark":"humaneval","model":"step-2","score":84.1,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan-3","score":70.1,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4-0520","score":78.5,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan-3","score":68.2,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-3.5-turbo","score":52.5,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b","score":32.5,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm2-6b-base","score":51.7,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-base","score":56.3,"metric":"percent"},{"benchmark":"c-eval","model":"bluelm-7b-base","score":67.5,"metric":"percent"},{"benchmark":"c-eval","model":"bluelm-7b-chat","score":72.7,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-3.5-turbo","score":70,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b-base","score":47.9,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-base","score":54.7,"metric":"percent"},{"benchmark":"mmlu","model":"bluelm-7b-base","score":55.2,"metric":"percent"},{"benchmark":"mmlu","model":"bluelm-7b-chat","score":50.7,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-4","score":71.2,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-3.5-turbo","score":53.9,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b","score":31.8,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm2-6b-base","score":50,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-base","score":57,"metric":"percent"},{"benchmark":"cmmlu","model":"bluelm-7b-base","score":66.6,"metric":"percent"},{"benchmark":"cmmlu","model":"bluelm-7b-chat","score":74.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"gpt-4","score":72.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"gpt-3.5-turbo","score":51.1,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-7b","score":18.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-7b-base","score":34.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"bluelm-7b-base","score":58.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"bluelm-7b-chat","score":48.7,"metric":"percent"},{"benchmark":"agieval","model":"gpt-4","score":55.1,"metric":"percent"},{"benchmark":"agieval","model":"gpt-3.5-turbo","score":39.9,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-7b","score":21.8,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-7b-base","score":34.6,"metric":"percent"},{"benchmark":"agieval","model":"bluelm-7b-base","score":43.4,"metric":"percent"},{"benchmark":"agieval","model":"bluelm-7b-chat","score":43.4,"metric":"percent"},{"benchmark":"bbh","model":"gpt-4","score":86.7,"metric":"percent"},{"benchmark":"bbh","model":"gpt-3.5-turbo","score":70.1,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-7b","score":38.2,"metric":"percent"},{"benchmark":"bbh","model":"chatglm2-6b-base","score":33.7,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-7b-base","score":41.8,"metric":"percent"},{"benchmark":"bbh","model":"bluelm-7b-base","score":41.7,"metric":"percent"},{"benchmark":"bbh","model":"bluelm-7b-chat","score":65.6,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4","score":91.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5-turbo","score":78.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b","score":16.7,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b-base","score":32.4,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-7b-base","score":24.6,"metric":"percent"},{"benchmark":"gsm8k","model":"bluelm-7b-base","score":27.2,"metric":"percent"},{"benchmark":"gsm8k","model":"bluelm-7b-chat","score":51.9,"metric":"percent"},{"benchmark":"math","model":"gpt-4","score":45.8,"metric":"percent"},{"benchmark":"math","model":"gpt-3.5-turbo","score":28,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b","score":3.3,"metric":"percent"},{"benchmark":"math","model":"chatglm2-6b-base","score":6.5,"metric":"percent"},{"benchmark":"math","model":"baichuan2-7b-base","score":5.4,"metric":"percent"},{"benchmark":"math","model":"bluelm-7b-base","score":6.2,"metric":"percent"},{"benchmark":"math","model":"bluelm-7b-chat","score":13.4,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4","score":74.4,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5-turbo","score":73.2,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-7b-base","score":17.7,"metric":"percent"},{"benchmark":"humaneval","model":"bluelm-7b-base","score":18.3,"metric":"percent"},{"benchmark":"humaneval","model":"bluelm-7b-chat","score":21.3,"metric":"percent"},{"benchmark":"cluewsc","model":"aquila2-34b","score":85.93,"metric":"percent"},{"benchmark":"cluewsc","model":"qwen-14b","score":83.6,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-2-70b","score":85.6,"metric":"percent"},{"benchmark":"cluewsc","model":"internlm-20b","score":85,"metric":"percent"},{"benchmark":"cluewsc","model":"qwen-7b","score":84.7,"metric":"percent"},{"benchmark":"cluewsc","model":"baichuan2-13b-base","score":63.3,"metric":"percent"},{"benchmark":"cluewsc","model":"aquila2-7b","score":75.6,"metric":"percent"},{"benchmark":"cluewsc","model":"baichuan2-7b-base","score":49.2,"metric":"percent"},{"benchmark":"cluewsc","model":"internlm-7b","score":63.8,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-2-7b","score":53.9,"metric":"percent"},{"benchmark":"winogrande","model":"aquila2-34b","score":72.85,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-14b","score":71.82,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-70b","score":67.4,"metric":"percent"},{"benchmark":"winogrande","model":"internlm-20b","score":78,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-7b","score":75.1,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan2-13b-base","score":68.59,"metric":"percent"},{"benchmark":"winogrande","model":"aquila2-7b","score":70.3,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan2-7b-base","score":67.5,"metric":"percent"},{"benchmark":"winogrande","model":"internlm-7b","score":68.43,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-7b","score":68.19,"metric":"percent"},{"benchmark":"hellaswag","model":"aquila2-34b","score":82.51,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-14b","score":81.84,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm-20b","score":87.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-7b","score":82.1,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-13b-base","score":78.37,"metric":"percent"},{"benchmark":"hellaswag","model":"aquila2-7b","score":76.1,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-7b-base","score":71.5,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm-7b","score":73.8,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b","score":74.35,"metric":"percent"},{"benchmark":"openbookqa","model":"aquila2-34b","score":44.2,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen-14b","score":45.2,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-70b","score":43.6,"metric":"percent"},{"benchmark":"openbookqa","model":"internlm-20b","score":48.8,"metric":"percent"},{"benchmark":"openbookqa","model":"qwen-7b","score":42.6,"metric":"percent"},{"benchmark":"openbookqa","model":"baichuan2-13b-base","score":44.4,"metric":"percent"},{"benchmark":"openbookqa","model":"aquila2-7b","score":43.6,"metric":"percent"},{"benchmark":"openbookqa","model":"baichuan2-7b-base","score":44.8,"metric":"percent"},{"benchmark":"openbookqa","model":"internlm-7b","score":39.4,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-7b","score":39.8,"metric":"percent"},{"benchmark":"piqa","model":"aquila2-34b","score":74.92,"metric":"percent"},{"benchmark":"piqa","model":"qwen-14b","score":79.6,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-70b","score":81.07,"metric":"percent"},{"benchmark":"piqa","model":"internlm-20b","score":82.8,"metric":"percent"},{"benchmark":"piqa","model":"qwen-7b","score":80.6,"metric":"percent"},{"benchmark":"piqa","model":"baichuan2-13b-base","score":78.18,"metric":"percent"},{"benchmark":"piqa","model":"aquila2-7b","score":78.8,"metric":"percent"},{"benchmark":"piqa","model":"baichuan2-7b-base","score":77.9,"metric":"percent"},{"benchmark":"piqa","model":"internlm-7b","score":77.42,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-7b","score":73.94,"metric":"percent"},{"benchmark":"arc-easy","model":"aquila2-34b","score":79.38,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-14b","score":76.35,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-70b","score":70.41,"metric":"percent"},{"benchmark":"arc-easy","model":"internlm-20b","score":81,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-7b","score":81.1,"metric":"percent"},{"benchmark":"arc-easy","model":"baichuan2-13b-base","score":72.01,"metric":"percent"},{"benchmark":"arc-easy","model":"aquila2-7b","score":73.9,"metric":"percent"},{"benchmark":"arc-easy","model":"baichuan2-7b-base","score":71.5,"metric":"percent"},{"benchmark":"arc-easy","model":"internlm-7b","score":72.9,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-7b","score":69.99,"metric":"percent"},{"benchmark":"boolq","model":"aquila2-34b","score":88.84,"metric":"percent"},{"benchmark":"boolq","model":"qwen-14b","score":89.2,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-70b","score":86.67,"metric":"percent"},{"benchmark":"boolq","model":"internlm-20b","score":83.7,"metric":"percent"},{"benchmark":"boolq","model":"qwen-7b","score":82.1,"metric":"percent"},{"benchmark":"boolq","model":"baichuan2-13b-base","score":68.01,"metric":"percent"},{"benchmark":"boolq","model":"aquila2-7b","score":79.1,"metric":"percent"},{"benchmark":"boolq","model":"baichuan2-7b-base","score":77.6,"metric":"percent"},{"benchmark":"boolq","model":"internlm-7b","score":73,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-7b","score":43.88,"metric":"percent"},{"benchmark":"truthfulqa","model":"aquila2-34b","score":46.99,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen-14b","score":38.75,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-2-70b","score":49.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"internlm-20b","score":44.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen-7b","score":51.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"baichuan2-13b-base","score":47.85,"metric":"percent"},{"benchmark":"truthfulqa","model":"aquila2-7b","score":39.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"baichuan2-7b-base","score":44.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"internlm-7b","score":37.55,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-2-7b","score":39.34,"metric":"percent"},{"benchmark":"ocnli","model":"aquila2-34b","score":79.92,"metric":"percent"},{"benchmark":"ocnli","model":"qwen-14b","score":62.27,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-70b","score":55,"metric":"percent"},{"benchmark":"ocnli","model":"internlm-20b","score":57.6,"metric":"percent"},{"benchmark":"ocnli","model":"qwen-7b","score":62.9,"metric":"percent"},{"benchmark":"ocnli","model":"baichuan2-13b-base","score":51,"metric":"percent"},{"benchmark":"ocnli","model":"aquila2-7b","score":43.3,"metric":"percent"},{"benchmark":"ocnli","model":"baichuan2-7b-base","score":57,"metric":"percent"},{"benchmark":"ocnli","model":"internlm-7b","score":37.1,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-7b","score":36.9,"metric":"percent"},{"benchmark":"mmlu","model":"aquila2-34b","score":73.74,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b","score":67.79,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b","score":65.8,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-20b","score":69.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b","score":61.8,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-base","score":60.16,"metric":"percent"},{"benchmark":"mmlu","model":"aquila2-7b","score":56.9,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-base","score":58.1,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-7b","score":54.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b","score":51.2,"metric":"percent"},{"benchmark":"c-eval","model":"aquila2-34b","score":63.07,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b","score":63.07,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b","score":71.4,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-20b","score":52.1,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b","score":53.7,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-base","score":58.74,"metric":"percent"},{"benchmark":"c-eval","model":"aquila2-7b","score":55.6,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-base","score":50.3,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-7b","score":52.28,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b","score":48.62,"metric":"percent"},{"benchmark":"cmmlu","model":"aquila2-34b","score":73.1,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-14b","score":71.36,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-70b","score":70.5,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-7b","score":59,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-base","score":64.2,"metric":"percent"},{"benchmark":"cmmlu","model":"aquila2-7b","score":62,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-base","score":58.75,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm-7b","score":57.07,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b","score":51.8,"metric":"percent"},{"benchmark":"humaneval","model":"aquila2-34b","score":39.02,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-14b","score":35.4,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":32.3,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-20b","score":29.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b","score":25.6,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-13b-base","score":22.12,"metric":"percent"},{"benchmark":"humaneval","model":"aquila2-7b","score":17.1,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-7b-base","score":21.4,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-7b","score":18.29,"metric":"percent"},{"benchmark":"humaneval","model":"tigerbot-70b-chat","score":31.1,"metric":"percent"},{"benchmark":"humaneval","model":"tigerbot-13b-chat","score":26.83,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b-chat","score":26.22,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b-chat","score":11.59,"metric":"percent"},{"benchmark":"piqa","model":"tigerbot-70b-chat","score":83.57,"metric":"percent"},{"benchmark":"piqa","model":"tigerbot-13b-chat","score":80.09,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-70b-chat","score":80.25,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-13b-chat","score":78.67,"metric":"percent"},{"benchmark":"siqa","model":"tigerbot-70b-chat","score":51.89,"metric":"percent"},{"benchmark":"siqa","model":"tigerbot-13b-chat","score":49.44,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-70b-chat","score":51.59,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-13b-chat","score":50.97,"metric":"percent"},{"benchmark":"hellaswag","model":"tigerbot-70b-chat","score":76.68,"metric":"percent"},{"benchmark":"hellaswag","model":"tigerbot-13b-chat","score":70.63,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-70b-chat","score":77.63,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-13b-chat","score":74.71,"metric":"percent"},{"benchmark":"winogrande","model":"tigerbot-70b-chat","score":67.01,"metric":"percent"},{"benchmark":"winogrande","model":"tigerbot-13b-chat","score":63.3,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-70b-chat","score":68.11,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-13b-chat","score":65.82,"metric":"percent"},{"benchmark":"openbookqa","model":"tigerbot-70b-chat","score":85,"metric":"percent"},{"benchmark":"openbookqa","model":"tigerbot-13b-chat","score":67.4,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-70b-chat","score":85,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-13b-chat","score":80,"metric":"percent"},{"benchmark":"boolq","model":"tigerbot-70b-chat","score":80.67,"metric":"percent"},{"benchmark":"boolq","model":"tigerbot-13b-chat","score":78.87,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-70b-chat","score":78,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-13b-chat","score":78.32,"metric":"percent"},{"benchmark":"gsm8k","model":"tigerbot-70b-chat","score":84.91,"metric":"percent"},{"benchmark":"gsm8k","model":"tigerbot-13b-chat","score":51.25,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b-chat","score":58.91,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b-chat","score":54.62,"metric":"percent"},{"benchmark":"mmlu","model":"tigerbot-70b-chat","score":68.03,"metric":"percent"},{"benchmark":"mmlu","model":"tigerbot-13b-chat","score":55.94,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b-chat","score":64.84,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b-chat","score":54.61,"metric":"percent"},{"benchmark":"c3","model":"tigerbot-70b-chat","score":75.34,"metric":"percent"},{"benchmark":"c3","model":"tigerbot-13b-chat","score":69.42,"metric":"percent"},{"benchmark":"c3","model":"llama-2-70b-chat","score":54.85,"metric":"percent"},{"benchmark":"c3","model":"llama-2-13b-chat","score":51.01,"metric":"percent"},{"benchmark":"ocnli","model":"tigerbot-70b-chat","score":38.07,"metric":"percent"},{"benchmark":"ocnli","model":"tigerbot-13b-chat","score":40.17,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-70b-chat","score":36.23,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-13b-chat","score":30,"metric":"percent"},{"benchmark":"c-eval","model":"tigerbot-70b-chat","score":60.4,"metric":"percent"},{"benchmark":"c-eval","model":"tigerbot-13b-chat","score":48.89,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b-chat","score":44.17,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b-chat","score":39.22,"metric":"percent"},{"benchmark":"cmrc2018","model":"tigerbot-70b-chat","score":85.37,"metric":"percent"},{"benchmark":"cmrc2018","model":"tigerbot-13b-chat","score":76.17,"metric":"percent"},{"benchmark":"cmrc2018","model":"llama-2-70b-chat","score":80.06,"metric":"percent"},{"benchmark":"cmrc2018","model":"llama-2-13b-chat","score":74.62,"metric":"percent"},{"benchmark":"humaneval","model":"tigerbot-70b-base","score":28.66,"metric":"percent"},{"benchmark":"humaneval","model":"tigerbot-13b-base","score":18.29,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":31.1,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b","score":15.27,"metric":"percent"},{"benchmark":"piqa","model":"tigerbot-70b-base","score":83.3,"metric":"percent"},{"benchmark":"piqa","model":"tigerbot-13b-base","score":79.33,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-70b","score":82.21,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-13b","score":79.21,"metric":"percent"},{"benchmark":"siqa","model":"tigerbot-70b-base","score":48.77,"metric":"percent"},{"benchmark":"siqa","model":"tigerbot-13b-base","score":48.52,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-70b","score":46.01,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-13b","score":46.32,"metric":"percent"},{"benchmark":"hellaswag","model":"tigerbot-70b-base","score":78.62,"metric":"percent"},{"benchmark":"hellaswag","model":"tigerbot-13b-base","score":72.64,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-70b","score":79.46,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-13b","score":74.96,"metric":"percent"},{"benchmark":"winogrande","model":"tigerbot-70b-base","score":69.38,"metric":"percent"},{"benchmark":"winogrande","model":"tigerbot-13b-base","score":64.17,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-70b","score":69.69,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-13b","score":64.09,"metric":"percent"},{"benchmark":"openbookqa","model":"tigerbot-70b-base","score":88.6,"metric":"percent"},{"benchmark":"openbookqa","model":"tigerbot-13b-base","score":72.4,"metric":"percent"},{"benchmark":"openbookqa","model":"llama-2-70b","score":57.4,"metric":"percent"},{"benchmark":"boolq","model":"tigerbot-70b-base","score":67.52,"metric":"percent"},{"benchmark":"boolq","model":"tigerbot-13b-base","score":63.18,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-70b","score":69.69,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-13b","score":71.5,"metric":"percent"},{"benchmark":"gsm8k","model":"tigerbot-70b-base","score":65.66,"metric":"percent"},{"benchmark":"gsm8k","model":"tigerbot-13b-base","score":35.86,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b","score":63.99,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b","score":28.81,"metric":"percent"},{"benchmark":"mmlu","model":"tigerbot-70b-base","score":68.68,"metric":"percent"},{"benchmark":"mmlu","model":"tigerbot-13b-base","score":55.35,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b","score":69.58,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b","score":55.81,"metric":"percent"},{"benchmark":"c3","model":"tigerbot-70b-base","score":77.37,"metric":"percent"},{"benchmark":"c3","model":"tigerbot-13b-base","score":67.01,"metric":"percent"},{"benchmark":"c3","model":"llama-2-70b","score":60.16,"metric":"percent"},{"benchmark":"c3","model":"llama-2-13b","score":47.51,"metric":"percent"},{"benchmark":"ocnli","model":"tigerbot-70b-base","score":30,"metric":"percent"},{"benchmark":"ocnli","model":"tigerbot-13b-base","score":30.6,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-70b","score":30.03,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-13b","score":30,"metric":"percent"},{"benchmark":"c-eval","model":"tigerbot-70b-base","score":67.75,"metric":"percent"},{"benchmark":"c-eval","model":"tigerbot-13b-base","score":48.46,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b","score":38.67,"metric":"percent"},{"benchmark":"cmrc2018","model":"tigerbot-70b-base","score":85.93,"metric":"percent"},{"benchmark":"cmrc2018","model":"tigerbot-13b-base","score":66.57,"metric":"percent"},{"benchmark":"cmrc2018","model":"llama-2-70b","score":68.97,"metric":"percent"},{"benchmark":"cmrc2018","model":"llama-2-13b","score":76.73,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b-instruct","score":84.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-7b-instruct","score":91.9,"metric":"percent"},{"benchmark":"gsm8k","model":"skywork-o1-open-llama-3.1-8b","score":91.6,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-8b-instruct","score":49.6,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-7b-instruct","score":75.2,"metric":"percent"},{"benchmark":"math","model":"skywork-o1-open-llama-3.1-8b","score":78.1,"metric":"percent"},{"benchmark":"olympiadbench","model":"llama-3.1-8b-instruct","score":15.4,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2.5-7b-instruct","score":38.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"skywork-o1-open-llama-3.1-8b","score":43.1,"metric":"percent"},{"benchmark":"aime-2024","model":"llama-3.1-8b-instruct","score":10,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-7b-instruct","score":13.3,"metric":"percent"},{"benchmark":"aime-2024","model":"skywork-o1-open-llama-3.1-8b","score":13.3,"metric":"percent"},{"benchmark":"amc-23","model":"llama-3.1-8b-instruct","score":30,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-7b-instruct","score":45,"metric":"percent"},{"benchmark":"amc-23","model":"skywork-o1-open-llama-3.1-8b","score":55,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-8b-instruct","score":72,"metric":"percent"},{"benchmark":"mbpp","model":"skywork-o1-open-llama-3.1-8b","score":77.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3.1-8b-instruct","score":56.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"skywork-o1-open-llama-3.1-8b","score":65.2,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-8b-instruct","score":72,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-7b-instruct","score":84.8,"metric":"percent"},{"benchmark":"humaneval","model":"skywork-o1-open-llama-3.1-8b","score":82.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3.1-8b-instruct","score":66.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"skywork-o1-open-llama-3.1-8b","score":78.7,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-8b-instruct","score":18.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-7b-instruct","score":25.3,"metric":"percent"},{"benchmark":"livecodebench","model":"skywork-o1-open-llama-3.1-8b","score":26,"metric":"percent"},{"benchmark":"c-eval","model":"kwaiyii-13b-base","score":62.6,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm2-12b-base","score":61.6,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b","score":59.6,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan-13b-base","score":53.6,"metric":"percent"},{"benchmark":"c-eval","model":"kwaiyii-13b-chat","score":59,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm2-12b","score":57,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-3.5-turbo","score":54.4,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan-13b-chat","score":51.5,"metric":"percent"},{"benchmark":"mmlu","model":"kwaiyii-13b-base","score":57.42,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b","score":56.7,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-12b-base","score":56.18,"metric":"percent"},{"benchmark":"mmlu","model":"kwaiyii-13b-chat","score":56.44,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-12b","score":52.13,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan-13b-chat","score":52.1,"metric":"percent"},{"benchmark":"cmmlu","model":"kwaiyii-13b-base","score":61.73,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-7b","score":58.66,"metric":"percent"},{"benchmark":"cmmlu","model":"milm-6b","score":57.17,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan-13b-base","score":55.82,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm2-6b-base","score":48.8,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-4","score":70.95,"metric":"percent"},{"benchmark":"cmmlu","model":"kwaiyii-13b-chat","score":59.97,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan-13b-chat","score":55.8,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-3.5-turbo","score":55.51,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b","score":51.6,"metric":"percent"},{"benchmark":"gsm8k","model":"kwaiyii-13b-base","score":48.4,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-12b-base","score":40.94,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan-13b-base","score":22.44,"metric":"percent"},{"benchmark":"gsm8k","model":"kwaiyii-13b-chat","score":52.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b-chat","score":43.5,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-12b","score":38.13,"metric":"percent"},{"benchmark":"humaneval","model":"kwaiyii-13b-base","score":40.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b","score":24.4,"metric":"percent"},{"benchmark":"humaneval","model":"kwaiyii-13b-chat","score":43.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b-chat","score":24.4,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b-chat","score":15.85,"metric":"percent"},{"benchmark":"mmlu","model":"mpt-7b","score":30.8,"metric":"percent"},{"benchmark":"c-eval","model":"mpt-7b","score":23.5,"metric":"percent"},{"benchmark":"gsm8k","model":"mpt-7b","score":9.1,"metric":"percent"},{"benchmark":"math","model":"mpt-7b","score":3,"metric":"percent"},{"benchmark":"mbpp","model":"mpt-7b","score":22.8,"metric":"percent"},{"benchmark":"bbh","model":"mpt-7b","score":35.6,"metric":"percent"},{"benchmark":"mmlu","model":"mpt-30b","score":47.9,"metric":"percent"},{"benchmark":"math","model":"mpt-30b","score":3.1,"metric":"percent"},{"benchmark":"mbpp","model":"mpt-30b","score":32.8,"metric":"percent"},{"benchmark":"bbh","model":"mpt-30b","score":38,"metric":"percent"},{"benchmark":"math","model":"falcon-7b","score":2.3,"metric":"percent"},{"benchmark":"mbpp","model":"falcon-7b","score":11.2,"metric":"percent"},{"benchmark":"bbh","model":"falcon-7b","score":28,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-40b","score":57,"metric":"percent"},{"benchmark":"math","model":"falcon-40b","score":5.5,"metric":"percent"},{"benchmark":"mbpp","model":"falcon-40b","score":29.8,"metric":"percent"},{"benchmark":"bbh","model":"falcon-40b","score":37.1,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b","score":47.9,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm2-6b","score":51.7,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b","score":32.4,"metric":"percent"},{"benchmark":"bbh","model":"chatglm2-6b","score":33.7,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-7b","score":53.4,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-7b","score":31.2,"metric":"percent"},{"benchmark":"math","model":"internlm-7b","score":6.3,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-7b","score":10.4,"metric":"percent"},{"benchmark":"mbpp","model":"internlm-7b","score":14,"metric":"percent"},{"benchmark":"bbh","model":"internlm-7b","score":37,"metric":"percent"},{"benchmark":"math","model":"baichuan2-7b-base","score":5.6,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-7b-base","score":18.3,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-7b-base","score":24.2,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-7b-base","score":41.6,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-13b-base","score":30.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-7b","score":35.6,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-7b","score":27.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-7b","score":11,"metric":"percent"},{"benchmark":"math","model":"llama-1-7b","score":2.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-7b","score":12.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-7b","score":17.7,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-7b","score":33.5,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-13b","score":47.7,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-13b","score":31.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-13b","score":20.3,"metric":"percent"},{"benchmark":"math","model":"llama-1-13b","score":4.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-13b","score":22,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-13b","score":37.9,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-33b","score":58.7,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-33b","score":37.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-33b","score":42.3,"metric":"percent"},{"benchmark":"math","model":"llama-1-33b","score":7.1,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-33b","score":21.7,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-33b","score":30.2,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-33b","score":50,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-65b","score":63.7,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-65b","score":40.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-65b","score":54.4,"metric":"percent"},{"benchmark":"math","model":"llama-1-65b","score":10.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-65b","score":37.7,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-65b","score":58.4,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b","score":20.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-13b","score":30.3,"metric":"percent"},{"benchmark":"math","model":"llama-2-34b","score":6.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b","score":69.8,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b","score":50.1,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b","score":63.3,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-70b","score":45,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-70b","score":64.9,"metric":"percent"},{"benchmark":"mmlu","model":"stablebeluga2-70b","score":68.6,"metric":"percent"},{"benchmark":"c-eval","model":"stablebeluga2-70b","score":51.4,"metric":"percent"},{"benchmark":"gsm8k","model":"stablebeluga2-70b","score":69.6,"metric":"percent"},{"benchmark":"math","model":"stablebeluga2-70b","score":14.6,"metric":"percent"},{"benchmark":"humaneval","model":"stablebeluga2-70b","score":28,"metric":"percent"},{"benchmark":"mbpp","model":"stablebeluga2-70b","score":11.4,"metric":"percent"},{"benchmark":"bbh","model":"stablebeluga2-70b","score":69.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-1.8b","score":44.6,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-1.8b","score":54.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-1.8b","score":21.2,"metric":"percent"},{"benchmark":"math","model":"qwen-1.8b","score":5.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-1.8b","score":17.1,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-1.8b","score":14.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen-1.8b","score":28.2,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b","score":58.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b","score":63.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b","score":51.7,"metric":"percent"},{"benchmark":"math","model":"qwen-7b","score":11.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b","score":29.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-7b","score":31.6,"metric":"percent"},{"benchmark":"bbh","model":"qwen-7b","score":45,"metric":"percent"},{"benchmark":"math","model":"qwen-14b","score":24.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-14b","score":40.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen-14b","score":53.4,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-3.5","score":69.1,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-3.5","score":52.5,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5","score":78.2,"metric":"percent"},{"benchmark":"bbh","model":"gpt-3.5","score":70.1,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b","score":46,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-chat-7b","score":51.1,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-chat-7b","score":53.6,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-chat-7b","score":33,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-chat-7b","score":14.6,"metric":"percent"},{"benchmark":"bbh","model":"internlm-chat-7b","score":32.5,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-chat","score":52.9,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-chat","score":57.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b-chat","score":37.1,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b-chat","score":40.1,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b-chat","score":63.8,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b-chat","score":44.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b-chat","score":59.3,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b-chat","score":32.3,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-70b-chat","score":60.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-1.8b-chat","score":42.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-1.8b-chat","score":43.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-1.8b-chat","score":50.7,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-1.8b-chat","score":50.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-1.8b-chat","score":27.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-1.8b-chat","score":19.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-1.8b-chat","score":14.6,"metric":"percent"},{"benchmark":"bbh","model":"qwen-1.8b-chat","score":27.1,"metric":"percent"},{"benchmark":"bbh","model":"qwen-1.8b-chat","score":25,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b-chat","score":55.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b-chat","score":57,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b-chat","score":59.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b-chat","score":50.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b-chat","score":54.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b-chat","score":37.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen-7b-chat","score":39.6,"metric":"percent"},{"benchmark":"bbh","model":"qwen-7b-chat","score":46.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b-chat","score":64.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b-chat","score":66.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b-chat","score":69.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b-chat","score":60.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b-chat","score":59.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-14b-chat","score":43.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen-14b-chat","score":46.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen-14b-chat","score":58.7,"metric":"percent"},{"benchmark":"humaneval","model":"palm-540b","score":26.2,"metric":"percent"},{"benchmark":"mbpp","model":"palm-540b","score":36.8,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b","score":20.1,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-13b","score":27.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-34b","score":33.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-70b","score":45.4,"metric":"percent"},{"benchmark":"humaneval","model":"codegeex2-6b","score":35.9,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-7b","score":33.5,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b","score":41.4,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-13b","score":47,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-34b","score":48.8,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-34b","score":55,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-7b-instruct","score":34.8,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b-instruct","score":44.4,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-13b-instruct","score":42.7,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-13b-instruct","score":49.4,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-34b-instruct","score":41.5,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-34b-instruct","score":57,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-python-7b","score":38.4,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-python-7b","score":47.6,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-python-13b","score":43.3,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-python-13b","score":49,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-python-34b","score":56.2,"metric":"percent"},{"benchmark":"humaneval","model":"wizardcoder-python-13b-v1.0","score":64,"metric":"percent"},{"benchmark":"mbpp","model":"wizardcoder-python-13b-v1.0","score":55.6,"metric":"percent"},{"benchmark":"mbpp","model":"wizardcoder-python-34b-v1.0","score":61.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-7b-chat","score":35.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-14b-chat","score":46.4,"metric":"percent"},{"benchmark":"humaneval","model":"code-qwen-7b","score":40.2,"metric":"percent"},{"benchmark":"mbpp","model":"code-qwen-7b","score":41.8,"metric":"percent"},{"benchmark":"humaneval","model":"code-qwen-14b","score":45.1,"metric":"percent"},{"benchmark":"mbpp","model":"code-qwen-14b","score":51.4,"metric":"percent"},{"benchmark":"humaneval","model":"code-qwen-7b-chat","score":43.3,"metric":"percent"},{"benchmark":"mbpp","model":"code-qwen-7b-chat","score":44.2,"metric":"percent"},{"benchmark":"humaneval","model":"code-qwen-14b-chat","score":66.4,"metric":"percent"},{"benchmark":"mbpp","model":"code-qwen-14b-chat","score":52.4,"metric":"percent"},{"benchmark":"math","model":"gpt-4","score":42.5,"metric":"percent"},{"benchmark":"gsm8k","model":"wizardmath-7b-v1.0","score":54.9,"metric":"percent"},{"benchmark":"math","model":"wizardmath-7b-v1.0","score":10.7,"metric":"percent"},{"benchmark":"gsm8k","model":"gairmath-abel-7b","score":59.7,"metric":"percent"},{"benchmark":"math","model":"gairmath-abel-7b","score":13,"metric":"percent"},{"benchmark":"gsm8k","model":"gairmath-abel-13b","score":66.4,"metric":"percent"},{"benchmark":"math","model":"gairmath-abel-13b","score":17.3,"metric":"percent"},{"benchmark":"gsm8k","model":"gairmath-abel-70b","score":83.6,"metric":"percent"},{"benchmark":"math","model":"gairmath-abel-70b","score":28.3,"metric":"percent"},{"benchmark":"math","model":"qwen-7b-chat","score":6.8,"metric":"percent"},{"benchmark":"math","model":"qwen-14b-chat","score":18.4,"metric":"percent"},{"benchmark":"gsm8k","model":"math-qwen-7b-chat","score":62.5,"metric":"percent"},{"benchmark":"math","model":"math-qwen-7b-chat","score":17.2,"metric":"percent"},{"benchmark":"gsm8k","model":"math-qwen-14b-chat","score":69.8,"metric":"percent"},{"benchmark":"math","model":"math-qwen-14b-chat","score":24.2,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-12b","score":56.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-33b","score":57.8,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-7b","score":52.8,"metric":"percent"},{"benchmark":"cmmlu","model":"mpt-7b","score":25.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"mpt-7b","score":19.8,"metric":"percent"},{"benchmark":"arc-easy","model":"mpt-7b","score":70.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"mpt-7b","score":42.6,"metric":"percent"},{"benchmark":"arc-easy","model":"falcon-7b","score":70,"metric":"percent"},{"benchmark":"arc-challenge","model":"falcon-7b","score":42.4,"metric":"percent"},{"benchmark":"arc-easy","model":"chatglm2-6b","score":73,"metric":"percent"},{"benchmark":"arc-challenge","model":"chatglm2-6b","score":61,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm-7b","score":51.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm-7b","score":43,"metric":"percent"},{"benchmark":"arc-easy","model":"internlm-7b","score":78.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"internlm-7b","score":69.5,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-base","score":57.1,"metric":"percent"},{"benchmark":"arc-easy","model":"baichuan2-7b-base","score":54.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"baichuan2-7b-base","score":32.5,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-1-7b","score":26.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-7b","score":21.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-13b","score":20.4,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-1-33b","score":36,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-33b","score":18.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-1-33b","score":67.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-65b","score":19.1,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-1-65b","score":80.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-1-65b","score":69.5,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-7b","score":75.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-7b","score":45.9,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-13b","score":77.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-70b","score":23.3,"metric":"percent"},{"benchmark":"arc-easy","model":"llama-2-70b","score":85.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-2-70b","score":78.3,"metric":"percent"},{"benchmark":"cmmlu","model":"stablebeluga2-70b","score":51.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"stablebeluga2-70b","score":40.9,"metric":"percent"},{"benchmark":"arc-easy","model":"stablebeluga2-70b","score":91.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"stablebeluga2-70b","score":86.1,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-1.8b","score":49.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-1.8b","score":44.9,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-1.8b","score":71.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-1.8b","score":53.2,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-7b","score":62.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-7b","score":52.5,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-7b","score":84,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen-7b","score":75.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-14b","score":61.9,"metric":"percent"},{"benchmark":"arc-easy","model":"qwen-14b","score":90.3,"metric":"percent"},{"benchmark":"commonsenseqa","model":"mpt-7b","score":61.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"mpt-7b","score":11.6,"metric":"percent"},{"benchmark":"lambada","model":"mpt-7b","score":70,"metric":"percent"},{"benchmark":"commonsenseqa","model":"falcon-7b","score":20.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"falcon-7b","score":15.7,"metric":"percent"},{"benchmark":"boolq","model":"chatglm2-6b","score":79,"metric":"percent"},{"benchmark":"commonsenseqa","model":"chatglm2-6b","score":65.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"chatglm2-6b","score":9.7,"metric":"percent"},{"benchmark":"lambada","model":"chatglm2-6b","score":54.3,"metric":"percent"},{"benchmark":"boolq","model":"internlm-7b","score":64.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"internlm-7b","score":59.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm-7b","score":8.9,"metric":"percent"},{"benchmark":"lambada","model":"internlm-7b","score":67,"metric":"percent"},{"benchmark":"boolq","model":"xverse-13b","score":64.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"xverse-13b","score":62.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"xverse-13b","score":0.3,"metric":"percent"},{"benchmark":"lambada","model":"xverse-13b","score":48.2,"metric":"percent"},{"benchmark":"boolq","model":"baichuan2-7b-base","score":63.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"baichuan2-7b-base","score":63,"metric":"percent"},{"benchmark":"naturalquestions","model":"baichuan2-7b-base","score":9.4,"metric":"percent"},{"benchmark":"lambada","model":"baichuan2-7b-base","score":73.3,"metric":"percent"},{"benchmark":"lambada","model":"baichuan2-13b-base","score":74,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-1-7b","score":64.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-7b","score":16.8,"metric":"percent"},{"benchmark":"lambada","model":"llama-1-7b","score":73.3,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-13b","score":78.7,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-1-13b","score":67.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-13b","score":20.2,"metric":"percent"},{"benchmark":"lambada","model":"llama-1-13b","score":75.2,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-33b","score":84.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-1-33b","score":72.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-33b","score":30.9,"metric":"percent"},{"benchmark":"lambada","model":"llama-1-33b","score":77.2,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-65b","score":86.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-1-65b","score":74.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-65b","score":33.4,"metric":"percent"},{"benchmark":"lambada","model":"llama-1-65b","score":77.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b","score":19.1,"metric":"percent"},{"benchmark":"lambada","model":"llama-2-7b","score":73.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-13b","score":24.9,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-70b","score":87.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-70b","score":34.2,"metric":"percent"},{"benchmark":"lambada","model":"llama-2-70b","score":78.9,"metric":"percent"},{"benchmark":"boolq","model":"stablebeluga2-70b","score":89.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"stablebeluga2-70b","score":72.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"stablebeluga2-70b","score":25.1,"metric":"percent"},{"benchmark":"lambada","model":"stablebeluga2-70b","score":71.3,"metric":"percent"},{"benchmark":"boolq","model":"qwen-1.8b","score":68,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen-1.8b","score":60.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-1.8b","score":3.2,"metric":"percent"},{"benchmark":"lambada","model":"qwen-1.8b","score":58.4,"metric":"percent"},{"benchmark":"boolq","model":"qwen-7b","score":76.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen-7b","score":66.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-7b","score":17.4,"metric":"percent"},{"benchmark":"lambada","model":"qwen-7b","score":67.9,"metric":"percent"},{"benchmark":"boolq","model":"qwen-14b","score":86.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"qwen-14b","score":70.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-14b","score":23.9,"metric":"percent"},{"benchmark":"lambada","model":"qwen-14b","score":71.1,"metric":"percent"},{"benchmark":"piqa","model":"mpt-7b","score":80.6,"metric":"percent"},{"benchmark":"siqa","model":"mpt-7b","score":48.5,"metric":"percent"},{"benchmark":"ocnli","model":"mpt-7b","score":30,"metric":"percent"},{"benchmark":"piqa","model":"falcon-7b","score":76.7,"metric":"percent"},{"benchmark":"siqa","model":"falcon-7b","score":47.2,"metric":"percent"},{"benchmark":"piqa","model":"chatglm2-6b","score":69.6,"metric":"percent"},{"benchmark":"siqa","model":"chatglm2-6b","score":64.3,"metric":"percent"},{"benchmark":"ocnli","model":"chatglm2-6b","score":33.1,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm-7b","score":70.6,"metric":"percent"},{"benchmark":"piqa","model":"internlm-7b","score":77.9,"metric":"percent"},{"benchmark":"siqa","model":"internlm-7b","score":60.5,"metric":"percent"},{"benchmark":"ocnli","model":"internlm-7b","score":37.5,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-7b-base","score":67,"metric":"percent"},{"benchmark":"piqa","model":"baichuan2-7b-base","score":76.2,"metric":"percent"},{"benchmark":"siqa","model":"baichuan2-7b-base","score":44.4,"metric":"percent"},{"benchmark":"ocnli","model":"baichuan2-7b-base","score":30.3,"metric":"percent"},{"benchmark":"ocnli","model":"llama-1-7b","score":33.6,"metric":"percent"},{"benchmark":"siqa","model":"llama-1-13b","score":52.5,"metric":"percent"},{"benchmark":"ocnli","model":"llama-1-13b","score":32.1,"metric":"percent"},{"benchmark":"siqa","model":"llama-1-33b","score":57.8,"metric":"percent"},{"benchmark":"ocnli","model":"llama-1-33b","score":30.7,"metric":"percent"},{"benchmark":"siqa","model":"llama-1-65b","score":61.2,"metric":"percent"},{"benchmark":"ocnli","model":"llama-1-65b","score":44.9,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-7b","score":78.8,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-7b","score":48.5,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-7b","score":32.1,"metric":"percent"},{"benchmark":"siqa","model":"llama-2-70b","score":64.8,"metric":"percent"},{"benchmark":"ocnli","model":"llama-2-70b","score":46.5,"metric":"percent"},{"benchmark":"hellaswag","model":"stablebeluga2-70b","score":84.1,"metric":"percent"},{"benchmark":"piqa","model":"stablebeluga2-70b","score":83.3,"metric":"percent"},{"benchmark":"siqa","model":"stablebeluga2-70b","score":78.1,"metric":"percent"},{"benchmark":"ocnli","model":"stablebeluga2-70b","score":48.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-1.8b","score":56.7,"metric":"percent"},{"benchmark":"piqa","model":"qwen-1.8b","score":73.3,"metric":"percent"},{"benchmark":"siqa","model":"qwen-1.8b","score":56.1,"metric":"percent"},{"benchmark":"ocnli","model":"qwen-1.8b","score":39,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-7b","score":75.1,"metric":"percent"},{"benchmark":"piqa","model":"qwen-7b","score":77.9,"metric":"percent"},{"benchmark":"siqa","model":"qwen-7b","score":69.9,"metric":"percent"},{"benchmark":"ocnli","model":"qwen-7b","score":47.4,"metric":"percent"},{"benchmark":"piqa","model":"qwen-14b","score":79.9,"metric":"percent"},{"benchmark":"siqa","model":"qwen-14b","score":77.9,"metric":"percent"},{"benchmark":"ocnli","model":"qwen-14b","score":57.9,"metric":"percent"},{"benchmark":"flickr30k","model":"flamingo-9b","score":61.5,"metric":"cider"},{"benchmark":"vqav2","model":"flamingo-9b","score":51.8,"metric":"percent"},{"benchmark":"okvqa","model":"flamingo-9b","score":44.7,"metric":"percent"},{"benchmark":"vizwiz","model":"flamingo-9b","score":28.8,"metric":"percent"},{"benchmark":"flickr30k","model":"flamingo-80b","score":67.2,"metric":"cider"},{"benchmark":"vqav2","model":"flamingo-80b","score":56.3,"metric":"percent"},{"benchmark":"okvqa","model":"flamingo-80b","score":50.6,"metric":"percent"},{"benchmark":"vizwiz","model":"flamingo-80b","score":31.6,"metric":"percent"},{"benchmark":"flickr30k","model":"kosmos-1","score":67.1,"metric":"cider"},{"benchmark":"vqav2","model":"kosmos-1","score":51,"metric":"percent"},{"benchmark":"vizwiz","model":"kosmos-1","score":29.2,"metric":"percent"},{"benchmark":"flickr30k","model":"kosmos2","score":80.5,"metric":"cider"},{"benchmark":"vqav2","model":"kosmos2","score":51.1,"metric":"percent"},{"benchmark":"nocaps","model":"blip-2-vicuna-13b","score":103.9,"metric":"cider"},{"benchmark":"flickr30k","model":"blip-2-vicuna-13b","score":71.6,"metric":"cider"},{"benchmark":"vqav2","model":"blip-2-vicuna-13b","score":65,"metric":"percent"},{"benchmark":"okvqa","model":"blip-2-vicuna-13b","score":45.9,"metric":"percent"},{"benchmark":"gqa","model":"blip-2-vicuna-13b","score":32.3,"metric":"percent"},{"benchmark":"scienceqa","model":"blip-2-vicuna-13b","score":61,"metric":"percent"},{"benchmark":"vizwiz","model":"blip-2-vicuna-13b","score":19.6,"metric":"percent"},{"benchmark":"nocaps","model":"instructblip-vicuna-13b","score":121.9,"metric":"cider"},{"benchmark":"flickr30k","model":"instructblip-vicuna-13b","score":82.8,"metric":"cider"},{"benchmark":"gqa","model":"instructblip-vicuna-13b","score":49.5,"metric":"percent"},{"benchmark":"scienceqa","model":"instructblip-vicuna-13b","score":63.1,"metric":"percent"},{"benchmark":"vizwiz","model":"instructblip-vicuna-13b","score":33.4,"metric":"percent"},{"benchmark":"flickr30k","model":"shikra-13b","score":73.9,"metric":"cider"},{"benchmark":"vqav2","model":"shikra-13b","score":77.36,"metric":"percent"},{"benchmark":"okvqa","model":"shikra-13b","score":47.16,"metric":"percent"},{"benchmark":"nocaps","model":"qwen-vl","score":121.4,"metric":"cider"},{"benchmark":"flickr30k","model":"qwen-vl","score":85.8,"metric":"cider"},{"benchmark":"vqav2","model":"qwen-vl","score":79.5,"metric":"percent"},{"benchmark":"okvqa","model":"qwen-vl","score":58.6,"metric":"percent"},{"benchmark":"gqa","model":"qwen-vl","score":59.3,"metric":"percent"},{"benchmark":"scienceqa","model":"qwen-vl","score":67.1,"metric":"percent"},{"benchmark":"vizwiz","model":"qwen-vl","score":35.2,"metric":"percent"},{"benchmark":"nocaps","model":"qwen-vl-chat","score":120.2,"metric":"cider"},{"benchmark":"flickr30k","model":"qwen-vl-chat","score":81,"metric":"cider"},{"benchmark":"vqav2","model":"qwen-vl-chat","score":78.2,"metric":"percent"},{"benchmark":"okvqa","model":"qwen-vl-chat","score":56.6,"metric":"percent"},{"benchmark":"gqa","model":"qwen-vl-chat","score":57.5,"metric":"percent"},{"benchmark":"scienceqa","model":"qwen-vl-chat","score":68.2,"metric":"percent"},{"benchmark":"vizwiz","model":"qwen-vl-chat","score":38.9,"metric":"percent"},{"benchmark":"textvqa","model":"blip-2-vicuna-13b","score":42.4,"metric":"percent"},{"benchmark":"textvqa","model":"instructblip-vicuna-13b","score":50.7,"metric":"percent"},{"benchmark":"textvqa","model":"mplug-docowl-7b","score":52.6,"metric":"percent"},{"benchmark":"docvqa","model":"mplug-docowl-7b","score":62.2,"metric":"percent"},{"benchmark":"chartqa","model":"mplug-docowl-7b","score":57.4,"metric":"percent"},{"benchmark":"textvqa","model":"qwen-vl","score":63.8,"metric":"percent"},{"benchmark":"docvqa","model":"qwen-vl","score":65.1,"metric":"percent"},{"benchmark":"chartqa","model":"qwen-vl","score":65.7,"metric":"percent"},{"benchmark":"ai2d","model":"qwen-vl","score":62.3,"metric":"percent"},{"benchmark":"ocrvqa","model":"qwen-vl","score":75.7,"metric":"percent"},{"benchmark":"chartqa","model":"qwen-vl-chat","score":66.3,"metric":"percent"},{"benchmark":"ai2d","model":"qwen-vl-chat","score":57.7,"metric":"percent"},{"benchmark":"ocrvqa","model":"qwen-vl-chat","score":70.5,"metric":"percent"},{"benchmark":"refcoco","model":"ofa-large","score":79.96,"metric":"percent"},{"benchmark":"refcocoplus","model":"ofa-large","score":68.29,"metric":"percent"},{"benchmark":"refcocog","model":"ofa-large","score":67.57,"metric":"percent"},{"benchmark":"refcoco","model":"shikra-7b","score":87.01,"metric":"percent"},{"benchmark":"refcocog","model":"shikra-7b","score":82.27,"metric":"percent"},{"benchmark":"refcoco","model":"shikra-13b","score":87.83,"metric":"percent"},{"benchmark":"refcocoplus","model":"shikra-13b","score":82.89,"metric":"percent"},{"benchmark":"refcocog","model":"shikra-13b","score":82.64,"metric":"percent"},{"benchmark":"refcoco","model":"qwen-vl","score":89.36,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen-vl","score":83.12,"metric":"percent"},{"benchmark":"refcocog","model":"qwen-vl","score":85.58,"metric":"percent"},{"benchmark":"refcoco","model":"qwen-vl-chat","score":88.55,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen-vl-chat","score":82.82,"metric":"percent"},{"benchmark":"refcocog","model":"qwen-vl-chat","score":85.96,"metric":"percent"},{"benchmark":"seedbench","model":"qwen-vl","score":56.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen-vl","score":62.3,"metric":"percent"},{"benchmark":"seedbench","model":"qwen-vl-chat","score":58.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen-vl-chat","score":65.4,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan-7b","score":44.4,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm2-6b","score":48.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-vl","score":50.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-vl","score":49.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-vl","score":51.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-70b-base","score":52.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-72b","score":45.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-110b","score":49.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-72b","score":55.6,"metric":"percent"},{"benchmark":"gpqa","model":"mixtral-8x22b","score":34.3,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-70b-base","score":36.3,"metric":"percent"},{"benchmark":"gpqa","model":"qwen1.5-72b","score":36.3,"metric":"percent"},{"benchmark":"gpqa","model":"qwen1.5-110b","score":35.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-72b","score":37.9,"metric":"percent"},{"benchmark":"theoremqa","model":"mixtral-8x22b","score":35.9,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-3-70b-base","score":32.3,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen1.5-72b","score":29.3,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen1.5-110b","score":34.9,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-72b","score":43.1,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-72b","score":65.5,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-110b","score":74.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-72b","score":82.4,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3-70b-base","score":88,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-72b","score":86,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-110b","score":87.5,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2-72b","score":87.6,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3-70b-base","score":85.3,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-72b","score":83,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-110b","score":83.5,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2-72b","score":85.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"mixtral-8x22b","score":70.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-70b-base","score":68.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-72b","score":65.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-110b","score":69.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2-72b","score":68.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"mixtral-8x22b","score":51,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3-70b-base","score":45.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-72b","score":59.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-110b","score":49.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2-72b","score":54.8,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x22b","score":46.3,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x22b","score":71.7,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-70b-base","score":70.4,"metric":"percent"},{"benchmark":"evalplus","model":"mixtral-8x22b","score":54.1,"metric":"percent"},{"benchmark":"evalplus","model":"llama-3-70b-base","score":54.8,"metric":"percent"},{"benchmark":"evalplus","model":"qwen1.5-72b","score":52.9,"metric":"percent"},{"benchmark":"evalplus","model":"qwen1.5-110b","score":57.7,"metric":"percent"},{"benchmark":"evalplus","model":"qwen2-72b","score":65.4,"metric":"percent"},{"benchmark":"multipl-e","model":"mixtral-8x22b","score":46.7,"metric":"percent"},{"benchmark":"multipl-e","model":"llama-3-70b-base","score":46.3,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen1.5-72b","score":41.8,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen1.5-110b","score":52.7,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-72b","score":59.6,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x22b","score":41.7,"metric":"percent"},{"benchmark":"math","model":"llama-3-70b-base","score":42.5,"metric":"percent"},{"benchmark":"c-eval","model":"mixtral-8x22b","score":54.6,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-70b-base","score":65.2,"metric":"percent"},{"benchmark":"cmmlu","model":"mixtral-8x22b","score":53.4,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-70b-base","score":67.2,"metric":"percent"},{"benchmark":"mmlu","model":"jamba-v0.1","score":67.4,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x7b","score":71.8,"metric":"percent"},{"benchmark":"mmlu","model":"yi-1.5-34b","score":77.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-32b","score":74.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.57b-a14b","score":76.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mixtral-8x7b","score":41,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-1.5-34b","score":48.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-32b","score":44,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.57b-a14b","score":43,"metric":"percent"},{"benchmark":"gpqa","model":"mixtral-8x7b","score":29.2,"metric":"percent"},{"benchmark":"gpqa","model":"qwen1.5-32b","score":30.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.57b-a14b","score":34.3,"metric":"percent"},{"benchmark":"theoremqa","model":"mixtral-8x7b","score":23.2,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen1.5-32b","score":28.8,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.57b-a14b","score":33.5,"metric":"percent"},{"benchmark":"bbh","model":"jamba-v0.1","score":45.4,"metric":"percent"},{"benchmark":"bbh","model":"mixtral-8x7b","score":50.3,"metric":"percent"},{"benchmark":"bbh","model":"yi-1.5-34b","score":76.4,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-32b","score":66.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.57b-a14b","score":67,"metric":"percent"},{"benchmark":"hellaswag","model":"jamba-v0.1","score":87.1,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x7b","score":86.5,"metric":"percent"},{"benchmark":"hellaswag","model":"yi-1.5-34b","score":85.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-32b","score":85,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.57b-a14b","score":85.2,"metric":"percent"},{"benchmark":"winogrande","model":"jamba-v0.1","score":82.5,"metric":"percent"},{"benchmark":"winogrande","model":"mixtral-8x7b","score":81.9,"metric":"percent"},{"benchmark":"winogrande","model":"yi-1.5-34b","score":84.9,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-32b","score":81.5,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.57b-a14b","score":79.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"jamba-v0.1","score":64.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"mixtral-8x7b","score":66,"metric":"percent"},{"benchmark":"arc-challenge","model":"yi-1.5-34b","score":65.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-32b","score":63.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.57b-a14b","score":64.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"jamba-v0.1","score":46.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"mixtral-8x7b","score":51.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-1.5-34b","score":53.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-32b","score":57.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.57b-a14b","score":57.7,"metric":"percent"},{"benchmark":"humaneval","model":"jamba-v0.1","score":29.3,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x7b","score":37.2,"metric":"percent"},{"benchmark":"humaneval","model":"yi-1.5-34b","score":46.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-32b","score":43.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.57b-a14b","score":53,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x7b","score":63.9,"metric":"percent"},{"benchmark":"mbpp","model":"yi-1.5-34b","score":65.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-32b","score":64.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.57b-a14b","score":71.9,"metric":"percent"},{"benchmark":"evalplus","model":"mixtral-8x7b","score":46.4,"metric":"percent"},{"benchmark":"evalplus","model":"yi-1.5-34b","score":51.9,"metric":"percent"},{"benchmark":"evalplus","model":"qwen1.5-32b","score":50.4,"metric":"percent"},{"benchmark":"evalplus","model":"qwen2.57b-a14b","score":57.2,"metric":"percent"},{"benchmark":"multipl-e","model":"mixtral-8x7b","score":39,"metric":"percent"},{"benchmark":"multipl-e","model":"yi-1.5-34b","score":39.5,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen1.5-32b","score":38.5,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.57b-a14b","score":49.8,"metric":"percent"},{"benchmark":"gsm8k","model":"jamba-v0.1","score":59.9,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x7b","score":62.5,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-34b","score":82.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-32b","score":76.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.57b-a14b","score":80.7,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x7b","score":30.8,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-34b","score":41.7,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-32b","score":36.1,"metric":"percent"},{"benchmark":"math","model":"qwen2.57b-a14b","score":43,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-32b","score":83.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2.57b-a14b","score":87.7,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-1.5-34b","score":84.8,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-32b","score":82.3,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2.57b-a14b","score":88.5,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-v0.1","score":64.2,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-7b","score":64.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-8b-base","score":66.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-7b","score":61,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-7b","score":70.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-7b-v0.1","score":30.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-7b","score":33.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-8b-base","score":35.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-7b","score":29.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-7b","score":40,"metric":"percent"},{"benchmark":"gpqa","model":"mistral-7b-v0.1","score":24.7,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-7b","score":25.7,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-8b-base","score":25.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen1.5-7b","score":26.7,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-7b","score":31.8,"metric":"percent"},{"benchmark":"theoremqa","model":"mistral-7b-v0.1","score":19.2,"metric":"percent"},{"benchmark":"theoremqa","model":"gemma-7b","score":21.5,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-3-8b-base","score":22.1,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen1.5-7b","score":14.2,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-7b","score":31.1,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b-v0.1","score":56.1,"metric":"percent"},{"benchmark":"bbh","model":"gemma-7b","score":55.1,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-8b-base","score":57.7,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-7b","score":40.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-7b","score":62.6,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-v0.1","score":83.2,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-7b","score":82.2,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-3-8b-base","score":82.1,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-7b","score":78.5,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2-7b","score":80.7,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b-v0.1","score":78.4,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-7b","score":79,"metric":"percent"},{"benchmark":"winogrande","model":"llama-3-8b-base","score":77.4,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-7b","score":71.3,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2-7b","score":77,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b-v0.1","score":60,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-7b","score":61.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"llama-3-8b-base","score":59.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-7b","score":54.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2-7b","score":60.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"mistral-7b-v0.1","score":42.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-7b","score":44.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-3-8b-base","score":44,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-7b","score":51.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2-7b","score":54.2,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-v0.1","score":29.3,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-7b","score":37.2,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-7b","score":36,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-7b","score":51.2,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-v0.1","score":51.1,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-7b","score":50.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b-base","score":53.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-7b","score":51.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-7b","score":65.9,"metric":"percent"},{"benchmark":"evalplus","model":"mistral-7b-v0.1","score":36.4,"metric":"percent"},{"benchmark":"evalplus","model":"gemma-7b","score":39.6,"metric":"percent"},{"benchmark":"evalplus","model":"llama-3-8b-base","score":40.3,"metric":"percent"},{"benchmark":"evalplus","model":"qwen1.5-7b","score":40,"metric":"percent"},{"benchmark":"evalplus","model":"qwen2-7b","score":54.2,"metric":"percent"},{"benchmark":"multipl-e","model":"mistral-7b-v0.1","score":29.4,"metric":"percent"},{"benchmark":"multipl-e","model":"gemma-7b","score":29.7,"metric":"percent"},{"benchmark":"multipl-e","model":"llama-3-8b-base","score":22.6,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen1.5-7b","score":28.1,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-7b","score":46.3,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.1","score":52.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b-base","score":56,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-7b","score":62.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-7b","score":79.9,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-v0.1","score":13.1,"metric":"percent"},{"benchmark":"math","model":"gemma-7b","score":24.3,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b-base","score":20.5,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-7b","score":20.3,"metric":"percent"},{"benchmark":"math","model":"qwen2-7b","score":44.2,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b-v0.1","score":47.4,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-7b","score":43.6,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-8b-base","score":49.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-7b","score":74.1,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-7b","score":83.2,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-8b-base","score":50.8,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-7b","score":73.1,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2-7b","score":83.9,"metric":"percent"},{"benchmark":"mmlu","model":"phi-2","score":52.7,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2b","score":42.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-1.8b","score":46.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-0.5b","score":45.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-1.5b","score":56.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2b","score":15.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-0.5b","score":14.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-1.5b","score":21.8,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-0.5b","score":8.9,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-1.5b","score":15,"metric":"percent"},{"benchmark":"bbh","model":"phi-2","score":43.4,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2b","score":35.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-1.8b","score":24.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-0.5b","score":28.4,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-1.5b","score":37.2,"metric":"percent"},{"benchmark":"hellaswag","model":"phi-2","score":73.1,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2b","score":71.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen1.5-1.8b","score":61.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2-0.5b","score":49.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2-1.5b","score":66.6,"metric":"percent"},{"benchmark":"winogrande","model":"phi-2","score":74.4,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-2b","score":66.8,"metric":"percent"},{"benchmark":"winogrande","model":"qwen1.5-1.8b","score":60.3,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2-0.5b","score":56.8,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2-1.5b","score":66.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"phi-2","score":61.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2b","score":48.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen1.5-1.8b","score":37.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2-0.5b","score":31.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2-1.5b","score":43.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"phi-2","score":44.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-2b","score":33.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen1.5-1.8b","score":39.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2-0.5b","score":39.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2-1.5b","score":45.9,"metric":"percent"},{"benchmark":"humaneval","model":"phi-2","score":47.6,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2b","score":22,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-1.8b","score":20.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-0.5b","score":22,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-1.5b","score":31.1,"metric":"percent"},{"benchmark":"mbpp","model":"phi-2","score":55,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2b","score":29.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-1.8b","score":18,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-0.5b","score":22,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-1.5b","score":37.4,"metric":"percent"},{"benchmark":"gsm8k","model":"phi-2","score":57.2,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2b","score":17.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-1.8b","score":38.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-0.5b","score":36.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-1.5b","score":58.5,"metric":"percent"},{"benchmark":"math","model":"gemma-2b","score":11.8,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-1.8b","score":10.1,"metric":"percent"},{"benchmark":"math","model":"qwen2-0.5b","score":10.7,"metric":"percent"},{"benchmark":"math","model":"qwen2-1.5b","score":21.7,"metric":"percent"},{"benchmark":"c-eval","model":"phi-2","score":23.4,"metric":"percent"},{"benchmark":"c-eval","model":"gemma-2b","score":28,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-1.8b","score":59.7,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-0.5b","score":58.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-1.5b","score":70.6,"metric":"percent"},{"benchmark":"cmmlu","model":"phi-2","score":24.2,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-1.8b","score":57.8,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2-0.5b","score":55.1,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2-1.5b","score":70.3,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x22b-instruct-v0.1","score":74,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-70b-instruct","score":82,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-72b-chat","score":75.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-110b-chat","score":76.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mixtral-8x22b-instruct-v0.1","score":56.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-72b-chat","score":51.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-110b-chat","score":50.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-72b-instruct","score":64.4,"metric":"percent"},{"benchmark":"gpqa","model":"mixtral-8x22b-instruct-v0.1","score":49.7,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-70b-instruct","score":41.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen1.5-72b-chat","score":39.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen1.5-110b-chat","score":32.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-72b-instruct","score":42.4,"metric":"percent"},{"benchmark":"theoremqa","model":"mixtral-8x22b-instruct-v0.1","score":40.8,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-3-70b-instruct","score":42.5,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen1.5-72b-chat","score":28.8,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen1.5-110b-chat","score":18.8,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-72b-instruct","score":44.4,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x22b-instruct-v0.1","score":73.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-72b-chat","score":71.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-110b-chat","score":74.4,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x22b-instruct-v0.1","score":75.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-72b-chat","score":71.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-110b-chat","score":76.4,"metric":"percent"},{"benchmark":"multipl-e","model":"mixtral-8x22b-instruct-v0.1","score":61.1,"metric":"percent"},{"benchmark":"multipl-e","model":"llama-3-70b-instruct","score":63.4,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen1.5-72b-chat","score":48.1,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen1.5-110b-chat","score":55.4,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-72b-instruct","score":69.2,"metric":"percent"},{"benchmark":"livecodebench","model":"mixtral-8x22b-instruct-v0.1","score":21.8,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3-70b-instruct","score":29.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen1.5-72b-chat","score":17.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen1.5-110b-chat","score":25.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2-72b-instruct","score":35.7,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b-instruct-v0.1","score":89.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-72b-chat","score":82.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-110b-chat","score":84.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-72b-instruct","score":93.2,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x22b-instruct-v0.1","score":47.4,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-72b-chat","score":42.5,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-110b-chat","score":42,"metric":"percent"},{"benchmark":"math","model":"qwen2-72b-instruct","score":69,"metric":"percent"},{"benchmark":"mixeval","model":"mixtral-8x22b-instruct-v0.1","score":82.3,"metric":"percent"},{"benchmark":"mixeval","model":"llama-3-70b-instruct","score":84,"metric":"percent"},{"benchmark":"mixeval","model":"qwen1.5-72b-chat","score":84.1,"metric":"percent"},{"benchmark":"mixeval","model":"qwen1.5-110b-chat","score":85.7,"metric":"percent"},{"benchmark":"mixeval","model":"qwen2-72b-instruct","score":86.7,"metric":"percent"},{"benchmark":"arena-hard","model":"mixtral-8x22b-instruct-v0.1","score":36.4,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3-70b-instruct","score":41.1,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen1.5-72b-chat","score":36.1,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen1.5-110b-chat","score":39.8,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2-72b-instruct","score":48.1,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"mixtral-8x22b-instruct-v0.1","score":67.1,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llama-3-70b-instruct","score":77.3,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen1.5-72b-chat","score":55.8,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen1.5-110b-chat","score":57.5,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2-72b-instruct","score":77.6,"metric":"percent"},{"benchmark":"alignbench","model":"llama-3-70b-instruct","score":7.42,"metric":"score"},{"benchmark":"alignbench","model":"qwen1.5-72b-chat","score":7.28,"metric":"score"},{"benchmark":"alignbench","model":"qwen1.5-110b-chat","score":7.87,"metric":"score"},{"benchmark":"mmlu","model":"mixtral-8x7b-instruct-v0.1","score":71.4,"metric":"percent"},{"benchmark":"mmlu","model":"yi-1.5-34b-chat","score":76.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-32b-chat","score":74.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-57b-a14b-instruct","score":75.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mixtral-8x7b-instruct-v0.1","score":43.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"yi-1.5-34b-chat","score":52.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-32b-chat","score":46.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-57b-a14b-instruct","score":52.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen1.5-32b-chat","score":30.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-57b-a14b-instruct","score":34.3,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen1.5-32b-chat","score":30.9,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-57b-a14b-instruct","score":33.1,"metric":"percent"},{"benchmark":"humaneval","model":"yi-1.5-34b-chat","score":75.2,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-32b-chat","score":68.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-57b-a14b-instruct","score":79.9,"metric":"percent"},{"benchmark":"mbpp","model":"yi-1.5-34b-chat","score":74.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-32b-chat","score":67.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-57b-a14b-instruct","score":70.9,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen1.5-32b-chat","score":50.7,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-57b-a14b-instruct","score":66.4,"metric":"percent"},{"benchmark":"livecodebench","model":"mixtral-8x7b-instruct-v0.1","score":12.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen1.5-32b-chat","score":15.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2-57b-a14b-instruct","score":25.5,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x7b-instruct-v0.1","score":65.7,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-34b-chat","score":90.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-32b-chat","score":83.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-57b-a14b-instruct","score":85.3,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x7b-instruct-v0.1","score":30.7,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-34b-chat","score":50.1,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-32b-chat","score":42.4,"metric":"percent"},{"benchmark":"math","model":"qwen2-57b-a14b-instruct","score":49.1,"metric":"percent"},{"benchmark":"mt-bench","model":"mixtral-8x7b-instruct-v0.1","score":8.3,"metric":"percent"},{"benchmark":"mt-bench","model":"yi-1.5-34b-chat","score":8.5,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen1.5-32b-chat","score":8.3,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2-57b-a14b-instruct","score":8.55,"metric":"percent"},{"benchmark":"mixeval","model":"mixtral-8x7b-instruct-v0.1","score":70,"metric":"percent"},{"benchmark":"mixeval","model":"yi-1.5-34b-chat","score":81.7,"metric":"percent"},{"benchmark":"mixeval","model":"qwen1.5-32b-chat","score":81,"metric":"percent"},{"benchmark":"mixeval","model":"qwen2-57b-a14b-instruct","score":82.3,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen1.5-32b-chat","score":50.3,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2-57b-a14b-instruct","score":59.9,"metric":"percent"},{"benchmark":"alignbench","model":"mixtral-8x7b-instruct-v0.1","score":5.7,"metric":"score"},{"benchmark":"alignbench","model":"yi-1.5-34b-chat","score":7.2,"metric":"score"},{"benchmark":"alignbench","model":"qwen1.5-32b-chat","score":7.19,"metric":"score"},{"benchmark":"alignbench","model":"qwen2-57b-a14b-instruct","score":7.36,"metric":"score"},{"benchmark":"mmlu","model":"yi-1.5-9b-chat","score":69.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-7b-chat","score":59.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-8b-instruct","score":41,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-7b-chat","score":29.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-7b-instruct","score":44.1,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-8b-instruct","score":34.2,"metric":"percent"},{"benchmark":"gpqa","model":"qwen1.5-7b-chat","score":27.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-7b-instruct","score":34.3,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-3-8b-instruct","score":23,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen1.5-7b-chat","score":14.1,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-7b-instruct","score":25.3,"metric":"percent"},{"benchmark":"humaneval","model":"yi-1.5-9b-chat","score":66.5,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4-9b-chat","score":71.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-7b-chat","score":46.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-7b-instruct","score":79.9,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b-instruct","score":67.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-7b-chat","score":48.9,"metric":"percent"},{"benchmark":"multipl-e","model":"llama-3-8b-instruct","score":48.5,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen1.5-7b-chat","score":27.2,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-7b-instruct","score":59.1,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3-8b-instruct","score":17.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen1.5-7b-chat","score":6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2-7b-instruct","score":26.6,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-9b-chat","score":84.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-7b-chat","score":60.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-7b-instruct","score":85.7,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-9b-chat","score":47.7,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-7b-chat","score":23.2,"metric":"percent"},{"benchmark":"math","model":"qwen2-7b-instruct","score":52.9,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3-8b-instruct","score":8.05,"metric":"percent"},{"benchmark":"mt-bench","model":"yi-1.5-9b-chat","score":8.2,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen1.5-7b-chat","score":7.6,"metric":"percent"},{"benchmark":"mixeval","model":"llama-3-8b-instruct","score":75,"metric":"percent"},{"benchmark":"mixeval","model":"yi-1.5-9b-chat","score":74.2,"metric":"percent"},{"benchmark":"mixeval","model":"qwen1.5-7b-chat","score":71.4,"metric":"percent"},{"benchmark":"mixeval","model":"qwen2-7b-instruct","score":76.5,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llama-3-8b-instruct","score":72.1,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"glm-4-9b-chat","score":69,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen1.5-7b-chat","score":38.3,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2-7b-instruct","score":54.7,"metric":"percent"},{"benchmark":"alignbench","model":"llama-3-8b-instruct","score":6.2,"metric":"score"},{"benchmark":"alignbench","model":"yi-1.5-9b-chat","score":6.9,"metric":"score"},{"benchmark":"alignbench","model":"glm-4-9b-chat","score":7.01,"metric":"score"},{"benchmark":"alignbench","model":"qwen1.5-7b-chat","score":6.2,"metric":"score"},{"benchmark":"alignbench","model":"qwen2-7b-instruct","score":7.21,"metric":"score"},{"benchmark":"mmlu","model":"qwen1.5-0.5b-chat","score":35,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-0.5b-instruct","score":37.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-1.8b-chat","score":43.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-1.5b-instruct","score":52.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-0.5b-chat","score":10.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-0.5b-instruct","score":29.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-1.8b-chat","score":27.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-1.5b-instruct","score":47,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-0.5b-chat","score":14.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-0.5b-instruct","score":37.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-1.8b-chat","score":28.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-1.5b-instruct","score":51.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-0.5b-chat","score":11.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-0.5b-instruct","score":40.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-1.8b-chat","score":35.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-1.5b-instruct","score":61.6,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen1.5-0.5b-chat","score":14.6,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2-0.5b-instruct","score":20,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen1.5-1.8b-chat","score":16.8,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2-1.5b-instruct","score":29,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mixtral-8x22b","score":51.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-72b","score":55.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3-70b-base","score":75,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mixtral-8x22b","score":72.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-72b","score":80.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen-2.5-72b","score":83.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen-2.5-72b","score":60.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2-72b","score":87.3,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-72b","score":37.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen-2.5-72b","score":45.9,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-72b","score":42.8,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen-2.5-72b","score":42.4,"metric":"percent"},{"benchmark":"math","model":"qwen2-72b","score":50.9,"metric":"percent"},{"benchmark":"math","model":"qwen-2.5-72b","score":62.1,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3-70b-base","score":73.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"mixtral-8x22b","score":71.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-72b","score":79.6,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen-2.5-72b","score":82.7,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b-base","score":77.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-72b","score":89,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-2.5-72b","score":91.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-2.5-72b","score":59.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3-70b-base","score":42.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mixtral-8x22b","score":40.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2-72b","score":56.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen-2.5-72b","score":51.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-405b-base","score":73,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-2.5-72b","score":84.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-70b-base","score":58.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mixtral-8x22b","score":58.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2-72b","score":63.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen-2.5-72b","score":69.2,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen-2.5-72b","score":60.5,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-27b","score":75.2,"metric":"percent"},{"benchmark":"mmlu","model":"yi-1.5-34b","score":77.2,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-14b","score":79.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-32b-base","score":83.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen1.5-32b","score":44.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-27b","score":49.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-14b","score":51.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-32b-base","score":55.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen1.5-32b","score":69,"metric":"percent"},{"benchmark":"mmlu-redux","model":"yi-1.5-34b","score":74.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-14b","score":76.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-32b-base","score":82,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-27b","score":74.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-14b","score":78.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-32b-base","score":84.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-14b","score":67.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-32b-base","score":70.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-2-27b","score":40.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-14b","score":58.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-32b-base","score":57.8,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-2-27b","score":59.7,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-14b","score":81,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-32b-base","score":82,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2-27b","score":86.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-14b","score":84.3,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-32b-base","score":85.2,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-27b","score":34.9,"metric":"percent"},{"benchmark":"gpqa","model":"yi-1.5-34b","score":37.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-14b","score":32.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-32b-base","score":48,"metric":"percent"},{"benchmark":"theoremqa","model":"gemma-2-27b","score":35.8,"metric":"percent"},{"benchmark":"theoremqa","model":"yi-1.5-34b","score":40,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-14b","score":43,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-32b-base","score":44.1,"metric":"percent"},{"benchmark":"math","model":"gemma-2-27b","score":42.7,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-14b","score":55.6,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-32b-base","score":57.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen1.5-32b","score":66.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-2-27b","score":71,"metric":"percent"},{"benchmark":"mmlu-stem","model":"yi-1.5-34b","score":72.6,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-14b","score":76.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-32b-base","score":80.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-32b","score":78.5,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-27b","score":81.1,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-34b","score":81.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-14b","score":90.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-32b-base","score":92.9,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2-27b","score":54.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-14b","score":56.7,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-32b-base","score":58.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen1.5-32b","score":40.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-2-27b","score":46.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"yi-1.5-34b","score":40.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-14b","score":51.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-32b-base","score":52.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-27b","score":75.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-14b","score":76.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-32b-base","score":84.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen1.5-32b","score":53.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-2-27b","score":60.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"yi-1.5-34b","score":55.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-14b","score":63.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-32b-base","score":67.2,"metric":"percent"},{"benchmark":"multipl-e","model":"gemma-2-27b","score":48,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-14b","score":53.5,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-32b-base","score":59.4,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-9b","score":71.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-7b","score":40.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mistral-7b-v0.1","score":58.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3-8b-base","score":61.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-2-9b","score":67.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-7b","score":68.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-7b","score":71.1,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-9b","score":68.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-7b","score":62.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-7b","score":70.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2-9b","score":68.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-7b","score":63.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-2-9b","score":45.3,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-7b","score":56.4,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-2-9b","score":79.5,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-7b","score":75.9,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-v0.1","score":83.3,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2-9b","score":81.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-7b","score":80.2,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-9b","score":32.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-7b","score":30.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-7b","score":36.4,"metric":"percent"},{"benchmark":"theoremqa","model":"gemma-2-9b","score":28.9,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-7b","score":29.6,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-7b","score":36,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-v0.1","score":10.2,"metric":"percent"},{"benchmark":"math","model":"gemma-2-9b","score":37.7,"metric":"percent"},{"benchmark":"math","model":"qwen2-7b","score":43.5,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-7b","score":49.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"mistral-7b-v0.1","score":50.1,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3-8b-base","score":55.3,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-2-9b","score":65.1,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-7b","score":64.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-7b","score":72.3,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.1","score":36.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b-base","score":55.3,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-9b","score":70.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-7b","score":80.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-7b","score":85.4,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2-9b","score":37.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-7b","score":57.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-7b-v0.1","score":24.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-2-9b","score":30.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2-7b","score":43.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-7b","score":50.6,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-9b","score":62.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-7b","score":64.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-7b","score":74.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistral-7b-v0.1","score":40.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-8b-base","score":44.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-2-9b","score":50.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2-7b","score":51.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-7b","score":62.9,"metric":"percent"},{"benchmark":"multipl-e","model":"gemma-2-9b","score":34.9,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-7b","score":41,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-7b","score":50.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-0.5b","score":44.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-0.5b","score":47.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-1.5b","score":55.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-1.5b","score":60.9,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-2b","score":52.2,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-3b","score":65.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-0.5b","score":15.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-1.5b","score":21.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-1.5b","score":28.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-2b","score":23,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-3b","score":34.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-0.5b","score":40.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-0.5b","score":45.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-1.5b","score":51.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-1.5b","score":58.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-2-2b","score":50.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-3b","score":63.7,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-0.5b","score":18.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-0.5b","score":20.3,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-1.5b","score":36.5,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-1.5b","score":45.1,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-2b","score":41.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen2.5-3b","score":56.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2-0.5b","score":31,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-0.5b","score":35.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2-1.5b","score":43.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-1.5b","score":54.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-2-2b","score":55.7,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-3b","score":56.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-0.5b","score":40.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-1.5b","score":46.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"gemma-2-2b","score":36.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-3b","score":48.9,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2-0.5b","score":56.9,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-0.5b","score":56.3,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2-1.5b","score":65,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-1.5b","score":65,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-2-2b","score":71.5,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-3b","score":71.1,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2-0.5b","score":49.1,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-0.5b","score":52.1,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2-1.5b","score":67,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-1.5b","score":67.9,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-2-2b","score":74.6,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-3b","score":74.6,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-0.5b","score":29.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-0.5b","score":24.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-1.5b","score":20.7,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-1.5b","score":24.2,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-2b","score":25.3,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-3b","score":26.3,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-0.5b","score":9.6,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-0.5b","score":16,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2-1.5b","score":14.8,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-1.5b","score":22.1,"metric":"percent"},{"benchmark":"theoremqa","model":"gemma-2-2b","score":15.9,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-3b","score":27.4,"metric":"percent"},{"benchmark":"math","model":"qwen2-0.5b","score":11.2,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-0.5b","score":19.5,"metric":"percent"},{"benchmark":"math","model":"qwen2-1.5b","score":21.6,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-1.5b","score":35,"metric":"percent"},{"benchmark":"math","model":"gemma-2-2b","score":18.3,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-3b","score":42.6,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-0.5b","score":27.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-0.5b","score":39.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-1.5b","score":42.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-1.5b","score":54.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gemma-2-2b","score":45.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-3b","score":62.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-0.5b","score":36.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-0.5b","score":41.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-1.5b","score":46.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-1.5b","score":68.5,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-2b","score":30.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-3b","score":79.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-0.5b","score":22.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-0.5b","score":30.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-1.5b","score":34.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-1.5b","score":37.2,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2-2b","score":19.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-3b","score":42.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2-0.5b","score":18.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-0.5b","score":26.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2-1.5b","score":29.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-1.5b","score":32.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-2-2b","score":15.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-3b","score":36,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-0.5b","score":33.1,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-0.5b","score":39.3,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-1.5b","score":46.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-1.5b","score":60.2,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-2b","score":42.1,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-3b","score":57.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2-0.5b","score":27.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-0.5b","score":33.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2-1.5b","score":37.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-1.5b","score":49.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-2-2b","score":33.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-3b","score":49.4,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-0.5b","score":16.3,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-0.5b","score":18.9,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-1.5b","score":27.9,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-1.5b","score":33.1,"metric":"percent"},{"benchmark":"multipl-e","model":"gemma-2-2b","score":17.6,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-3b","score":41.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-70b-instruct","score":66.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-72b-instruct","score":71.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-plus-1127","score":72.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3.1-70b-instruct","score":83,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-72b-instruct","score":81.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-plus-1127","score":86.3,"metric":"percent"},{"benchmark":"livebench","model":"llama-3.1-70b-instruct","score":46.6,"metric":"percent"},{"benchmark":"livebench","model":"llama-3.1-405b-instruct","score":53.2,"metric":"percent"},{"benchmark":"livebench","model":"qwen2-72b-instruct","score":41.5,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-72b-instruct","score":52.3,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-plus-1127","score":54.6,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.1-70b-instruct","score":46.7,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.1-405b-instruct","score":51.1,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-72b-instruct","score":49,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-plus-1127","score":49.7,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-plus-1127","score":84.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-plus-1127","score":96,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-72b-instruct","score":86.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-plus-1127","score":87.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-70b-instruct","score":84.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-405b-instruct","score":84.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-plus-1127","score":85.5,"metric":"percent"},{"benchmark":"multipl-e","model":"llama-3.1-70b-instruct","score":68.2,"metric":"percent"},{"benchmark":"multipl-e","model":"llama-3.1-405b-instruct","score":73.5,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-72b-instruct","score":75.1,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-plus-1127","score":77,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-70b-instruct","score":32.1,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-405b-instruct","score":41.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2-72b-instruct","score":32.2,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-72b-instruct","score":55.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-plus-1127","score":51.4,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2.5-72b-instruct","score":84.1,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2.5-plus-1127","score":86.3,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2.5-plus-1127","score":81.4,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.1-405b-instruct","score":9.08,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-72b-instruct","score":9.35,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-plus-1127","score":9.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-27b-it","score":55.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gpt-4o-mini","score":63.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-turbo","score":64.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-14b-instruct","score":63.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-32b-instruct","score":69,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-57b-a14b-instruct","score":72.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-2-27b-it","score":75.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4o-mini","score":81.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-turbo","score":81.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-14b-instruct","score":80,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-32b-instruct","score":83.9,"metric":"percent"},{"benchmark":"livebench","model":"qwen2-57b-a14b-instruct","score":31.1,"metric":"percent"},{"benchmark":"livebench","model":"gemma-2-27b-it","score":39.6,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4o-mini","score":43.3,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-turbo","score":42.3,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-14b-instruct","score":44.4,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-32b-instruct","score":50.7,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-27b-it","score":38.4,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4o-mini","score":40.2,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-turbo","score":42.3,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-14b-instruct","score":45.5,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-32b-instruct","score":49.5,"metric":"percent"},{"benchmark":"math","model":"gemma-2-27b-it","score":54.4,"metric":"percent"},{"benchmark":"math","model":"gpt-4o-mini","score":70.2,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-turbo","score":81.1,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-14b-instruct","score":80,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-32b-instruct","score":83.1,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-27b-it","score":90.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4o-mini","score":93.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-turbo","score":93.8,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2-27b-it","score":78.7,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-mini","score":88.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-turbo","score":86.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-14b-instruct","score":83.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-32b-instruct","score":88.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-27b-it","score":81,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4o-mini","score":85.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-turbo","score":82.8,"metric":"percent"},{"benchmark":"multipl-e","model":"gemma-2-27b-it","score":67.4,"metric":"percent"},{"benchmark":"multipl-e","model":"gpt-4o-mini","score":75,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-turbo","score":73.7,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-14b-instruct","score":72.8,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-32b-instruct","score":75.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2-57b-a14b-instruct","score":22.5,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o-mini","score":40.7,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-turbo","score":37.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-14b-instruct","score":42.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-32b-instruct","score":51.2,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"gemma-2-27b-it","score":77.1,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"gpt-4o-mini","score":80.4,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2.5-turbo","score":76.3,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2.5-14b-instruct","score":81,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2.5-32b-instruct","score":79.5,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2-57b-a14b-instruct","score":17.8,"metric":"percent"},{"benchmark":"arena-hard","model":"gemma-2-27b-it","score":57.5,"metric":"percent"},{"benchmark":"arena-hard","model":"gpt-4o-mini","score":74.9,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2.5-turbo","score":67.1,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2.5-14b-instruct","score":68.3,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2.5-32b-instruct","score":74.5,"metric":"percent"},{"benchmark":"mt-bench","model":"gemma-2-27b-it","score":9.1,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-turbo","score":8.81,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-14b-instruct","score":8.88,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-32b-instruct","score":9.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-9b-it","score":52.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3.1-8b-instruct","score":48.3,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-7b-instruct","score":56.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-2-9b-it","score":72.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3.1-8b-instruct","score":67.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-7b-instruct","score":67.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-7b-instruct","score":75.4,"metric":"percent"},{"benchmark":"livebench","model":"gemma-2-9b-it","score":30.6,"metric":"percent"},{"benchmark":"livebench","model":"llama-3.1-8b-instruct","score":26.7,"metric":"percent"},{"benchmark":"livebench","model":"qwen2-7b-instruct","score":29.2,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-7b-instruct","score":35.9,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-9b-it","score":32.8,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.1-8b-instruct","score":32.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-7b-instruct","score":36.4,"metric":"percent"},{"benchmark":"math","model":"gemma-2-9b-it","score":44.3,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-7b-instruct","score":75.5,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-9b-it","score":76.7,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2-9b-it","score":68.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-8b-instruct","score":72.6,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-9b-it","score":74.9,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3.1-8b-instruct","score":69.6,"metric":"percent"},{"benchmark":"multipl-e","model":"gemma-2-9b-it","score":53.4,"metric":"percent"},{"benchmark":"multipl-e","model":"llama-3.1-8b-instruct","score":50.7,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-7b-instruct","score":70.4,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-2-9b-it","score":18.9,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-8b-instruct","score":8.3,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2-7b-instruct","score":23.9,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-7b-instruct","score":28.7,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"gemma-2-9b-it","score":70.1,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llama-3.1-8b-instruct","score":75.9,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2.5-7b-instruct","score":71.2,"metric":"percent"},{"benchmark":"arena-hard","model":"gemma-2-9b-it","score":41.6,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3.1-8b-instruct","score":27.8,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2-7b-instruct","score":25,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2.5-7b-instruct","score":52,"metric":"percent"},{"benchmark":"mt-bench","model":"gemma-2-9b-it","score":8.49,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3.1-8b-instruct","score":8.23,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2-7b-instruct","score":8.26,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen2.5-7b-instruct","score":8.75,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-2-2b-it","score":26.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"phi-3.5-mini-instruct","score":47.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"minicpm3-4b","score":43,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen-2.5-3b-instruct","score":43.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gemma-2-2b-it","score":51.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"phi-3.5-mini-instruct","score":67.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"minicpm3-4b","score":59.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen-2.5-3b-instruct","score":64.4,"metric":"percent"},{"benchmark":"livebench","model":"gemma-2-2b-it","score":20.1,"metric":"percent"},{"benchmark":"livebench","model":"phi-3.5-mini-instruct","score":27.4,"metric":"percent"},{"benchmark":"livebench","model":"minicpm3-4b","score":27.6,"metric":"percent"},{"benchmark":"livebench","model":"qwen-2.5-3b-instruct","score":26.8,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-2b-it","score":29.3,"metric":"percent"},{"benchmark":"gpqa","model":"phi-3.5-mini-instruct","score":27.2,"metric":"percent"},{"benchmark":"gpqa","model":"minicpm3-4b","score":31.3,"metric":"percent"},{"benchmark":"gpqa","model":"qwen-2.5-3b-instruct","score":30.3,"metric":"percent"},{"benchmark":"math","model":"gemma-2-2b-it","score":26.6,"metric":"percent"},{"benchmark":"math","model":"phi-3.5-mini-instruct","score":48.5,"metric":"percent"},{"benchmark":"math","model":"qwen-2.5-3b-instruct","score":65.9,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-2b-it","score":63.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-2.5-3b-instruct","score":86.7,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-2-2b-it","score":68.9,"metric":"percent"},{"benchmark":"humaneval","model":"phi-3.5-mini-instruct","score":72.6,"metric":"percent"},{"benchmark":"humaneval","model":"minicpm3-4b","score":74.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-2.5-3b-instruct","score":74.4,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-2-2b-it","score":74.9,"metric":"percent"},{"benchmark":"mbpp","model":"phi-3.5-mini-instruct","score":63.2,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm3-4b","score":72.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-2.5-3b-instruct","score":72.7,"metric":"percent"},{"benchmark":"multipl-e","model":"gemma-2-2b-it","score":30.5,"metric":"percent"},{"benchmark":"multipl-e","model":"phi-3.5-mini-instruct","score":47.2,"metric":"percent"},{"benchmark":"multipl-e","model":"minicpm3-4b","score":49.1,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen-2.5-3b-instruct","score":60.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-2-2b-it","score":5.8,"metric":"percent"},{"benchmark":"livecodebench","model":"phi-3.5-mini-instruct","score":15.8,"metric":"percent"},{"benchmark":"livecodebench","model":"minicpm3-4b","score":23.8,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen-2.5-3b-instruct","score":19.9,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"gemma-2-2b-it","score":51,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"phi-3.5-mini-instruct","score":52.1,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen-2.5-3b-instruct","score":58.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-0.5b-instruct","score":14.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-0.5b-instruct","score":15,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2-1.5b-instruct","score":22.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-1.5b-instruct","score":32.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-0.5b-instruct","score":12.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-0.5b-instruct","score":24.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2-1.5b-instruct","score":41.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-1.5b-instruct","score":50.7,"metric":"percent"},{"benchmark":"livebench","model":"qwen2-0.5b-instruct","score":7.4,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-0.5b-instruct","score":12.6,"metric":"percent"},{"benchmark":"livebench","model":"qwen2-1.5b-instruct","score":12.4,"metric":"percent"},{"benchmark":"livebench","model":"qwen2.5-1.5b-instruct","score":18.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-0.5b-instruct","score":23.7,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-0.5b-instruct","score":29.8,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-1.5b-instruct","score":21.2,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-1.5b-instruct","score":29.8,"metric":"percent"},{"benchmark":"math","model":"qwen2-0.5b-instruct","score":13.9,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-0.5b-instruct","score":34.4,"metric":"percent"},{"benchmark":"math","model":"qwen2-1.5b-instruct","score":25.3,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-1.5b-instruct","score":55.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-0.5b-instruct","score":49.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-1.5b-instruct","score":73.2,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-0.5b-instruct","score":31.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-0.5b-instruct","score":35.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-1.5b-instruct","score":42.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-1.5b-instruct","score":61.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-0.5b-instruct","score":39.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-0.5b-instruct","score":49.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2-1.5b-instruct","score":44.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-1.5b-instruct","score":63.2,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-0.5b-instruct","score":20.8,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-0.5b-instruct","score":28.5,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2-1.5b-instruct","score":38.5,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen2.5-1.5b-instruct","score":50.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2-0.5b-instruct","score":1.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-0.5b-instruct","score":5.1,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2-1.5b-instruct","score":4.5,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-1.5b-instruct","score":14.8,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2-0.5b-instruct","score":14.6,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2.5-0.5b-instruct","score":27.9,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen2.5-1.5b-instruct","score":42.5,"metric":"percent"},{"benchmark":"arabicmmlu","model":"qwen2-72b-instruct","score":68.85,"metric":"percent"},{"benchmark":"arabicmmlu","model":"llama-3.1-70b-instruct","score":70.08,"metric":"percent"},{"benchmark":"arabicmmlu","model":"qwen2.5-32b-instruct","score":70.44,"metric":"percent"},{"benchmark":"arabicmmlu","model":"mistral-large-instruct-2407","score":69.24,"metric":"percent"},{"benchmark":"arabicmmlu","model":"gpt-4o-mini","score":69.73,"metric":"percent"},{"benchmark":"arabicmmlu","model":"qwen2.5-72b-instruct","score":72.44,"metric":"percent"},{"benchmark":"jmmlu","model":"qwen2-72b-instruct","score":77.37,"metric":"percent"},{"benchmark":"jmmlu","model":"llama-3.1-70b-instruct","score":73.89,"metric":"percent"},{"benchmark":"jmmlu","model":"qwen2.5-32b-instruct","score":76.55,"metric":"percent"},{"benchmark":"jmmlu","model":"mistral-large-instruct-2407","score":75.77,"metric":"percent"},{"benchmark":"jmmlu","model":"gpt-4o-mini","score":73.74,"metric":"percent"},{"benchmark":"jmmlu","model":"qwen2.5-72b-instruct","score":80.56,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen2-72b-instruct","score":57.04,"metric":"percent"},{"benchmark":"kmmlu","model":"llama-3.1-70b-instruct","score":53.23,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen2.5-32b-instruct","score":60.75,"metric":"percent"},{"benchmark":"kmmlu","model":"mistral-large-instruct-2407","score":56.42,"metric":"percent"},{"benchmark":"kmmlu","model":"gpt-4o-mini","score":56.77,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen2.5-72b-instruct","score":61.96,"metric":"percent"},{"benchmark":"indommlu","model":"qwen2-72b-instruct","score":66.31,"metric":"percent"},{"benchmark":"indommlu","model":"llama-3.1-70b-instruct","score":67.5,"metric":"percent"},{"benchmark":"indommlu","model":"qwen2.5-32b-instruct","score":66.42,"metric":"percent"},{"benchmark":"indommlu","model":"mistral-large-instruct-2407","score":63.21,"metric":"percent"},{"benchmark":"indommlu","model":"gpt-4o-mini","score":67.75,"metric":"percent"},{"benchmark":"indommlu","model":"qwen2.5-72b-instruct","score":69.25,"metric":"percent"},{"benchmark":"turkishmmlu","model":"qwen2-72b-instruct","score":69.22,"metric":"percent"},{"benchmark":"turkishmmlu","model":"llama-3.1-70b-instruct","score":66.89,"metric":"percent"},{"benchmark":"turkishmmlu","model":"qwen2.5-32b-instruct","score":72.41,"metric":"percent"},{"benchmark":"turkishmmlu","model":"mistral-large-instruct-2407","score":64.78,"metric":"percent"},{"benchmark":"turkishmmlu","model":"gpt-4o-mini","score":71.19,"metric":"percent"},{"benchmark":"turkishmmlu","model":"qwen2.5-72b-instruct","score":76.12,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2-72b-instruct","score":77.84,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"llama-3.1-70b-instruct","score":76.49,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2.5-32b-instruct","score":77.16,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"mistral-large-instruct-2407","score":78.37,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gpt-4o-mini","score":73.44,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2.5-72b-instruct","score":79.97,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2-72b-instruct","score":82.72,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.1-70b-instruct","score":73.31,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2.5-32b-instruct","score":87.15,"metric":"percent"},{"benchmark":"mgsm","model":"mistral-large-instruct-2407","score":89.01,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4o-mini","score":87.36,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2.5-72b-instruct","score":88.16,"metric":"percent"},{"benchmark":"blend","model":"qwen2-72b-instruct","score":25.9,"metric":"percent"},{"benchmark":"blend","model":"llama-3.1-70b-instruct","score":30.49,"metric":"percent"},{"benchmark":"blend","model":"qwen2.5-32b-instruct","score":27.88,"metric":"percent"},{"benchmark":"blend","model":"mistral-large-instruct-2407","score":33.47,"metric":"percent"},{"benchmark":"blend","model":"gpt-4o-mini","score":35.91,"metric":"percent"},{"benchmark":"blend","model":"qwen2.5-72b-instruct","score":32.48,"metric":"percent"},{"benchmark":"arabicmmlu","model":"qwen2-7b-instruct","score":54.87,"metric":"percent"},{"benchmark":"arabicmmlu","model":"llama-3.1-8b-instruct","score":54.28,"metric":"percent"},{"benchmark":"arabicmmlu","model":"qwen2.5-7b-instruct","score":59.78,"metric":"percent"},{"benchmark":"arabicmmlu","model":"gemma-2-9b-it","score":60.26,"metric":"percent"},{"benchmark":"arabicmmlu","model":"qwen2.5-14b-instruct","score":66.81,"metric":"percent"},{"benchmark":"jmmlu","model":"qwen2-7b-instruct","score":57.71,"metric":"percent"},{"benchmark":"jmmlu","model":"llama-3.1-8b-instruct","score":53.26,"metric":"percent"},{"benchmark":"jmmlu","model":"qwen2.5-7b-instruct","score":61.88,"metric":"percent"},{"benchmark":"jmmlu","model":"gemma-2-9b-it","score":64.59,"metric":"percent"},{"benchmark":"jmmlu","model":"qwen2.5-14b-instruct","score":72.78,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen2-7b-instruct","score":43.96,"metric":"percent"},{"benchmark":"kmmlu","model":"llama-3.1-8b-instruct","score":42.28,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen2.5-7b-instruct","score":46.59,"metric":"percent"},{"benchmark":"kmmlu","model":"gemma-2-9b-it","score":46.24,"metric":"percent"},{"benchmark":"kmmlu","model":"qwen2.5-14b-instruct","score":59.71,"metric":"percent"},{"benchmark":"indommlu","model":"qwen2-7b-instruct","score":54.05,"metric":"percent"},{"benchmark":"indommlu","model":"llama-3.1-8b-instruct","score":53.92,"metric":"percent"},{"benchmark":"indommlu","model":"qwen2.5-7b-instruct","score":56.42,"metric":"percent"},{"benchmark":"indommlu","model":"gemma-2-9b-it","score":61.73,"metric":"percent"},{"benchmark":"indommlu","model":"qwen2.5-14b-instruct","score":65.09,"metric":"percent"},{"benchmark":"turkishmmlu","model":"qwen2-7b-instruct","score":49.27,"metric":"percent"},{"benchmark":"turkishmmlu","model":"llama-3.1-8b-instruct","score":45.61,"metric":"percent"},{"benchmark":"turkishmmlu","model":"qwen2.5-7b-instruct","score":54.28,"metric":"percent"},{"benchmark":"turkishmmlu","model":"gemma-2-9b-it","score":55.44,"metric":"percent"},{"benchmark":"turkishmmlu","model":"qwen2.5-14b-instruct","score":66.85,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2-7b-instruct","score":60.47,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"llama-3.1-8b-instruct","score":55.18,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2.5-7b-instruct","score":66.98,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gemma-2-9b-it","score":46.72,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2.5-14b-instruct","score":72.12,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2-7b-instruct","score":56.13,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3.1-8b-instruct","score":66.05,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2.5-7b-instruct","score":66.11,"metric":"percent"},{"benchmark":"mgsm","model":"gemma-2-9b-it","score":78.37,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2.5-14b-instruct","score":82.27,"metric":"percent"},{"benchmark":"blend","model":"qwen2-7b-instruct","score":22.49,"metric":"percent"},{"benchmark":"blend","model":"llama-3.1-8b-instruct","score":19.47,"metric":"percent"},{"benchmark":"blend","model":"qwen2.5-7b-instruct","score":23.66,"metric":"percent"},{"benchmark":"blend","model":"gemma-2-9b-it","score":28.31,"metric":"percent"},{"benchmark":"blend","model":"qwen2.5-14b-instruct","score":26.99,"metric":"percent"},{"benchmark":"rewardbench","model":"athene-rm-70b","score":88.32,"metric":"percent"},{"benchmark":"rewardbench","model":"qwen2.5-rm-72b","score":91.59,"metric":"percent"},{"benchmark":"ruler-4k","model":"glm-4-9b-chat-1m","score":94.7,"metric":"percent"},{"benchmark":"ruler-8k","model":"glm-4-9b-chat-1m","score":92.8,"metric":"percent"},{"benchmark":"ruler-16k","model":"glm-4-9b-chat-1m","score":92.1,"metric":"percent"},{"benchmark":"ruler-32k","model":"glm-4-9b-chat-1m","score":89.9,"metric":"percent"},{"benchmark":"ruler-64k","model":"glm-4-9b-chat-1m","score":86.7,"metric":"percent"},{"benchmark":"ruler-128k","model":"glm-4-9b-chat-1m","score":83.1,"metric":"percent"},{"benchmark":"ruler-4k","model":"llama-3-8b-instruct-gradient-1048k","score":95.5,"metric":"percent"},{"benchmark":"ruler-8k","model":"llama-3-8b-instruct-gradient-1048k","score":93.8,"metric":"percent"},{"benchmark":"ruler-16k","model":"llama-3-8b-instruct-gradient-1048k","score":91.6,"metric":"percent"},{"benchmark":"ruler-32k","model":"llama-3-8b-instruct-gradient-1048k","score":87.4,"metric":"percent"},{"benchmark":"ruler-64k","model":"llama-3-8b-instruct-gradient-1048k","score":84.7,"metric":"percent"},{"benchmark":"ruler-128k","model":"llama-3-8b-instruct-gradient-1048k","score":77,"metric":"percent"},{"benchmark":"ruler-4k","model":"llama-3.1-70b-instruct","score":96.5,"metric":"percent"},{"benchmark":"ruler-8k","model":"llama-3.1-70b-instruct","score":95.8,"metric":"percent"},{"benchmark":"ruler-16k","model":"llama-3.1-70b-instruct","score":95.4,"metric":"percent"},{"benchmark":"ruler-32k","model":"llama-3.1-70b-instruct","score":94.8,"metric":"percent"},{"benchmark":"ruler-64k","model":"llama-3.1-70b-instruct","score":88.4,"metric":"percent"},{"benchmark":"ruler-128k","model":"llama-3.1-70b-instruct","score":66.6,"metric":"percent"},{"benchmark":"ruler-4k","model":"gpt-4o-mini","score":95,"metric":"percent"},{"benchmark":"ruler-8k","model":"gpt-4o-mini","score":92.9,"metric":"percent"},{"benchmark":"ruler-16k","model":"gpt-4o-mini","score":92.7,"metric":"percent"},{"benchmark":"ruler-32k","model":"gpt-4o-mini","score":90.2,"metric":"percent"},{"benchmark":"ruler-64k","model":"gpt-4o-mini","score":87.6,"metric":"percent"},{"benchmark":"ruler-128k","model":"gpt-4o-mini","score":65.8,"metric":"percent"},{"benchmark":"ruler-4k","model":"gpt-4-1106-preview","score":96.6,"metric":"percent"},{"benchmark":"ruler-8k","model":"gpt-4-1106-preview","score":96.3,"metric":"percent"},{"benchmark":"ruler-16k","model":"gpt-4-1106-preview","score":95.2,"metric":"percent"},{"benchmark":"ruler-32k","model":"gpt-4-1106-preview","score":93.2,"metric":"percent"},{"benchmark":"ruler-64k","model":"gpt-4-1106-preview","score":87,"metric":"percent"},{"benchmark":"ruler-128k","model":"gpt-4-1106-preview","score":81.2,"metric":"percent"},{"benchmark":"ruler-4k","model":"qwen2.5-7b-instruct","score":96.7,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen2.5-7b-instruct","score":95.1,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen2.5-7b-instruct","score":93.7,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen2.5-7b-instruct","score":89.4,"metric":"percent"},{"benchmark":"ruler-64k","model":"qwen2.5-7b-instruct","score":82.3,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen2.5-7b-instruct","score":55.1,"metric":"percent"},{"benchmark":"ruler-4k","model":"qwen2.5-14b-instruct","score":97.7,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen2.5-14b-instruct","score":96.8,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen2.5-14b-instruct","score":95.9,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen2.5-14b-instruct","score":93.4,"metric":"percent"},{"benchmark":"ruler-64k","model":"qwen2.5-14b-instruct","score":86.7,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen2.5-14b-instruct","score":78.1,"metric":"percent"},{"benchmark":"ruler-4k","model":"qwen2.5-32b-instruct","score":96.9,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen2.5-32b-instruct","score":97.1,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen2.5-32b-instruct","score":95.5,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen2.5-32b-instruct","score":95.5,"metric":"percent"},{"benchmark":"ruler-64k","model":"qwen2.5-32b-instruct","score":90.3,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen2.5-32b-instruct","score":82,"metric":"percent"},{"benchmark":"ruler-4k","model":"qwen2.5-72b-instruct","score":97.7,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen2.5-72b-instruct","score":97.2,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen2.5-72b-instruct","score":97.7,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen2.5-72b-instruct","score":96.5,"metric":"percent"},{"benchmark":"ruler-64k","model":"qwen2.5-72b-instruct","score":93,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen2.5-72b-instruct","score":88.4,"metric":"percent"},{"benchmark":"ruler-4k","model":"qwen2.5-turbo","score":97.5,"metric":"percent"},{"benchmark":"ruler-8k","model":"qwen2.5-turbo","score":95.7,"metric":"percent"},{"benchmark":"ruler-16k","model":"qwen2.5-turbo","score":95.5,"metric":"percent"},{"benchmark":"ruler-32k","model":"qwen2.5-turbo","score":94.8,"metric":"percent"},{"benchmark":"ruler-64k","model":"qwen2.5-turbo","score":90.8,"metric":"percent"},{"benchmark":"ruler-128k","model":"qwen2.5-turbo","score":84.5,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-0.5b","score":28,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-0.5b","score":23.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-0.5b","score":52.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-0.5b","score":47.1,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-0.5b","score":40.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-0.5b","score":16.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-0.5b","score":4.7,"metric":"pass@1"},{"benchmark":"humaneval-plus","model":"deepseek-coder-1.3b-base","score":26.8,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-1.3b-base","score":55.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-1.3b-base","score":46.9,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-1.3b-base","score":26.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-1.3b-base","score":3.4,"metric":"pass@1"},{"benchmark":"humaneval","model":"qwen2.5-coder-1.5b","score":43.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-1.5b","score":36.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-1.5b","score":69.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-1.5b","score":58.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-1.5b","score":59.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-1.5b","score":34.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-1.5b","score":9.5,"metric":"pass@1"},{"benchmark":"mbpp","model":"starcoder2-3b","score":60.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"starcoder2-3b","score":49.1,"metric":"percent"},{"benchmark":"mbpp","model":"starcoder2-3b","score":47.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"starcoder2-3b","score":21.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"starcoder2-3b","score":4.7,"metric":"pass@1"},{"benchmark":"humaneval","model":"qwen2.5-coder-3b","score":52.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-3b","score":42.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-3b","score":72.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-3b","score":61.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-3b","score":65.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-3b","score":41.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-3b","score":11.5,"metric":"pass@1"},{"benchmark":"mbpp","model":"starcoder2-7b","score":54.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"starcoder2-7b","score":45.6,"metric":"percent"},{"benchmark":"mbpp","model":"starcoder2-7b","score":51.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"starcoder2-7b","score":27.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"starcoder2-7b","score":8.8,"metric":"pass@1"},{"benchmark":"mbpp-plus","model":"deepseek-coder-6.7b-base","score":56.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-6.7b-base","score":41.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-6.7b-base","score":11.5,"metric":"pass@1"},{"benchmark":"humaneval","model":"deepseek-coder-v2-lite-base","score":40.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-v2-lite-base","score":34.1,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-v2-lite-base","score":71.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-v2-lite-base","score":59.4,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-v2-lite-base","score":62.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-v2-lite-base","score":30.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-lite-base","score":8.1,"metric":"pass@1"},{"benchmark":"mbpp","model":"codeqwen1.5-7b","score":72.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codeqwen1.5-7b","score":60.2,"metric":"percent"},{"benchmark":"mbpp","model":"codeqwen1.5-7b","score":61.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"codeqwen1.5-7b","score":45.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codeqwen1.5-7b","score":15.5,"metric":"pass@1"},{"benchmark":"humaneval","model":"qwen2.5-coder-7b","score":61.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-7b","score":53,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-7b","score":76.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-7b","score":62.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-7b","score":68.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-7b","score":45.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-7b","score":16.2,"metric":"pass@1"},{"benchmark":"mbpp","model":"starcoder2-15b","score":66.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"starcoder2-15b","score":53.1,"metric":"percent"},{"benchmark":"mbpp","model":"starcoder2-15b","score":57,"metric":"percent"},{"benchmark":"bigcodebench","model":"starcoder2-15b","score":38.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"starcoder2-15b","score":12.2,"metric":"pass@1"},{"benchmark":"humaneval","model":"qwen2.5-coder-14b","score":64,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-14b","score":57.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-14b","score":81,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-14b","score":66.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-14b","score":71.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-14b","score":51.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-14b","score":22.3,"metric":"pass@1"},{"benchmark":"humaneval","model":"deepseek-coder-33b-base","score":54.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-33b-base","score":47.6,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-33b-base","score":74.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-33b-base","score":60.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-33b-base","score":49.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-33b-base","score":20.3,"metric":"pass@1"},{"benchmark":"humaneval","model":"deepseek-coder-v2-base","score":50,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-v2-base","score":43.3,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-v2-base","score":82.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-v2-base","score":65.7,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-v2-base","score":71.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-v2-base","score":48.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-base","score":21.6,"metric":"pass@1"},{"benchmark":"humaneval","model":"qwen2.5-coder-32b","score":65.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-32b","score":60.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-32b","score":83,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-32b","score":68.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-32b","score":76.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-32b","score":53.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-32b","score":26.4,"metric":"pass@1"},{"benchmark":"crux-i","model":"qwen2.5-coder-0.5b","score":35.2,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-0.5b","score":23,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-1.3b-base","score":32.1,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-1.3b-base","score":28.2,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-1.5b","score":43.8,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-1.5b","score":34.6,"metric":"percent"},{"benchmark":"crux-i","model":"starcoder2-3b","score":42.1,"metric":"percent"},{"benchmark":"crux-o","model":"starcoder2-3b","score":29.2,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-3b","score":46.5,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-3b","score":43.8,"metric":"percent"},{"benchmark":"crux-i","model":"starcoder2-7b","score":39.5,"metric":"percent"},{"benchmark":"crux-o","model":"starcoder2-7b","score":35.1,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-6.7b-base","score":39,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-v2-lite-base","score":53.4,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-v2-lite-base","score":46.1,"metric":"percent"},{"benchmark":"crux-i","model":"codeqwen1.5-7b","score":44.8,"metric":"percent"},{"benchmark":"crux-o","model":"codeqwen1.5-7b","score":40.1,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-7b","score":56.5,"metric":"percent"},{"benchmark":"crux-i","model":"starcoder2-15b","score":46.1,"metric":"percent"},{"benchmark":"crux-o","model":"starcoder2-15b","score":47.6,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-14b","score":60.6,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-14b","score":66.4,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-33b-base","score":50.6,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-33b-base","score":48.8,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-v2-base","score":62.7,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-v2-base","score":67.4,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-32b","score":62.5,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-32b","score":69.4,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-0.5b","score":15.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-0.5b","score":34.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-coder-0.5b","score":34.4,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-coder-0.5b","score":14.3,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-1.3b-base","score":4.6,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-1.3b-base","score":4.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-coder-1.3b-base","score":24.5,"metric":"percent"},{"benchmark":"theoremqa","model":"deepseek-coder-1.3b-base","score":8.9,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-1.5b","score":30.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-1.5b","score":65.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-coder-1.5b","score":49,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-coder-1.5b","score":21.4,"metric":"percent"},{"benchmark":"math","model":"starcoder2-3b","score":10.8,"metric":"percent"},{"benchmark":"gsm8k","model":"starcoder2-3b","score":21.6,"metric":"percent"},{"benchmark":"mmlu-stem","model":"starcoder2-3b","score":34.9,"metric":"percent"},{"benchmark":"theoremqa","model":"starcoder2-3b","score":12.1,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-3b","score":40,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-3b","score":75.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-coder-3b","score":56,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-coder-3b","score":29.5,"metric":"percent"},{"benchmark":"math","model":"starcoder2-7b","score":14.6,"metric":"percent"},{"benchmark":"gsm8k","model":"starcoder2-7b","score":32.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"starcoder2-7b","score":39.8,"metric":"percent"},{"benchmark":"theoremqa","model":"starcoder2-7b","score":16,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-6.7b-base","score":10.3,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-6.7b-base","score":21.3,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-coder-6.7b-base","score":34.2,"metric":"percent"},{"benchmark":"theoremqa","model":"deepseek-coder-6.7b-base","score":13.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-v2-lite-base","score":39,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-lite-base","score":67.1,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-coder-v2-lite-base","score":58.5,"metric":"percent"},{"benchmark":"theoremqa","model":"deepseek-coder-v2-lite-base","score":29.3,"metric":"percent"},{"benchmark":"math","model":"codeqwen1.5-7b","score":10.6,"metric":"percent"},{"benchmark":"gsm8k","model":"codeqwen1.5-7b","score":37.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"codeqwen1.5-7b","score":39.6,"metric":"percent"},{"benchmark":"theoremqa","model":"codeqwen1.5-7b","score":15.8,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-7b","score":46.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-7b","score":83.9,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-coder-7b","score":67.6,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-coder-7b","score":34,"metric":"percent"},{"benchmark":"math","model":"starcoder2-15b","score":23.7,"metric":"percent"},{"benchmark":"gsm8k","model":"starcoder2-15b","score":57.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"starcoder2-15b","score":49.2,"metric":"percent"},{"benchmark":"theoremqa","model":"starcoder2-15b","score":20.5,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-14b","score":52.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-14b","score":88.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-coder-14b","score":73.9,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-coder-14b","score":39.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-33b-base","score":14.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-33b-base","score":35.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-coder-33b-base","score":39.5,"metric":"percent"},{"benchmark":"theoremqa","model":"deepseek-coder-33b-base","score":17.5,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-v2-base","score":50.6,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-base","score":85.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-coder-v2-base","score":76,"metric":"percent"},{"benchmark":"theoremqa","model":"deepseek-coder-v2-base","score":39.4,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-32b","score":57.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-32b","score":91.1,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-coder-32b","score":75.1,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen2.5-coder-32b","score":43.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-0.5b","score":42,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-0.5b","score":13.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-coder-0.5b","score":40.6,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-1.3b-base","score":25.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-1.3b-base","score":11.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-coder-1.3b-base","score":24.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-1.5b","score":53.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-1.5b","score":23.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-coder-1.5b","score":50.9,"metric":"percent"},{"benchmark":"mmlu","model":"starcoder2-3b","score":36.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"starcoder2-3b","score":15.5,"metric":"percent"},{"benchmark":"mmlu-redux","model":"starcoder2-3b","score":37,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-3b","score":61.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-3b","score":32,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-coder-3b","score":59.5,"metric":"percent"},{"benchmark":"mmlu","model":"starcoder2-7b","score":38.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"starcoder2-7b","score":17.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"starcoder2-7b","score":38.6,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-6.7b-base","score":36.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-6.7b-base","score":16.7,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-coder-6.7b-base","score":36.5,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-v2-lite-base","score":60.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-v2-lite-base","score":33.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-coder-v2-lite-base","score":58.3,"metric":"percent"},{"benchmark":"mmlu","model":"codeqwen1.5-7b","score":40.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"codeqwen1.5-7b","score":17.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"codeqwen1.5-7b","score":41.2,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-7b","score":68,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-7b","score":40.1,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-coder-7b","score":66.6,"metric":"percent"},{"benchmark":"mmlu","model":"starcoder2-15b","score":64.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"starcoder2-15b","score":24.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"starcoder2-15b","score":48.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-14b","score":75.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-14b","score":49.3,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-coder-14b","score":72.4,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-33b-base","score":39.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-33b-base","score":18.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-coder-33b-base","score":38.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-32b","score":79.1,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-32b","score":50.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.5-coder-32b","score":77.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-coder-0.5b","score":34.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-coder-0.5b","score":42.7,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-coder-0.5b","score":54.8,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-coder-0.5b","score":48.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-1.3b-base","score":25.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"deepseek-coder-1.3b-base","score":42.7,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-1.3b-base","score":53.3,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-1.3b-base","score":39.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-coder-1.5b","score":45.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-coder-1.5b","score":44,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-coder-1.5b","score":60.7,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-coder-1.5b","score":61.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"starcoder2-3b","score":34.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"starcoder2-3b","score":40.5,"metric":"percent"},{"benchmark":"winogrande","model":"starcoder2-3b","score":57.1,"metric":"percent"},{"benchmark":"hellaswag","model":"starcoder2-3b","score":48.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-coder-3b","score":52.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-coder-3b","score":49.2,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-coder-3b","score":67.4,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-coder-3b","score":70.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"starcoder2-7b","score":38.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"starcoder2-7b","score":42,"metric":"percent"},{"benchmark":"winogrande","model":"starcoder2-7b","score":57.1,"metric":"percent"},{"benchmark":"hellaswag","model":"starcoder2-7b","score":52.4,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-6.7b-base","score":36.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"deepseek-coder-6.7b-base","score":40.2,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-6.7b-base","score":57.6,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-v2-lite-base","score":57.3,"metric":"percent"},{"benchmark":"truthfulqa","model":"deepseek-coder-v2-lite-base","score":38.8,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-v2-lite-base","score":72.9,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-v2-lite-base","score":76.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"codeqwen1.5-7b","score":35.7,"metric":"percent"},{"benchmark":"truthfulqa","model":"codeqwen1.5-7b","score":42.2,"metric":"percent"},{"benchmark":"winogrande","model":"codeqwen1.5-7b","score":59.8,"metric":"percent"},{"benchmark":"hellaswag","model":"codeqwen1.5-7b","score":56,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-coder-7b","score":60.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-coder-7b","score":50.6,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-coder-7b","score":72.9,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-coder-7b","score":76.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"starcoder2-15b","score":47.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"starcoder2-15b","score":37.9,"metric":"percent"},{"benchmark":"winogrande","model":"starcoder2-15b","score":64.3,"metric":"percent"},{"benchmark":"hellaswag","model":"starcoder2-15b","score":64.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-coder-14b","score":66,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-coder-14b","score":55.2,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-coder-14b","score":76.8,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-coder-14b","score":80.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-33b-base","score":42.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"deepseek-coder-33b-base","score":40,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-33b-base","score":62,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-33b-base","score":60.2,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-v2-base","score":64.3,"metric":"percent"},{"benchmark":"truthfulqa","model":"deepseek-coder-v2-base","score":41.4,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-v2-base","score":83.7,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-v2-base","score":86,"metric":"percent"},{"benchmark":"arc-challenge","model":"qwen2.5-coder-32b","score":70.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen2.5-coder-32b","score":54.2,"metric":"percent"},{"benchmark":"winogrande","model":"qwen2.5-coder-32b","score":80.8,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen2.5-coder-32b","score":83,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-0.5b-instruct","score":61.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-0.5b-instruct","score":57.3,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-0.5b-instruct","score":52.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-0.5b-instruct","score":43.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-0.5b-instruct","score":11.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-0.5b-instruct","score":1.4,"metric":"pass@1"},{"benchmark":"livecodebench","model":"qwen2.5-coder-0.5b-instruct","score":2,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-1.3b-instruct","score":22.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-1.3b-instruct","score":3.4,"metric":"pass@1"},{"benchmark":"livecodebench","model":"deepseek-coder-1.3b-instruct","score":5.1,"metric":"percent"},{"benchmark":"humaneval","model":"yi-coder-1.5b-chat","score":69.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"yi-coder-1.5b-chat","score":64,"metric":"percent"},{"benchmark":"mbpp","model":"yi-coder-1.5b-chat","score":65.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"yi-coder-1.5b-chat","score":57.7,"metric":"percent"},{"benchmark":"bigcodebench","model":"yi-coder-1.5b-chat","score":23.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"yi-coder-1.5b-chat","score":11.5,"metric":"pass@1"},{"benchmark":"livecodebench","model":"yi-coder-1.5b-chat","score":4.8,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-1.5b-instruct","score":70.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-1.5b-instruct","score":66.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-1.5b-instruct","score":69.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-1.5b-instruct","score":59.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-1.5b-instruct","score":32.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-1.5b-instruct","score":6.8,"metric":"pass@1"},{"benchmark":"livecodebench","model":"qwen2.5-coder-1.5b-instruct","score":6.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-3b-instruct","score":84.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-3b-instruct","score":80.5,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-3b-instruct","score":73.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-3b-instruct","score":62.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-3b-instruct","score":35.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-3b-instruct","score":14.2,"metric":"pass@1"},{"benchmark":"livecodebench","model":"qwen2.5-coder-3b-instruct","score":10.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-7b-instruct","score":33.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codellama-7b-instruct","score":44.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"codellama-7b-instruct","score":21.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-7b-instruct","score":3.4,"metric":"pass@1"},{"benchmark":"livecodebench","model":"codellama-7b-instruct","score":7.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-6.7b-instruct","score":35.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-6.7b-instruct","score":10.1,"metric":"pass@1"},{"benchmark":"livecodebench","model":"deepseek-coder-6.7b-instruct","score":15.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codeqwen1.5-7b-chat","score":67.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"codeqwen1.5-7b-chat","score":39.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codeqwen1.5-7b-chat","score":18.9,"metric":"pass@1"},{"benchmark":"livecodebench","model":"codeqwen1.5-7b-chat","score":7.9,"metric":"percent"},{"benchmark":"humaneval-plus","model":"yi-coder-9b-chat","score":74.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"yi-coder-9b-chat","score":69,"metric":"percent"},{"benchmark":"bigcodebench","model":"yi-coder-9b-chat","score":38.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"yi-coder-9b-chat","score":11.5,"metric":"pass@1"},{"benchmark":"livecodebench","model":"yi-coder-9b-chat","score":17.2,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-v2-lite-instruct","score":82.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-v2-lite-instruct","score":70.4,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-v2-lite-instruct","score":36.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-lite-instruct","score":16.2,"metric":"pass@1"},{"benchmark":"livecodebench","model":"deepseek-coder-v2-lite-instruct","score":16.3,"metric":"percent"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-7b-instruct","score":18.2,"metric":"pass@1"},{"benchmark":"livecodebench","model":"qwen2.5-coder-7b-instruct","score":18.2,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-13b-instruct","score":40.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-13b-instruct","score":32.3,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-13b-instruct","score":60.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codellama-13b-instruct","score":51.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"codellama-13b-instruct","score":28.5,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-13b-instruct","score":9.5,"metric":"pass@1"},{"benchmark":"livecodebench","model":"codellama-13b-instruct","score":6.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"starcoder2-15b-instruct-v0.1","score":37.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"starcoder2-15b-instruct-v0.1","score":11.5,"metric":"pass@1"},{"benchmark":"livecodebench","model":"starcoder2-15b-instruct-v0.1","score":12.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-14b-instruct","score":89.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.5-coder-14b-instruct","score":87.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen2.5-coder-14b-instruct","score":86.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-14b-instruct","score":72.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-14b-instruct","score":48.4,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-14b-instruct","score":22.2,"metric":"pass@1"},{"benchmark":"livecodebench","model":"qwen2.5-coder-14b-instruct","score":23.4,"metric":"percent"},{"benchmark":"humaneval","model":"codellama-34b-instruct","score":48.2,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-34b-instruct","score":40.2,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-34b-instruct","score":61.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codellama-34b-instruct","score":50.5,"metric":"percent"},{"benchmark":"bigcodebench","model":"codellama-34b-instruct","score":29,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-34b-instruct","score":8.8,"metric":"pass@1"},{"benchmark":"livecodebench","model":"codellama-34b-instruct","score":8.4,"metric":"percent"},{"benchmark":"humaneval","model":"codestral-22b-v0.1","score":81.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codestral-22b-v0.1","score":73.2,"metric":"percent"},{"benchmark":"mbpp","model":"codestral-22b-v0.1","score":78.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codestral-22b-v0.1","score":62.2,"metric":"percent"},{"benchmark":"bigcodebench","model":"codestral-22b-v0.1","score":41.8,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codestral-22b-v0.1","score":16.9,"metric":"pass@1"},{"benchmark":"livecodebench","model":"codestral-22b-v0.1","score":22.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-33b-instruct","score":42,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-33b-instruct","score":17.6,"metric":"pass@1"},{"benchmark":"livecodebench","model":"deepseek-coder-33b-instruct","score":21.3,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-70b-instruct","score":77.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codellama-70b-instruct","score":64.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"codellama-70b-instruct","score":40.7,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"codellama-70b-instruct","score":11.5,"metric":"pass@1"},{"benchmark":"livecodebench","model":"codellama-70b-instruct","score":3.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"deepseek-coder-v2-instruct","score":48.2,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"deepseek-coder-v2-instruct","score":24.3,"metric":"pass@1"},{"benchmark":"livecodebench","model":"deepseek-coder-v2-instruct","score":27.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-coder-32b-instruct","score":92.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.5-coder-32b-instruct","score":75.1,"metric":"percent"},{"benchmark":"bigcodebench","model":"qwen2.5-coder-32b-instruct","score":49.6,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"qwen2.5-coder-32b-instruct","score":27,"metric":"pass@1"},{"benchmark":"livecodebench","model":"qwen2.5-coder-32b-instruct","score":31.4,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3.5-sonnet-20240620","score":89,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3.5-sonnet-20240620","score":81.1,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3.5-sonnet-20240620","score":87.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3.5-sonnet-20240620","score":72,"metric":"percent"},{"benchmark":"bigcodebench","model":"claude-3.5-sonnet-20240620","score":45.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3.5-sonnet-20240620","score":25.7,"metric":"pass@1"},{"benchmark":"livecodebench","model":"claude-3.5-sonnet-20240620","score":32.1,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3.5-sonnet-20241022","score":92.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"claude-3.5-sonnet-20241022","score":86,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3.5-sonnet-20241022","score":91,"metric":"percent"},{"benchmark":"mbpp-plus","model":"claude-3.5-sonnet-20241022","score":74.6,"metric":"percent"},{"benchmark":"bigcodebench","model":"claude-3.5-sonnet-20241022","score":45.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"claude-3.5-sonnet-20241022","score":23.6,"metric":"pass@1"},{"benchmark":"livecodebench","model":"claude-3.5-sonnet-20241022","score":31.6,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-mini-2024-07-18","score":87.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4o-mini-2024-07-18","score":84.8,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4o-mini-2024-07-18","score":86,"metric":"percent"},{"benchmark":"bigcodebench","model":"gpt-4o-mini-2024-07-18","score":46.9,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4o-mini-2024-07-18","score":23.6,"metric":"pass@1"},{"benchmark":"livecodebench","model":"gpt-4o-mini-2024-07-18","score":28.3,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-2024-08-06","score":92.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-4o-2024-08-06","score":86,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4o-2024-08-06","score":86.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4o-2024-08-06","score":72.5,"metric":"percent"},{"benchmark":"bigcodebench","model":"gpt-4o-2024-08-06","score":50.1,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"gpt-4o-2024-08-06","score":25,"metric":"pass@1"},{"benchmark":"livecodebench","model":"gpt-4o-2024-08-06","score":34.6,"metric":"percent"},{"benchmark":"humaneval","model":"o1-mini","score":97.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"o1-mini","score":90.2,"metric":"percent"},{"benchmark":"mbpp","model":"o1-mini","score":93.9,"metric":"percent"},{"benchmark":"mbpp-plus","model":"o1-mini","score":78.3,"metric":"percent"},{"benchmark":"bigcodebench","model":"o1-mini","score":46.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-mini","score":23,"metric":"pass@1"},{"benchmark":"livecodebench","model":"o1-mini","score":60,"metric":"percent"},{"benchmark":"humaneval","model":"o1-preview","score":95.1,"metric":"percent"},{"benchmark":"humaneval-plus","model":"o1-preview","score":88.4,"metric":"percent"},{"benchmark":"mbpp","model":"o1-preview","score":93.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"o1-preview","score":77.8,"metric":"percent"},{"benchmark":"bigcodebench","model":"o1-preview","score":49.3,"metric":"pass@1"},{"benchmark":"bigcodebench-hard","model":"o1-preview","score":27.7,"metric":"pass@1"},{"benchmark":"livecodebench","model":"o1-preview","score":43.1,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-0.5b-instruct","score":33.9,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-0.5b-instruct","score":27.8,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-1.3b-instruct","score":12.9,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-1.3b-instruct","score":28.1,"metric":"percent"},{"benchmark":"crux-i","model":"yi-coder-1.5b-chat","score":19.9,"metric":"percent"},{"benchmark":"crux-o","model":"yi-coder-1.5b-chat","score":24.9,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-1.5b-instruct","score":45.4,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-1.5b-instruct","score":37.5,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-3b-instruct","score":53.2,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-3b-instruct","score":56,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-7b-instruct","score":36.1,"metric":"percent"},{"benchmark":"crux-o","model":"codellama-7b-instruct","score":36.2,"metric":"percent"},{"benchmark":"crux-i","model":"deepseek-coder-6.7b-instruct","score":42.6,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-6.7b-instruct","score":45.1,"metric":"percent"},{"benchmark":"crux-i","model":"codeqwen1.5-7b-chat","score":44,"metric":"percent"},{"benchmark":"crux-o","model":"codeqwen1.5-7b-chat","score":38.8,"metric":"percent"},{"benchmark":"crux-i","model":"yi-coder-9b-chat","score":47.5,"metric":"percent"},{"benchmark":"crux-o","model":"yi-coder-9b-chat","score":55.6,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-7b-instruct","score":65.8,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-7b-instruct","score":65.9,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-13b-instruct","score":47.5,"metric":"percent"},{"benchmark":"crux-o","model":"codellama-13b-instruct","score":41.1,"metric":"percent"},{"benchmark":"crux-i","model":"starcoder2-15b-instruct-v0.1","score":45.5,"metric":"percent"},{"benchmark":"crux-o","model":"starcoder2-15b-instruct-v0.1","score":50.9,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-14b-instruct","score":69.5,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-14b-instruct","score":79.5,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-34b-instruct","score":48.5,"metric":"percent"},{"benchmark":"crux-o","model":"codellama-34b-instruct","score":47.1,"metric":"percent"},{"benchmark":"crux-i","model":"codestral-22b-v0.1","score":61.3,"metric":"percent"},{"benchmark":"crux-o","model":"codestral-22b-v0.1","score":63.5,"metric":"percent"},{"benchmark":"crux-i","model":"codellama-70b-instruct","score":56.5,"metric":"percent"},{"benchmark":"crux-o","model":"codellama-70b-instruct","score":57.8,"metric":"percent"},{"benchmark":"crux-i","model":"qwen2.5-coder-32b-instruct","score":75.2,"metric":"percent"},{"benchmark":"crux-o","model":"qwen2.5-coder-32b-instruct","score":83.4,"metric":"percent"},{"benchmark":"crux-i","model":"claude-3.5-sonnet-20240620","score":75.5,"metric":"percent"},{"benchmark":"crux-o","model":"claude-3.5-sonnet-20240620","score":81.8,"metric":"percent"},{"benchmark":"crux-i","model":"claude-3.5-sonnet-20241022","score":84.4,"metric":"percent"},{"benchmark":"crux-o","model":"claude-3.5-sonnet-20241022","score":87.2,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4o-mini-2024-07-18","score":67.5,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-4o-mini-2024-07-18","score":78.4,"metric":"percent"},{"benchmark":"crux-i","model":"gpt-4o-2024-08-06","score":78.6,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-4o-2024-08-06","score":89.2,"metric":"percent"},{"benchmark":"crux-i","model":"o1-mini","score":91.6,"metric":"percent"},{"benchmark":"crux-o","model":"o1-mini","score":96.2,"metric":"percent"},{"benchmark":"crux-i","model":"o1-preview","score":86.5,"metric":"percent"},{"benchmark":"crux-o","model":"o1-preview","score":81.4,"metric":"percent"},{"benchmark":"aider-code-editing","model":"qwen2.5-coder-0.5b-instruct","score":14.3,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-coder-1.3b-instruct","score":18.8,"metric":"percent"},{"benchmark":"aider-code-editing","model":"yi-coder-1.5b-chat","score":17.3,"metric":"percent"},{"benchmark":"aider-code-editing","model":"qwen2.5-coder-1.5b-instruct","score":31.6,"metric":"percent"},{"benchmark":"aider-code-editing","model":"qwen2.5-coder-3b-instruct","score":39.1,"metric":"percent"},{"benchmark":"aider-code-editing","model":"codellama-7b-instruct","score":1.5,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-coder-6.7b-instruct","score":44.4,"metric":"percent"},{"benchmark":"aider-code-editing","model":"codeqwen1.5-7b-chat","score":38.3,"metric":"percent"},{"benchmark":"aider-code-editing","model":"yi-coder-9b-chat","score":54.1,"metric":"percent"},{"benchmark":"aider-code-editing","model":"deepseek-coder-v2-lite-instruct","score":52.6,"metric":"percent"},{"benchmark":"aider-code-editing","model":"qwen2.5-coder-7b-instruct","score":68.4,"metric":"percent"},{"benchmark":"aider-code-editing","model":"codellama-13b-instruct","score":1.5,"metric":"percent"},{"benchmark":"aider-code-editing","model":"qwen2.5-coder-14b-instruct","score":69.2,"metric":"percent"},{"benchmark":"aider-code-editing","model":"codellama-34b-instruct","score":1.5,"metric":"percent"},{"benchmark":"aider-code-editing","model":"codestral-22b-v0.1","score":51.1,"metric":"percent"},{"benchmark":"aider-code-editing","model":"codellama-70b-instruct","score":15,"metric":"percent"},{"benchmark":"aider-code-editing","model":"qwen2.5-coder-32b-instruct","score":73.7,"metric":"percent"},{"benchmark":"aider-code-editing","model":"claude-3.5-sonnet-20240620","score":66.2,"metric":"percent"},{"benchmark":"aider-code-editing","model":"claude-3.5-sonnet-20241022","score":86.5,"metric":"percent"},{"benchmark":"aider-code-editing","model":"gpt-4o-mini-2024-07-18","score":55.6,"metric":"percent"},{"benchmark":"aider-code-editing","model":"gpt-4o-2024-08-06","score":74.4,"metric":"percent"},{"benchmark":"aider-code-editing","model":"o1-mini","score":70.7,"metric":"percent"},{"benchmark":"aider-code-editing","model":"o1-preview","score":88,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-v2-lite-instruct","score":61,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-lite-instruct","score":87.6,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"deepseek-coder-v2-lite-instruct","score":56.1,"metric":"percent"},{"benchmark":"olympiadbench","model":"deepseek-coder-v2-lite-instruct","score":26.4,"metric":"percent"},{"benchmark":"collegemath","model":"deepseek-coder-v2-lite-instruct","score":39.8,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-coder-v2-lite-instruct","score":6.7,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-v2-instruct","score":74.2,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-instruct","score":94.5,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"deepseek-coder-v2-instruct","score":65.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"deepseek-coder-v2-instruct","score":37.8,"metric":"percent"},{"benchmark":"collegemath","model":"deepseek-coder-v2-instruct","score":45.9,"metric":"percent"},{"benchmark":"aime-2024","model":"deepseek-coder-v2-instruct","score":6.7,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-3b-instruct","score":58.1,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-3b-instruct","score":80.7,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2.5-coder-3b-instruct","score":48.8,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2.5-coder-3b-instruct","score":23.6,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2.5-coder-3b-instruct","score":39.7,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-coder-3b-instruct","score":6.7,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-7b-instruct","score":66.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-7b-instruct","score":86.7,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2.5-coder-7b-instruct","score":60.5,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2.5-coder-7b-instruct","score":29.8,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2.5-coder-7b-instruct","score":43.5,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-coder-7b-instruct","score":10,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-14b-instruct","score":66.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-14b-instruct","score":94.2,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2.5-coder-14b-instruct","score":66,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2.5-coder-14b-instruct","score":40.1,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2.5-coder-14b-instruct","score":47.3,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-coder-14b-instruct","score":10,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-coder-32b-instruct","score":76.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-coder-32b-instruct","score":93,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2.5-coder-32b-instruct","score":68.3,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2.5-coder-32b-instruct","score":42.5,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2.5-coder-32b-instruct","score":47.7,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-coder-32b-instruct","score":20,"metric":"percent"},{"benchmark":"amc-23","model":"deepseek-coder-v2-lite-instruct","score":40.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-v2-lite-instruct","score":42.5,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-v2-lite-instruct","score":60.6,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-coder-v2-lite-instruct","score":38.6,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-coder-v2-lite-instruct","score":60.1,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-coder-v2-lite-instruct","score":27.6,"metric":"percent"},{"benchmark":"amc-23","model":"deepseek-coder-v2-instruct","score":52.5,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-v2-instruct","score":76.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"deepseek-coder-v2-instruct","score":65.6,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-coder-v2-instruct","score":40.9,"metric":"percent"},{"benchmark":"c-eval","model":"deepseek-coder-v2-instruct","score":73.4,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-coder-v2-instruct","score":44.3,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-coder-3b-instruct","score":25,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-3b-instruct","score":56.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-3b-instruct","score":35.2,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-coder-3b-instruct","score":44.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2.5-coder-3b-instruct","score":53.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-coder-3b-instruct","score":28.3,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-coder-7b-instruct","score":42.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-7b-instruct","score":68.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-7b-instruct","score":45.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-coder-7b-instruct","score":58.6,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2.5-coder-7b-instruct","score":61.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-coder-7b-instruct","score":35.6,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-coder-14b-instruct","score":50,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-14b-instruct","score":71.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-14b-instruct","score":55.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-coder-14b-instruct","score":66.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2.5-coder-14b-instruct","score":66.2,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-coder-14b-instruct","score":36.8,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-coder-32b-instruct","score":55,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2.5-coder-32b-instruct","score":77.6,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen2.5-coder-32b-instruct","score":62.3,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-coder-32b-instruct","score":79.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2.5-coder-32b-instruct","score":68.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-coder-32b-instruct","score":41.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b-base","score":56.7,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-8b-base","score":20.3,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.1-8b-base","score":53.1,"metric":"percent"},{"benchmark":"cmath","model":"llama-3.1-8b-base","score":51.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b-base","score":85.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.1-70b-base","score":78.1,"metric":"percent"},{"benchmark":"cmath","model":"llama-3.1-70b-base","score":75.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-1.5b","score":44.8,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-1.5b","score":55.6,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-7b","score":67.6,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-7b","score":76.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-72b","score":79.9,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-72b","score":85.4,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-v2-lite-base","score":68.3,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-v2-lite-base","score":38.1,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-coder-v2-lite-base","score":59.5,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-coder-v2-lite-base","score":77.8,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-base-20b","score":68.2,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-base-20b","score":30.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"internlm2-math-base-20b","score":63,"metric":"percent"},{"benchmark":"cmath","model":"internlm2-math-base-20b","score":65.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-math-1.5b","score":71.3,"metric":"percent"},{"benchmark":"math","model":"qwen2-math-1.5b","score":44.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-math-1.5b","score":50.4,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-math-1.5b","score":79.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-math-7b","score":80.4,"metric":"percent"},{"benchmark":"math","model":"qwen2-math-7b","score":50.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-math-7b","score":65.7,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-math-7b","score":83.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-math-72b","score":89.1,"metric":"percent"},{"benchmark":"math","model":"qwen2-math-72b","score":60.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-math-72b","score":79.1,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-math-72b","score":86.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-math-1.5b","score":76.8,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-math-1.5b","score":49.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-math-1.5b","score":51.3,"metric":"percent"},{"benchmark":"cmath","model":"qwen2.5-math-1.5b","score":83,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-math-7b","score":91.6,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-math-7b","score":55.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-math-7b","score":67.8,"metric":"percent"},{"benchmark":"cmath","model":"qwen2.5-math-7b","score":85,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-math-72b","score":90.8,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-math-72b","score":66.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-math-72b","score":82.8,"metric":"percent"},{"benchmark":"cmath","model":"qwen2.5-math-72b","score":89.7,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4o-2024-08-06","score":92.9,"metric":"percent"},{"benchmark":"math","model":"gpt-4o-2024-08-06","score":81.1,"metric":"percent"},{"benchmark":"minerva-math","model":"gpt-4o-2024-08-06","score":36.8,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"gpt-4o-2024-08-06","score":67.5,"metric":"percent"},{"benchmark":"olympiadbench","model":"gpt-4o-2024-08-06","score":43.3,"metric":"percent"},{"benchmark":"collegemath","model":"gpt-4o-2024-08-06","score":48.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"gpt-4o-2024-08-06","score":64.2,"metric":"percent"},{"benchmark":"math","model":"deepseek-math-7b-rl","score":52.4,"metric":"percent"},{"benchmark":"minerva-math","model":"deepseek-math-7b-rl","score":20.6,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"deepseek-math-7b-rl","score":43.6,"metric":"percent"},{"benchmark":"olympiadbench","model":"deepseek-math-7b-rl","score":19,"metric":"percent"},{"benchmark":"collegemath","model":"deepseek-math-7b-rl","score":37.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-math-7b-rl","score":64.8,"metric":"percent"},{"benchmark":"minerva-math","model":"deepseek-coder-v2-lite-instruct","score":29.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"deepseek-coder-v2-lite-instruct","score":68.6,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-plus-7b","score":84,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-plus-7b","score":54.4,"metric":"percent"},{"benchmark":"minerva-math","model":"internlm2-math-plus-7b","score":17.3,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"internlm2-math-plus-7b","score":50.1,"metric":"percent"},{"benchmark":"olympiadbench","model":"internlm2-math-plus-7b","score":18.8,"metric":"percent"},{"benchmark":"collegemath","model":"internlm2-math-plus-7b","score":36.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"internlm2-math-plus-7b","score":55.2,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-plus-20b","score":87.9,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-plus-20b","score":56.5,"metric":"percent"},{"benchmark":"minerva-math","model":"internlm2-math-plus-20b","score":20.2,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"internlm2-math-plus-20b","score":51.9,"metric":"percent"},{"benchmark":"olympiadbench","model":"internlm2-math-plus-20b","score":23.1,"metric":"percent"},{"benchmark":"collegemath","model":"internlm2-math-plus-20b","score":37.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"internlm2-math-plus-20b","score":63.5,"metric":"percent"},{"benchmark":"gsm8k","model":"mathstral-7b","score":84.9,"metric":"percent"},{"benchmark":"minerva-math","model":"mathstral-7b","score":16.2,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"mathstral-7b","score":46,"metric":"percent"},{"benchmark":"olympiadbench","model":"mathstral-7b","score":21.5,"metric":"percent"},{"benchmark":"collegemath","model":"mathstral-7b","score":33.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"mathstral-7b","score":64,"metric":"percent"},{"benchmark":"gsm8k","model":"numinamath-7b-cot","score":75.4,"metric":"percent"},{"benchmark":"math","model":"numinamath-7b-cot","score":55.2,"metric":"percent"},{"benchmark":"minerva-math","model":"numinamath-7b-cot","score":19.1,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"numinamath-7b-cot","score":47.5,"metric":"percent"},{"benchmark":"olympiadbench","model":"numinamath-7b-cot","score":19.9,"metric":"percent"},{"benchmark":"collegemath","model":"numinamath-7b-cot","score":36.9,"metric":"percent"},{"benchmark":"mmlu-stem","model":"numinamath-7b-cot","score":60.8,"metric":"percent"},{"benchmark":"gsm8k","model":"numinamath-72b-cot","score":90.8,"metric":"percent"},{"benchmark":"math","model":"numinamath-72b-cot","score":66.7,"metric":"percent"},{"benchmark":"minerva-math","model":"numinamath-72b-cot","score":25,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"numinamath-72b-cot","score":58.4,"metric":"percent"},{"benchmark":"olympiadbench","model":"numinamath-72b-cot","score":32.6,"metric":"percent"},{"benchmark":"collegemath","model":"numinamath-72b-cot","score":39.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"numinamath-72b-cot","score":64.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-8b-instruct","score":76.6,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-8b-instruct","score":47.2,"metric":"percent"},{"benchmark":"minerva-math","model":"llama-3.1-8b-instruct","score":21.7,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"llama-3.1-8b-instruct","score":38.4,"metric":"percent"},{"benchmark":"collegemath","model":"llama-3.1-8b-instruct","score":33.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.1-8b-instruct","score":60.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3.1-70b-instruct","score":94.1,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-70b-instruct","score":65.7,"metric":"percent"},{"benchmark":"minerva-math","model":"llama-3.1-70b-instruct","score":34.2,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"llama-3.1-70b-instruct","score":54,"metric":"percent"},{"benchmark":"olympiadbench","model":"llama-3.1-70b-instruct","score":27.7,"metric":"percent"},{"benchmark":"collegemath","model":"llama-3.1-70b-instruct","score":42.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"llama-3.1-70b-instruct","score":80.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-1.5b-instruct","score":64.1,"metric":"percent"},{"benchmark":"math","model":"qwen2-1.5b-instruct","score":25.1,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2-1.5b-instruct","score":5.5,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2-1.5b-instruct","score":19.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2-1.5b-instruct","score":4.1,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2-1.5b-instruct","score":10.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-1.5b-instruct","score":46.2,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2-7b-instruct","score":19.5,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2-7b-instruct","score":36.4,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2-7b-instruct","score":21.3,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2-7b-instruct","score":24.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-7b-instruct","score":68.2,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2-72b-instruct","score":31.6,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2-72b-instruct","score":58.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2-72b-instruct","score":33.2,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2-72b-instruct","score":43.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-72b-instruct","score":84.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-math-1.5b-instruct","score":84.2,"metric":"percent"},{"benchmark":"math","model":"qwen2-math-1.5b-instruct","score":69.4,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2-math-1.5b-instruct","score":29.4,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2-math-1.5b-instruct","score":59.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2-math-1.5b-instruct","score":31.3,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2-math-1.5b-instruct","score":44.2,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-math-1.5b-instruct","score":54.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-math-7b-instruct","score":89.9,"metric":"percent"},{"benchmark":"math","model":"qwen2-math-7b-instruct","score":75.1,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2-math-7b-instruct","score":34.6,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2-math-7b-instruct","score":62.1,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2-math-7b-instruct","score":38.2,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2-math-7b-instruct","score":45.9,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-math-7b-instruct","score":63.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-math-72b-instruct","score":96.7,"metric":"percent"},{"benchmark":"math","model":"qwen2-math-72b-instruct","score":84,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2-math-72b-instruct","score":40.1,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2-math-72b-instruct","score":68.3,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2-math-72b-instruct","score":43,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2-math-72b-instruct","score":47.9,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2-math-72b-instruct","score":79.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-math-1.5b-instruct","score":84.8,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-math-1.5b-instruct","score":75.8,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2.5-math-1.5b-instruct","score":29.4,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2.5-math-1.5b-instruct","score":65.5,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2.5-math-1.5b-instruct","score":38.1,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2.5-math-1.5b-instruct","score":47.7,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-math-1.5b-instruct","score":57.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-math-7b-instruct","score":95.2,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-math-7b-instruct","score":83.6,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2.5-math-7b-instruct","score":37.1,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2.5-math-7b-instruct","score":66.8,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2.5-math-7b-instruct","score":41.6,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2.5-math-7b-instruct","score":46.8,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-math-7b-instruct","score":71.9,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2.5-math-72b-instruct","score":95.9,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-math-72b-instruct","score":85.9,"metric":"percent"},{"benchmark":"minerva-math","model":"qwen2.5-math-72b-instruct","score":44.1,"metric":"percent"},{"benchmark":"gaokao-2023-en","model":"qwen2.5-math-72b-instruct","score":71.9,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2.5-math-72b-instruct","score":49,"metric":"percent"},{"benchmark":"collegemath","model":"qwen2.5-math-72b-instruct","score":49.5,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.5-math-72b-instruct","score":80.8,"metric":"percent"},{"benchmark":"cmath","model":"gpt-4o-2024-08-06","score":92.5,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-math-7b-rl","score":86.7,"metric":"percent"},{"benchmark":"cmath","model":"deepseek-coder-v2-lite-instruct","score":89.8,"metric":"percent"},{"benchmark":"cmath","model":"internlm2-math-plus-7b","score":82.7,"metric":"percent"},{"benchmark":"cmath","model":"internlm2-math-plus-20b","score":81.3,"metric":"percent"},{"benchmark":"cmath","model":"mathstral-7b","score":76.7,"metric":"percent"},{"benchmark":"cmath","model":"numinamath-7b-cot","score":78.2,"metric":"percent"},{"benchmark":"cmath","model":"numinamath-72b-cot","score":87.3,"metric":"percent"},{"benchmark":"cmath","model":"llama-3.1-8b-instruct","score":64.8,"metric":"percent"},{"benchmark":"cmath","model":"llama-3.1-70b-instruct","score":86.7,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-1.5b-instruct","score":65.5,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-7b-instruct","score":83.5,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-72b-instruct","score":92.2,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-math-1.5b-instruct","score":84.2,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-math-7b-instruct","score":90,"metric":"percent"},{"benchmark":"cmath","model":"qwen2-math-72b-instruct","score":92.8,"metric":"percent"},{"benchmark":"cmath","model":"qwen2.5-math-1.5b-instruct","score":89.7,"metric":"percent"},{"benchmark":"cmath","model":"qwen2.5-math-7b-instruct","score":91.8,"metric":"percent"},{"benchmark":"cmath","model":"qwen2.5-math-72b-instruct","score":94.3,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-3-opus","score":6.7,"metric":"percent"},{"benchmark":"aime-2024","model":"gpt-4-turbo","score":3.3,"metric":"percent"},{"benchmark":"aime-2024","model":"numinamath-72b-cot","score":3.3,"metric":"percent"},{"benchmark":"amc-23","model":"numinamath-72b-cot","score":52.5,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2-math-1.5b-instruct","score":3.3,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2-math-1.5b-instruct","score":45,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2-math-7b-instruct","score":13.3,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2-math-7b-instruct","score":62.5,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2-math-72b-instruct","score":20,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2-math-72b-instruct","score":60,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-math-1.5b-instruct","score":10,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-math-1.5b-instruct","score":60,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-math-7b-instruct","score":16.7,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-math-7b-instruct","score":62.5,"metric":"percent"},{"benchmark":"aime-2024","model":"qwen2.5-math-72b-instruct","score":30,"metric":"percent"},{"benchmark":"amc-23","model":"qwen2.5-math-72b-instruct","score":70,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2-vl-72b-instruct","score":64.5,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2-vl-7b-instruct","score":54.1,"metric":"percent"},{"benchmark":"mmmu","model":"qwen2-vl-2b-instruct","score":41.1,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2-vl-72b-instruct","score":96.5,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2-vl-7b-instruct","score":94.5,"metric":"percent"},{"benchmark":"docvqa","model":"qwen2-vl-2b-instruct","score":90.1,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2-vl-72b-instruct","score":84.5,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2-vl-7b-instruct","score":76.5,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2-vl-2b-instruct","score":65.5,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3.5-sonnet","score":80.2,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2-vl-72b-instruct","score":88.1,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2-vl-7b-instruct","score":83,"metric":"percent"},{"benchmark":"ai2d","model":"qwen2-vl-2b-instruct","score":74.7,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2-vl-72b-instruct","score":88.3,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2-vl-7b-instruct","score":83,"metric":"percent"},{"benchmark":"chartqa","model":"qwen2-vl-2b-instruct","score":73.5,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2-vl-72b-instruct","score":85.5,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2-vl-7b-instruct","score":84.3,"metric":"percent"},{"benchmark":"textvqa","model":"qwen2-vl-2b-instruct","score":79.7,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-3.5-sonnet","score":78.8,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2-vl-72b-instruct","score":87.7,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2-vl-7b-instruct","score":86.6,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2-vl-2b-instruct","score":80.9,"metric":"percent"},{"benchmark":"mtvqa","model":"claude-3.5-sonnet","score":25.7,"metric":"percent"},{"benchmark":"mtvqa","model":"gpt-4o","score":27.8,"metric":"percent"},{"benchmark":"mtvqa","model":"qwen2-vl-72b-instruct","score":30.9,"metric":"percent"},{"benchmark":"mtvqa","model":"qwen2-vl-7b-instruct","score":25.6,"metric":"percent"},{"benchmark":"mtvqa","model":"qwen2-vl-2b-instruct","score":18.1,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2-vl-72b-instruct","score":77.8,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2-vl-7b-instruct","score":70.1,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2-vl-2b-instruct","score":62.9,"metric":"percent"},{"benchmark":"mme-elo","model":"claude-3.5-sonnet","score":1920,"metric":"points"},{"benchmark":"mme-elo","model":"gpt-4o","score":2328.7,"metric":"points"},{"benchmark":"mme-elo","model":"qwen2-vl-72b-instruct","score":2482.7,"metric":"points"},{"benchmark":"mme-elo","model":"qwen2-vl-7b-instruct","score":2326.8,"metric":"points"},{"benchmark":"mme-elo","model":"qwen2-vl-2b-instruct","score":1872,"metric":"points"},{"benchmark":"mmbench","model":"claude-3.5-sonnet","score":79.7,"metric":"percent"},{"benchmark":"mmbench","model":"qwen2-vl-72b-instruct","score":86.5,"metric":"percent"},{"benchmark":"mmbench","model":"qwen2-vl-7b-instruct","score":83,"metric":"percent"},{"benchmark":"mmbench","model":"qwen2-vl-2b-instruct","score":74.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"claude-3.5-sonnet","score":80.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen2-vl-72b-instruct","score":86.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen2-vl-7b-instruct","score":80.5,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen2-vl-2b-instruct","score":73.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3.5-sonnet","score":78.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-72b-instruct","score":85.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-7b-instruct","score":80.7,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-2b-instruct","score":72.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen2-vl-72b-instruct","score":71.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen2-vl-7b-instruct","score":63.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen2-vl-2b-instruct","score":54.5,"metric":"percent"},{"benchmark":"mmstar","model":"claude-3.5-sonnet","score":62.2,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2-vl-72b-instruct","score":68.3,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2-vl-7b-instruct","score":60.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2-vl-2b-instruct","score":48,"metric":"percent"},{"benchmark":"mmvet","model":"claude-3.5-sonnet","score":66,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4o","score":69.1,"metric":"percent"},{"benchmark":"mmvet","model":"qwen2-vl-72b-instruct","score":74,"metric":"percent"},{"benchmark":"mmvet","model":"qwen2-vl-7b-instruct","score":62,"metric":"percent"},{"benchmark":"mmvet","model":"qwen2-vl-2b-instruct","score":49.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-3.5-sonnet","score":49.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2-vl-72b-instruct","score":58.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2-vl-7b-instruct","score":50.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2-vl-2b-instruct","score":41.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2-vl-72b-instruct","score":70.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2-vl-7b-instruct","score":58.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2-vl-2b-instruct","score":43,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-4o","score":30.4,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2-vl-72b-instruct","score":25.9,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2-vl-7b-instruct","score":16.3,"metric":"percent"},{"benchmark":"mathvision","model":"qwen2-vl-2b-instruct","score":12.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-3.5-sonnet","score":51.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-4o","score":51.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2-vl-72b-instruct","score":46.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2-vl-7b-instruct","score":43.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2-vl-2b-instruct","score":37.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen2-vl-72b-instruct","score":73.6,"metric":"percent"},{"benchmark":"mvbench","model":"qwen2-vl-7b-instruct","score":67,"metric":"percent"},{"benchmark":"mvbench","model":"qwen2-vl-2b-instruct","score":63.2,"metric":"percent"},{"benchmark":"perceptiontest","model":"qwen2-vl-72b-instruct","score":68,"metric":"percent"},{"benchmark":"perceptiontest","model":"qwen2-vl-7b-instruct","score":62.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"qwen2-vl-2b-instruct","score":53.9,"metric":"percent"},{"benchmark":"egoschema","model":"gemini-1.5-pro","score":63.2,"metric":"percent"},{"benchmark":"egoschema","model":"qwen2-vl-7b-instruct","score":66.7,"metric":"percent"},{"benchmark":"egoschema","model":"qwen2-vl-2b-instruct","score":54.9,"metric":"percent"},{"benchmark":"video-mme","model":"gemini-1.5-pro","score":75,"metric":"percent"},{"benchmark":"video-mme","model":"gpt-4o","score":71.9,"metric":"percent"},{"benchmark":"video-mme","model":"qwen2-vl-72b-instruct","score":71.2,"metric":"percent"},{"benchmark":"video-mme","model":"qwen2-vl-7b-instruct","score":63.3,"metric":"percent"},{"benchmark":"video-mme","model":"qwen2-vl-2b-instruct","score":55.6,"metric":"percent"},{"benchmark":"refcoco","model":"ofa-large","score":80,"metric":"percent"},{"benchmark":"refcocoplus","model":"ofa-large","score":68.3,"metric":"percent"},{"benchmark":"refcocog","model":"ofa-large","score":67.6,"metric":"percent"},{"benchmark":"refcoco","model":"qwen-vl","score":89.4,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen-vl","score":83.1,"metric":"percent"},{"benchmark":"refcocog","model":"qwen-vl","score":85.6,"metric":"percent"},{"benchmark":"refcoco","model":"ferret-v2-13b","score":92.6,"metric":"percent"},{"benchmark":"refcocoplus","model":"ferret-v2-13b","score":87.4,"metric":"percent"},{"benchmark":"refcocog","model":"ferret-v2-13b","score":89.4,"metric":"percent"},{"benchmark":"refcoco","model":"cogvlm-grounding-generalist","score":92.8,"metric":"percent"},{"benchmark":"refcocoplus","model":"cogvlm-grounding-generalist","score":88.7,"metric":"percent"},{"benchmark":"refcocog","model":"cogvlm-grounding-generalist","score":89.8,"metric":"percent"},{"benchmark":"refcoco","model":"internvl2-76b","score":92.2,"metric":"percent"},{"benchmark":"refcocoplus","model":"internvl2-76b","score":88.8,"metric":"percent"},{"benchmark":"refcocog","model":"internvl2-76b","score":89.5,"metric":"percent"},{"benchmark":"refcoco","model":"qwen2-vl-2b-instruct","score":87.6,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen2-vl-2b-instruct","score":79,"metric":"percent"},{"benchmark":"refcocog","model":"qwen2-vl-2b-instruct","score":81.2,"metric":"percent"},{"benchmark":"refcoco","model":"qwen2-vl-7b-instruct","score":91.7,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen2-vl-7b-instruct","score":85.8,"metric":"percent"},{"benchmark":"refcocog","model":"qwen2-vl-7b-instruct","score":87.3,"metric":"percent"},{"benchmark":"refcoco","model":"qwen2-vl-72b-instruct","score":93.2,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen2-vl-72b-instruct","score":90.1,"metric":"percent"},{"benchmark":"refcocog","model":"qwen2-vl-72b-instruct","score":89.9,"metric":"percent"},{"benchmark":"asr-librispeech-clean","model":"salmonn-13b","score":2.1,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"salmonn-13b","score":4.9,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"qwen-audio","score":2,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"qwen-audio","score":4.2,"metric":"wer"},{"benchmark":"asr-librispeech-clean","model":"qwen2-audio-7b","score":1.6,"metric":"wer"},{"benchmark":"asr-librispeech-other","model":"qwen2-audio-7b","score":3.6,"metric":"wer"},{"benchmark":"mbpp","model":"gpt-4","score":61.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b","score":54.4,"metric":"percent"},{"benchmark":"math","model":"llama-2-70b","score":10.6,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":23.7,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-70b","score":37.7,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-70b","score":58.4,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-v0.1","score":64.1,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-v0.1","score":47.5,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-v0.1","score":11.3,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-v0.1","score":27.4,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-v0.1","score":38.6,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b-v0.1","score":56.7,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b-v0.1","score":44.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-7b","score":37.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-14b","score":67.6,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-14b","score":78.7,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-14b","score":70.1,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-14b","score":29.2,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-14b","score":37.8,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-14b","score":44,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-14b","score":53.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-14b","score":77.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-32b","score":73.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-32b","score":77.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-32b","score":37.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-32b","score":49.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-72b","score":53.4,"metric":"percent"},{"benchmark":"c-eval","model":"tinyllama-1.1b","score":25,"metric":"percent"},{"benchmark":"gsm8k","model":"tinyllama-1.1b","score":2.3,"metric":"percent"},{"benchmark":"math","model":"tinyllama-1.1b","score":0.7,"metric":"percent"},{"benchmark":"humaneval","model":"tinyllama-1.1b","score":6.7,"metric":"percent"},{"benchmark":"mbpp","model":"tinyllama-1.1b","score":19.9,"metric":"percent"},{"benchmark":"bbh","model":"tinyllama-1.1b","score":28.8,"metric":"percent"},{"benchmark":"cmmlu","model":"tinyllama-1.1b","score":24,"metric":"percent"},{"benchmark":"c-eval","model":"stablelm-zephyr-3b","score":30.3,"metric":"percent"},{"benchmark":"gsm8k","model":"stablelm-zephyr-3b","score":52.5,"metric":"percent"},{"benchmark":"math","model":"stablelm-zephyr-3b","score":12.5,"metric":"percent"},{"benchmark":"humaneval","model":"stablelm-zephyr-3b","score":35.4,"metric":"percent"},{"benchmark":"mbpp","model":"stablelm-zephyr-3b","score":31.9,"metric":"percent"},{"benchmark":"bbh","model":"stablelm-zephyr-3b","score":37.7,"metric":"percent"},{"benchmark":"cmmlu","model":"stablelm-zephyr-3b","score":30.9,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm-2b-sft","score":53.5,"metric":"percent"},{"benchmark":"c-eval","model":"minicpm-2b-sft","score":51.1,"metric":"percent"},{"benchmark":"gsm8k","model":"minicpm-2b-sft","score":53.8,"metric":"percent"},{"benchmark":"math","model":"minicpm-2b-sft","score":10.2,"metric":"percent"},{"benchmark":"mbpp","model":"minicpm-2b-sft","score":47.3,"metric":"percent"},{"benchmark":"bbh","model":"minicpm-2b-sft","score":36.9,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-2b-sft","score":51.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-0.5b","score":39.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-0.5b","score":50.5,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-0.5b","score":22,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-0.5b","score":3.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-0.5b","score":12.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-0.5b","score":6.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-0.5b","score":18.3,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-0.5b","score":46.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-4b","score":56.1,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-4b","score":67.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-4b","score":57,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-4b","score":10,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-4b","score":25.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-4b","score":29.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-4b","score":32.5,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-4b","score":66.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-moe-a2.7b","score":62.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-moe-a2.7b","score":79.2,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-moe-a2.7b","score":61.5,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-moe-a2.7b","score":21.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-moe-a2.7b","score":34.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-moe-a2.7b","score":36.6,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-moe-a2.7b","score":39.1,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-moe-a2.7b","score":79.2,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen1.5-14b-chat","score":7.91,"metric":"percent"},{"benchmark":"l-eval","model":"qwen-72b-chat","score":73.42,"metric":"percent"},{"benchmark":"l-eval","model":"qwen1.5-0.5b-chat","score":32.14,"metric":"percent"},{"benchmark":"l-eval","model":"qwen1.5-1.8b-chat","score":43.72,"metric":"percent"},{"benchmark":"l-eval","model":"qwen1.5-4b-chat","score":57.05,"metric":"percent"},{"benchmark":"l-eval","model":"qwen1.5-7b-chat","score":65.16,"metric":"percent"},{"benchmark":"l-eval","model":"qwen1.5-14b-chat","score":76.44,"metric":"percent"},{"benchmark":"l-eval","model":"qwen1.5-72b-chat","score":78.12,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b","score":81.4,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-34b","score":67.2,"metric":"percent"},{"benchmark":"math","model":"yi-34b","score":14.4,"metric":"percent"},{"benchmark":"humaneval","model":"yi-34b","score":23.2,"metric":"percent"},{"benchmark":"mbpp","model":"yi-34b","score":41,"metric":"percent"},{"benchmark":"bbh","model":"yi-34b","score":54.3,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-34b","score":83.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen1.5-32b-chat","score":27.49,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-3-70b-base","score":32,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-70b-base","score":36.4,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-70b-base","score":76.6,"metric":"percent"},{"benchmark":"bbh","model":"mixtral-8x22b","score":69.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b-base","score":79.2,"metric":"percent"},{"benchmark":"math","model":"llama-3-70b-base","score":41,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-110b","score":52.4,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b-base","score":45.7,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-110b","score":58.1,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-70b-base","score":55.1,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3-70b-instruct","score":8.85,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen1.5-110b-chat","score":43.9,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-7b","score":50.9,"metric":"percent"},{"benchmark":"mt-bench","model":"deepseek-moe-16b-chat","score":6.93,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen1.5-moe-a2.7b-chat","score":7.17,"metric":"percent"},{"benchmark":"humaneval-plus","model":"codellama-7b","score":25.6,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b","score":52.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"codellama-7b","score":41.6,"metric":"percent"},{"benchmark":"mbpp","model":"starcoder2-7b","score":51,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gpt-3.5-turbo","score":70.7,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-3.5-turbo","score":82.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-3.5-turbo","score":69.7,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4-1106-preview","score":83.5,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gpt-4-1106-preview","score":70.7,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4-1106-preview","score":80,"metric":"percent"},{"benchmark":"humaneval-plus","model":"deepseek-coder-6.7b-instruct","score":70.1,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-6.7b-instruct","score":73.2,"metric":"percent"},{"benchmark":"mbpp-plus","model":"deepseek-coder-6.7b-instruct","score":63.4,"metric":"percent"},{"benchmark":"mbpp","model":"codeqwen1.5-7b-chat","score":70.6,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-v2","score":84.8,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-v2","score":70,"metric":"percent"},{"benchmark":"truthfulqa","model":"deepseek-v2","score":42.2,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2","score":45.7,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2","score":73.9,"metric":"percent"},{"benchmark":"evalplus","model":"deepseek-v2","score":55,"metric":"percent"},{"benchmark":"multipl-e","model":"deepseek-v2","score":44.4,"metric":"percent"},{"benchmark":"hellaswag","model":"minicpm-2b-sft","score":68.3,"metric":"percent"},{"benchmark":"evalplus","model":"llama-3-70b-instruct","score":75.2,"metric":"percent"},{"benchmark":"evalplus","model":"qwen1.5-72b-chat","score":66.9,"metric":"percent"},{"benchmark":"evalplus","model":"qwen2-72b-instruct","score":79,"metric":"percent"},{"benchmark":"math","model":"qwen2-72b-instruct","score":59.7,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-70b-instruct","score":61.6,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-72b-chat","score":76.1,"metric":"percent"},{"benchmark":"evalplus","model":"mixtral-8x7b-instruct-v0.1","score":48.5,"metric":"percent"},{"benchmark":"evalplus","model":"qwen1.5-32b-chat","score":63.6,"metric":"percent"},{"benchmark":"evalplus","model":"qwen2-57b-a14b-instruct","score":71.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-57b-a14b-instruct","score":79.6,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-32b-chat","score":76.7,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-57b-a14b-instruct","score":80.5,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-7b-instruct","score":25.3,"metric":"percent"},{"benchmark":"evalplus","model":"llama-3-8b-instruct","score":60.9,"metric":"percent"},{"benchmark":"evalplus","model":"qwen1.5-7b-chat","score":44.8,"metric":"percent"},{"benchmark":"evalplus","model":"qwen2-7b-instruct","score":70.3,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-8b-instruct","score":45.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-7b-chat","score":67.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-0.5b-chat","score":9.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-0.5b-instruct","score":17.1,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-1.8b-chat","score":25,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-1.5b-instruct","score":37.8,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-0.5b-chat","score":37.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-0.5b-instruct","score":45.2,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-1.8b-chat","score":55.3,"metric":"percent"},{"benchmark":"c-eval","model":"qwen2-1.5b-instruct","score":63.8,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gpt-4-0613","score":78,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4-0613","score":87,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gpt-4-turbo-2024-04-09","score":79.3,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4-turbo-2024-04-09","score":90.5,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"gpt-4o-2024-05-13","score":83.2,"metric":"percent"},{"benchmark":"mgsm","model":"gpt-4o-2024-05-13","score":89.6,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"claude-3-opus-20240229","score":80.1,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3-opus-20240229","score":91,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"claude-3-sonnet-20240229","score":71,"metric":"percent"},{"benchmark":"mgsm","model":"claude-3-sonnet-20240229","score":85.6,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"command-r-plus","score":65.5,"metric":"percent"},{"benchmark":"mgsm","model":"command-r-plus","score":63.5,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen1.5-7b-chat","score":50,"metric":"percent"},{"benchmark":"mgsm","model":"qwen1.5-7b-chat","score":37,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen1.5-32b-chat","score":65,"metric":"percent"},{"benchmark":"mgsm","model":"qwen1.5-32b-chat","score":65,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen1.5-72b-chat","score":68.4,"metric":"percent"},{"benchmark":"mgsm","model":"qwen1.5-72b-chat","score":71.7,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2-7b-instruct","score":60,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2-7b-instruct","score":57,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2-57b-a14b-instruct","score":68,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2-57b-a14b-instruct","score":74,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"qwen2-72b-instruct","score":78,"metric":"percent"},{"benchmark":"mgsm","model":"qwen2-72b-instruct","score":86.6,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen2.57b-a14b","score":72.4,"metric":"percent"},{"benchmark":"mmlu-stem","model":"qwen2.57b-a14b","score":69.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen2.57b-a14b","score":46.3,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen2.57b-a14b","score":57.4,"metric":"percent"},{"benchmark":"mmlu-pro","model":"mistral-large-instruct-2407","score":69.4,"metric":"percent"},{"benchmark":"mmlu-redux","model":"mistral-large-instruct-2407","score":83,"metric":"percent"},{"benchmark":"gpqa","model":"mistral-large-instruct-2407","score":52,"metric":"percent"},{"benchmark":"math","model":"mistral-large-instruct-2407","score":69.9,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-large-instruct-2407","score":92.7,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-large-instruct-2407","score":92.1,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-large-instruct-2407","score":80,"metric":"percent"},{"benchmark":"multipl-e","model":"mistral-large-instruct-2407","score":76.9,"metric":"percent"},{"benchmark":"livecodebench","model":"mistral-large-instruct-2407","score":42.2,"metric":"percent"},{"benchmark":"livebench","model":"mistral-large-instruct-2407","score":48.5,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"mistral-large-instruct-2407","score":64.1,"metric":"percent"},{"benchmark":"arena-hard","model":"mistral-large-instruct-2407","score":73.1,"metric":"percent"},{"benchmark":"alignbench","model":"mistral-large-instruct-2407","score":7.69,"metric":"score"},{"benchmark":"alignbench","model":"llama-3.1-70b-instruct","score":5.94,"metric":"score"},{"benchmark":"alignbench","model":"llama-3.1-405b-instruct","score":5.95,"metric":"score"},{"benchmark":"alignbench","model":"qwen2-72b-instruct","score":8.15,"metric":"score"},{"benchmark":"alignbench","model":"qwen2.5-72b-instruct","score":8.16,"metric":"score"},{"benchmark":"mt-bench","model":"mistral-large-instruct-2407","score":8.61,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen-turbo-0919","score":64.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen-turbo-0919","score":80.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen-turbo-0919","score":44.4,"metric":"percent"},{"benchmark":"math","model":"qwen-turbo-0919","score":81,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-turbo-0919","score":93.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-turbo-0919","score":86.6,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-turbo-0919","score":80.2,"metric":"percent"},{"benchmark":"multipl-e","model":"qwen-turbo-0919","score":73,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen-turbo-0919","score":43.1,"metric":"percent"},{"benchmark":"livebench","model":"qwen-turbo-0919","score":41.6,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"qwen-turbo-0919","score":74.9,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen-turbo-0919","score":68.4,"metric":"percent"},{"benchmark":"alignbench","model":"qwen2-57b-a14b-instruct","score":7.02,"metric":"score"},{"benchmark":"alignbench","model":"gemma-2-27b-it","score":7.22,"metric":"score"},{"benchmark":"alignbench","model":"gpt-4o-mini","score":7.81,"metric":"score"},{"benchmark":"alignbench","model":"qwen-turbo-0919","score":7.99,"metric":"score"},{"benchmark":"alignbench","model":"qwen2.5-14b-instruct","score":7.94,"metric":"score"},{"benchmark":"alignbench","model":"qwen2.5-32b-instruct","score":7.93,"metric":"score"},{"benchmark":"mt-bench","model":"qwen-turbo-0919","score":8.86,"metric":"percent"},{"benchmark":"alignbench","model":"gemma-2-9b-it","score":7.05,"metric":"score"},{"benchmark":"alignbench","model":"llama-3.1-8b-instruct","score":4.75,"metric":"score"},{"benchmark":"alignbench","model":"qwen2-7b-instruct","score":7.13,"metric":"score"},{"benchmark":"alignbench","model":"qwen2.5-7b-instruct","score":7.33,"metric":"score"},{"benchmark":"arabicmmlu","model":"mistral-nemo-instruct-2407","score":53.92,"metric":"percent"},{"benchmark":"jmmlu","model":"mistral-nemo-instruct-2407","score":55.17,"metric":"percent"},{"benchmark":"kmmlu","model":"mistral-nemo-instruct-2407","score":42.22,"metric":"percent"},{"benchmark":"indommlu","model":"mistral-nemo-instruct-2407","score":50.76,"metric":"percent"},{"benchmark":"turkishmmlu","model":"mistral-nemo-instruct-2407","score":34.44,"metric":"percent"},{"benchmark":"multilingual-mmlu","model":"mistral-nemo-instruct-2407","score":59.65,"metric":"percent"},{"benchmark":"mgsm","model":"mistral-nemo-instruct-2407","score":54.75,"metric":"percent"},{"benchmark":"blend","model":"mistral-nemo-instruct-2407","score":26.61,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-1.0-pro","score":74.1,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-1.0-pro","score":73.9,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.0-pro","score":47.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-1.0-pro","score":45.2,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-1.0-ultra","score":90.9,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-1.0-ultra","score":80.8,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-1.0-ultra","score":79.5,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-1.0-ultra","score":82.3,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.0-ultra","score":59.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-1.0-ultra","score":53,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4v","score":88.4,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-4v","score":78.5,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4v","score":78.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4v","score":49.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gpt-4v","score":73.9,"metric":"percent"},{"benchmark":"docvqa","model":"qwen-vl-plus","score":91.4,"metric":"percent"},{"benchmark":"chartqa","model":"qwen-vl-plus","score":78.1,"metric":"percent"},{"benchmark":"ai2d","model":"qwen-vl-plus","score":75.9,"metric":"percent"},{"benchmark":"textvqa","model":"qwen-vl-plus","score":78.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen-vl-plus","score":68,"metric":"percent"},{"benchmark":"chartqa","model":"qwen-vl-max","score":79.8,"metric":"percent"},{"benchmark":"ai2d","model":"qwen-vl-max","score":79.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen-vl-max","score":50,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen-vl-max","score":75.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwq-32b-preview","score":65.2,"metric":"percent"},{"benchmark":"aime-2024","model":"qwq-32b-preview","score":50,"metric":"percent"},{"benchmark":"math500","model":"qwq-32b-preview","score":90.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwq-32b-preview","score":50,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"o1-preview","score":72.3,"metric":"percent"},{"benchmark":"math500","model":"o1-preview","score":85.5,"metric":"percent"},{"benchmark":"aime-2024","model":"o1-mini","score":56.7,"metric":"percent"},{"benchmark":"livecodebench","model":"o1-mini","score":58,"metric":"percent"},{"benchmark":"math500","model":"gpt-4o","score":76.6,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-3.5-sonnet","score":65,"metric":"percent"},{"benchmark":"aime-2024","model":"claude-3.5-sonnet","score":16,"metric":"percent"},{"benchmark":"math500","model":"claude-3.5-sonnet","score":78.3,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.5-sonnet","score":36.3,"metric":"percent"},{"benchmark":"math500","model":"qwen2.5-72b-instruct","score":82.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen2.5-72b-instruct","score":30.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qvq-72b","score":71.4,"metric":"percent"},{"benchmark":"olympiadbench","model":"qvq-72b","score":20.4,"metric":"percent"},{"benchmark":"mmmu","model":"o1-2024-12-17","score":77.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"o1-2024-12-17","score":71,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4o-2024-05-13","score":69.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4o-2024-05-13","score":63.8,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-4o-2024-05-13","score":30.4,"metric":"percent"},{"benchmark":"olympiadbench","model":"gpt-4o-2024-05-13","score":25.9,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3.5-sonnet","score":70.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-3.5-sonnet","score":65.3,"metric":"percent"},{"benchmark":"mathvision","model":"claude-3.5-sonnet","score":35.6,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2-vl-72b-instruct","score":11.2,"metric":"percent"},{"benchmark":"mmlu-pro","model":"llama-3-8b-instruct-gradient-1048k","score":22.9,"metric":"percent"},{"benchmark":"mmlu-redux","model":"llama-3-8b-instruct-gradient-1048k","score":52.7,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-8b-instruct-gradient-1048k","score":29.8,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b-instruct-gradient-1048k","score":18.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b-instruct-gradient-1048k","score":54.1,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-8b-instruct-gradient-1048k","score":22.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b-instruct-gradient-1048k","score":27.2,"metric":"percent"},{"benchmark":"livebench","model":"llama-3-8b-instruct-gradient-1048k","score":17,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"llama-3-8b-instruct-gradient-1048k","score":39,"metric":"percent"},{"benchmark":"alignbench","model":"llama-3-8b-instruct-gradient-1048k","score":6.6,"metric":"score"},{"benchmark":"mmlu-pro","model":"glm-4-9b-chat-1m","score":44.2,"metric":"percent"},{"benchmark":"mmlu-redux","model":"glm-4-9b-chat-1m","score":68.5,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4-9b-chat-1m","score":32.3,"metric":"percent"},{"benchmark":"math","model":"glm-4-9b-chat-1m","score":47.7,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4-9b-chat-1m","score":82.6,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4-9b-chat-1m","score":68.9,"metric":"percent"},{"benchmark":"mbpp","model":"glm-4-9b-chat-1m","score":54,"metric":"percent"},{"benchmark":"livebench","model":"glm-4-9b-chat-1m","score":26.6,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"glm-4-9b-chat-1m","score":55.8,"metric":"percent"},{"benchmark":"arena-hard","model":"glm-4-9b-chat-1m","score":23.6,"metric":"percent"},{"benchmark":"alignbench","model":"glm-4-9b-chat-1m","score":6.44,"metric":"score"},{"benchmark":"alignbench","model":"qwen2.5-turbo","score":7.9,"metric":"score"},{"benchmark":"mmlu-pro","model":"deepseek-v2.5","score":65.8,"metric":"percent"},{"benchmark":"mmlu-redux","model":"deepseek-v2.5","score":80.4,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v2.5","score":45.5,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-v2.5","score":85.2,"metric":"percent"},{"benchmark":"multipl-e","model":"deepseek-v2.5","score":73.5,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-v2.5","score":49.4,"metric":"percent"},{"benchmark":"livebench","model":"deepseek-v2.5","score":47.3,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"deepseek-v2.5","score":73.9,"metric":"percent"},{"benchmark":"alignbench","model":"deepseek-v2.5","score":7.74,"metric":"score"},{"benchmark":"ifeval-strict-prompt","model":"llama-3.1-405b-instruct","score":80.8,"metric":"percent"},{"benchmark":"mmlu-pro","model":"claude-3.5-sonnet-20240620","score":76.1,"metric":"percent"},{"benchmark":"gpqa","model":"claude-3.5-sonnet-20240620","score":59.4,"metric":"percent"},{"benchmark":"math","model":"claude-3.5-sonnet-20240620","score":71.1,"metric":"percent"},{"benchmark":"mbpp","model":"claude-3.5-sonnet-20240620","score":89.2,"metric":"percent"},{"benchmark":"multipl-e","model":"claude-3.5-sonnet-20240620","score":80,"metric":"percent"},{"benchmark":"livecodebench","model":"claude-3.5-sonnet-20240620","score":54.1,"metric":"percent"},{"benchmark":"livebench","model":"claude-3.5-sonnet-20240620","score":59.8,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"claude-3.5-sonnet-20240620","score":82.6,"metric":"percent"},{"benchmark":"arena-hard","model":"claude-3.5-sonnet-20240620","score":79.3,"metric":"percent"},{"benchmark":"alignbench","model":"claude-3.5-sonnet-20240620","score":8.19,"metric":"score"},{"benchmark":"mmlu-pro","model":"gpt-4o","score":77,"metric":"percent"},{"benchmark":"mmlu-redux","model":"gpt-4o","score":88.3,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4o","score":53.6,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4o","score":96.1,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o","score":91.5,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4o","score":86.2,"metric":"percent"},{"benchmark":"multipl-e","model":"gpt-4o","score":75.1,"metric":"percent"},{"benchmark":"livecodebench","model":"gpt-4o","score":48,"metric":"percent"},{"benchmark":"livebench","model":"gpt-4o","score":56,"metric":"percent"},{"benchmark":"ifeval-strict-prompt","model":"gpt-4o","score":84.3,"metric":"percent"},{"benchmark":"arena-hard","model":"gpt-4o","score":77.9,"metric":"percent"},{"benchmark":"alignbench","model":"gpt-4o","score":8.15,"metric":"score"},{"benchmark":"cmmlu","model":"gpt-3.5","score":55.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"gpt-3.5","score":51.1,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b","score":66.7,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b","score":69.7,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-70b","score":53.3,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-base","score":55,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-base","score":61.97,"metric":"percent"},{"benchmark":"mmlu","model":"skywork-13b","score":62.1,"metric":"percent"},{"benchmark":"bbh","model":"skywork-13b","score":41.7,"metric":"percent"},{"benchmark":"c-eval","model":"skywork-13b","score":60.6,"metric":"percent"},{"benchmark":"cmmlu","model":"skywork-13b","score":61.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"skywork-13b","score":68.1,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-180b","score":70.4,"metric":"percent"},{"benchmark":"bbh","model":"falcon-180b","score":54,"metric":"percent"},{"benchmark":"c-eval","model":"falcon-180b","score":57.8,"metric":"percent"},{"benchmark":"cmmlu","model":"falcon-180b","score":58,"metric":"percent"},{"benchmark":"gaokao-bench","model":"falcon-180b","score":59,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b","score":63.2,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b","score":42.8,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b","score":72,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b","score":75.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"yi-6b","score":72.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"yi-34b","score":82.8,"metric":"percent"},{"benchmark":"math","model":"gpt-3.5","score":14,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-3.5","score":61.4,"metric":"percent"},{"benchmark":"math","model":"gpt-4","score":40.2,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-4","score":63.6,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-180b","score":54.4,"metric":"percent"},{"benchmark":"mbpp","model":"falcon-180b","score":47,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-7b","score":34,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-14b","score":48.9,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-7b-base","score":24.5,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-7b-base","score":28.3,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-base","score":22.1,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-13b-base","score":20.7,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-13b-base","score":26.1,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b","score":14.8,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":31.7,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b","score":47.5,"metric":"percent"},{"benchmark":"math","model":"mistral-7b","score":11.3,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-20b","score":62.9,"metric":"percent"},{"benchmark":"math","model":"internlm-20b","score":10.9,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-20b","score":28.1,"metric":"percent"},{"benchmark":"mbpp","model":"internlm-20b","score":41.4,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-6b","score":32.5,"metric":"percent"},{"benchmark":"math","model":"yi-6b","score":4.6,"metric":"percent"},{"benchmark":"humaneval","model":"yi-6b","score":15.9,"metric":"percent"},{"benchmark":"mbpp","model":"yi-6b","score":26.3,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b-chat","score":47.3,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b-chat","score":35.1,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b-chat","score":35.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-2-13b-chat","score":36.8,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b-chat","score":58.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b-chat","score":2.7,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b-chat","score":59.9,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-70b-chat","score":41,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b-chat","score":41.3,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-2-70b-chat","score":54,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-70b-chat","score":58.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b-chat","score":58.7,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-chat","score":50.1,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-chat","score":59.5,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-chat","score":54.8,"metric":"percent"},{"benchmark":"truthfulqa","model":"baichuan2-13b-chat","score":49,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-chat","score":47.2,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-chat","score":23.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b-chat","score":65,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-14b-chat","score":70.6,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b-chat","score":70.1,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen-14b-chat","score":52.5,"metric":"percent"},{"benchmark":"bbh","model":"qwen-14b-chat","score":55,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b-chat","score":61.2,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-chat-20b","score":57.4,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm-chat-20b","score":53.8,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-chat-20b","score":53.6,"metric":"percent"},{"benchmark":"truthfulqa","model":"internlm-chat-20b","score":51.8,"metric":"percent"},{"benchmark":"bbh","model":"internlm-chat-20b","score":36.7,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-chat-20b","score":43.4,"metric":"percent"},{"benchmark":"mmlu","model":"aquilachat2-34b","score":66.7,"metric":"percent"},{"benchmark":"cmmlu","model":"aquilachat2-34b","score":70,"metric":"percent"},{"benchmark":"c-eval","model":"aquilachat2-34b","score":89.4,"metric":"percent"},{"benchmark":"truthfulqa","model":"aquilachat2-34b","score":64.3,"metric":"percent"},{"benchmark":"bbh","model":"aquilachat2-34b","score":34.3,"metric":"percent"},{"benchmark":"gsm8k","model":"aquilachat2-34b","score":48.5,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b-chat","score":61,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b-chat","score":74.7,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b-chat","score":74.2,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-6b-chat","score":50.6,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b-chat","score":47.2,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-6b-chat","score":44.9,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b-chat-8bits","score":61,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b-chat-8bits","score":74.7,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b-chat-8bits","score":73.9,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-6b-chat-8bits","score":49.9,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b-chat-8bits","score":47.3,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-6b-chat-8bits","score":44.9,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b-chat-4bits","score":59.9,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b-chat-4bits","score":73.3,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b-chat-4bits","score":72.3,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-6b-chat-4bits","score":50.3,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b-chat-4bits","score":43.6,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-6b-chat-4bits","score":38.4,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b-chat","score":73.5,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-34b-chat","score":81.3,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b-chat","score":78.5,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-34b-chat","score":62.4,"metric":"percent"},{"benchmark":"bbh","model":"yi-34b-chat","score":71.7,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-34b-chat","score":76,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b-chat-8bits","score":73.7,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-34b-chat-8bits","score":81.2,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b-chat-8bits","score":79,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-34b-chat-8bits","score":61.8,"metric":"percent"},{"benchmark":"bbh","model":"yi-34b-chat-8bits","score":71,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-34b-chat-8bits","score":75.7,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b-chat-4bits","score":72.4,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-34b-chat-4bits","score":80.5,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b-chat-4bits","score":77.3,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-34b-chat-4bits","score":61.8,"metric":"percent"},{"benchmark":"bbh","model":"yi-34b-chat-4bits","score":69.4,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-34b-chat-4bits","score":74,"metric":"percent"},{"benchmark":"alpacaeval-1.0","model":"gpt-4-turbo","score":97.7,"metric":"percent"},{"benchmark":"lmarena-text","model":"gpt-4-turbo","score":1243,"metric":"elo"},{"benchmark":"alpacaeval-1.0","model":"gpt-3.5-turbo","score":89.37,"metric":"percent"},{"benchmark":"lmarena-text","model":"gpt-3.5-turbo","score":1117,"metric":"elo"},{"benchmark":"alpacaeval-1.0","model":"llama-2-70b-chat","score":92.66,"metric":"percent"},{"benchmark":"lmarena-text","model":"llama-2-70b-chat","score":1077,"metric":"elo"},{"benchmark":"alpacaeval-1.0","model":"yi-34b-chat","score":94.08,"metric":"percent"},{"benchmark":"lmarena-text","model":"yi-34b-chat","score":1110,"metric":"elo"},{"benchmark":"mmlu","model":"yi-6b-200k","score":61.73,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b-200k","score":75.56,"metric":"percent"},{"benchmark":"mmmu-test","model":"gpt-4v","score":55.7,"metric":"percent"},{"benchmark":"mmmu-test","model":"yi-vl-34b","score":41.6,"metric":"percent"},{"benchmark":"mmmu-test","model":"qwen-vl-plus","score":40.8,"metric":"percent"},{"benchmark":"mmmu-test","model":"yi-vl-6b","score":37.8,"metric":"percent"},{"benchmark":"mmmu-test","model":"emu2-chat","score":34.1,"metric":"percent"},{"benchmark":"mmmu-test","model":"blip-2-flan-t5-xxl","score":34,"metric":"percent"},{"benchmark":"mmmu-test","model":"instructblip-flan-t5-xxl","score":33.8,"metric":"percent"},{"benchmark":"mmmu-test","model":"llava-1.5-13b","score":33.6,"metric":"percent"},{"benchmark":"mmmu-test","model":"qwen-vl-chat","score":32.9,"metric":"percent"},{"benchmark":"mmmu-test","model":"mplug-owl2","score":32.1,"metric":"percent"},{"benchmark":"mmmu-test","model":"blip-2-flan-t5-xl","score":31,"metric":"percent"},{"benchmark":"mmmu-test","model":"instructblip-flan-t5-xl","score":30.6,"metric":"percent"},{"benchmark":"mmmu-test","model":"cogvlm-17b-chat","score":30.1,"metric":"percent"},{"benchmark":"arc-challenge","model":"yi-6b","score":50.3,"metric":"percent"},{"benchmark":"hellaswag","model":"yi-6b","score":74.4,"metric":"percent"},{"benchmark":"winogrande","model":"yi-6b","score":71.3,"metric":"percent"},{"benchmark":"arc-challenge","model":"yi-9b","score":55.6,"metric":"percent"},{"benchmark":"hellaswag","model":"yi-9b","score":76.4,"metric":"percent"},{"benchmark":"mmlu","model":"yi-9b","score":68.4,"metric":"percent"},{"benchmark":"winogrande","model":"yi-9b","score":73,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-9b","score":52.3,"metric":"percent"},{"benchmark":"math","model":"yi-9b","score":15.9,"metric":"percent"},{"benchmark":"humaneval","model":"yi-9b","score":39,"metric":"percent"},{"benchmark":"mbpp","model":"yi-9b","score":54.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2.5-72b-instruct","score":49.1,"metric":"percent"},{"benchmark":"math","model":"qwen2.5-72b-instruct","score":82.7,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2.5-72b-instruct","score":86,"metric":"percent"},{"benchmark":"ifeval","model":"qwen2.5-72b-instruct","score":86,"metric":"percent"},{"benchmark":"wildbench-v2","model":"qwen2.5-72b-instruct","score":59.9,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen2.5-72b-instruct","score":90.5,"metric":"percent"},{"benchmark":"alignbench","model":"qwen2.5-72b-instruct","score":7.51,"metric":"score"},{"benchmark":"mt-bench","model":"qwen2.5-72b-instruct","score":8.62,"metric":"percent"},{"benchmark":"gpqa","model":"deepseek-v2.5","score":42.4,"metric":"percent"},{"benchmark":"math","model":"deepseek-v2.5","score":73.9,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-v2.5","score":85.4,"metric":"percent"},{"benchmark":"ifeval","model":"deepseek-v2.5","score":82.1,"metric":"percent"},{"benchmark":"wildbench-v2","model":"deepseek-v2.5","score":57.9,"metric":"percent"},{"benchmark":"arena-hard","model":"deepseek-v2.5","score":88.3,"metric":"percent"},{"benchmark":"alignbench","model":"deepseek-v2.5","score":7.38,"metric":"score"},{"benchmark":"mt-bench","model":"deepseek-v2.5","score":8.43,"metric":"percent"},{"benchmark":"gpqa","model":"mistral-large-instruct-2407","score":50.1,"metric":"percent"},{"benchmark":"math","model":"mistral-large-instruct-2407","score":73.3,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-large-instruct-2407","score":86,"metric":"percent"},{"benchmark":"ifeval","model":"mistral-large-instruct-2407","score":82.8,"metric":"percent"},{"benchmark":"wildbench-v2","model":"mistral-large-instruct-2407","score":57.4,"metric":"percent"},{"benchmark":"arena-hard","model":"mistral-large-instruct-2407","score":85.1,"metric":"percent"},{"benchmark":"alignbench","model":"mistral-large-instruct-2407","score":7.1,"metric":"score"},{"benchmark":"mt-bench","model":"mistral-large-instruct-2407","score":8.53,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.1-70b-instruct","score":45.1,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-70b-instruct","score":67.1,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-70b-instruct","score":76.2,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-70b-instruct","score":87.1,"metric":"percent"},{"benchmark":"wildbench-v2","model":"llama-3.1-70b-instruct","score":49,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3.1-70b-instruct","score":74,"metric":"percent"},{"benchmark":"alignbench","model":"llama-3.1-70b-instruct","score":5.81,"metric":"score"},{"benchmark":"mt-bench","model":"llama-3.1-70b-instruct","score":8.23,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3.1-405b-instruct-fp8","score":53,"metric":"percent"},{"benchmark":"math","model":"llama-3.1-405b-instruct-fp8","score":67.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3.1-405b-instruct-fp8","score":84.1,"metric":"percent"},{"benchmark":"ifeval","model":"llama-3.1-405b-instruct-fp8","score":88.5,"metric":"percent"},{"benchmark":"wildbench-v2","model":"llama-3.1-405b-instruct-fp8","score":51.6,"metric":"percent"},{"benchmark":"arena-hard","model":"llama-3.1-405b-instruct-fp8","score":71.2,"metric":"percent"},{"benchmark":"alignbench","model":"llama-3.1-405b-instruct-fp8","score":5.56,"metric":"score"},{"benchmark":"mt-bench","model":"llama-3.1-405b-instruct-fp8","score":8.36,"metric":"percent"},{"benchmark":"gpqa","model":"yi-lightning","score":50.9,"metric":"percent"},{"benchmark":"math","model":"yi-lightning","score":76.4,"metric":"percent"},{"benchmark":"humaneval","model":"yi-lightning","score":83.5,"metric":"percent"},{"benchmark":"ifeval","model":"yi-lightning","score":81.9,"metric":"percent"},{"benchmark":"wildbench-v2","model":"yi-lightning","score":65.1,"metric":"percent"},{"benchmark":"arena-hard","model":"yi-lightning","score":91.8,"metric":"percent"},{"benchmark":"alignbench","model":"yi-lightning","score":7.54,"metric":"score"},{"benchmark":"mt-bench","model":"yi-lightning","score":8.75,"metric":"percent"},{"benchmark":"gpqa","model":"yi-large-preview","score":43.8,"metric":"percent"},{"benchmark":"math","model":"yi-large-preview","score":62.6,"metric":"percent"},{"benchmark":"humaneval","model":"yi-large-preview","score":75.6,"metric":"percent"},{"benchmark":"ifeval","model":"yi-large-preview","score":79.3,"metric":"percent"},{"benchmark":"wildbench-v2","model":"yi-large-preview","score":55.3,"metric":"percent"},{"benchmark":"arena-hard","model":"yi-large-preview","score":79.1,"metric":"percent"},{"benchmark":"alignbench","model":"yi-large-preview","score":7.2,"metric":"score"},{"benchmark":"mt-bench","model":"yi-large-preview","score":8.32,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4o-2024-05-13","score":51.9,"metric":"percent"},{"benchmark":"math","model":"gpt-4o-2024-05-13","score":76,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4o-2024-05-13","score":90.5,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4o-2024-05-13","score":87.6,"metric":"percent"},{"benchmark":"wildbench-v2","model":"gpt-4o-2024-05-13","score":59.3,"metric":"percent"},{"benchmark":"arena-hard","model":"gpt-4o-2024-05-13","score":92.9,"metric":"percent"},{"benchmark":"alignbench","model":"gpt-4o-2024-05-13","score":7.59,"metric":"score"},{"benchmark":"mt-bench","model":"gpt-4o-2024-05-13","score":8.59,"metric":"percent"},{"benchmark":"gpqa","model":"claude-3.5-sonnet-20240620","score":57.8,"metric":"percent"},{"benchmark":"math","model":"claude-3.5-sonnet-20240620","score":74,"metric":"percent"},{"benchmark":"humaneval","model":"claude-3.5-sonnet-20240620","score":88.3,"metric":"percent"},{"benchmark":"ifeval","model":"claude-3.5-sonnet-20240620","score":88.5,"metric":"percent"},{"benchmark":"wildbench-v2","model":"claude-3.5-sonnet-20240620","score":54.7,"metric":"percent"},{"benchmark":"arena-hard","model":"claude-3.5-sonnet-20240620","score":85.6,"metric":"percent"},{"benchmark":"alignbench","model":"claude-3.5-sonnet-20240620","score":7.17,"metric":"score"},{"benchmark":"mt-bench","model":"claude-3.5-sonnet-20240620","score":6.96,"metric":"percent"},{"benchmark":"lmarena-text","model":"yi-lightning","score":1287,"metric":"elo"},{"benchmark":"c-eval","model":"gpt-4","score":68.4,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4","score":83.93,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-4","score":70.33,"metric":"percent"},{"benchmark":"gaokao-bench","model":"gpt-4","score":66.15,"metric":"percent"},{"benchmark":"agieval","model":"gpt-4","score":63.27,"metric":"percent"},{"benchmark":"bbh","model":"gpt-4","score":75.12,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4","score":89.99,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4","score":69.51,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-3.5-turbo","score":51.1,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-3.5-turbo","score":68.54,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-3.5-turbo","score":54.06,"metric":"percent"},{"benchmark":"gaokao-bench","model":"gpt-3.5-turbo","score":47.07,"metric":"percent"},{"benchmark":"agieval","model":"gpt-3.5-turbo","score":46.13,"metric":"percent"},{"benchmark":"bbh","model":"gpt-3.5-turbo","score":61.59,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5-turbo","score":57.77,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-3.5-turbo","score":52.44,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-7b","score":27.1,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-1-7b","score":26.75,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-7b","score":27.81,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-7b","score":28.17,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-7b","score":32.38,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-7b","score":9.78,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-7b","score":11.59,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b","score":45.73,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b","score":31.38,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-7b","score":25.97,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-7b","score":26.53,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-7b","score":39.16,"metric":"percent"},{"benchmark":"c-eval","model":"mpt-7b","score":27.15,"metric":"percent"},{"benchmark":"mmlu","model":"mpt-7b","score":27.93,"metric":"percent"},{"benchmark":"cmmlu","model":"mpt-7b","score":26,"metric":"percent"},{"benchmark":"gaokao-bench","model":"mpt-7b","score":26.54,"metric":"percent"},{"benchmark":"agieval","model":"mpt-7b","score":24.83,"metric":"percent"},{"benchmark":"bbh","model":"mpt-7b","score":35.2,"metric":"percent"},{"benchmark":"gsm8k","model":"mpt-7b","score":8.64,"metric":"percent"},{"benchmark":"humaneval","model":"mpt-7b","score":14.02,"metric":"percent"},{"benchmark":"c-eval","model":"falcon-7b","score":24.23,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-7b","score":26.03,"metric":"percent"},{"benchmark":"cmmlu","model":"falcon-7b","score":25.66,"metric":"percent"},{"benchmark":"gaokao-bench","model":"falcon-7b","score":24.24,"metric":"percent"},{"benchmark":"agieval","model":"falcon-7b","score":24.1,"metric":"percent"},{"benchmark":"bbh","model":"falcon-7b","score":28.77,"metric":"percent"},{"benchmark":"gsm8k","model":"falcon-7b","score":5.46,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b","score":47.86,"metric":"percent"},{"benchmark":"bbh","model":"chatglm2-6b","score":33.68,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b","score":32.37,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan-7b","score":44.02,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan-7b","score":36.34,"metric":"percent"},{"benchmark":"agieval","model":"baichuan-7b","score":34.44,"metric":"percent"},{"benchmark":"bbh","model":"baichuan-7b","score":32.48,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan-7b","score":9.17,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan-7b","score":9.2,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-base","score":54.16,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-base","score":57.07,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-7b-base","score":47.47,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-7b-base","score":42.73,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-7b-base","score":41.56,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-7b-base","score":24.49,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-7b-base","score":18.29,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-13b","score":28.5,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-13b","score":46.3,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-1-13b","score":31.15,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-1-13b","score":28.23,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-13b","score":28.22,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-13b","score":37.89,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-13b","score":20.55,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-13b","score":15.24,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b","score":35.8,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b","score":55.09,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b","score":37.99,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-13b","score":30.83,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-13b","score":32.29,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b","score":46.98,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b","score":28.89,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b","score":15.24,"metric":"percent"},{"benchmark":"c-eval","model":"vicuna-13b","score":32.8,"metric":"percent"},{"benchmark":"mmlu","model":"vicuna-13b","score":52,"metric":"percent"},{"benchmark":"cmmlu","model":"vicuna-13b","score":36.28,"metric":"percent"},{"benchmark":"gaokao-bench","model":"vicuna-13b","score":30.11,"metric":"percent"},{"benchmark":"agieval","model":"vicuna-13b","score":31.55,"metric":"percent"},{"benchmark":"bbh","model":"vicuna-13b","score":43.04,"metric":"percent"},{"benchmark":"gsm8k","model":"vicuna-13b","score":28.13,"metric":"percent"},{"benchmark":"humaneval","model":"vicuna-13b","score":16.46,"metric":"percent"},{"benchmark":"c-eval","model":"chinese-alpaca-plus-13b","score":38.8,"metric":"percent"},{"benchmark":"mmlu","model":"chinese-alpaca-plus-13b","score":43.9,"metric":"percent"},{"benchmark":"cmmlu","model":"chinese-alpaca-plus-13b","score":33.43,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chinese-alpaca-plus-13b","score":34.78,"metric":"percent"},{"benchmark":"agieval","model":"chinese-alpaca-plus-13b","score":35.46,"metric":"percent"},{"benchmark":"bbh","model":"chinese-alpaca-plus-13b","score":28.94,"metric":"percent"},{"benchmark":"gsm8k","model":"chinese-alpaca-plus-13b","score":11.98,"metric":"percent"},{"benchmark":"humaneval","model":"chinese-alpaca-plus-13b","score":16.46,"metric":"percent"},{"benchmark":"c-eval","model":"xverse-13b","score":53.7,"metric":"percent"},{"benchmark":"mmlu","model":"xverse-13b","score":55.21,"metric":"percent"},{"benchmark":"cmmlu","model":"xverse-13b","score":58.44,"metric":"percent"},{"benchmark":"gaokao-bench","model":"xverse-13b","score":44.69,"metric":"percent"},{"benchmark":"agieval","model":"xverse-13b","score":42.54,"metric":"percent"},{"benchmark":"bbh","model":"xverse-13b","score":38.06,"metric":"percent"},{"benchmark":"gsm8k","model":"xverse-13b","score":18.2,"metric":"percent"},{"benchmark":"humaneval","model":"xverse-13b","score":15.85,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan-13b-base","score":49.69,"metric":"percent"},{"benchmark":"agieval","model":"baichuan-13b-base","score":43.2,"metric":"percent"},{"benchmark":"bbh","model":"baichuan-13b-base","score":43.01,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan-13b-base","score":11.59,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-base","score":59.17,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-13b-base","score":54.33,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-13b-base","score":48.17,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-base","score":48.78,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-13b-base","score":17.07,"metric":"percent"},{"benchmark":"jec-qa","model":"gpt-4","score":59.32,"metric":"percent"},{"benchmark":"medqa","model":"gpt-4","score":80.28,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"gpt-4","score":74.58,"metric":"percent"},{"benchmark":"medmcqa","model":"gpt-4","score":72.51,"metric":"percent"},{"benchmark":"jec-qa","model":"gpt-3.5-turbo","score":42.31,"metric":"percent"},{"benchmark":"medqa","model":"gpt-3.5-turbo","score":53.81,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"gpt-3.5-turbo","score":52.92,"metric":"percent"},{"benchmark":"medmcqa","model":"gpt-3.5-turbo","score":56.25,"metric":"percent"},{"benchmark":"jec-qa","model":"llama-1-7b","score":27.45,"metric":"percent"},{"benchmark":"medqa","model":"llama-1-7b","score":24.12,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"llama-1-7b","score":21.72,"metric":"percent"},{"benchmark":"medmcqa","model":"llama-1-7b","score":27.45,"metric":"percent"},{"benchmark":"jec-qa","model":"llama-2-7b","score":29.2,"metric":"percent"},{"benchmark":"medqa","model":"llama-2-7b","score":27.49,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"llama-2-7b","score":24.78,"metric":"percent"},{"benchmark":"medmcqa","model":"llama-2-7b","score":37.93,"metric":"percent"},{"benchmark":"jec-qa","model":"mpt-7b","score":27.45,"metric":"percent"},{"benchmark":"medqa","model":"mpt-7b","score":16.97,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"mpt-7b","score":19.79,"metric":"percent"},{"benchmark":"medmcqa","model":"mpt-7b","score":31.96,"metric":"percent"},{"benchmark":"jec-qa","model":"falcon-7b","score":23.66,"metric":"percent"},{"benchmark":"medqa","model":"falcon-7b","score":21.29,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"falcon-7b","score":18.07,"metric":"percent"},{"benchmark":"medmcqa","model":"falcon-7b","score":33.88,"metric":"percent"},{"benchmark":"jec-qa","model":"chatglm2-6b","score":40.76,"metric":"percent"},{"benchmark":"medqa","model":"chatglm2-6b","score":26.24,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"chatglm2-6b","score":45.53,"metric":"percent"},{"benchmark":"medmcqa","model":"chatglm2-6b","score":30.22,"metric":"percent"},{"benchmark":"jec-qa","model":"baichuan-7b","score":34.64,"metric":"percent"},{"benchmark":"medqa","model":"baichuan-7b","score":27.42,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"baichuan-7b","score":39.46,"metric":"percent"},{"benchmark":"medmcqa","model":"baichuan-7b","score":31.39,"metric":"percent"},{"benchmark":"jec-qa","model":"baichuan2-7b-base","score":44.46,"metric":"percent"},{"benchmark":"medqa","model":"baichuan2-7b-base","score":32.68,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"baichuan2-7b-base","score":54.93,"metric":"percent"},{"benchmark":"medmcqa","model":"baichuan2-7b-base","score":41.73,"metric":"percent"},{"benchmark":"jec-qa","model":"llama-1-13b","score":27.54,"metric":"percent"},{"benchmark":"medqa","model":"llama-1-13b","score":28.83,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"llama-1-13b","score":23.38,"metric":"percent"},{"benchmark":"medmcqa","model":"llama-1-13b","score":39.52,"metric":"percent"},{"benchmark":"jec-qa","model":"llama-2-13b","score":34.08,"metric":"percent"},{"benchmark":"medqa","model":"llama-2-13b","score":35.04,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"llama-2-13b","score":29.74,"metric":"percent"},{"benchmark":"medmcqa","model":"llama-2-13b","score":42.12,"metric":"percent"},{"benchmark":"jec-qa","model":"vicuna-13b","score":28.38,"metric":"percent"},{"benchmark":"medqa","model":"vicuna-13b","score":34.8,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"vicuna-13b","score":27.67,"metric":"percent"},{"benchmark":"medmcqa","model":"vicuna-13b","score":40.66,"metric":"percent"},{"benchmark":"jec-qa","model":"chinese-alpaca-plus-13b","score":35.32,"metric":"percent"},{"benchmark":"medqa","model":"chinese-alpaca-plus-13b","score":27.49,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"chinese-alpaca-plus-13b","score":32.66,"metric":"percent"},{"benchmark":"medmcqa","model":"chinese-alpaca-plus-13b","score":35.87,"metric":"percent"},{"benchmark":"jec-qa","model":"xverse-13b","score":46.42,"metric":"percent"},{"benchmark":"medqa","model":"xverse-13b","score":32.99,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"xverse-13b","score":58.76,"metric":"percent"},{"benchmark":"medmcqa","model":"xverse-13b","score":41.34,"metric":"percent"},{"benchmark":"jec-qa","model":"baichuan-13b-base","score":41.34,"metric":"percent"},{"benchmark":"medqa","model":"baichuan-13b-base","score":29.07,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"baichuan-13b-base","score":43.67,"metric":"percent"},{"benchmark":"medmcqa","model":"baichuan-13b-base","score":39.6,"metric":"percent"},{"benchmark":"jec-qa","model":"baichuan2-13b-base","score":47.4,"metric":"percent"},{"benchmark":"medqa","model":"baichuan2-13b-base","score":40.38,"metric":"percent"},{"benchmark":"medqa-mcmle","model":"baichuan2-13b-base","score":61.62,"metric":"percent"},{"benchmark":"medmcqa","model":"baichuan2-13b-base","score":42.86,"metric":"percent"},{"benchmark":"math","model":"gpt-3.5-turbo","score":13.96,"metric":"percent"},{"benchmark":"mbpp","model":"gpt-3.5-turbo","score":61.4,"metric":"percent"},{"benchmark":"math","model":"llama-1-7b","score":3.02,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-7b","score":14,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b","score":3.24,"metric":"percent"},{"benchmark":"math","model":"mpt-7b","score":2.9,"metric":"percent"},{"benchmark":"mbpp","model":"mpt-7b","score":23.4,"metric":"percent"},{"benchmark":"math","model":"falcon-7b","score":1.68,"metric":"percent"},{"benchmark":"mbpp","model":"falcon-7b","score":10.2,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b","score":28.89,"metric":"percent"},{"benchmark":"math","model":"chatglm2-6b","score":6.4,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm2-6b","score":9.15,"metric":"percent"},{"benchmark":"mbpp","model":"chatglm2-6b","score":9,"metric":"percent"},{"benchmark":"math","model":"baichuan-7b","score":2.54,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan-7b","score":6.6,"metric":"percent"},{"benchmark":"math","model":"baichuan2-7b-base","score":5.58,"metric":"percent"},{"benchmark":"math","model":"llama-1-13b","score":3.68,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-13b","score":21.4,"metric":"percent"},{"benchmark":"math","model":"llama-2-13b","score":4.96,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-13b","score":27,"metric":"percent"},{"benchmark":"math","model":"vicuna-13b","score":4.36,"metric":"percent"},{"benchmark":"mbpp","model":"vicuna-13b","score":15,"metric":"percent"},{"benchmark":"math","model":"chinese-alpaca-plus-13b","score":2.5,"metric":"percent"},{"benchmark":"mbpp","model":"chinese-alpaca-plus-13b","score":20,"metric":"percent"},{"benchmark":"math","model":"xverse-13b","score":2.18,"metric":"percent"},{"benchmark":"mbpp","model":"xverse-13b","score":16.8,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan-13b-base","score":22.8,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b","score":31.9,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b","score":32.4,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-7b","score":21.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-7b","score":19,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b","score":64,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b","score":44.6,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b","score":47.5,"metric":"percent"},{"benchmark":"agieval","model":"mistral-7b","score":32.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"mistral-7b","score":28.7,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-base","score":56.2,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-7b-base","score":34.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-7b-base","score":34.7,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm3-6b-base","score":62.7,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm3-6b-base","score":66.5,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm3-6b-base","score":67.2,"metric":"percent"},{"benchmark":"agieval","model":"chatglm3-6b-base","score":47.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm3-6b-base","score":59.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b","score":59.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-7b","score":62.5,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b","score":63.1,"metric":"percent"},{"benchmark":"agieval","model":"qwen-7b","score":45.6,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-7b","score":52.8,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-base-7b","score":64,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-base-7b","score":63,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-base-7b","score":60.7,"metric":"percent"},{"benchmark":"agieval","model":"internlm2-base-7b","score":38.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-base-7b","score":40.7,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-7b","score":65.8,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-7b","score":66.3,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-7b","score":65.8,"metric":"percent"},{"benchmark":"agieval","model":"internlm2-7b","score":49.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-7b","score":58.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b","score":55.8,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b","score":38.8,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b","score":40.1,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-13b","score":27.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-13b","score":18.4,"metric":"percent"},{"benchmark":"cmmlu","model":"mixtral-8x7b","score":53.3,"metric":"percent"},{"benchmark":"c-eval","model":"mixtral-8x7b","score":55.4,"metric":"percent"},{"benchmark":"agieval","model":"mixtral-8x7b","score":40.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"mixtral-8x7b","score":32.3,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-base","score":59.6,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-base","score":59.2,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-14b","score":70.1,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b","score":71.8,"metric":"percent"},{"benchmark":"agieval","model":"qwen-14b","score":52,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-20b","score":67.7,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-20b","score":68.7,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-20b","score":68.5,"metric":"percent"},{"benchmark":"agieval","model":"internlm2-20b","score":53,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-20b","score":57.1,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-3.5-turbo","score":69.1,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-7b-chat","score":48.2,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-7b-chat","score":30.7,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-7b-chat","score":34.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-7b-chat","score":19.8,"metric":"percent"},{"benchmark":"mmlu","model":"mistral-7b-instruct-v0.2","score":59.2,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b-instruct-v0.2","score":42,"metric":"percent"},{"benchmark":"c-eval","model":"mistral-7b-instruct-v0.2","score":42.4,"metric":"percent"},{"benchmark":"agieval","model":"mistral-7b-instruct-v0.2","score":34.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"mistral-7b-instruct-v0.2","score":28.6,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-chat","score":50.1,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-chat","score":53.4,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-chat","score":53.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-7b-chat","score":37.5,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm3-6b","score":58,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm3-6b","score":57.8,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm3-6b","score":59.1,"metric":"percent"},{"benchmark":"agieval","model":"chatglm3-6b","score":44.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm3-6b","score":56.3,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-7b-chat","score":57.1,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-7b-chat","score":57.9,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-7b-chat","score":59.8,"metric":"percent"},{"benchmark":"agieval","model":"qwen-7b-chat","score":39.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-7b-chat","score":62.1,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-chat-7b-sft","score":63.8,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-chat-7b-sft","score":63.2,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-chat-7b-sft","score":60.9,"metric":"percent"},{"benchmark":"agieval","model":"internlm2-chat-7b-sft","score":49,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-chat-7b-sft","score":57.3,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-chat-7b","score":63.7,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-chat-7b","score":63,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-chat-7b","score":60.8,"metric":"percent"},{"benchmark":"agieval","model":"internlm2-chat-7b","score":47.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-chat-7b","score":58,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b-chat","score":54.1,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b-chat","score":33.8,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b-chat","score":35,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-13b-chat","score":30.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-13b-chat","score":23.2,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x7b-instruct-v0.1","score":70.3,"metric":"percent"},{"benchmark":"cmmlu","model":"mixtral-8x7b-instruct-v0.1","score":50.6,"metric":"percent"},{"benchmark":"c-eval","model":"mixtral-8x7b-instruct-v0.1","score":54,"metric":"percent"},{"benchmark":"agieval","model":"mixtral-8x7b-instruct-v0.1","score":41.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"mixtral-8x7b-instruct-v0.1","score":42.6,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-chat","score":56.6,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-chat","score":54.8,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-chat","score":56.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan2-13b-chat","score":45.8,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b-chat","score":66.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-14b-chat","score":68.1,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b-chat","score":71.5,"metric":"percent"},{"benchmark":"agieval","model":"qwen-14b-chat","score":46.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"qwen-14b-chat","score":76.3,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-chat-20b-sft","score":66.5,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-chat-20b-sft","score":65.3,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-chat-20b-sft","score":63.7,"metric":"percent"},{"benchmark":"agieval","model":"internlm2-chat-20b-sft","score":51.2,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-chat-20b-sft","score":58.6,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-chat-20b","score":66.5,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-chat-20b","score":65.1,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-chat-20b","score":63,"metric":"percent"},{"benchmark":"agieval","model":"internlm2-chat-20b","score":50.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-chat-20b","score":58.3,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-7b","score":55.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b","score":28.8,"metric":"percent"},{"benchmark":"c3","model":"llama-2-7b","score":43.8,"metric":"percent"},{"benchmark":"race","model":"llama-2-7b","score":37.6,"metric":"percent"},{"benchmark":"triviaqa","model":"mistral-7b","score":68.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"mistral-7b","score":31.1,"metric":"percent"},{"benchmark":"c3","model":"mistral-7b","score":54.6,"metric":"percent"},{"benchmark":"race","model":"mistral-7b","score":69.1,"metric":"percent"},{"benchmark":"triviaqa","model":"baichuan2-7b-base","score":51,"metric":"percent"},{"benchmark":"naturalquestions","model":"baichuan2-7b-base","score":24,"metric":"percent"},{"benchmark":"c3","model":"baichuan2-7b-base","score":64.6,"metric":"percent"},{"benchmark":"race","model":"baichuan2-7b-base","score":63.2,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen-7b","score":54.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-7b","score":22.7,"metric":"percent"},{"benchmark":"c3","model":"qwen-7b","score":71.4,"metric":"percent"},{"benchmark":"race","model":"qwen-7b","score":83.9,"metric":"percent"},{"benchmark":"triviaqa","model":"chatglm3-6b-base","score":63.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"chatglm3-6b-base","score":38.7,"metric":"percent"},{"benchmark":"c3","model":"chatglm3-6b-base","score":78.9,"metric":"percent"},{"benchmark":"race","model":"chatglm3-6b-base","score":84.8,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-base-7b","score":57,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-base-7b","score":28.4,"metric":"percent"},{"benchmark":"c3","model":"internlm2-base-7b","score":61.9,"metric":"percent"},{"benchmark":"race","model":"internlm2-base-7b","score":74.2,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-7b","score":58.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-7b","score":42.2,"metric":"percent"},{"benchmark":"c3","model":"internlm2-7b","score":74.1,"metric":"percent"},{"benchmark":"race","model":"internlm2-7b","score":81.4,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-13b","score":60.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-13b","score":34.5,"metric":"percent"},{"benchmark":"c3","model":"llama-2-13b","score":47.5,"metric":"percent"},{"benchmark":"race","model":"llama-2-13b","score":59.1,"metric":"percent"},{"benchmark":"triviaqa","model":"mixtral-8x7b","score":77.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"mixtral-8x7b","score":39.6,"metric":"percent"},{"benchmark":"c3","model":"mixtral-8x7b","score":59.1,"metric":"percent"},{"benchmark":"race","model":"mixtral-8x7b","score":80.2,"metric":"percent"},{"benchmark":"triviaqa","model":"baichuan2-13b-base","score":54.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"baichuan2-13b-base","score":27.5,"metric":"percent"},{"benchmark":"race","model":"baichuan2-13b-base","score":75.6,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen-14b","score":62.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-14b","score":37.1,"metric":"percent"},{"benchmark":"c3","model":"qwen-14b","score":80.6,"metric":"percent"},{"benchmark":"race","model":"qwen-14b","score":90.3,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-base-20b","score":63.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-base-20b","score":30.3,"metric":"percent"},{"benchmark":"c3","model":"internlm2-base-20b","score":67.6,"metric":"percent"},{"benchmark":"race","model":"internlm2-base-20b","score":75.6,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-20b","score":60.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-20b","score":44.6,"metric":"percent"},{"benchmark":"c3","model":"internlm2-20b","score":79.1,"metric":"percent"},{"benchmark":"race","model":"internlm2-20b","score":72.9,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-7b-chat","score":46.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-7b-chat","score":19.6,"metric":"percent"},{"benchmark":"c3","model":"llama-2-7b-chat","score":51.7,"metric":"percent"},{"benchmark":"race","model":"llama-2-7b-chat","score":3,"metric":"percent"},{"benchmark":"triviaqa","model":"mistral-7b-instruct-v0.2","score":35,"metric":"percent"},{"benchmark":"naturalquestions","model":"mistral-7b-instruct-v0.2","score":8.1,"metric":"percent"},{"benchmark":"c3","model":"mistral-7b-instruct-v0.2","score":66.9,"metric":"percent"},{"benchmark":"race","model":"mistral-7b-instruct-v0.2","score":71.2,"metric":"percent"},{"benchmark":"triviaqa","model":"baichuan2-7b-chat","score":37.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"baichuan2-7b-chat","score":12.8,"metric":"percent"},{"benchmark":"c3","model":"baichuan2-7b-chat","score":78.5,"metric":"percent"},{"benchmark":"race","model":"baichuan2-7b-chat","score":67.5,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen-7b-chat","score":46.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-7b-chat","score":18.6,"metric":"percent"},{"benchmark":"c3","model":"qwen-7b-chat","score":84.4,"metric":"percent"},{"benchmark":"race","model":"qwen-7b-chat","score":74.8,"metric":"percent"},{"benchmark":"triviaqa","model":"chatglm3-6b","score":38.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"chatglm3-6b","score":14,"metric":"percent"},{"benchmark":"c3","model":"chatglm3-6b","score":79.3,"metric":"percent"},{"benchmark":"race","model":"chatglm3-6b","score":79.1,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-chat-7b-sft","score":51.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-chat-7b-sft","score":24.5,"metric":"percent"},{"benchmark":"c3","model":"internlm2-chat-7b-sft","score":91.7,"metric":"percent"},{"benchmark":"race","model":"internlm2-chat-7b-sft","score":85.2,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-chat-7b","score":50.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-chat-7b","score":24.1,"metric":"percent"},{"benchmark":"c3","model":"internlm2-chat-7b","score":91.5,"metric":"percent"},{"benchmark":"race","model":"internlm2-chat-7b","score":85.1,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-13b-chat","score":54.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-13b-chat","score":25.2,"metric":"percent"},{"benchmark":"c3","model":"llama-2-13b-chat","score":56.9,"metric":"percent"},{"benchmark":"race","model":"llama-2-13b-chat","score":19.2,"metric":"percent"},{"benchmark":"triviaqa","model":"mixtral-8x7b-instruct-v0.1","score":57.7,"metric":"percent"},{"benchmark":"naturalquestions","model":"mixtral-8x7b-instruct-v0.1","score":22.5,"metric":"percent"},{"benchmark":"c3","model":"mixtral-8x7b-instruct-v0.1","score":82.1,"metric":"percent"},{"benchmark":"race","model":"mixtral-8x7b-instruct-v0.1","score":81.4,"metric":"percent"},{"benchmark":"triviaqa","model":"baichuan2-13b-chat","score":40.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"baichuan2-13b-chat","score":12.7,"metric":"percent"},{"benchmark":"c3","model":"baichuan2-13b-chat","score":84.4,"metric":"percent"},{"benchmark":"race","model":"baichuan2-13b-chat","score":73.2,"metric":"percent"},{"benchmark":"triviaqa","model":"qwen-14b-chat","score":54.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"qwen-14b-chat","score":22.9,"metric":"percent"},{"benchmark":"c3","model":"qwen-14b-chat","score":91.5,"metric":"percent"},{"benchmark":"race","model":"qwen-14b-chat","score":84.7,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-chat-20b-sft","score":55.5,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-chat-20b-sft","score":27.8,"metric":"percent"},{"benchmark":"c3","model":"internlm2-chat-20b-sft","score":93.5,"metric":"percent"},{"benchmark":"race","model":"internlm2-chat-20b-sft","score":87.3,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-chat-20b","score":53.9,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-chat-20b","score":25.9,"metric":"percent"},{"benchmark":"c3","model":"internlm2-chat-20b","score":93.5,"metric":"percent"},{"benchmark":"race","model":"internlm2-chat-20b","score":87.1,"metric":"percent"},{"benchmark":"winogrande","model":"chatglm3-6b-base","score":51.4,"metric":"percent"},{"benchmark":"hellaswag","model":"chatglm3-6b-base","score":76.5,"metric":"percent"},{"benchmark":"bbh","model":"chatglm3-6b-base","score":66.2,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan2-7b-base","score":68.7,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-7b-base","score":70.2,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-7b-base","score":41.9,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b","score":74,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-7b","score":39.3,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b","score":78.9,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b","score":56.7,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-7b","score":68.6,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-7b","score":75,"metric":"percent"},{"benchmark":"bbh","model":"qwen-7b","score":45.2,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-base-7b","score":74.6,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-base-7b","score":76.3,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-base-7b","score":55.5,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-7b","score":84.7,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-7b","score":79.3,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-7b","score":65,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-13b","score":72.3,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b","score":47.2,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan2-13b-base","score":70,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-13b-base","score":73.7,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-base","score":48.9,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-14b","score":67.5,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-14b","score":80.3,"metric":"percent"},{"benchmark":"winogrande","model":"mixtral-8x7b","score":77.3,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x7b","score":81.9,"metric":"percent"},{"benchmark":"bbh","model":"mixtral-8x7b","score":68.8,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-20b","score":85.2,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-20b","score":81.6,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-20b","score":72.1,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-base-20b","score":76.2,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-base-20b","score":78.1,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-base-20b","score":62,"metric":"percent"},{"benchmark":"winogrande","model":"chatglm3-6b","score":61.7,"metric":"percent"},{"benchmark":"hellaswag","model":"chatglm3-6b","score":73.1,"metric":"percent"},{"benchmark":"bbh","model":"chatglm3-6b","score":56,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-7b-chat","score":51.5,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-7b-chat","score":49.5,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-7b-chat","score":41.4,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan2-7b-chat","score":49.9,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-7b-chat","score":36.4,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-7b-chat","score":35.9,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b-instruct-v0.2","score":50.8,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b-instruct-v0.2","score":64.1,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b-instruct-v0.2","score":46.4,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-7b-chat","score":54.2,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-7b-chat","score":61.9,"metric":"percent"},{"benchmark":"bbh","model":"qwen-7b-chat","score":45.5,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-chat-7b-sft","score":65.8,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-chat-7b-sft","score":83.5,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-chat-7b-sft","score":60.9,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-chat-7b","score":65.8,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-chat-7b","score":83,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-chat-7b","score":61.2,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-13b-chat","score":50.8,"metric":"percent"},{"benchmark":"hellaswag","model":"llama-2-13b-chat","score":57,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b-chat","score":49.7,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan2-13b-chat","score":50.9,"metric":"percent"},{"benchmark":"hellaswag","model":"baichuan2-13b-chat","score":34.4,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-chat","score":42.5,"metric":"percent"},{"benchmark":"winogrande","model":"mixtral-8x7b-instruct-v0.1","score":60.9,"metric":"percent"},{"benchmark":"hellaswag","model":"mixtral-8x7b-instruct-v0.1","score":80.3,"metric":"percent"},{"benchmark":"bbh","model":"mixtral-8x7b-instruct-v0.1","score":57.3,"metric":"percent"},{"benchmark":"winogrande","model":"qwen-14b-chat","score":55.7,"metric":"percent"},{"benchmark":"hellaswag","model":"qwen-14b-chat","score":79.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen-14b-chat","score":55.8,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-chat-20b-sft","score":75,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-chat-20b-sft","score":85.9,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-chat-20b-sft","score":66.9,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-chat-20b","score":74.8,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-chat-20b","score":85.8,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-chat-20b","score":68.3,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm3-6b-base","score":60.7,"metric":"percent"},{"benchmark":"math","model":"chatglm3-6b-base","score":19.2,"metric":"percent"},{"benchmark":"theoremqa","model":"chatglm3-6b-base","score":6.5,"metric":"percent"},{"benchmark":"math","model":"baichuan2-7b-base","score":5.5,"metric":"percent"},{"benchmark":"theoremqa","model":"baichuan2-7b-base","score":1.6,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b","score":16.2,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-2-7b","score":1,"metric":"percent"},{"benchmark":"theoremqa","model":"mistral-7b","score":1.8,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b","score":54,"metric":"percent"},{"benchmark":"math","model":"qwen-7b","score":13.4,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen-7b","score":5,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-base-7b","score":36,"metric":"percent"},{"benchmark":"math","model":"internlm2-base-7b","score":8.9,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-base-7b","score":2.6,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-7b","score":70.8,"metric":"percent"},{"benchmark":"math","model":"internlm2-7b","score":20.2,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-7b","score":10.5,"metric":"percent"},{"benchmark":"math","model":"llama-2-13b","score":4.9,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-2-13b","score":2.6,"metric":"percent"},{"benchmark":"theoremqa","model":"baichuan2-13b-base","score":4.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b","score":60.1,"metric":"percent"},{"benchmark":"math","model":"qwen-14b","score":25.1,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen-14b","score":10.4,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x7b","score":66,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x7b","score":22.7,"metric":"percent"},{"benchmark":"theoremqa","model":"mixtral-8x7b","score":2.5,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-base-20b","score":54.3,"metric":"percent"},{"benchmark":"math","model":"internlm2-base-20b","score":13.6,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-base-20b","score":3.3,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-20b","score":76.1,"metric":"percent"},{"benchmark":"math","model":"internlm2-20b","score":25.5,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-20b","score":13.5,"metric":"percent"},{"benchmark":"theoremqa","model":"gpt-3.5-turbo","score":9.1,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm3-6b","score":53.8,"metric":"percent"},{"benchmark":"math","model":"chatglm3-6b","score":20.4,"metric":"percent"},{"benchmark":"theoremqa","model":"chatglm3-6b","score":9.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-7b-chat","score":28.4,"metric":"percent"},{"benchmark":"math","model":"llama-2-7b-chat","score":4.1,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-2-7b-chat","score":0.3,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-7b-chat","score":32.4,"metric":"percent"},{"benchmark":"math","model":"baichuan2-7b-chat","score":5.7,"metric":"percent"},{"benchmark":"theoremqa","model":"baichuan2-7b-chat","score":2.4,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b-instruct-v0.2","score":48.3,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-instruct-v0.2","score":8.6,"metric":"percent"},{"benchmark":"theoremqa","model":"mistral-7b-instruct-v0.2","score":2.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b-chat","score":44.1,"metric":"percent"},{"benchmark":"math","model":"qwen-7b-chat","score":12,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen-7b-chat","score":5.8,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-chat-7b-sft","score":68.8,"metric":"percent"},{"benchmark":"math","model":"internlm2-chat-7b-sft","score":23.2,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-chat-7b-sft","score":11.3,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-chat-7b","score":70.7,"metric":"percent"},{"benchmark":"math","model":"internlm2-chat-7b","score":23.6,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-chat-7b","score":9.5,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b-chat","score":43.1,"metric":"percent"},{"benchmark":"math","model":"llama-2-13b-chat","score":5.2,"metric":"percent"},{"benchmark":"theoremqa","model":"llama-2-13b-chat","score":1.1,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-chat","score":56,"metric":"percent"},{"benchmark":"math","model":"baichuan2-13b-chat","score":4.3,"metric":"percent"},{"benchmark":"theoremqa","model":"baichuan2-13b-chat","score":3.4,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x7b-instruct-v0.1","score":71.7,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x7b-instruct-v0.1","score":22.5,"metric":"percent"},{"benchmark":"theoremqa","model":"mixtral-8x7b-instruct-v0.1","score":9.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b-chat","score":57.7,"metric":"percent"},{"benchmark":"math","model":"qwen-14b-chat","score":27.6,"metric":"percent"},{"benchmark":"theoremqa","model":"qwen-14b-chat","score":8.1,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-chat-20b-sft","score":77.1,"metric":"percent"},{"benchmark":"math","model":"internlm2-chat-20b-sft","score":31.9,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-chat-20b-sft","score":13.6,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-chat-20b","score":79.6,"metric":"percent"},{"benchmark":"math","model":"internlm2-chat-20b","score":32.4,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-chat-20b","score":14.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"llama-2-7b","score":11.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b","score":28.8,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b","score":27.4,"metric":"percent"},{"benchmark":"humaneval-x","model":"mistral-7b","score":28.5,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-7b-base","score":22,"metric":"percent"},{"benchmark":"humaneval-x","model":"baichuan2-7b-base","score":16.1,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-7b-base","score":35,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-7b-chat","score":36,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen-7b-chat","score":24.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-7b-chat","score":33.9,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm3-6b-base","score":45.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"chatglm3-6b-base","score":38.3,"metric":"percent"},{"benchmark":"mbpp","model":"chatglm3-6b-base","score":68.9,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-7b","score":56.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"internlm2-7b","score":39.6,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-7b","score":51.8,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-base-7b","score":31.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"internlm2-base-7b","score":28.8,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-base-7b","score":54.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"llama-2-13b","score":17.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-13b","score":38.9,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x7b","score":32.3,"metric":"percent"},{"benchmark":"humaneval-x","model":"mixtral-8x7b","score":38.3,"metric":"percent"},{"benchmark":"mbpp","model":"mixtral-8x7b","score":59.5,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-13b-base","score":23.2,"metric":"percent"},{"benchmark":"humaneval-x","model":"baichuan2-13b-base","score":19.5,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-13b-base","score":44,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-14b","score":30.5,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen-14b","score":31,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-14b","score":52.9,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-20b","score":48.8,"metric":"percent"},{"benchmark":"humaneval-x","model":"internlm2-20b","score":48.2,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-20b","score":63,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-base-20b","score":32.3,"metric":"percent"},{"benchmark":"humaneval-x","model":"internlm2-base-20b","score":31.5,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-base-20b","score":59.9,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-7b-chat","score":15.2,"metric":"percent"},{"benchmark":"humaneval-x","model":"llama-2-7b-chat","score":10.6,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-7b-chat","score":30.4,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-instruct-v0.2","score":35.4,"metric":"percent"},{"benchmark":"humaneval-x","model":"mistral-7b-instruct-v0.2","score":27.1,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-instruct-v0.2","score":23.7,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-7b-chat","score":17.7,"metric":"percent"},{"benchmark":"humaneval-x","model":"baichuan2-7b-chat","score":15.4,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-7b-chat","score":37.7,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm3-6b","score":53.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"chatglm3-6b","score":17.6,"metric":"percent"},{"benchmark":"mbpp","model":"chatglm3-6b","score":54.9,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-chat-7b-sft","score":61.6,"metric":"percent"},{"benchmark":"humaneval-x","model":"internlm2-chat-7b-sft","score":43.9,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-chat-7b-sft","score":47.5,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-chat-7b","score":59.2,"metric":"percent"},{"benchmark":"humaneval-x","model":"internlm2-chat-7b","score":41.7,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-chat-7b","score":52.5,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-13b-chat","score":8.5,"metric":"percent"},{"benchmark":"humaneval-x","model":"llama-2-13b-chat","score":12.9,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-13b-chat","score":19.8,"metric":"percent"},{"benchmark":"humaneval","model":"mixtral-8x7b-instruct-v0.1","score":32.3,"metric":"percent"},{"benchmark":"humaneval-x","model":"mixtral-8x7b-instruct-v0.1","score":38.3,"metric":"percent"},{"benchmark":"humaneval","model":"baichuan2-13b-chat","score":19.5,"metric":"percent"},{"benchmark":"humaneval-x","model":"baichuan2-13b-chat","score":18.3,"metric":"percent"},{"benchmark":"mbpp","model":"baichuan2-13b-chat","score":40.9,"metric":"percent"},{"benchmark":"humaneval","model":"qwen-14b-chat","score":41.5,"metric":"percent"},{"benchmark":"humaneval-x","model":"qwen-14b-chat","score":29.9,"metric":"percent"},{"benchmark":"mbpp","model":"qwen-14b-chat","score":29.2,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-chat-20b-sft","score":67.1,"metric":"percent"},{"benchmark":"humaneval-x","model":"internlm2-chat-20b-sft","score":42,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-chat-20b-sft","score":63.4,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-chat-20b","score":67.7,"metric":"percent"},{"benchmark":"humaneval-x","model":"internlm2-chat-20b","score":39.8,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-chat-20b","score":65.8,"metric":"percent"},{"benchmark":"l-eval","model":"llama-2-7b-chat","score":29.4,"metric":"percent"},{"benchmark":"longbench","model":"llama-2-7b-chat","score":14.3,"metric":"percent"},{"benchmark":"l-eval","model":"mistral-7b-instruct-v0.2","score":39.7,"metric":"percent"},{"benchmark":"longbench","model":"mistral-7b-instruct-v0.2","score":38.3,"metric":"percent"},{"benchmark":"l-eval","model":"baichuan2-7b-chat","score":33.4,"metric":"percent"},{"benchmark":"longbench","model":"baichuan2-7b-chat","score":25.9,"metric":"percent"},{"benchmark":"l-eval","model":"qwen-7b-chat","score":27.3,"metric":"percent"},{"benchmark":"longbench","model":"qwen-7b-chat","score":20.4,"metric":"percent"},{"benchmark":"l-eval","model":"chatglm3-6b","score":41.7,"metric":"percent"},{"benchmark":"longbench","model":"chatglm3-6b","score":48.4,"metric":"percent"},{"benchmark":"l-eval","model":"internlm2-chat-7b","score":48.5,"metric":"percent"},{"benchmark":"longbench","model":"internlm2-chat-7b","score":46.1,"metric":"percent"},{"benchmark":"l-eval","model":"internlm2-chat-7b-sft","score":48.6,"metric":"percent"},{"benchmark":"longbench","model":"internlm2-chat-7b-sft","score":48.1,"metric":"percent"},{"benchmark":"l-eval","model":"llama-2-13b-chat","score":32.5,"metric":"percent"},{"benchmark":"longbench","model":"llama-2-13b-chat","score":13.6,"metric":"percent"},{"benchmark":"l-eval","model":"mixtral-8x7b-instruct-v0.1","score":43.9,"metric":"percent"},{"benchmark":"longbench","model":"mixtral-8x7b-instruct-v0.1","score":37,"metric":"percent"},{"benchmark":"l-eval","model":"baichuan2-13b-chat","score":34.6,"metric":"percent"},{"benchmark":"longbench","model":"baichuan2-13b-chat","score":30.9,"metric":"percent"},{"benchmark":"l-eval","model":"qwen-14b-chat","score":34,"metric":"percent"},{"benchmark":"longbench","model":"qwen-14b-chat","score":29.7,"metric":"percent"},{"benchmark":"l-eval","model":"internlm2-chat-20b","score":48.4,"metric":"percent"},{"benchmark":"longbench","model":"internlm2-chat-20b","score":44.8,"metric":"percent"},{"benchmark":"l-eval","model":"internlm2-chat-20b-sft","score":49.4,"metric":"percent"},{"benchmark":"longbench","model":"internlm2-chat-20b-sft","score":46.8,"metric":"percent"},{"benchmark":"t-eval","model":"llama-2-7b-chat","score":37.2,"metric":"percent"},{"benchmark":"cibench","model":"llama-2-7b-chat","score":11.4,"metric":"percent"},{"benchmark":"t-eval","model":"chatglm3-6b","score":63,"metric":"percent"},{"benchmark":"cibench","model":"chatglm3-6b","score":23.2,"metric":"percent"},{"benchmark":"t-eval","model":"qwen-7b-chat","score":59.3,"metric":"percent"},{"benchmark":"cibench","model":"qwen-7b-chat","score":38.5,"metric":"percent"},{"benchmark":"t-eval","model":"qwen1.5-7b-chat","score":52.5,"metric":"percent"},{"benchmark":"cibench","model":"qwen1.5-7b-chat","score":35.8,"metric":"percent"},{"benchmark":"t-eval","model":"mistral-7b-instruct-v0.2","score":39,"metric":"percent"},{"benchmark":"cibench","model":"mistral-7b-instruct-v0.2","score":42.8,"metric":"percent"},{"benchmark":"t-eval","model":"internlm2-chat-7b-sft","score":65.5,"metric":"percent"},{"benchmark":"cibench","model":"internlm2-chat-7b-sft","score":39.9,"metric":"percent"},{"benchmark":"t-eval","model":"internlm2-chat-7b","score":65.8,"metric":"percent"},{"benchmark":"cibench","model":"internlm2-chat-7b","score":48.9,"metric":"percent"},{"benchmark":"t-eval","model":"llama-2-13b-chat","score":46.8,"metric":"percent"},{"benchmark":"cibench","model":"llama-2-13b-chat","score":16.1,"metric":"percent"},{"benchmark":"t-eval","model":"qwen-14b-chat","score":66.2,"metric":"percent"},{"benchmark":"cibench","model":"qwen-14b-chat","score":47.8,"metric":"percent"},{"benchmark":"t-eval","model":"qwen1.5-14b-chat","score":65.4,"metric":"percent"},{"benchmark":"cibench","model":"qwen1.5-14b-chat","score":53.8,"metric":"percent"},{"benchmark":"t-eval","model":"mixtral-8x7b-instruct-v0.1","score":58.3,"metric":"percent"},{"benchmark":"cibench","model":"mixtral-8x7b-instruct-v0.1","score":41.5,"metric":"percent"},{"benchmark":"t-eval","model":"internlm2-chat-20b-sft","score":64.4,"metric":"percent"},{"benchmark":"cibench","model":"internlm2-chat-20b-sft","score":46.4,"metric":"percent"},{"benchmark":"t-eval","model":"internlm2-chat-20b","score":64.3,"metric":"percent"},{"benchmark":"cibench","model":"internlm2-chat-20b","score":55.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"gpt-3.5-turbo","score":9.6,"metric":"percent"},{"benchmark":"mt-bench","model":"gpt-3.5-turbo","score":8.4,"metric":"percent"},{"benchmark":"alignbench","model":"gpt-3.5-turbo","score":5.7,"metric":"score"},{"benchmark":"alignbench","model":"chatglm3-6b","score":5,"metric":"score"},{"benchmark":"ifeval","model":"chatglm3-6b","score":33.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-2-7b-chat","score":5,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-2-7b-chat","score":6.3,"metric":"percent"},{"benchmark":"ifeval","model":"llama-2-7b-chat","score":44.6,"metric":"percent"},{"benchmark":"alignbench","model":"baichuan2-7b-chat","score":5.1,"metric":"score"},{"benchmark":"ifeval","model":"baichuan2-7b-chat","score":42.1,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"mistral-7b-instruct-v0.2","score":14.7,"metric":"percent"},{"benchmark":"ifeval","model":"mistral-7b-instruct-v0.2","score":57.9,"metric":"percent"},{"benchmark":"alignbench","model":"qwen-7b-chat","score":4.7,"metric":"score"},{"benchmark":"ifeval","model":"qwen-7b-chat","score":37.3,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"internlm2-chat-7b-sft","score":6.9,"metric":"percent"},{"benchmark":"mt-bench","model":"internlm2-chat-7b-sft","score":7.1,"metric":"percent"},{"benchmark":"alignbench","model":"internlm2-chat-7b-sft","score":4.9,"metric":"score"},{"benchmark":"ifeval","model":"internlm2-chat-7b-sft","score":48.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"internlm2-chat-7b","score":11.3,"metric":"percent"},{"benchmark":"mt-bench","model":"internlm2-chat-7b","score":7.7,"metric":"percent"},{"benchmark":"alignbench","model":"internlm2-chat-7b","score":6.1,"metric":"score"},{"benchmark":"ifeval","model":"internlm2-chat-7b","score":45.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"llama-2-13b-chat","score":7.7,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-2-13b-chat","score":6.7,"metric":"percent"},{"benchmark":"ifeval","model":"llama-2-13b-chat","score":46.1,"metric":"percent"},{"benchmark":"alignbench","model":"baichuan2-13b-chat","score":5.3,"metric":"score"},{"benchmark":"ifeval","model":"baichuan2-13b-chat","score":42.5,"metric":"percent"},{"benchmark":"ifeval","model":"mixtral-8x7b-instruct-v0.1","score":56.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen-14b-chat","score":7.5,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen-14b-chat","score":7,"metric":"percent"},{"benchmark":"alignbench","model":"qwen-14b-chat","score":5.4,"metric":"score"},{"benchmark":"ifeval","model":"qwen-14b-chat","score":43.8,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"internlm2-chat-20b-sft","score":8,"metric":"percent"},{"benchmark":"mt-bench","model":"internlm2-chat-20b-sft","score":7.3,"metric":"percent"},{"benchmark":"alignbench","model":"internlm2-chat-20b-sft","score":5.3,"metric":"score"},{"benchmark":"ifeval","model":"internlm2-chat-20b-sft","score":48.7,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"internlm2-chat-20b","score":21.8,"metric":"percent"},{"benchmark":"mt-bench","model":"internlm2-chat-20b","score":7.9,"metric":"percent"},{"benchmark":"alignbench","model":"internlm2-chat-20b","score":6.8,"metric":"score"},{"benchmark":"ifeval","model":"internlm2-chat-20b","score":42.2,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4v","score":1926.6,"metric":"points"},{"benchmark":"mmbench","model":"gpt-4v","score":77,"metric":"percent"},{"benchmark":"ccbench","model":"gpt-4v","score":46.5,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4v","score":67.6,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gpt-4v","score":71.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4v","score":46.5,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-1.0-ultra","score":80.3,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-1.0-pro","score":75.2,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-1.0-pro","score":65.9,"metric":"percent"},{"benchmark":"mme-elo","model":"gemini-1.0-pro","score":1933.4,"metric":"points"},{"benchmark":"ccbench","model":"gemini-1.0-pro","score":52.5,"metric":"percent"},{"benchmark":"mmvet","model":"gemini-1.0-pro","score":64.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gemini-1.0-pro","score":70.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-1.0-pro","score":45.2,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-1.5-pro","score":81.3,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-1.5-pro","score":72.7,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-1.5-pro","score":67.5,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-1.5-pro","score":80.3,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.5-pro","score":58.5,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-1.5-pro","score":52.1,"metric":"percent"},{"benchmark":"infovqa","model":"qwen-vl-max","score":73.4,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen-vl-max","score":72.3,"metric":"percent"},{"benchmark":"mme-elo","model":"qwen-vl-max","score":2433.6,"metric":"points"},{"benchmark":"mmmu","model":"qwen-vl-max","score":51.3,"metric":"percent"},{"benchmark":"mmbench","model":"qwen-vl-max","score":77.6,"metric":"percent"},{"benchmark":"ccbench","model":"qwen-vl-max","score":63.5,"metric":"percent"},{"benchmark":"mmvet","model":"qwen-vl-max","score":66.6,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen-vl-plus","score":69.4,"metric":"percent"},{"benchmark":"mme-elo","model":"qwen-vl-plus","score":2183.4,"metric":"points"},{"benchmark":"mmbench","model":"qwen-vl-plus","score":67,"metric":"percent"},{"benchmark":"ccbench","model":"qwen-vl-plus","score":55.1,"metric":"percent"},{"benchmark":"mmvet","model":"qwen-vl-plus","score":61.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen-vl-plus","score":72.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen-vl-plus","score":40.6,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-3-opus","score":69.4,"metric":"percent"},{"benchmark":"ccbench","model":"claude-3-opus","score":26.3,"metric":"percent"},{"benchmark":"mmvet","model":"claude-3-opus","score":58.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-3-opus","score":37.8,"metric":"percent"},{"benchmark":"docvqa","model":"claude-3-sonnet","score":89.5,"metric":"percent"},{"benchmark":"chartqa","model":"claude-3-sonnet","score":81.1,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-3-sonnet","score":64.6,"metric":"percent"},{"benchmark":"mme-elo","model":"claude-3-sonnet","score":1625.9,"metric":"points"},{"benchmark":"realworldqa","model":"claude-3-sonnet","score":51.9,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3-sonnet","score":88.7,"metric":"percent"},{"benchmark":"mmmu","model":"claude-3-sonnet","score":53.1,"metric":"percent"},{"benchmark":"mmbench","model":"claude-3-sonnet","score":67.8,"metric":"percent"},{"benchmark":"ccbench","model":"claude-3-sonnet","score":27.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-3-sonnet","score":41.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"claude-3-sonnet","score":47.9,"metric":"percent"},{"benchmark":"ocrbench","model":"claude-3-haiku","score":65.8,"metric":"percent"},{"benchmark":"mme-elo","model":"claude-3-haiku","score":1453.2,"metric":"points"},{"benchmark":"mmbench","model":"claude-3-haiku","score":60.7,"metric":"percent"},{"benchmark":"ccbench","model":"claude-3-haiku","score":24.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-3-haiku","score":39.2,"metric":"percent"},{"benchmark":"mme-elo","model":"mm1-30b","score":2069,"metric":"points"},{"benchmark":"mmbench","model":"mm1-30b","score":75.1,"metric":"percent"},{"benchmark":"mmvet","model":"mm1-30b","score":48.7,"metric":"percent"},{"benchmark":"mmbench","model":"step-1v-32k","score":80.7,"metric":"percent"},{"benchmark":"ccbench","model":"step-1v-32k","score":71.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"step-1v-32k","score":70.3,"metric":"percent"},{"benchmark":"docvqa","model":"grok-1.5v","score":85.6,"metric":"percent"},{"benchmark":"chartqa","model":"grok-1.5v","score":76.1,"metric":"percent"},{"benchmark":"textvqa","model":"grok-1.5v","score":78.1,"metric":"percent"},{"benchmark":"realworldqa","model":"grok-1.5v","score":68.7,"metric":"percent"},{"benchmark":"ai2d","model":"grok-1.5v","score":88.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"grok-1.5v","score":52.8,"metric":"percent"},{"benchmark":"chartqa","model":"textmonkey","score":59.9,"metric":"percent"},{"benchmark":"infovqa","model":"textmonkey","score":28.6,"metric":"percent"},{"benchmark":"ocrbench","model":"textmonkey","score":56.1,"metric":"percent"},{"benchmark":"docvqa","model":"docowl-1.5-chat","score":82.2,"metric":"percent"},{"benchmark":"chartqa","model":"docowl-1.5-chat","score":70.2,"metric":"percent"},{"benchmark":"infovqa","model":"docowl-1.5-chat","score":50.7,"metric":"percent"},{"benchmark":"textvqa","model":"docowl-1.5-chat","score":68.6,"metric":"percent"},{"benchmark":"ocrbench","model":"docowl-1.5-chat","score":59.9,"metric":"percent"},{"benchmark":"mmbench","model":"mini-gemini-hd-34b","score":80.6,"metric":"percent"},{"benchmark":"docvqa","model":"llava-next-34b","score":84,"metric":"percent"},{"benchmark":"chartqa","model":"llava-next-34b","score":68.7,"metric":"percent"},{"benchmark":"infovqa","model":"llava-next-34b","score":51.5,"metric":"percent"},{"benchmark":"mme-elo","model":"llava-next-34b","score":2028,"metric":"points"},{"benchmark":"ai2d","model":"llava-next-34b","score":74.9,"metric":"percent"},{"benchmark":"ccbench","model":"llava-next-34b","score":49.2,"metric":"percent"},{"benchmark":"mmvet","model":"llava-next-34b","score":57.4,"metric":"percent"},{"benchmark":"docvqa","model":"internvl-chat-v1.2","score":57.7,"metric":"percent"},{"benchmark":"chartqa","model":"internvl-chat-v1.2","score":68,"metric":"percent"},{"benchmark":"infovqa","model":"internvl-chat-v1.2","score":39.5,"metric":"percent"},{"benchmark":"textvqa","model":"internvl-chat-v1.2","score":72.5,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl-chat-v1.2","score":56.9,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl-chat-v1.2","score":2175.4,"metric":"points"},{"benchmark":"realworldqa","model":"internvl-chat-v1.2","score":67.5,"metric":"percent"},{"benchmark":"ai2d","model":"internvl-chat-v1.2","score":79,"metric":"percent"},{"benchmark":"mmmu","model":"internvl-chat-v1.2","score":51.6,"metric":"percent"},{"benchmark":"mmbench","model":"internvl-chat-v1.2","score":82.2,"metric":"percent"},{"benchmark":"ccbench","model":"internvl-chat-v1.2","score":59.2,"metric":"percent"},{"benchmark":"mmvet","model":"internvl-chat-v1.2","score":48.9,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internvl-chat-v1.2","score":75.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl-chat-v1.2","score":47.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl-chat-v1.2","score":47.7,"metric":"percent"},{"benchmark":"docvqa","model":"internvl-chat-v1.5","score":90.9,"metric":"percent"},{"benchmark":"chartqa","model":"internvl-chat-v1.5","score":83.8,"metric":"percent"},{"benchmark":"infovqa","model":"internvl-chat-v1.5","score":72.5,"metric":"percent"},{"benchmark":"textvqa","model":"internvl-chat-v1.5","score":80.6,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl-chat-v1.5","score":72.4,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl-chat-v1.5","score":2187.8,"metric":"points"},{"benchmark":"realworldqa","model":"internvl-chat-v1.5","score":66,"metric":"percent"},{"benchmark":"ai2d","model":"internvl-chat-v1.5","score":80.7,"metric":"percent"},{"benchmark":"mmmu","model":"internvl-chat-v1.5","score":45.2,"metric":"percent"},{"benchmark":"mmbench","model":"internvl-chat-v1.5","score":82.2,"metric":"percent"},{"benchmark":"ccbench","model":"internvl-chat-v1.5","score":69.8,"metric":"percent"},{"benchmark":"mmvet","model":"internvl-chat-v1.5","score":62.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internvl-chat-v1.5","score":76,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl-chat-v1.5","score":49.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl-chat-v1.5","score":53.5,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gpt-4v","score":74.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen-vl-max","score":75.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen-vl-plus","score":70.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"claude-3-sonnet","score":64.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"claude-3-haiku","score":57.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"step-1v-32k","score":79.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl-chat-v1.2","score":81.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl-chat-v1.5","score":82,"metric":"percent"},{"benchmark":"mmt-bench","model":"gpt-4v","score":62,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen-vl-plus","score":62.3,"metric":"percent"},{"benchmark":"mmt-bench","model":"gemini-1.0-pro","score":61.6,"metric":"percent"},{"benchmark":"mmt-bench","model":"claude-3-haiku","score":52.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"llava-next-34b","score":60.8,"metric":"percent"},{"benchmark":"mmt-bench","model":"internlm-xcomposer2-vl-7b","score":55.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"blip-2-flan-t5-xxl","score":54.8,"metric":"percent"},{"benchmark":"mmt-bench","model":"yi-vl-34b","score":54.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"monkey-chat","score":53.4,"metric":"percent"},{"benchmark":"mmt-bench","model":"deepseek-vl-7b","score":53.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"cogvlm-17b-chat","score":51.6,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl-chat-v1.2","score":63.4,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl-chat-v1.5","score":59,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4o","score":88,"metric":"percent"},{"benchmark":"cmmlu","model":"gpt-4o","score":78.3,"metric":"percent"},{"benchmark":"agieval","model":"gpt-4o","score":62.3,"metric":"percent"},{"benchmark":"c-eval","model":"gpt-4o","score":86,"metric":"percent"},{"benchmark":"mmlu","model":"map-neo-7b-instruct","score":58.2,"metric":"percent"},{"benchmark":"cmmlu","model":"map-neo-7b-instruct","score":55.1,"metric":"percent"},{"benchmark":"agieval","model":"map-neo-7b-instruct","score":33.9,"metric":"percent"},{"benchmark":"c-eval","model":"map-neo-7b-instruct","score":57.5,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-7b-chat","score":61.5,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-7b-chat","score":68,"metric":"percent"},{"benchmark":"agieval","model":"qwen1.5-7b-chat","score":39.3,"metric":"percent"},{"benchmark":"c-eval","model":"qwen1.5-7b-chat","score":68.8,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-8b-instruct","score":51.7,"metric":"percent"},{"benchmark":"agieval","model":"llama-3-8b-instruct","score":38.4,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-8b-instruct","score":50.7,"metric":"percent"},{"benchmark":"mmlu","model":"olmo-7b-instruct","score":28.4,"metric":"percent"},{"benchmark":"cmmlu","model":"olmo-7b-instruct","score":25.6,"metric":"percent"},{"benchmark":"agieval","model":"olmo-7b-instruct","score":19.9,"metric":"percent"},{"benchmark":"c-eval","model":"olmo-7b-instruct","score":27.3,"metric":"percent"},{"benchmark":"mmlu","model":"vita","score":71,"metric":"percent"},{"benchmark":"cmmlu","model":"vita","score":46.6,"metric":"percent"},{"benchmark":"agieval","model":"vita","score":46.2,"metric":"percent"},{"benchmark":"c-eval","model":"vita","score":56.7,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan-omni","score":65.3,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan-omni","score":72.2,"metric":"percent"},{"benchmark":"agieval","model":"baichuan-omni","score":47.7,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan-omni","score":68.9,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4o-mini","score":2003.4,"metric":"points"},{"benchmark":"mmmu","model":"gpt-4o-mini","score":60,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4o-mini","score":46.1,"metric":"percent"},{"benchmark":"mmbench","model":"qwen2-vl-7b","score":86.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen2-vl-7b","score":81.9,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen2-vl-7b","score":76.5,"metric":"percent"},{"benchmark":"mme-elo","model":"qwen2-vl-7b","score":2326.8,"metric":"points"},{"benchmark":"mmmu","model":"qwen2-vl-7b","score":52.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2-vl-7b","score":50.6,"metric":"percent"},{"benchmark":"mmbench","model":"minicpm-llama3-v2.5","score":76.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"minicpm-llama3-v2.5","score":73.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"minicpm-llama3-v2.5","score":72.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"minicpm-llama3-v2.5","score":42.5,"metric":"percent"},{"benchmark":"mmbench","model":"vita","score":74.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"vita","score":71.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"vita","score":72.6,"metric":"percent"},{"benchmark":"mme-elo","model":"vita","score":2189.1,"metric":"points"},{"benchmark":"mmmu","model":"vita","score":45.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"vita","score":39.7,"metric":"percent"},{"benchmark":"mmbench","model":"baichuan-omni","score":76.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"baichuan-omni","score":74.9,"metric":"percent"},{"benchmark":"seed-bench-img","model":"baichuan-omni","score":74.1,"metric":"percent"},{"benchmark":"mme-elo","model":"baichuan-omni","score":2186.9,"metric":"points"},{"benchmark":"mmmu","model":"baichuan-omni","score":47.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"baichuan-omni","score":47.8,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-4o-mini","score":67.1,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4o-mini","score":66.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4o-mini","score":52.4,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4o-mini","score":78.5,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2-vl-7b","score":69.7,"metric":"percent"},{"benchmark":"mmvet","model":"qwen2-vl-7b","score":62,"metric":"percent"},{"benchmark":"mmvet","model":"minicpm-llama3-v2.5","score":52,"metric":"percent"},{"benchmark":"chartqa","model":"minicpm-llama3-v2.5","score":72,"metric":"percent"},{"benchmark":"realworldqa","model":"vita","score":59,"metric":"percent"},{"benchmark":"mmvet","model":"vita","score":41.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"vita","score":44.9,"metric":"percent"},{"benchmark":"textvqa","model":"vita","score":71.8,"metric":"percent"},{"benchmark":"chartqa","model":"vita","score":76.6,"metric":"percent"},{"benchmark":"ocrbench","model":"vita","score":68.5,"metric":"percent"},{"benchmark":"realworldqa","model":"baichuan-omni","score":62.6,"metric":"percent"},{"benchmark":"mmvet","model":"baichuan-omni","score":65.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"baichuan-omni","score":51.9,"metric":"percent"},{"benchmark":"textvqa","model":"baichuan-omni","score":74.3,"metric":"percent"},{"benchmark":"chartqa","model":"baichuan-omni","score":79.6,"metric":"percent"},{"benchmark":"ocrbench","model":"baichuan-omni","score":70,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-1.5-pro","score":81.3,"metric":"percent"},{"benchmark":"videomme","model":"gemini-1.5-pro","score":75,"metric":"percent"},{"benchmark":"egoschema","model":"gpt-4o","score":77.2,"metric":"percent"},{"benchmark":"videomme","model":"gpt-4o","score":71.9,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-4v","score":43.7,"metric":"percent"},{"benchmark":"egoschema","model":"gpt-4v","score":55.6,"metric":"percent"},{"benchmark":"mvbench","model":"anygpt","score":33.2,"metric":"percent"},{"benchmark":"egoschema","model":"anygpt","score":32.1,"metric":"percent"},{"benchmark":"videomme","model":"anygpt","score":29.8,"metric":"percent"},{"benchmark":"perceptiontest","model":"anygpt","score":29.1,"metric":"percent"},{"benchmark":"mvbench","model":"videollama2-7b","score":54.6,"metric":"percent"},{"benchmark":"egoschema","model":"videollama2-7b","score":51.7,"metric":"percent"},{"benchmark":"videomme","model":"videollama2-7b","score":46.6,"metric":"percent"},{"benchmark":"perceptiontest","model":"videollama2-7b","score":51.4,"metric":"percent"},{"benchmark":"mvbench","model":"videochat2-7b","score":51.1,"metric":"percent"},{"benchmark":"egoschema","model":"videochat2-7b","score":42.1,"metric":"percent"},{"benchmark":"videomme","model":"videochat2-7b","score":33.7,"metric":"percent"},{"benchmark":"perceptiontest","model":"videochat2-7b","score":47.3,"metric":"percent"},{"benchmark":"mvbench","model":"llava-next-video-7b","score":46.5,"metric":"percent"},{"benchmark":"egoschema","model":"llava-next-video-7b","score":43.9,"metric":"percent"},{"benchmark":"videomme","model":"llava-next-video-7b","score":33.7,"metric":"percent"},{"benchmark":"perceptiontest","model":"llava-next-video-7b","score":48.8,"metric":"percent"},{"benchmark":"mvbench","model":"video-llava-7b","score":41,"metric":"percent"},{"benchmark":"egoschema","model":"video-llava-7b","score":38.4,"metric":"percent"},{"benchmark":"videomme","model":"video-llava-7b","score":39.9,"metric":"percent"},{"benchmark":"perceptiontest","model":"video-llava-7b","score":44.3,"metric":"percent"},{"benchmark":"mvbench","model":"vita","score":53.4,"metric":"percent"},{"benchmark":"egoschema","model":"vita","score":53.9,"metric":"percent"},{"benchmark":"videomme","model":"vita","score":56.1,"metric":"percent"},{"benchmark":"perceptiontest","model":"vita","score":56.2,"metric":"percent"},{"benchmark":"mvbench","model":"baichuan-omni","score":60.9,"metric":"percent"},{"benchmark":"egoschema","model":"baichuan-omni","score":58.8,"metric":"percent"},{"benchmark":"videomme","model":"baichuan-omni","score":58.2,"metric":"percent"},{"benchmark":"perceptiontest","model":"baichuan-omni","score":56.8,"metric":"percent"},{"benchmark":"mvbench","model":"qwen2-vl-7b","score":67,"metric":"percent"},{"benchmark":"egoschema","model":"qwen2-vl-7b","score":66.7,"metric":"percent"},{"benchmark":"videomme","model":"qwen2-vl-7b","score":63.3,"metric":"percent"},{"benchmark":"perceptiontest","model":"qwen2-vl-7b","score":62.3,"metric":"percent"},{"benchmark":"activitynet-qa","model":"gemini-1.5-pro","score":56.7,"metric":"percent"},{"benchmark":"activitynet-qa","model":"gpt-4o","score":61.9,"metric":"percent"},{"benchmark":"activitynet-qa","model":"gpt-4v","score":59.5,"metric":"percent"},{"benchmark":"activitynet-qa","model":"qwen2-vl-7b","score":17.4,"metric":"percent"},{"benchmark":"msvd-qa","model":"qwen2-vl-7b","score":61.1,"metric":"percent"},{"benchmark":"activitynet-qa","model":"videollama2-7b","score":50.2,"metric":"percent"},{"benchmark":"msvd-qa","model":"videollama2-7b","score":70.9,"metric":"percent"},{"benchmark":"activitynet-qa","model":"videochat2-7b","score":49.1,"metric":"percent"},{"benchmark":"msvd-qa","model":"videochat2-7b","score":70,"metric":"percent"},{"benchmark":"activitynet-qa","model":"llava-next-video-7b","score":53.5,"metric":"percent"},{"benchmark":"msvd-qa","model":"llava-next-video-7b","score":67.4,"metric":"percent"},{"benchmark":"activitynet-qa","model":"video-llava-7b","score":45.3,"metric":"percent"},{"benchmark":"msvd-qa","model":"video-llava-7b","score":70.7,"metric":"percent"},{"benchmark":"activitynet-qa","model":"vita","score":55,"metric":"percent"},{"benchmark":"msvd-qa","model":"vita","score":63.9,"metric":"percent"},{"benchmark":"activitynet-qa","model":"baichuan-omni","score":58.6,"metric":"percent"},{"benchmark":"msvd-qa","model":"baichuan-omni","score":72.2,"metric":"percent"},{"benchmark":"mathverse-mini","model":"llava-onevision-0.5b","score":17.9,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-1b","score":36.7,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2-1b","score":32.8,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2-1b","score":13.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2-1b","score":14.8,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2-1b","score":11.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2-1b","score":18.4,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2-1b","score":0.3,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2.5-1b","score":40.9,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2.5-1b","score":35.8,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2.5-1b","score":15.5,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2.5-1b","score":19.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2.5-1b","score":43.2,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2.5-1b","score":28,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2.5-1b","score":1.7,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"qwen2-vl-2b","score":17.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2-vl-2b","score":21.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"qwen2-vl-2b","score":43,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen2-vl-2b","score":21,"metric":"percent"},{"benchmark":"mmmu","model":"aquila-vl-2b","score":47.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"aquila-vl-2b","score":59,"metric":"percent"},{"benchmark":"mathvision","model":"aquila-vl-2b","score":18.4,"metric":"percent"},{"benchmark":"mathverse-mini","model":"aquila-vl-2b","score":26.2,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2-2b","score":34.7,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2-2b","score":14.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2-2b","score":18.2,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2-2b","score":12.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2-2b","score":25.3,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2-2b","score":0.4,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2.5-2b","score":38.2,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2.5-2b","score":20.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2.5-2b","score":23.7,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2.5-2b","score":30.6,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2.5-2b","score":2,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"phi-3.5-vision-instruct","score":13.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"phi-3.5-vision-instruct","score":19.7,"metric":"percent"},{"benchmark":"mathvision","model":"phi-3.5-vision-instruct","score":15.5,"metric":"percent"},{"benchmark":"mathverse-mini","model":"phi-3.5-vision-instruct","score":24.1,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2-4b","score":41.4,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2-4b","score":21.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2-4b","score":24.7,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2-4b","score":16.5,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2-4b","score":32,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2-4b","score":1.1,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2.5-4b","score":46.3,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2.5-4b","score":29,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2.5-4b","score":32.7,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2.5-4b","score":20.9,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2.5-4b","score":37.1,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2.5-4b","score":3,"metric":"percent"},{"benchmark":"mmmu","model":"ovis1.6-gemma2-9b","score":55,"metric":"percent"},{"benchmark":"mathvista-mini","model":"ovis1.6-gemma2-9b","score":67.2,"metric":"percent"},{"benchmark":"mathvision","model":"ovis1.6-gemma2-9b","score":18.8,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"minicpm-v-2_6","score":24.2,"metric":"percent"},{"benchmark":"mmmu-pro","model":"minicpm-v-2_6","score":27.2,"metric":"percent"},{"benchmark":"mathvision","model":"minicpm-v-2_6","score":17.5,"metric":"percent"},{"benchmark":"mathverse-mini","model":"minicpm-v-2_6","score":25.7,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"qwen2-vl-7b","score":27,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2-vl-7b","score":30.5,"metric":"percent"},{"benchmark":"mathverse-mini","model":"qwen2-vl-7b","score":31.9,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-8b","score":52.6,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2-8b","score":44.3,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2-8b","score":25.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2-8b","score":29,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2-8b","score":18.4,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2-8b","score":37,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2-8b","score":1.9,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2.5-8b","score":56,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2.5-8b","score":48.9,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2.5-8b","score":30.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2.5-8b","score":34.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2.5-8b","score":64.4,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2.5-8b","score":39.5,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2.5-8b","score":4.9,"metric":"percent"},{"benchmark":"mmmu","model":"internvl-chat-v1.5","score":46.8,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl-chat-v1.5","score":41,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl-chat-v1.5","score":19.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl-chat-v1.5","score":24.7,"metric":"percent"},{"benchmark":"mathvision","model":"internvl-chat-v1.5","score":15,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl-chat-v1.5","score":28.4,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl-chat-v1.5","score":0.6,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-26b","score":51.2,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2-26b","score":43.8,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2-26b","score":27.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2-26b","score":30,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2-26b","score":59.4,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2-26b","score":17,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2-26b","score":31.1,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2-26b","score":3.5,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2.5-26b","score":60,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2.5-26b","score":51.8,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2.5-26b","score":32.6,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2.5-26b","score":37.1,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2.5-26b","score":40.1,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2.5-26b","score":8.8,"metric":"percent"},{"benchmark":"mmmu","model":"vila1.5-40b","score":55.1,"metric":"percent"},{"benchmark":"mmmu-test","model":"vila1.5-40b","score":46.9,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"vila1.5-40b","score":14.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"vila1.5-40b","score":25,"metric":"percent"},{"benchmark":"mathvista-mini","model":"vila1.5-40b","score":49.5,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-40b","score":55.2,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2-40b","score":49.3,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2-40b","score":32.1,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2-40b","score":34.2,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2-40b","score":63.7,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2-40b","score":16.9,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2-40b","score":36.3,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2-40b","score":3.9,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2.5-38b","score":63.9,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2.5-38b","score":57.6,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2.5-38b","score":44,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2.5-38b","score":46,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2.5-38b","score":71.9,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2.5-38b","score":49.4,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2.5-38b","score":12.1,"metric":"percent"},{"benchmark":"mathvision","model":"gpt-4v","score":24,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gpt-4v","score":32.8,"metric":"percent"},{"benchmark":"olympiadbench","model":"gpt-4v","score":18,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"gpt-4o-2024-05-13","score":49.7,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gpt-4o-2024-05-13","score":51.9,"metric":"percent"},{"benchmark":"mathverse-mini","model":"gpt-4o-2024-05-13","score":50.2,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"claude-3.5-sonnet-20240620","score":48,"metric":"percent"},{"benchmark":"mmmu-pro","model":"claude-3.5-sonnet-20240620","score":51.5,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"gemini-1.5-pro","score":44.4,"metric":"percent"},{"benchmark":"mmmu-pro","model":"gemini-1.5-pro","score":46.9,"metric":"percent"},{"benchmark":"mathvision","model":"gemini-1.5-pro","score":19.2,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"llava-onevision-72b","score":24,"metric":"percent"},{"benchmark":"mmmu-pro","model":"llava-onevision-72b","score":31,"metric":"percent"},{"benchmark":"mathverse-mini","model":"llava-onevision-72b","score":39.1,"metric":"percent"},{"benchmark":"mmmu","model":"nvlm-d-72b","score":59.7,"metric":"percent"},{"benchmark":"mmmu-test","model":"nvlm-d-72b","score":54.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"nvlm-d-72b","score":66.6,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"qwen2-vl-72b","score":43.3,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen2-vl-72b","score":46.2,"metric":"percent"},{"benchmark":"olympiadbench","model":"qwen2-vl-72b","score":11.2,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-llama-3-76b","score":62.7,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2-llama-3-76b","score":55.1,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2-llama-3-76b","score":38,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2-llama-3-76b","score":40,"metric":"percent"},{"benchmark":"mathvision","model":"internvl2-llama-3-76b","score":23.6,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2-llama-3-76b","score":42.8,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2-llama-3-76b","score":5.5,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2.5-78b","score":70.1,"metric":"percent"},{"benchmark":"mmmu-test","model":"internvl2.5-78b","score":61.8,"metric":"percent"},{"benchmark":"mmmu-pro-vision","model":"internvl2.5-78b","score":45.9,"metric":"percent"},{"benchmark":"mmmu-pro","model":"internvl2.5-78b","score":48.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2.5-78b","score":72.3,"metric":"percent"},{"benchmark":"mathverse-mini","model":"internvl2.5-78b","score":51.7,"metric":"percent"},{"benchmark":"olympiadbench","model":"internvl2.5-78b","score":11.6,"metric":"percent"},{"benchmark":"ocrbench","model":"llava-onevision-0.5b","score":56.5,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2-1b","score":54.3,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2-1b","score":18.1,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-1b","score":30.7,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2-1b","score":21.5,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2.5-1b","score":69.3,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2.5-1b","score":75.9,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2.5-1b","score":72,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2.5-1b","score":84.8,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2.5-1b","score":56,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2.5-1b","score":78.5,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2.5-1b","score":59,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2.5-1b","score":91.5,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"qwen2-vl-2b","score":81.5,"metric":"percent"},{"benchmark":"ai2d","model":"aquila-vl-2b","score":75,"metric":"percent"},{"benchmark":"chartqa","model":"aquila-vl-2b","score":76.5,"metric":"percent"},{"benchmark":"textvqa","model":"aquila-vl-2b","score":76.4,"metric":"percent"},{"benchmark":"docvqa","model":"aquila-vl-2b","score":85,"metric":"percent"},{"benchmark":"infovqa","model":"aquila-vl-2b","score":58.3,"metric":"percent"},{"benchmark":"ocrbench","model":"aquila-vl-2b","score":77.2,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"aquila-vl-2b","score":63,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"aquila-vl-2b","score":70,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2-2b","score":60,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2-2b","score":21,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-2b","score":40.6,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2-2b","score":32.9,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2.5-2b","score":60.9,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2.5-2b","score":93.2,"metric":"percent"},{"benchmark":"ai2d","model":"phi-3.5-vision-instruct","score":77.8,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"phi-3.5-vision-instruct","score":62.2,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"phi-3.5-vision-instruct","score":39.3,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2-4b","score":63.9,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2-4b","score":24.5,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-4b","score":48,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2-4b","score":33.7,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2.5-4b","score":66.9,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2.5-4b","score":93.7,"metric":"percent"},{"benchmark":"ai2d","model":"ovis1.6-gemma2-9b","score":84.4,"metric":"percent"},{"benchmark":"ocrbench","model":"ovis1.6-gemma2-9b","score":83,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"minicpm-v-2_6","score":65.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"minicpm-v-2_6","score":31,"metric":"percent"},{"benchmark":"charxiv-dq","model":"minicpm-v-2_6","score":57.1,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"minicpm-v-2_6","score":73.9,"metric":"percent"},{"benchmark":"infovqa","model":"molmo-7b-d","score":72.6,"metric":"percent"},{"benchmark":"ocrbench","model":"molmo-7b-d","score":69.4,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2-vl-7b","score":86.6,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"qwen2-vl-7b","score":69,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"qwen2-vl-7b","score":89.7,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2-8b","score":67.5,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2-8b","score":31.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-8b","score":56.1,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2-8b","score":37.9,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2.5-8b","score":84.5,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2.5-8b","score":84.8,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2.5-8b","score":79.1,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2.5-8b","score":93,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2.5-8b","score":77.6,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2.5-8b","score":82.2,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2.5-8b","score":69.7,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2.5-8b","score":92.6,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl-chat-v1.5","score":66.3,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl-chat-v1.5","score":14.7,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-26b","score":84.5,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2-26b","score":84.9,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2-26b","score":82.3,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2-26b","score":92.9,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2-26b","score":75.9,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2-26b","score":82.5,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2-26b","score":67.6,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2-26b","score":74.5,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2.5-26b","score":70.8,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2.5-26b","score":94.4,"metric":"percent"},{"benchmark":"ai2d","model":"cambrian-34b","score":79.5,"metric":"percent"},{"benchmark":"infovqa","model":"cambrian-34b","score":46,"metric":"percent"},{"benchmark":"charxiv-dq","model":"cambrian-34b","score":59.7,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"cambrian-34b","score":79.7,"metric":"percent"},{"benchmark":"ai2d","model":"vila1.5-40b","score":69.9,"metric":"percent"},{"benchmark":"chartqa","model":"vila1.5-40b","score":67.2,"metric":"percent"},{"benchmark":"textvqa","model":"vila1.5-40b","score":73.6,"metric":"percent"},{"benchmark":"ocrbench","model":"vila1.5-40b","score":46,"metric":"percent"},{"benchmark":"charxiv-dq","model":"vila1.5-40b","score":38.7,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-40b","score":86.6,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2-40b","score":86.2,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2-40b","score":83,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2-40b","score":93.9,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2-40b","score":78.7,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2-40b","score":83.7,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2-40b","score":69.2,"metric":"percent"},{"benchmark":"charxiv-rq","model":"internvl2-40b","score":32.3,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-40b","score":66,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2-40b","score":84.7,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2.5-38b","score":87.6,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2.5-38b","score":88.2,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2.5-38b","score":82.7,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2.5-38b","score":95.3,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2.5-38b","score":83.6,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2.5-38b","score":84.2,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2.5-38b","score":71.2,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2.5-38b","score":94.7,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"gpt-4v","score":53.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4v","score":79.9,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"gpt-4v","score":52,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-4o-2024-05-13","score":85.7,"metric":"percent"},{"benchmark":"textvqa","model":"gpt-4o-2024-05-13","score":77.4,"metric":"percent"},{"benchmark":"infovqa","model":"gpt-4o-2024-05-13","score":79.2,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"gpt-4o-2024-05-13","score":72,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gpt-4o-2024-05-13","score":84.5,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"gpt-4o-2024-05-13","score":91.6,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3-opus","score":70.6,"metric":"percent"},{"benchmark":"infovqa","model":"claude-3-opus","score":55.6,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"claude-3-opus","score":44.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-3-opus","score":71.6,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"claude-3-opus","score":62,"metric":"percent"},{"benchmark":"ai2d","model":"claude-3.5-sonnet-20240620","score":81.2,"metric":"percent"},{"benchmark":"infovqa","model":"claude-3.5-sonnet-20240620","score":74.3,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"claude-3.5-sonnet-20240620","score":71.7,"metric":"percent"},{"benchmark":"charxiv-rq","model":"claude-3.5-sonnet-20240620","score":60.2,"metric":"percent"},{"benchmark":"charxiv-dq","model":"claude-3.5-sonnet-20240620","score":84.3,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"claude-3.5-sonnet-20240620","score":63.9,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-1.5-pro","score":78.8,"metric":"percent"},{"benchmark":"charxiv-dq","model":"gemini-1.5-pro","score":72,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"gemini-1.5-pro","score":62.7,"metric":"percent"},{"benchmark":"infovqa","model":"llava-onevision-72b","score":74.9,"metric":"percent"},{"benchmark":"ocrbench","model":"llava-onevision-72b","score":74.1,"metric":"percent"},{"benchmark":"ai2d","model":"nvlm-d-72b","score":85.2,"metric":"percent"},{"benchmark":"chartqa","model":"nvlm-d-72b","score":86,"metric":"percent"},{"benchmark":"textvqa","model":"nvlm-d-72b","score":82.1,"metric":"percent"},{"benchmark":"docvqa","model":"nvlm-d-72b","score":92.6,"metric":"percent"},{"benchmark":"ocrbench","model":"nvlm-d-72b","score":85.3,"metric":"percent"},{"benchmark":"infovqa","model":"molmo-72b","score":81.9,"metric":"percent"},{"benchmark":"infovqa","model":"qwen2-vl-72b","score":84.5,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen2-vl-72b","score":87.7,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"qwen2-vl-72b","score":91.3,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2-llama-3-76b","score":82,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2-llama-3-76b","score":83.9,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2-llama-3-76b","score":69.7,"metric":"percent"},{"benchmark":"charxiv-dq","model":"internvl2-llama-3-76b","score":75.2,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2-llama-3-76b","score":83.2,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2.5-78b","score":89.1,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2.5-78b","score":88.3,"metric":"percent"},{"benchmark":"textvqa","model":"internvl2.5-78b","score":83.4,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2.5-78b","score":95.1,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2.5-78b","score":84.1,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2.5-78b","score":85.4,"metric":"percent"},{"benchmark":"seed-bench-2-plus","model":"internvl2.5-78b","score":71.3,"metric":"percent"},{"benchmark":"vcr-en-easy","model":"internvl2.5-78b","score":95.7,"metric":"percent"},{"benchmark":"blink","model":"llava-onevision-0.5b","score":52.1,"metric":"percent"},{"benchmark":"mantis","model":"llava-onevision-0.5b","score":39.6,"metric":"percent"},{"benchmark":"muirbench","model":"llava-onevision-0.5b","score":25.5,"metric":"percent"},{"benchmark":"blink","model":"internvl2-1b","score":38.6,"metric":"percent"},{"benchmark":"mantis","model":"internvl2-1b","score":46.1,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2-1b","score":37.3,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2-1b","score":29.3,"metric":"percent"},{"benchmark":"mirb","model":"internvl2-1b","score":31.5,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2-1b","score":40.2,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2-1b","score":17.8,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2-1b","score":55.6,"metric":"percent"},{"benchmark":"blink","model":"internvl2.5-1b","score":42,"metric":"percent"},{"benchmark":"mantis","model":"internvl2.5-1b","score":51.2,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2.5-1b","score":38.5,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2.5-1b","score":29.9,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2.5-1b","score":50.3,"metric":"percent"},{"benchmark":"mirb","model":"internvl2.5-1b","score":35.6,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2.5-1b","score":57.5,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2.5-1b","score":44.2,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2.5-1b","score":43.4,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2.5-1b","score":59,"metric":"percent"},{"benchmark":"blink","model":"qwen2-vl-2b","score":44.4,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen2-vl-2b","score":55.1,"metric":"percent"},{"benchmark":"realworldqa","model":"qwen2-vl-2b","score":62.6,"metric":"percent"},{"benchmark":"blink","model":"internvl2-2b","score":43.8,"metric":"percent"},{"benchmark":"mantis","model":"internvl2-2b","score":48.4,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2-2b","score":39.8,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2-2b","score":32.5,"metric":"percent"},{"benchmark":"mirb","model":"internvl2-2b","score":32.1,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2-2b","score":47.3,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2-2b","score":31.8,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2-2b","score":56.8,"metric":"percent"},{"benchmark":"blink","model":"internvl2.5-2b","score":44,"metric":"percent"},{"benchmark":"mantis","model":"internvl2.5-2b","score":54.8,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2.5-2b","score":43.5,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2.5-2b","score":40.6,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2.5-2b","score":54.5,"metric":"percent"},{"benchmark":"mirb","model":"internvl2.5-2b","score":36.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2.5-2b","score":48.8,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2.5-2b","score":44.2,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2.5-2b","score":62.2,"metric":"percent"},{"benchmark":"blink","model":"phi-3.5-vision-instruct","score":58.3,"metric":"percent"},{"benchmark":"r-bench","model":"phi-3.5-vision-instruct","score":55.5,"metric":"percent"},{"benchmark":"blink","model":"internvl2-4b","score":46.1,"metric":"percent"},{"benchmark":"mantis","model":"internvl2-4b","score":61.3,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2-4b","score":43.3,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2-4b","score":40.5,"metric":"percent"},{"benchmark":"mirb","model":"internvl2-4b","score":39.9,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2-4b","score":52.1,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2-4b","score":44.2,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2-4b","score":64.5,"metric":"percent"},{"benchmark":"blink","model":"internvl2.5-4b","score":50.8,"metric":"percent"},{"benchmark":"mantis","model":"internvl2.5-4b","score":62.7,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2.5-4b","score":43.8,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2.5-4b","score":45.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2.5-4b","score":62.4,"metric":"percent"},{"benchmark":"mirb","model":"internvl2.5-4b","score":51.7,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2.5-4b","score":55.3,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2.5-4b","score":49.4,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2.5-4b","score":66.1,"metric":"percent"},{"benchmark":"blink","model":"qwen2-vl-7b","score":53.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen2-vl-7b","score":64,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"qwen2-vl-7b","score":56.5,"metric":"percent"},{"benchmark":"r-bench","model":"qwen2-vl-7b","score":64,"metric":"percent"},{"benchmark":"mantis","model":"minicpm-v-2_6","score":69,"metric":"percent"},{"benchmark":"mantis","model":"internvl2-8b","score":65.4,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2-8b","score":42,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2-8b","score":48.7,"metric":"percent"},{"benchmark":"mirb","model":"internvl2-8b","score":50,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2-8b","score":53.5,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2-8b","score":54.4,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2-8b","score":67.9,"metric":"percent"},{"benchmark":"blink","model":"internvl2.5-8b","score":54.8,"metric":"percent"},{"benchmark":"mantis","model":"internvl2.5-8b","score":67.7,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2.5-8b","score":46.7,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2.5-8b","score":51.1,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2.5-8b","score":62.3,"metric":"percent"},{"benchmark":"mirb","model":"internvl2.5-8b","score":52.5,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2.5-8b","score":70.1,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2.5-8b","score":59.1,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2.5-8b","score":62,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2.5-8b","score":70.1,"metric":"percent"},{"benchmark":"blink","model":"internvl-chat-v1.5","score":46.6,"metric":"percent"},{"benchmark":"mantis","model":"internvl-chat-v1.5","score":66.8,"metric":"percent"},{"benchmark":"mmiu","model":"internvl-chat-v1.5","score":37.4,"metric":"percent"},{"benchmark":"muirbench","model":"internvl-chat-v1.5","score":38.5,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl-chat-v1.5","score":58,"metric":"percent"},{"benchmark":"mirb","model":"internvl-chat-v1.5","score":50.3,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl-chat-v1.5","score":49.4,"metric":"percent"},{"benchmark":"wildvision","model":"internvl-chat-v1.5","score":56.6,"metric":"percent"},{"benchmark":"r-bench","model":"internvl-chat-v1.5","score":67.9,"metric":"percent"},{"benchmark":"blink","model":"internvl2-26b","score":56.2,"metric":"percent"},{"benchmark":"mantis","model":"internvl2-26b","score":69.6,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2-26b","score":42.6,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2-26b","score":50.6,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2-26b","score":60.6,"metric":"percent"},{"benchmark":"mirb","model":"internvl2-26b","score":53.7,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-26b","score":68.3,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2-26b","score":58.7,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2-26b","score":62.2,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2-26b","score":70.1,"metric":"percent"},{"benchmark":"blink","model":"internvl2.5-26b","score":61.8,"metric":"percent"},{"benchmark":"mantis","model":"internvl2.5-26b","score":75.6,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2.5-26b","score":49.4,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2.5-26b","score":61.1,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2.5-26b","score":66.9,"metric":"percent"},{"benchmark":"mirb","model":"internvl2.5-26b","score":55.7,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2.5-26b","score":61.8,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2.5-26b","score":65.2,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2.5-26b","score":72.9,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"cambrian-34b","score":44.1,"metric":"percent"},{"benchmark":"blink","model":"internvl2-40b","score":57.2,"metric":"percent"},{"benchmark":"mantis","model":"internvl2-40b","score":71.4,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2-40b","score":47.9,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2-40b","score":54.4,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2-40b","score":66.2,"metric":"percent"},{"benchmark":"mirb","model":"internvl2-40b","score":55.2,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-40b","score":71.8,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2-40b","score":61.8,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2-40b","score":63.2,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2-40b","score":73.3,"metric":"percent"},{"benchmark":"blink","model":"internvl2.5-38b","score":63.2,"metric":"percent"},{"benchmark":"mantis","model":"internvl2.5-38b","score":78.3,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2.5-38b","score":55.3,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2.5-38b","score":62.7,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2.5-38b","score":70,"metric":"percent"},{"benchmark":"mirb","model":"internvl2.5-38b","score":61.2,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2.5-38b","score":73.5,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2.5-38b","score":64,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2.5-38b","score":66.4,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2.5-38b","score":72.1,"metric":"percent"},{"benchmark":"blink","model":"gpt-4v","score":54.6,"metric":"percent"},{"benchmark":"mantis","model":"gpt-4v","score":62.7,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-4v","score":62.3,"metric":"percent"},{"benchmark":"mirb","model":"gpt-4v","score":53.1,"metric":"percent"},{"benchmark":"wildvision","model":"gpt-4v","score":71.8,"metric":"percent"},{"benchmark":"r-bench","model":"gpt-4v","score":65.6,"metric":"percent"},{"benchmark":"blink","model":"gpt-4o-2024-05-13","score":68,"metric":"percent"},{"benchmark":"mmiu","model":"gpt-4o-2024-05-13","score":55.7,"metric":"percent"},{"benchmark":"muirbench","model":"gpt-4o-2024-05-13","score":68,"metric":"percent"},{"benchmark":"mmt-bench","model":"gpt-4o-2024-05-13","score":65.4,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-4o-2024-05-13","score":75.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gpt-4o-2024-05-13","score":45.2,"metric":"percent"},{"benchmark":"wildvision","model":"gpt-4o-2024-05-13","score":80.6,"metric":"percent"},{"benchmark":"r-bench","model":"gpt-4o-2024-05-13","score":77.7,"metric":"percent"},{"benchmark":"mmiu","model":"claude-3.5-sonnet-20240620","score":53.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"claude-3.5-sonnet-20240620","score":51.6,"metric":"percent"},{"benchmark":"mmiu","model":"gemini-1.5-pro","score":53.4,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"gemini-1.5-pro","score":38.2,"metric":"percent"},{"benchmark":"blink","model":"llava-onevision-72b","score":55.4,"metric":"percent"},{"benchmark":"mantis","model":"llava-onevision-72b","score":77.6,"metric":"percent"},{"benchmark":"muirbench","model":"llava-onevision-72b","score":54.8,"metric":"percent"},{"benchmark":"mmt-bench","model":"qwen2-vl-72b","score":71.8,"metric":"percent"},{"benchmark":"blink","model":"internvl2-llama-3-76b","score":56.8,"metric":"percent"},{"benchmark":"mantis","model":"internvl2-llama-3-76b","score":73.7,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2-llama-3-76b","score":44.2,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2-llama-3-76b","score":51.2,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2-llama-3-76b","score":67.4,"metric":"percent"},{"benchmark":"mirb","model":"internvl2-llama-3-76b","score":58.2,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2-llama-3-76b","score":72.2,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2-llama-3-76b","score":63,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2-llama-3-76b","score":65.8,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2-llama-3-76b","score":74.1,"metric":"percent"},{"benchmark":"blink","model":"internvl2.5-78b","score":63.8,"metric":"percent"},{"benchmark":"mantis","model":"internvl2.5-78b","score":77,"metric":"percent"},{"benchmark":"mmiu","model":"internvl2.5-78b","score":55.8,"metric":"percent"},{"benchmark":"muirbench","model":"internvl2.5-78b","score":63.5,"metric":"percent"},{"benchmark":"mmt-bench","model":"internvl2.5-78b","score":70.8,"metric":"percent"},{"benchmark":"mirb","model":"internvl2.5-78b","score":61.1,"metric":"percent"},{"benchmark":"realworldqa","model":"internvl2.5-78b","score":78.7,"metric":"percent"},{"benchmark":"mme-realworld-en","model":"internvl2.5-78b","score":62.9,"metric":"percent"},{"benchmark":"wildvision","model":"internvl2.5-78b","score":71.4,"metric":"percent"},{"benchmark":"r-bench","model":"internvl2.5-78b","score":77.2,"metric":"percent"},{"benchmark":"mme-elo","model":"llava-onevision-0.5b","score":1438,"metric":"points"},{"benchmark":"mmvet","model":"llava-onevision-0.5b","score":32.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"llava-onevision-0.5b","score":27.9,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-1b","score":1794.4,"metric":"points"},{"benchmark":"mmvet","model":"internvl2-1b","score":32.7,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2-1b","score":36.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2-1b","score":34,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2-1b","score":2.25,"metric":"score"},{"benchmark":"crpe","model":"internvl2-1b","score":57.5,"metric":"percent"},{"benchmark":"pope","model":"internvl2-1b","score":87.3,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2.5-1b","score":1950.5,"metric":"points"},{"benchmark":"mmbench","model":"internvl2.5-1b","score":70.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2.5-1b","score":66.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-1b","score":68.4,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2.5-1b","score":48.8,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2.5-1b","score":43.2,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2.5-1b","score":50.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2.5-1b","score":39,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2.5-1b","score":2.49,"metric":"score"},{"benchmark":"crpe","model":"internvl2.5-1b","score":60.9,"metric":"percent"},{"benchmark":"pope","model":"internvl2.5-1b","score":89.9,"metric":"percent"},{"benchmark":"mmvet","model":"qwen2-vl-2b","score":49.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2-vl-2b","score":41.7,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-2b","score":1876.8,"metric":"points"},{"benchmark":"mmvet","model":"internvl2-2b","score":39.5,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2-2b","score":39.6,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-2b","score":50.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2-2b","score":37.9,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2-2b","score":2.52,"metric":"score"},{"benchmark":"crpe","model":"internvl2-2b","score":66.3,"metric":"percent"},{"benchmark":"pope","model":"internvl2-2b","score":88.3,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2.5-2b","score":2138.2,"metric":"points"},{"benchmark":"mmbench","model":"internvl2.5-2b","score":74.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2.5-2b","score":71.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-2b","score":72.2,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2.5-2b","score":60.8,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2.5-2b","score":52.3,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2.5-2b","score":53.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2.5-2b","score":42.6,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2.5-2b","score":2.94,"metric":"score"},{"benchmark":"crpe","model":"internvl2.5-2b","score":70.2,"metric":"percent"},{"benchmark":"pope","model":"internvl2.5-2b","score":90.6,"metric":"percent"},{"benchmark":"mmvet","model":"phi-3.5-vision-instruct","score":43.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"phi-3.5-vision-instruct","score":40.5,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-4b","score":2059.8,"metric":"points"},{"benchmark":"mmvet","model":"internvl2-4b","score":51,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2-4b","score":46.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2-4b","score":41.9,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2-4b","score":2.75,"metric":"score"},{"benchmark":"crpe","model":"internvl2-4b","score":71.1,"metric":"percent"},{"benchmark":"pope","model":"internvl2-4b","score":87.2,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2.5-4b","score":2337.5,"metric":"points"},{"benchmark":"mmbench","model":"internvl2.5-4b","score":81.1,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2.5-4b","score":79.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-4b","score":79.3,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2.5-4b","score":60.6,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2.5-4b","score":55.4,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2.5-4b","score":58.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2.5-4b","score":46.3,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2.5-4b","score":3.31,"metric":"score"},{"benchmark":"crpe","model":"internvl2.5-4b","score":75.5,"metric":"percent"},{"benchmark":"pope","model":"internvl2.5-4b","score":90.9,"metric":"percent"},{"benchmark":"mmhal-bench","model":"qwen2-vl-7b","score":3.4,"metric":"score"},{"benchmark":"crpe","model":"qwen2-vl-7b","score":74.4,"metric":"percent"},{"benchmark":"pope","model":"qwen2-vl-7b","score":88.1,"metric":"percent"},{"benchmark":"mmhal-bench","model":"minicpm-v-2_6","score":3.6,"metric":"score"},{"benchmark":"crpe","model":"minicpm-v-2_6","score":75.2,"metric":"percent"},{"benchmark":"pope","model":"minicpm-v-2_6","score":87.3,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-8b","score":2210.3,"metric":"points"},{"benchmark":"mmvet","model":"internvl2-8b","score":54.2,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2-8b","score":52.3,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-8b","score":62,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2-8b","score":45.2,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2-8b","score":3.33,"metric":"score"},{"benchmark":"crpe","model":"internvl2-8b","score":75.8,"metric":"percent"},{"benchmark":"pope","model":"internvl2-8b","score":86.9,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2.5-8b","score":2344.1,"metric":"points"},{"benchmark":"mmbench","model":"internvl2.5-8b","score":84.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2.5-8b","score":82.6,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2.5-8b","score":62.8,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2.5-8b","score":58.1,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2.5-8b","score":62.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2.5-8b","score":50.1,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2.5-8b","score":3.65,"metric":"score"},{"benchmark":"crpe","model":"internvl2.5-8b","score":78.4,"metric":"percent"},{"benchmark":"pope","model":"internvl2.5-8b","score":90.6,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl-chat-v1.5","score":2194.2,"metric":"points"},{"benchmark":"mmvet","model":"internvl-chat-v1.5","score":61.5,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl-chat-v1.5","score":51.5,"metric":"percent"},{"benchmark":"mmstar","model":"internvl-chat-v1.5","score":57.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl-chat-v1.5","score":50.3,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl-chat-v1.5","score":3.11,"metric":"score"},{"benchmark":"crpe","model":"internvl-chat-v1.5","score":75.4,"metric":"percent"},{"benchmark":"pope","model":"internvl-chat-v1.5","score":88.4,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-26b","score":2260.7,"metric":"points"},{"benchmark":"mmbench","model":"internvl2-26b","score":83.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2-26b","score":82,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2-26b","score":62.1,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2-26b","score":57.2,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-26b","score":61.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2-26b","score":50.7,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2-26b","score":3.55,"metric":"score"},{"benchmark":"crpe","model":"internvl2-26b","score":75.6,"metric":"percent"},{"benchmark":"pope","model":"internvl2-26b","score":88,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2.5-26b","score":2373.3,"metric":"points"},{"benchmark":"mmbench","model":"internvl2.5-26b","score":85.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2.5-26b","score":85.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-26b","score":84.2,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2.5-26b","score":65,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2.5-26b","score":60.8,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2.5-26b","score":66.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2.5-26b","score":55,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2.5-26b","score":3.7,"metric":"score"},{"benchmark":"crpe","model":"internvl2.5-26b","score":79.1,"metric":"percent"},{"benchmark":"pope","model":"internvl2.5-26b","score":90.6,"metric":"percent"},{"benchmark":"mmbench","model":"cambrian-34b","score":80.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"cambrian-34b","score":79.2,"metric":"percent"},{"benchmark":"mmvet","model":"cambrian-34b","score":53.2,"metric":"percent"},{"benchmark":"mmstar","model":"cambrian-34b","score":54.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"cambrian-34b","score":41.6,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-40b","score":2307.5,"metric":"points"},{"benchmark":"mmbench","model":"internvl2-40b","score":86.8,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2-40b","score":86.5,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2-40b","score":65.5,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2-40b","score":63.8,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-40b","score":65.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2-40b","score":56.9,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2-40b","score":3.75,"metric":"score"},{"benchmark":"crpe","model":"internvl2-40b","score":77.6,"metric":"percent"},{"benchmark":"pope","model":"internvl2-40b","score":88.4,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2.5-38b","score":2455.8,"metric":"points"},{"benchmark":"mmbench","model":"internvl2.5-38b","score":86.5,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2.5-38b","score":86.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-38b","score":85.5,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2.5-38b","score":68.8,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2.5-38b","score":62.1,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2.5-38b","score":67.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2.5-38b","score":56.8,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2.5-38b","score":3.71,"metric":"score"},{"benchmark":"crpe","model":"internvl2.5-38b","score":78.3,"metric":"percent"},{"benchmark":"pope","model":"internvl2.5-38b","score":90.7,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4v","score":67.5,"metric":"percent"},{"benchmark":"mmvet-v2","model":"gpt-4v","score":66.3,"metric":"percent"},{"benchmark":"mmbench","model":"gpt-4o-2024-05-13","score":83.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gpt-4o-2024-05-13","score":82.1,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4o-2024-05-13","score":83.1,"metric":"percent"},{"benchmark":"mmvet-v2","model":"gpt-4o-2024-05-13","score":71,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4o-2024-05-13","score":64.7,"metric":"percent"},{"benchmark":"mmhal-bench","model":"gpt-4o-2024-05-13","score":4,"metric":"score"},{"benchmark":"crpe","model":"gpt-4o-2024-05-13","score":76.6,"metric":"percent"},{"benchmark":"pope","model":"gpt-4o-2024-05-13","score":86.9,"metric":"percent"},{"benchmark":"mmvet","model":"claude-3-opus","score":51.7,"metric":"percent"},{"benchmark":"mmvet-v2","model":"claude-3-opus","score":55.8,"metric":"percent"},{"benchmark":"mmstar","model":"claude-3-opus","score":45.7,"metric":"percent"},{"benchmark":"mmbench","model":"claude-3.5-sonnet-20240620","score":82.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"claude-3.5-sonnet-20240620","score":83.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"claude-3.5-sonnet-20240620","score":80.9,"metric":"percent"},{"benchmark":"mmvet","model":"claude-3.5-sonnet-20240620","score":70.1,"metric":"percent"},{"benchmark":"mmvet-v2","model":"claude-3.5-sonnet-20240620","score":71.8,"metric":"percent"},{"benchmark":"mmstar","model":"claude-3.5-sonnet-20240620","score":65.1,"metric":"percent"},{"benchmark":"hallusionbench","model":"claude-3.5-sonnet-20240620","score":55.5,"metric":"percent"},{"benchmark":"mmbench","model":"gemini-1.5-pro","score":73.9,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gemini-1.5-pro","score":73.8,"metric":"percent"},{"benchmark":"mmvet-v2","model":"gemini-1.5-pro","score":66.9,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-1.5-pro","score":59.1,"metric":"percent"},{"benchmark":"mme-elo","model":"llava-onevision-72b","score":2261,"metric":"points"},{"benchmark":"mmbench","model":"llava-onevision-72b","score":85.8,"metric":"percent"},{"benchmark":"mmbench-cn","model":"llava-onevision-72b","score":85.3,"metric":"percent"},{"benchmark":"mmvet","model":"llava-onevision-72b","score":60.6,"metric":"percent"},{"benchmark":"mmstar","model":"llava-onevision-72b","score":65.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"llava-onevision-72b","score":49,"metric":"percent"},{"benchmark":"mme-elo","model":"qwen2-vl-72b","score":2482.7,"metric":"points"},{"benchmark":"mmbench","model":"qwen2-vl-72b","score":86.5,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen2-vl-72b","score":86.6,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"qwen2-vl-72b","score":85.9,"metric":"percent"},{"benchmark":"mmvet","model":"qwen2-vl-72b","score":74,"metric":"percent"},{"benchmark":"mmvet-v2","model":"qwen2-vl-72b","score":66.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen2-vl-72b","score":68.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen2-vl-72b","score":58.1,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-llama-3-76b","score":2414.7,"metric":"points"},{"benchmark":"mmbench","model":"internvl2-llama-3-76b","score":86.5,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2-llama-3-76b","score":86.3,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2-llama-3-76b","score":65.7,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2-llama-3-76b","score":68.4,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-llama-3-76b","score":67.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2-llama-3-76b","score":55.2,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2-llama-3-76b","score":3.83,"metric":"score"},{"benchmark":"crpe","model":"internvl2-llama-3-76b","score":77.6,"metric":"percent"},{"benchmark":"pope","model":"internvl2-llama-3-76b","score":89,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2.5-78b","score":2494.5,"metric":"points"},{"benchmark":"mmbench","model":"internvl2.5-78b","score":88.3,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl2.5-78b","score":88.5,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internvl2.5-78b","score":87.4,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2.5-78b","score":72.3,"metric":"percent"},{"benchmark":"mmvet-v2","model":"internvl2.5-78b","score":65.5,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2.5-78b","score":69.5,"metric":"percent"},{"benchmark":"hallusionbench","model":"internvl2.5-78b","score":57.4,"metric":"percent"},{"benchmark":"mmhal-bench","model":"internvl2.5-78b","score":3.89,"metric":"score"},{"benchmark":"crpe","model":"internvl2.5-78b","score":78.8,"metric":"percent"},{"benchmark":"pope","model":"internvl2.5-78b","score":90.8,"metric":"percent"},{"benchmark":"refcoco","model":"internvl2.5-8b","score":90.3,"metric":"percent"},{"benchmark":"refcocoplus","model":"internvl2.5-8b","score":85.2,"metric":"percent"},{"benchmark":"refcocog","model":"internvl2.5-8b","score":86.7,"metric":"percent"},{"benchmark":"refcoco","model":"qwen2-vl-72b","score":93.2,"metric":"percent"},{"benchmark":"refcocoplus","model":"qwen2-vl-72b","score":90.1,"metric":"percent"},{"benchmark":"refcocog","model":"qwen2-vl-72b","score":89.9,"metric":"percent"},{"benchmark":"refcoco","model":"internvl2-llama-3-76b","score":92.2,"metric":"percent"},{"benchmark":"refcocoplus","model":"internvl2-llama-3-76b","score":88.8,"metric":"percent"},{"benchmark":"refcocog","model":"internvl2-llama-3-76b","score":89.5,"metric":"percent"},{"benchmark":"refcoco","model":"internvl2.5-78b","score":93.7,"metric":"percent"},{"benchmark":"refcocoplus","model":"internvl2.5-78b","score":90.4,"metric":"percent"},{"benchmark":"refcocog","model":"internvl2.5-78b","score":92.7,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2-1b","score":12.6,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2.5-1b","score":21.4,"metric":"percent"},{"benchmark":"mtvqa","model":"qwen2-vl-2b","score":20,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2-2b","score":10.9,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2.5-2b","score":21.8,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2-4b","score":15.3,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2.5-4b","score":28.4,"metric":"percent"},{"benchmark":"mtvqa","model":"qwen2-vl-7b","score":25.6,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2-8b","score":20.9,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2.5-8b","score":27.6,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl-chat-v1.5","score":20.5,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2-26b","score":17.7,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2.5-26b","score":28.5,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2-40b","score":20.6,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2.5-38b","score":31.7,"metric":"percent"},{"benchmark":"mtvqa","model":"gpt-4v","score":22,"metric":"percent"},{"benchmark":"mtvqa","model":"qwen2-vl-72b","score":30.9,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2-llama-3-76b","score":22,"metric":"percent"},{"benchmark":"mtvqa","model":"internvl2.5-78b","score":31.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2-1b","score":42.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2-1b","score":45.4,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2-1b","score":57.5,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2-1b","score":1.14,"metric":"score"},{"benchmark":"mlvu","model":"internvl2-1b","score":51.6,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2-1b","score":43.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2.5-1b","score":50.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2.5-1b","score":52.3,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2.5-1b","score":64.3,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2.5-1b","score":1.36,"metric":"score"},{"benchmark":"mlvu","model":"internvl2.5-1b","score":57.3,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2.5-1b","score":47.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen2-vl-2b","score":55.6,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen2-vl-2b","score":60.4,"metric":"percent"},{"benchmark":"mvbench","model":"qwen2-vl-2b","score":63.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2-2b","score":46.2,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2-2b","score":49.1,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2-2b","score":60.2,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2-2b","score":1.3,"metric":"score"},{"benchmark":"mlvu","model":"internvl2-2b","score":54.3,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2-2b","score":46,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2.5-2b","score":51.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2.5-2b","score":54.1,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2.5-2b","score":68.8,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2.5-2b","score":1.44,"metric":"score"},{"benchmark":"mlvu","model":"internvl2.5-2b","score":61.4,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2.5-2b","score":52,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2-4b","score":53.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2-4b","score":57,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2-4b","score":64,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2-4b","score":1.45,"metric":"score"},{"benchmark":"mlvu","model":"internvl2-4b","score":59.9,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2-4b","score":53,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2.5-4b","score":62.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2.5-4b","score":63.6,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2.5-4b","score":71.6,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2.5-4b","score":1.73,"metric":"score"},{"benchmark":"mlvu","model":"internvl2.5-4b","score":68.3,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2.5-4b","score":55.2,"metric":"percent"},{"benchmark":"videomme-nosub","model":"videochat2-hd-mistral","score":45.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"videochat2-hd-mistral","score":55.7,"metric":"percent"},{"benchmark":"mvbench","model":"videochat2-hd-mistral","score":62.3,"metric":"percent"},{"benchmark":"mmbench-video","model":"videochat2-hd-mistral","score":1.22,"metric":"score"},{"benchmark":"mlvu","model":"videochat2-hd-mistral","score":47.9,"metric":"percent"},{"benchmark":"mmbench-video","model":"minicpm-v-2_6","score":1.7,"metric":"score"},{"benchmark":"longvideobench","model":"minicpm-v-2_6","score":54.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"llava-onevision-7b","score":58.2,"metric":"percent"},{"benchmark":"mvbench","model":"llava-onevision-7b","score":56.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen2-vl-7b","score":63.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen2-vl-7b","score":69,"metric":"percent"},{"benchmark":"mmbench-video","model":"qwen2-vl-7b","score":1.44,"metric":"score"},{"benchmark":"longvideobench","model":"qwen2-vl-7b","score":55.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2-8b","score":56.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2-8b","score":59.3,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2-8b","score":65.8,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2-8b","score":1.57,"metric":"score"},{"benchmark":"mlvu","model":"internvl2-8b","score":64,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2-8b","score":54.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2.5-8b","score":64.2,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2.5-8b","score":66.9,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2.5-8b","score":72,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2.5-8b","score":1.68,"metric":"score"},{"benchmark":"mlvu","model":"internvl2.5-8b","score":68.9,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2.5-8b","score":60,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2-26b","score":57,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2-26b","score":60.2,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2-26b","score":67.5,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2-26b","score":1.67,"metric":"score"},{"benchmark":"mlvu","model":"internvl2-26b","score":64.2,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2-26b","score":56.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2.5-26b","score":66.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2.5-26b","score":69.2,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2.5-26b","score":75.2,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2.5-26b","score":1.86,"metric":"score"},{"benchmark":"mlvu","model":"internvl2.5-26b","score":72.3,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2.5-26b","score":59.9,"metric":"percent"},{"benchmark":"videomme-nosub","model":"oryx-1.5-32b","score":67.3,"metric":"percent"},{"benchmark":"videomme-sub","model":"oryx-1.5-32b","score":74.9,"metric":"percent"},{"benchmark":"mvbench","model":"oryx-1.5-32b","score":70.1,"metric":"percent"},{"benchmark":"mmbench-video","model":"oryx-1.5-32b","score":1.52,"metric":"score"},{"benchmark":"mlvu","model":"oryx-1.5-32b","score":72.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"vila1.5-40b","score":60.1,"metric":"percent"},{"benchmark":"videomme-sub","model":"vila1.5-40b","score":61.1,"metric":"percent"},{"benchmark":"mmbench-video","model":"vila1.5-40b","score":1.61,"metric":"score"},{"benchmark":"mlvu","model":"vila1.5-40b","score":56.7,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2-40b","score":66.1,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2-40b","score":68.6,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2-40b","score":72,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2-40b","score":1.78,"metric":"score"},{"benchmark":"mlvu","model":"internvl2-40b","score":71,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2-40b","score":60.6,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2.5-38b","score":70.7,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2.5-38b","score":73.1,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2.5-38b","score":74.4,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2.5-38b","score":1.82,"metric":"score"},{"benchmark":"mlvu","model":"internvl2.5-38b","score":75.3,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2.5-38b","score":63.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-4v","score":59.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-4v","score":63.3,"metric":"percent"},{"benchmark":"mmbench-video","model":"gpt-4v","score":1.53,"metric":"score"},{"benchmark":"mlvu","model":"gpt-4v","score":49.2,"metric":"percent"},{"benchmark":"longvideobench","model":"gpt-4v","score":59.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"gpt-4o-2024-05-13","score":71.9,"metric":"percent"},{"benchmark":"videomme-sub","model":"gpt-4o-2024-05-13","score":77.2,"metric":"percent"},{"benchmark":"mmbench-video","model":"gpt-4o-2024-05-13","score":1.63,"metric":"score"},{"benchmark":"mlvu","model":"gpt-4o-2024-05-13","score":64.6,"metric":"percent"},{"benchmark":"longvideobench","model":"gpt-4o-2024-05-13","score":66.7,"metric":"percent"},{"benchmark":"mmbench-video","model":"gpt-4o-2024-08-06","score":1.87,"metric":"score"},{"benchmark":"cgbench","model":"gpt-4o-2024-08-06","score":41.8,"metric":"percent"},{"benchmark":"videomme-sub","model":"gemini-1.5-pro","score":81.3,"metric":"percent"},{"benchmark":"mmbench-video","model":"gemini-1.5-pro","score":1.3,"metric":"score"},{"benchmark":"longvideobench","model":"gemini-1.5-pro","score":64,"metric":"percent"},{"benchmark":"cgbench","model":"gemini-1.5-pro","score":40.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"videollama2-72b","score":61.4,"metric":"percent"},{"benchmark":"videomme-sub","model":"videollama2-72b","score":63.1,"metric":"percent"},{"benchmark":"mvbench","model":"videollama2-72b","score":62,"metric":"percent"},{"benchmark":"videomme-nosub","model":"llava-onevision-72b","score":66.2,"metric":"percent"},{"benchmark":"videomme-sub","model":"llava-onevision-72b","score":69.5,"metric":"percent"},{"benchmark":"mvbench","model":"llava-onevision-72b","score":59.4,"metric":"percent"},{"benchmark":"mlvu","model":"llava-onevision-72b","score":66.4,"metric":"percent"},{"benchmark":"longvideobench","model":"llava-onevision-72b","score":61.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"qwen2-vl-72b","score":71.2,"metric":"percent"},{"benchmark":"videomme-sub","model":"qwen2-vl-72b","score":77.8,"metric":"percent"},{"benchmark":"mvbench","model":"qwen2-vl-72b","score":73.6,"metric":"percent"},{"benchmark":"mmbench-video","model":"qwen2-vl-72b","score":1.7,"metric":"score"},{"benchmark":"cgbench","model":"qwen2-vl-72b","score":41.3,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2-llama-3-76b","score":64.7,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2-llama-3-76b","score":67.8,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2-llama-3-76b","score":69.6,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2-llama-3-76b","score":1.71,"metric":"score"},{"benchmark":"mlvu","model":"internvl2-llama-3-76b","score":69.9,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2-llama-3-76b","score":61.1,"metric":"percent"},{"benchmark":"videomme-nosub","model":"internvl2.5-78b","score":72.1,"metric":"percent"},{"benchmark":"videomme-sub","model":"internvl2.5-78b","score":74,"metric":"percent"},{"benchmark":"mvbench","model":"internvl2.5-78b","score":76.4,"metric":"percent"},{"benchmark":"mmbench-video","model":"internvl2.5-78b","score":1.97,"metric":"score"},{"benchmark":"mlvu","model":"internvl2.5-78b","score":75.7,"metric":"percent"},{"benchmark":"longvideobench","model":"internvl2.5-78b","score":63.6,"metric":"percent"},{"benchmark":"cgbench","model":"internvl2.5-78b","score":42.2,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-chat-1.8b","score":47.3,"metric":"percent"},{"benchmark":"mmlu","model":"internvl2-2b","score":46.4,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2.5-1.8b-chat","score":50.5,"metric":"percent"},{"benchmark":"mmlu","model":"internvl2.5-2b","score":52.6,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2.5-7b-chat","score":72.8,"metric":"percent"},{"benchmark":"mmlu","model":"internvl2-8b","score":73.2,"metric":"percent"},{"benchmark":"mmlu","model":"internvl2.5-8b","score":74.6,"metric":"percent"},{"benchmark":"mmlu","model":"internvl2-26b","score":68.2,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2_5-20b-chat","score":73.3,"metric":"percent"},{"benchmark":"mmlu","model":"internvl2.5-26b","score":76.6,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-chat-1.8b","score":46.1,"metric":"percent"},{"benchmark":"cmmlu","model":"internvl2-2b","score":47.1,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2.5-1.8b-chat","score":62.7,"metric":"percent"},{"benchmark":"cmmlu","model":"internvl2.5-2b","score":57,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2.5-7b-chat","score":78.2,"metric":"percent"},{"benchmark":"cmmlu","model":"internvl2-8b","score":79.2,"metric":"percent"},{"benchmark":"cmmlu","model":"internvl2.5-8b","score":78.7,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-chat-20b","score":64.7,"metric":"percent"},{"benchmark":"cmmlu","model":"internvl2-26b","score":68.1,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2_5-20b-chat","score":79.4,"metric":"percent"},{"benchmark":"cmmlu","model":"internvl2.5-26b","score":81.9,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-chat-1.8b","score":48.6,"metric":"percent"},{"benchmark":"c-eval","model":"internvl2-2b","score":48.6,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2.5-1.8b-chat","score":60.4,"metric":"percent"},{"benchmark":"c-eval","model":"internvl2.5-2b","score":56.2,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2.5-7b-chat","score":77.9,"metric":"percent"},{"benchmark":"c-eval","model":"internvl2-8b","score":80.1,"metric":"percent"},{"benchmark":"c-eval","model":"internvl2.5-8b","score":79.7,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2-chat-20b","score":61.8,"metric":"percent"},{"benchmark":"c-eval","model":"internvl2-26b","score":67.7,"metric":"percent"},{"benchmark":"c-eval","model":"internlm2_5-20b-chat","score":80.2,"metric":"percent"},{"benchmark":"c-eval","model":"internvl2.5-26b","score":83.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-chat-1.8b","score":33.1,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internvl2-2b","score":32.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2.5-1.8b-chat","score":54.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internvl2.5-2b","score":52.6,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2.5-7b-chat","score":78.7,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internvl2-8b","score":75,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internvl2.5-8b","score":77.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2-chat-20b","score":63.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internvl2-26b","score":62.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internlm2_5-20b-chat","score":81,"metric":"percent"},{"benchmark":"gaokao-bench","model":"internvl2.5-26b","score":86.9,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-chat-1.8b","score":37.3,"metric":"percent"},{"benchmark":"triviaqa","model":"internvl2-2b","score":31.5,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2.5-1.8b-chat","score":32.3,"metric":"percent"},{"benchmark":"triviaqa","model":"internvl2.5-2b","score":31.2,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2.5-7b-chat","score":64,"metric":"percent"},{"benchmark":"triviaqa","model":"internvl2-8b","score":62,"metric":"percent"},{"benchmark":"triviaqa","model":"internvl2.5-8b","score":63.4,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2-chat-20b","score":61.8,"metric":"percent"},{"benchmark":"triviaqa","model":"internvl2-26b","score":61.8,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm2_5-20b-chat","score":67.3,"metric":"percent"},{"benchmark":"triviaqa","model":"internvl2.5-26b","score":69,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-chat-1.8b","score":15.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"internvl2-2b","score":13.2,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2.5-1.8b-chat","score":10.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"internvl2.5-2b","score":11.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2.5-7b-chat","score":21.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"internvl2-8b","score":28.1,"metric":"percent"},{"benchmark":"naturalquestions","model":"internvl2.5-8b","score":29.4,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2-chat-20b","score":23.6,"metric":"percent"},{"benchmark":"naturalquestions","model":"internvl2-26b","score":28.8,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm2_5-20b-chat","score":21.3,"metric":"percent"},{"benchmark":"naturalquestions","model":"internvl2.5-26b","score":36.1,"metric":"percent"},{"benchmark":"c3","model":"internlm2-chat-1.8b","score":75.8,"metric":"percent"},{"benchmark":"c3","model":"internvl2-2b","score":76.9,"metric":"percent"},{"benchmark":"c3","model":"internlm2.5-1.8b-chat","score":61.4,"metric":"percent"},{"benchmark":"c3","model":"internvl2.5-2b","score":78,"metric":"percent"},{"benchmark":"c3","model":"internlm2.5-7b-chat","score":88.1,"metric":"percent"},{"benchmark":"c3","model":"internvl2-8b","score":94.2,"metric":"percent"},{"benchmark":"c3","model":"internvl2.5-8b","score":94.7,"metric":"percent"},{"benchmark":"c3","model":"internlm2-chat-20b","score":92.2,"metric":"percent"},{"benchmark":"c3","model":"internvl2-26b","score":93.2,"metric":"percent"},{"benchmark":"c3","model":"internlm2_5-20b-chat","score":94,"metric":"percent"},{"benchmark":"c3","model":"internvl2.5-26b","score":95.8,"metric":"percent"},{"benchmark":"race","model":"internlm2-chat-1.8b","score":74,"metric":"percent"},{"benchmark":"race","model":"internvl2-2b","score":72.6,"metric":"percent"},{"benchmark":"race","model":"internlm2.5-1.8b-chat","score":78.5,"metric":"percent"},{"benchmark":"race","model":"internvl2.5-2b","score":77.4,"metric":"percent"},{"benchmark":"race","model":"internlm2.5-7b-chat","score":90.5,"metric":"percent"},{"benchmark":"race","model":"internvl2-8b","score":90.8,"metric":"percent"},{"benchmark":"race","model":"internvl2.5-8b","score":90.8,"metric":"percent"},{"benchmark":"race","model":"internlm2-chat-20b","score":86.2,"metric":"percent"},{"benchmark":"race","model":"internvl2-26b","score":86.5,"metric":"percent"},{"benchmark":"race","model":"internlm2_5-20b-chat","score":91.3,"metric":"percent"},{"benchmark":"race","model":"internvl2.5-26b","score":92.2,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-chat-1.8b","score":56.5,"metric":"percent"},{"benchmark":"winogrande","model":"internvl2-2b","score":58.7,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2.5-1.8b-chat","score":56.9,"metric":"percent"},{"benchmark":"winogrande","model":"internvl2.5-2b","score":59.1,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2.5-7b-chat","score":84.9,"metric":"percent"},{"benchmark":"winogrande","model":"internvl2-8b","score":85.9,"metric":"percent"},{"benchmark":"winogrande","model":"internvl2.5-8b","score":83.5,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2-chat-20b","score":76.4,"metric":"percent"},{"benchmark":"winogrande","model":"internvl2-26b","score":79.9,"metric":"percent"},{"benchmark":"winogrande","model":"internlm2_5-20b-chat","score":86.4,"metric":"percent"},{"benchmark":"winogrande","model":"internvl2.5-26b","score":87.9,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-chat-1.8b","score":57.9,"metric":"percent"},{"benchmark":"hellaswag","model":"internvl2-2b","score":53.7,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2.5-1.8b-chat","score":76.2,"metric":"percent"},{"benchmark":"hellaswag","model":"internvl2.5-2b","score":68.2,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2.5-7b-chat","score":94.8,"metric":"percent"},{"benchmark":"hellaswag","model":"internvl2-8b","score":94.9,"metric":"percent"},{"benchmark":"hellaswag","model":"internvl2.5-8b","score":94.1,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2-chat-20b","score":85.3,"metric":"percent"},{"benchmark":"hellaswag","model":"internvl2-26b","score":87.5,"metric":"percent"},{"benchmark":"hellaswag","model":"internlm2_5-20b-chat","score":95.9,"metric":"percent"},{"benchmark":"hellaswag","model":"internvl2.5-26b","score":95.8,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-chat-1.8b","score":37.9,"metric":"percent"},{"benchmark":"bbh","model":"internvl2-2b","score":36.3,"metric":"percent"},{"benchmark":"bbh","model":"internlm2.5-1.8b-chat","score":43.4,"metric":"percent"},{"benchmark":"bbh","model":"internvl2.5-2b","score":40.9,"metric":"percent"},{"benchmark":"bbh","model":"internlm2.5-7b-chat","score":73.1,"metric":"percent"},{"benchmark":"bbh","model":"internvl2-8b","score":72.7,"metric":"percent"},{"benchmark":"bbh","model":"internvl2.5-8b","score":73.4,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-chat-20b","score":70.1,"metric":"percent"},{"benchmark":"bbh","model":"internvl2-26b","score":69.8,"metric":"percent"},{"benchmark":"bbh","model":"internlm2_5-20b-chat","score":78.4,"metric":"percent"},{"benchmark":"bbh","model":"internvl2.5-26b","score":78.9,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-chat-1.8b","score":42.7,"metric":"percent"},{"benchmark":"gsm8k","model":"internvl2-2b","score":40.7,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2.5-1.8b-chat","score":53.3,"metric":"percent"},{"benchmark":"gsm8k","model":"internvl2.5-2b","score":55.1,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2.5-7b-chat","score":85.1,"metric":"percent"},{"benchmark":"gsm8k","model":"internvl2-8b","score":75.6,"metric":"percent"},{"benchmark":"gsm8k","model":"internvl2.5-8b","score":77.8,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-chat-20b","score":80.7,"metric":"percent"},{"benchmark":"gsm8k","model":"internvl2-26b","score":80,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2_5-20b-chat","score":88.5,"metric":"percent"},{"benchmark":"gsm8k","model":"internvl2.5-26b","score":82.9,"metric":"percent"},{"benchmark":"math","model":"internlm2-chat-1.8b","score":11,"metric":"percent"},{"benchmark":"math","model":"internvl2-2b","score":7,"metric":"percent"},{"benchmark":"math","model":"internlm2.5-1.8b-chat","score":39.5,"metric":"percent"},{"benchmark":"math","model":"internvl2.5-2b","score":33.5,"metric":"percent"},{"benchmark":"math","model":"internlm2.5-7b-chat","score":60.6,"metric":"percent"},{"benchmark":"math","model":"internvl2-8b","score":39.5,"metric":"percent"},{"benchmark":"math","model":"internvl2.5-8b","score":49.9,"metric":"percent"},{"benchmark":"math","model":"internlm2-chat-20b","score":34.9,"metric":"percent"},{"benchmark":"math","model":"internvl2-26b","score":35.5,"metric":"percent"},{"benchmark":"math","model":"internlm2_5-20b-chat","score":54.7,"metric":"percent"},{"benchmark":"math","model":"internvl2.5-26b","score":53.7,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-chat-1.8b","score":13.9,"metric":"percent"},{"benchmark":"theoremqa","model":"internvl2-2b","score":12.3,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2.5-1.8b-chat","score":11.4,"metric":"percent"},{"benchmark":"theoremqa","model":"internvl2.5-2b","score":12,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2.5-7b-chat","score":23.4,"metric":"percent"},{"benchmark":"theoremqa","model":"internvl2-8b","score":15.6,"metric":"percent"},{"benchmark":"theoremqa","model":"internvl2.5-8b","score":23.8,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2-chat-20b","score":22.1,"metric":"percent"},{"benchmark":"theoremqa","model":"internvl2-26b","score":15.3,"metric":"percent"},{"benchmark":"theoremqa","model":"internlm2_5-20b-chat","score":23.9,"metric":"percent"},{"benchmark":"theoremqa","model":"internvl2.5-26b","score":15.4,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-chat-1.8b","score":34.8,"metric":"percent"},{"benchmark":"humaneval","model":"internvl2-2b","score":32.3,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2.5-1.8b-chat","score":41.5,"metric":"percent"},{"benchmark":"humaneval","model":"internvl2.5-2b","score":52.4,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2.5-7b-chat","score":74.4,"metric":"percent"},{"benchmark":"humaneval","model":"internvl2-8b","score":69.5,"metric":"percent"},{"benchmark":"humaneval","model":"internvl2.5-8b","score":75,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-chat-20b","score":71.3,"metric":"percent"},{"benchmark":"humaneval","model":"internvl2-26b","score":67.1,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2_5-20b-chat","score":69.5,"metric":"percent"},{"benchmark":"humaneval","model":"internvl2.5-26b","score":68.9,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-chat-1.8b","score":40.9,"metric":"percent"},{"benchmark":"mbpp","model":"internvl2-2b","score":33.1,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2.5-1.8b-chat","score":42.8,"metric":"percent"},{"benchmark":"mbpp","model":"internvl2.5-2b","score":50.6,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2.5-7b-chat","score":63,"metric":"percent"},{"benchmark":"mbpp","model":"internvl2-8b","score":58.8,"metric":"percent"},{"benchmark":"mbpp","model":"internvl2.5-8b","score":68.5,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2-chat-20b","score":70.8,"metric":"percent"},{"benchmark":"mbpp","model":"internvl2-26b","score":66.2,"metric":"percent"},{"benchmark":"mbpp","model":"internlm2_5-20b-chat","score":70,"metric":"percent"},{"benchmark":"mbpp","model":"internvl2.5-26b","score":72,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4v","score":1926.5,"metric":"points"},{"benchmark":"seed-bench-img","model":"gpt-4v","score":69.1,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"gpt-4v","score":93.1,"metric":"percent"},{"benchmark":"q-bench","model":"gpt-4v","score":74.1,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4v","score":67.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4v","score":65.8,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-pro","score":73.9,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-pro","score":47.9,"metric":"percent"},{"benchmark":"mme-elo","model":"gemini-pro","score":1933.3,"metric":"points"},{"benchmark":"mmbench","model":"gemini-pro","score":73.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gemini-pro","score":74.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gemini-pro","score":70.7,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"gemini-pro","score":79.9,"metric":"percent"},{"benchmark":"q-bench","model":"gemini-pro","score":70.6,"metric":"percent"},{"benchmark":"mmvet","model":"gemini-pro","score":64.3,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-pro","score":63.9,"metric":"percent"},{"benchmark":"chartqa","model":"gemini-pro","score":74.1,"metric":"percent"},{"benchmark":"mmmu","model":"qwen-vl-plus","score":46.5,"metric":"percent"},{"benchmark":"mme-elo","model":"qwen-vl-plus","score":2183.3,"metric":"points"},{"benchmark":"llava-bench-in-the-wild","model":"qwen-vl-plus","score":73.7,"metric":"percent"},{"benchmark":"q-bench","model":"qwen-vl-plus","score":68.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen-vl-plus","score":56.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internlm-xcomposer2-vl-7b","score":57.6,"metric":"percent"},{"benchmark":"ai2d","model":"internlm-xcomposer2-vl-7b","score":78.7,"metric":"percent"},{"benchmark":"mmmu","model":"internlm-xcomposer2-vl-7b","score":42,"metric":"percent"},{"benchmark":"mme-elo","model":"internlm-xcomposer2-vl-7b","score":2242.7,"metric":"points"},{"benchmark":"mmbench","model":"internlm-xcomposer2-vl-7b","score":79.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internlm-xcomposer2-vl-7b","score":77.6,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internlm-xcomposer2-vl-7b","score":75.9,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"internlm-xcomposer2-vl-7b","score":81.8,"metric":"percent"},{"benchmark":"q-bench","model":"internlm-xcomposer2-vl-7b","score":72.5,"metric":"percent"},{"benchmark":"mmvet","model":"internlm-xcomposer2-vl-7b","score":51.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"internlm-xcomposer2-vl-7b","score":60.3,"metric":"percent"},{"benchmark":"chartqa","model":"internlm-xcomposer2-vl-7b","score":72.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"instructblip-7b","score":25.3,"metric":"percent"},{"benchmark":"mmmu","model":"instructblip-7b","score":30.6,"metric":"percent"},{"benchmark":"mmbench","model":"instructblip-7b","score":36,"metric":"percent"},{"benchmark":"mmbench-cn","model":"instructblip-7b","score":23.7,"metric":"percent"},{"benchmark":"seed-bench-img","model":"instructblip-7b","score":53.4,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"instructblip-7b","score":60.9,"metric":"percent"},{"benchmark":"q-bench","model":"instructblip-7b","score":55.9,"metric":"percent"},{"benchmark":"mmvet","model":"instructblip-7b","score":26.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"instructblip-7b","score":53.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"idefics-80b-instruct","score":26.2,"metric":"percent"},{"benchmark":"mmmu","model":"idefics-80b-instruct","score":24,"metric":"percent"},{"benchmark":"mmbench","model":"idefics-80b-instruct","score":54.5,"metric":"percent"},{"benchmark":"mmbench-cn","model":"idefics-80b-instruct","score":38.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"idefics-80b-instruct","score":52,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"idefics-80b-instruct","score":56.9,"metric":"percent"},{"benchmark":"mmvet","model":"idefics-80b-instruct","score":39.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"idefics-80b-instruct","score":46.1,"metric":"percent"},{"benchmark":"mmbench-cn","model":"qwen-vl-chat","score":56.7,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen-vl-chat","score":58.2,"metric":"percent"},{"benchmark":"q-bench","model":"qwen-vl-chat","score":61.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"qwen-vl-chat","score":56.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-v1-7b","score":23.7,"metric":"percent"},{"benchmark":"mmmu","model":"llava-v1-7b","score":32.3,"metric":"percent"},{"benchmark":"mmbench","model":"llava-v1-7b","score":34.1,"metric":"percent"},{"benchmark":"mmbench-cn","model":"llava-v1-7b","score":14.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"llava-v1-7b","score":25.5,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"llava-v1-7b","score":63,"metric":"percent"},{"benchmark":"q-bench","model":"llava-v1-7b","score":54.7,"metric":"percent"},{"benchmark":"mmvet","model":"llava-v1-7b","score":26.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"llava-v1-7b","score":44.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-1.5-13b","score":26.1,"metric":"percent"},{"benchmark":"mmbench","model":"llava-1.5-13b","score":67.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"llava-1.5-13b","score":63.6,"metric":"percent"},{"benchmark":"seed-bench-img","model":"llava-1.5-13b","score":68.2,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"llava-1.5-13b","score":70.7,"metric":"percent"},{"benchmark":"q-bench","model":"llava-1.5-13b","score":61.4,"metric":"percent"},{"benchmark":"mmvet","model":"llava-1.5-13b","score":35.4,"metric":"percent"},{"benchmark":"hallusionbench","model":"llava-1.5-13b","score":46.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"sharegpt4v-7b","score":25.8,"metric":"percent"},{"benchmark":"mmmu","model":"sharegpt4v-7b","score":36.6,"metric":"percent"},{"benchmark":"mmbench","model":"sharegpt4v-7b","score":68.8,"metric":"percent"},{"benchmark":"mmbench-cn","model":"sharegpt4v-7b","score":62.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"sharegpt4v-7b","score":69.7,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"sharegpt4v-7b","score":72.6,"metric":"percent"},{"benchmark":"mmvet","model":"sharegpt4v-7b","score":37.6,"metric":"percent"},{"benchmark":"hallusionbench","model":"sharegpt4v-7b","score":49.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"cogvlm-17b-chat","score":68.8,"metric":"percent"},{"benchmark":"hallusionbench","model":"cogvlm-17b-chat","score":55.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-internlm2-20b-qlora","score":24.6,"metric":"percent"},{"benchmark":"mmmu","model":"llava-internlm2-20b-qlora","score":39.4,"metric":"percent"},{"benchmark":"mmbench","model":"llava-internlm2-20b-qlora","score":75.1,"metric":"percent"},{"benchmark":"mmbench-cn","model":"llava-internlm2-20b-qlora","score":73.7,"metric":"percent"},{"benchmark":"seed-bench-img","model":"llava-internlm2-20b-qlora","score":70.2,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"llava-internlm2-20b-qlora","score":63.7,"metric":"percent"},{"benchmark":"mmvet","model":"llava-internlm2-20b-qlora","score":37.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"llava-internlm2-20b-qlora","score":47.7,"metric":"percent"},{"benchmark":"mathvista-mini","model":"monkey","score":34.8,"metric":"percent"},{"benchmark":"mmmu","model":"monkey","score":40.7,"metric":"percent"},{"benchmark":"mmbench","model":"monkey","score":72.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"monkey","score":67.5,"metric":"percent"},{"benchmark":"seed-bench-img","model":"monkey","score":68.9,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"monkey","score":33.5,"metric":"percent"},{"benchmark":"mmvet","model":"monkey","score":33,"metric":"percent"},{"benchmark":"hallusionbench","model":"monkey","score":58.4,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internlm-xcomposer","score":29.5,"metric":"percent"},{"benchmark":"mmmu","model":"internlm-xcomposer","score":35.6,"metric":"percent"},{"benchmark":"mmbench","model":"internlm-xcomposer","score":74.4,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internlm-xcomposer","score":72.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internlm-xcomposer","score":66.1,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"internlm-xcomposer","score":53.8,"metric":"percent"},{"benchmark":"q-bench","model":"internlm-xcomposer","score":64.4,"metric":"percent"},{"benchmark":"mmvet","model":"internlm-xcomposer","score":35.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"internlm-xcomposer","score":57,"metric":"percent"},{"benchmark":"pope","model":"instructblip-7b","score":78.9,"metric":"percent"},{"benchmark":"pope","model":"llava-v1-7b","score":80.2,"metric":"percent"},{"benchmark":"pope","model":"internlm-xcomposer2-vl-7b","score":87.7,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4v","score":51.6,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4v","score":57.1,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4v","score":75.5,"metric":"percent"},{"benchmark":"mmvet","model":"gpt-4v","score":56.8,"metric":"percent"},{"benchmark":"docvqa","model":"gemini-pro","score":88.1,"metric":"percent"},{"benchmark":"infovqa","model":"gemini-pro","score":75.2,"metric":"percent"},{"benchmark":"textvqa","model":"gemini-pro","score":74.6,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-pro","score":68,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-pro","score":42.6,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gemini-pro","score":45.8,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-pro","score":70.2,"metric":"percent"},{"benchmark":"hallusionbench","model":"gemini-pro","score":45.2,"metric":"percent"},{"benchmark":"docvqa","model":"internlm-xcomposer2-vl-7b","score":57.7,"metric":"percent"},{"benchmark":"infovqa","model":"internlm-xcomposer2-vl-7b","score":34.4,"metric":"percent"},{"benchmark":"textvqa","model":"internlm-xcomposer2-vl-7b","score":70.1,"metric":"percent"},{"benchmark":"ocrbench","model":"internlm-xcomposer2-vl-7b","score":53.2,"metric":"percent"},{"benchmark":"mmstar","model":"internlm-xcomposer2-vl-7b","score":55.4,"metric":"percent"},{"benchmark":"ai2d","model":"internlm-xcomposer2-vl-7b","score":81.2,"metric":"percent"},{"benchmark":"mmmu","model":"internlm-xcomposer2-vl-7b","score":41.4,"metric":"percent"},{"benchmark":"mme-elo","model":"internlm-xcomposer2-vl-7b","score":2220.4,"metric":"points"},{"benchmark":"mmbench","model":"internlm-xcomposer2-vl-7b","score":80.7,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internlm-xcomposer2-vl-7b","score":79.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internlm-xcomposer2-vl-7b","score":74.9,"metric":"percent"},{"benchmark":"mmvet","model":"internlm-xcomposer2-vl-7b","score":46.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"internlm-xcomposer2-vl-7b","score":41,"metric":"percent"},{"benchmark":"docvqa","model":"internlm-xcomposer2-4khd-7b","score":90,"metric":"percent"},{"benchmark":"chartqa","model":"internlm-xcomposer2-4khd-7b","score":81,"metric":"percent"},{"benchmark":"infovqa","model":"internlm-xcomposer2-4khd-7b","score":68.6,"metric":"percent"},{"benchmark":"textvqa","model":"internlm-xcomposer2-4khd-7b","score":77.2,"metric":"percent"},{"benchmark":"ocrbench","model":"internlm-xcomposer2-4khd-7b","score":67.5,"metric":"percent"},{"benchmark":"mmstar","model":"internlm-xcomposer2-4khd-7b","score":54.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internlm-xcomposer2-4khd-7b","score":57.8,"metric":"percent"},{"benchmark":"ai2d","model":"internlm-xcomposer2-4khd-7b","score":80.9,"metric":"percent"},{"benchmark":"mmmu","model":"internlm-xcomposer2-4khd-7b","score":39.7,"metric":"percent"},{"benchmark":"mme-elo","model":"internlm-xcomposer2-4khd-7b","score":2204.9,"metric":"points"},{"benchmark":"mmbench","model":"internlm-xcomposer2-4khd-7b","score":80.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internlm-xcomposer2-4khd-7b","score":77.7,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internlm-xcomposer2-4khd-7b","score":74.7,"metric":"percent"},{"benchmark":"q-bench","model":"internlm-xcomposer2-4khd-7b","score":71.8,"metric":"percent"},{"benchmark":"mmvet","model":"internlm-xcomposer2-4khd-7b","score":54.9,"metric":"percent"},{"benchmark":"hallusionbench","model":"internlm-xcomposer2-4khd-7b","score":40.9,"metric":"percent"},{"benchmark":"mmstar","model":"qwen-vl-chat","score":37.5,"metric":"percent"},{"benchmark":"ai2d","model":"qwen-vl-chat","score":63,"metric":"percent"},{"benchmark":"mmstar","model":"sharegpt4v-7b","score":33,"metric":"percent"},{"benchmark":"ai2d","model":"sharegpt4v-7b","score":58,"metric":"percent"},{"benchmark":"mmstar","model":"monkey","score":38.3,"metric":"percent"},{"benchmark":"ai2d","model":"monkey","score":62.5,"metric":"percent"},{"benchmark":"mmstar","model":"cogvlm-17b-chat","score":36.5,"metric":"percent"},{"benchmark":"ai2d","model":"cogvlm-17b-chat","score":63.3,"metric":"percent"},{"benchmark":"ai2d","model":"llava-internlm2-20b-qlora","score":65.4,"metric":"percent"},{"benchmark":"mmstar","model":"llava-1.5-13b","score":32.8,"metric":"percent"},{"benchmark":"mmstar","model":"llava-1.6-13b","score":38.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-1.6-13b","score":32.4,"metric":"percent"},{"benchmark":"ai2d","model":"llava-1.6-13b","score":72.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"llava-1.6-13b","score":68.5,"metric":"percent"},{"benchmark":"seed-bench-img","model":"llava-1.6-13b","score":71.4,"metric":"percent"},{"benchmark":"mmvet","model":"llava-1.6-13b","score":44.9,"metric":"percent"},{"benchmark":"ai2d","model":"internlm-xcomposer","score":56.9,"metric":"percent"},{"benchmark":"docvqa","model":"textmonkey","score":73,"metric":"percent"},{"benchmark":"chartqa","model":"textmonkey","score":66.9,"metric":"percent"},{"benchmark":"textvqa","model":"textmonkey","score":65.6,"metric":"percent"},{"benchmark":"textvqa","model":"llava-uhd-13b","score":67.7,"metric":"percent"},{"benchmark":"docvqa","model":"cogagent-18b","score":81.6,"metric":"percent"},{"benchmark":"chartqa","model":"cogagent-18b","score":68.4,"metric":"percent"},{"benchmark":"infovqa","model":"cogagent-18b","score":44.5,"metric":"percent"},{"benchmark":"textvqa","model":"cogagent-18b","score":76.1,"metric":"percent"},{"benchmark":"ocrbench","model":"cogagent-18b","score":59,"metric":"percent"},{"benchmark":"docvqa","model":"ureader","score":65.4,"metric":"percent"},{"benchmark":"chartqa","model":"ureader","score":59.3,"metric":"percent"},{"benchmark":"infovqa","model":"ureader","score":42.2,"metric":"percent"},{"benchmark":"textvqa","model":"ureader","score":57.6,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-4v","score":43.5,"metric":"percent"},{"benchmark":"mvbench","model":"internlm-xcomposer2.5","score":69.1,"metric":"percent"},{"benchmark":"mlvu","model":"internlm-xcomposer2.5","score":58.8,"metric":"percent"},{"benchmark":"tempcompass","model":"internlm-xcomposer2.5","score":67.1,"metric":"percent"},{"benchmark":"docvqa","model":"internlm-xcomposer2.5","score":90.9,"metric":"percent"},{"benchmark":"chartqa","model":"internlm-xcomposer2.5","score":82.2,"metric":"percent"},{"benchmark":"infovqa","model":"internlm-xcomposer2.5","score":69.9,"metric":"percent"},{"benchmark":"textvqa","model":"internlm-xcomposer2.5","score":78.2,"metric":"percent"},{"benchmark":"ocrbench","model":"internlm-xcomposer2.5","score":69,"metric":"percent"},{"benchmark":"wtq","model":"internlm-xcomposer2.5","score":53.6,"metric":"percent"},{"benchmark":"deepform","model":"internlm-xcomposer2.5","score":71.2,"metric":"percent"},{"benchmark":"visualmrc","model":"internlm-xcomposer2.5","score":307.5,"metric":"CIDEr"},{"benchmark":"tabfact","model":"internlm-xcomposer2.5","score":85.2,"metric":"percent"},{"benchmark":"mmdu","model":"gpt-4v","score":66.3,"metric":"percent"},{"benchmark":"realworldqa","model":"gpt-4v","score":68,"metric":"percent"},{"benchmark":"mmbench","model":"gpt-4v","score":81.3,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gpt-4v","score":79.8,"metric":"percent"},{"benchmark":"realworldqa","model":"gemini-pro","score":64.1,"metric":"percent"},{"benchmark":"mmbench","model":"gemini-pro","score":73.9,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"gemini-pro","score":73.9,"metric":"percent"},{"benchmark":"mmdu","model":"internlm-xcomposer2.5","score":56.6,"metric":"percent"},{"benchmark":"mmstar","model":"internlm-xcomposer2.5","score":59.9,"metric":"percent"},{"benchmark":"realworldqa","model":"internlm-xcomposer2.5","score":67.8,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internlm-xcomposer2.5","score":63.8,"metric":"percent"},{"benchmark":"ai2d","model":"internlm-xcomposer2.5","score":81.5,"metric":"percent"},{"benchmark":"mmmu","model":"internlm-xcomposer2.5","score":42.9,"metric":"percent"},{"benchmark":"mme-elo","model":"internlm-xcomposer2.5","score":2229,"metric":"points"},{"benchmark":"mmbench","model":"internlm-xcomposer2.5","score":82.2,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internlm-xcomposer2.5","score":80.8,"metric":"percent"},{"benchmark":"mmbench-v1.1-en","model":"internlm-xcomposer2.5","score":79.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internlm-xcomposer2.5","score":75.4,"metric":"percent"},{"benchmark":"mmvet","model":"internlm-xcomposer2.5","score":51.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"internlm-xcomposer2.5","score":42.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llemma-7b","score":36.4,"metric":"percent"},{"benchmark":"math","model":"llemma-7b","score":18,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-7b","score":36.5,"metric":"percent"},{"benchmark":"math","model":"internlm2-7b","score":8.6,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-base-7b","score":49.2,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-base-7b","score":21.5,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-20b","score":54.6,"metric":"percent"},{"benchmark":"math","model":"internlm2-20b","score":13.7,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-base-20b","score":63.7,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-base-20b","score":27.3,"metric":"percent"},{"benchmark":"gsm8k","model":"llemma-34b","score":51.5,"metric":"percent"},{"benchmark":"math","model":"llemma-34b","score":25,"metric":"percent"},{"benchmark":"gsm8k","model":"metamath-7b","score":66.5,"metric":"percent"},{"benchmark":"math","model":"metamath-7b","score":19.8,"metric":"percent"},{"benchmark":"gsm8k","model":"metamath-mistral-7b","score":77.7,"metric":"percent"},{"benchmark":"math","model":"metamath-mistral-7b","score":28.2,"metric":"percent"},{"benchmark":"gsm8k","model":"metamath-llemma-7b","score":69.2,"metric":"percent"},{"benchmark":"math","model":"metamath-llemma-7b","score":30,"metric":"percent"},{"benchmark":"minif2f-test","model":"codellama-7b","score":20.5,"metric":"percent"},{"benchmark":"minif2f-test","model":"codellama-34b","score":22.1,"metric":"percent"},{"benchmark":"minif2f-test","model":"mistral-7b-v0.1","score":22.1,"metric":"percent"},{"benchmark":"minif2f-test","model":"mixtral-8x7b","score":23.4,"metric":"percent"},{"benchmark":"minif2f-test","model":"llemma-7b","score":26.2,"metric":"percent"},{"benchmark":"minif2f-test","model":"llemma-34b","score":25.8,"metric":"percent"},{"benchmark":"minif2f-test","model":"deepseek-coder-7b-base-v1.5","score":28.7,"metric":"percent"},{"benchmark":"minif2f-test","model":"deepseek-math-7b","score":28.3,"metric":"percent"},{"benchmark":"minif2f-test","model":"internlm2-7b","score":22.1,"metric":"percent"},{"benchmark":"minif2f-test","model":"internlm2-20b","score":25.4,"metric":"percent"},{"benchmark":"minif2f-test","model":"internlm2-math-base-7b","score":30.3,"metric":"percent"},{"benchmark":"minif2f-test","model":"internlm2-math-base-20b","score":29.5,"metric":"percent"},{"benchmark":"minif2f-test","model":"internlm2-math-plus-1.8b","score":38.9,"metric":"percent"},{"benchmark":"minif2f-test","model":"internlm2-math-plus-7b","score":43.4,"metric":"percent"},{"benchmark":"minif2f-test","model":"internlm2-math-plus-20b","score":42.6,"metric":"percent"},{"benchmark":"minif2f-test","model":"internlm2-math-plus-mixtral8x22b","score":37.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-7b-chat","score":51.7,"metric":"percent"},{"benchmark":"math","model":"qwen-7b-chat","score":11.6,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"qwen-7b-chat","score":19,"metric":"percent"},{"benchmark":"mathbench-zh","model":"qwen-7b-chat","score":25,"metric":"percent"},{"benchmark":"mathbench-zh","model":"deepseek-llm-7b-chat","score":12.7,"metric":"percent"},{"benchmark":"math","model":"internlm2-chat-7b","score":23,"metric":"percent"},{"benchmark":"mathbench-zh","model":"internlm2-chat-7b","score":29.2,"metric":"percent"},{"benchmark":"mathbench-zh","model":"chatglm3-6b","score":15.2,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"metamath-mistral-7b","score":29,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-7b","score":78.1,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-7b","score":34.6,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"internlm2-math-7b","score":55,"metric":"percent"},{"benchmark":"mathbench-zh","model":"internlm2-math-7b","score":40,"metric":"percent"},{"benchmark":"math","model":"internlm2-chat-20b","score":31.9,"metric":"percent"},{"benchmark":"mathbench-zh","model":"internlm2-chat-20b","score":37.8,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"internlm2-math-20b","score":66,"metric":"percent"},{"benchmark":"mathbench-zh","model":"internlm2-math-20b","score":45.3,"metric":"percent"},{"benchmark":"mathbench-zh","model":"qwen-72b-chat","score":47.8,"metric":"percent"},{"benchmark":"mathbench-zh","model":"deepseek-llm-67b-chat","score":33.2,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-3.5-turbo","score":80.8,"metric":"percent"},{"benchmark":"math","model":"gpt-3.5-turbo","score":34.1,"metric":"percent"},{"benchmark":"hungarian-math-exam","model":"gpt-3.5-turbo","score":41,"metric":"percent"},{"benchmark":"mathbench-zh","model":"gpt-3.5-turbo","score":21.5,"metric":"percent"},{"benchmark":"mathbench-zh","model":"gpt-4","score":47.2,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-plus-1.8b","score":37,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-plus-1.8b","score":58.8,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-plus-7b","score":53,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-plus-7b","score":85.8,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-plus-20b","score":53.8,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-plus-20b","score":87.7,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x22b-instruct-v0.1","score":41.8,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b-instruct-v0.1","score":78.6,"metric":"percent"},{"benchmark":"math","model":"eurux-8x22b-nca","score":49,"metric":"percent"},{"benchmark":"math","model":"internlm2-math-plus-mixtral8x22b","score":58.1,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2-math-plus-mixtral8x22b","score":91.8,"metric":"percent"},{"benchmark":"mathbench-a","model":"gpt-4o-2024-05-13","score":70.9,"metric":"percent"},{"benchmark":"mathbench-a","model":"claude-3-opus","score":63,"metric":"percent"},{"benchmark":"mathbench-a","model":"qwen-max-0428","score":59.2,"metric":"percent"},{"benchmark":"mathbench-a","model":"qwen1.5-110b-chat","score":58.4,"metric":"percent"},{"benchmark":"mathbench-a","model":"deepseek-v2-chat","score":59.9,"metric":"percent"},{"benchmark":"mathbench-a","model":"llama-3-70b-instruct","score":56.5,"metric":"percent"},{"benchmark":"mathbench-a","model":"internlm2-math-plus-mixtral8x22b","score":62,"metric":"percent"},{"benchmark":"mathbench-a","model":"internlm2-math-20b","score":42,"metric":"percent"},{"benchmark":"mathbench-a","model":"internlm2-math-plus-20b","score":55.5,"metric":"percent"},{"benchmark":"mathbench-a","model":"llama-3-8b-instruct","score":36.7,"metric":"percent"},{"benchmark":"mathbench-a","model":"internlm2-math-7b","score":37.7,"metric":"percent"},{"benchmark":"mathbench-a","model":"deepseek-math-7b-rl","score":50.3,"metric":"percent"},{"benchmark":"mathbench-a","model":"internlm2-math-plus-7b","score":50.9,"metric":"percent"},{"benchmark":"mathbench-a","model":"internlm2-math-plus-1.8b","score":27.1,"metric":"percent"},{"benchmark":"arena-hard","model":"yi-1.5-34b-chat","score":42.6,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"yi-1.5-34b-chat","score":36.6,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-32b-chat","score":74.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-32b-chat","score":83.9,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-32b-chat","score":43.3,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-32b-chat","score":51.2,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-32b-chat","score":66.9,"metric":"percent"},{"benchmark":"alignbench","model":"qwen1.5-32b-chat","score":7.1,"metric":"score"},{"benchmark":"arena-hard","model":"qwen1.5-32b-chat","score":24.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen1.5-32b-chat","score":23.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-72b-chat","score":77.3,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-72b-chat","score":86,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-72b-chat","score":44.4,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-72b-chat","score":64.6,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen1.5-72b-chat","score":8.6,"metric":"percent"},{"benchmark":"alignbench","model":"qwen1.5-72b-chat","score":7.2,"metric":"score"},{"benchmark":"arena-hard","model":"mixtral-8x7b-instruct-v0.1","score":23.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"mixtral-8x7b-instruct-v0.1","score":23.7,"metric":"percent"},{"benchmark":"mmlu","model":"mixtral-8x22b-instruct-v0.1","score":77.7,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b-instruct-v0.1","score":84,"metric":"percent"},{"benchmark":"math","model":"mixtral-8x22b-instruct-v0.1","score":41.1,"metric":"percent"},{"benchmark":"mt-bench","model":"mixtral-8x22b-instruct-v0.1","score":8.6,"metric":"percent"},{"benchmark":"alignbench","model":"mixtral-8x22b-instruct-v0.1","score":6.5,"metric":"score"},{"benchmark":"mbpp","model":"yi-1.5-9b-chat","score":78.8,"metric":"percent"},{"benchmark":"arena-hard","model":"yi-1.5-9b-chat","score":34.4,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"yi-1.5-9b-chat","score":22.9,"metric":"percent"},{"benchmark":"mmlu","model":"yi-1.5-6b-chat","score":62.8,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-6b-chat","score":78.9,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-6b-chat","score":40.5,"metric":"percent"},{"benchmark":"humaneval","model":"yi-1.5-6b-chat","score":64,"metric":"percent"},{"benchmark":"mbpp","model":"yi-1.5-6b-chat","score":70.9,"metric":"percent"},{"benchmark":"mt-bench","model":"yi-1.5-6b-chat","score":7.5,"metric":"percent"},{"benchmark":"alignbench","model":"yi-1.5-6b-chat","score":6.2,"metric":"score"},{"benchmark":"arena-hard","model":"yi-1.5-6b-chat","score":17.9,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"yi-1.5-6b-chat","score":15.7,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-1.1-7b-it","score":60.9,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-1.1-7b-it","score":57.5,"metric":"percent"},{"benchmark":"math","model":"gemma-1.1-7b-it","score":24.2,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-1.1-7b-it","score":41.5,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-1.1-7b-it","score":55.6,"metric":"percent"},{"benchmark":"mt-bench","model":"gemma-1.1-7b-it","score":7.5,"metric":"percent"},{"benchmark":"alignbench","model":"gemma-1.1-7b-it","score":5,"metric":"score"},{"benchmark":"arena-hard","model":"gemma-1.1-7b-it","score":7.5,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"gemma-1.1-7b-it","score":10.4,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-7b-chat","score":60.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-7b-chat","score":62.9,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-7b-chat","score":22,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-7b-chat","score":38.4,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-7b-chat","score":41.5,"metric":"percent"},{"benchmark":"mt-bench","model":"qwen1.5-7b-chat","score":7.7,"metric":"percent"},{"benchmark":"arena-hard","model":"qwen1.5-7b-chat","score":10.2,"metric":"percent"},{"benchmark":"alpacaeval-2.0","model":"qwen1.5-7b-chat","score":14.7,"metric":"percent"},{"benchmark":"math","model":"mistral-7b-instruct-v0.2","score":13.4,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b-instruct-v0.2","score":23.8,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b-instruct-v0.2","score":36.5,"metric":"percent"},{"benchmark":"mt-bench","model":"mistral-7b-instruct-v0.2","score":7.6,"metric":"percent"},{"benchmark":"alignbench","model":"mistral-7b-instruct-v0.2","score":5.3,"metric":"score"},{"benchmark":"mmlu","model":"llama-3-8b-instruct","score":65.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b-instruct","score":54.7,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b-instruct","score":21.2,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b-instruct","score":61.4,"metric":"percent"},{"benchmark":"mt-bench","model":"llama-3-8b-instruct","score":8,"metric":"percent"},{"benchmark":"agieval","model":"yi-1.5-34b","score":71.1,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-34b","score":41,"metric":"percent"},{"benchmark":"mmlu","model":"qwen1.5-32b","score":73.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-32b","score":83,"metric":"percent"},{"benchmark":"agieval","model":"qwen1.5-32b","score":72.6,"metric":"percent"},{"benchmark":"humaneval","model":"qwen1.5-32b","score":37.8,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen1.5-32b","score":35.4,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen1.5-32b","score":44.4,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-32b","score":79.5,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-32b","score":37.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-72b","score":84.2,"metric":"percent"},{"benchmark":"agieval","model":"qwen1.5-72b","score":71.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen1.5-72b","score":39,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen1.5-72b","score":43.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-72b","score":81.4,"metric":"percent"},{"benchmark":"math","model":"qwen1.5-72b","score":41.8,"metric":"percent"},{"benchmark":"cmmlu","model":"mixtral-8x22b","score":60.4,"metric":"percent"},{"benchmark":"bbh","model":"mixtral-8x22b","score":82.1,"metric":"percent"},{"benchmark":"agieval","model":"mixtral-8x22b","score":58.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mixtral-8x22b","score":34.1,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x22b","score":81.7,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-70b","score":79.5,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-70b","score":68.9,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-70b","score":81.3,"metric":"percent"},{"benchmark":"agieval","model":"llama-3-70b","score":63,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-70b","score":38.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3-70b","score":34.8,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-70b","score":69.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-70b","score":52.9,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-70b","score":82.4,"metric":"percent"},{"benchmark":"math","model":"llama-3-70b","score":42.4,"metric":"percent"},{"benchmark":"mmlu","model":"yi-1.5-9b","score":69.5,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-1.5-9b","score":74.8,"metric":"percent"},{"benchmark":"bbh","model":"yi-1.5-9b","score":72.4,"metric":"percent"},{"benchmark":"agieval","model":"yi-1.5-9b","score":62.7,"metric":"percent"},{"benchmark":"humaneval","model":"yi-1.5-9b","score":41.4,"metric":"percent"},{"benchmark":"humaneval-plus","model":"yi-1.5-9b","score":34.1,"metric":"percent"},{"benchmark":"mbpp","model":"yi-1.5-9b","score":61.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"yi-1.5-9b","score":53.6,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-9b","score":73.7,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-9b","score":32.6,"metric":"percent"},{"benchmark":"mmlu","model":"yi-1.5-6b","score":63.5,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-1.5-6b","score":70.8,"metric":"percent"},{"benchmark":"bbh","model":"yi-1.5-6b","score":59,"metric":"percent"},{"benchmark":"agieval","model":"yi-1.5-6b","score":56,"metric":"percent"},{"benchmark":"humaneval","model":"yi-1.5-6b","score":36.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"yi-1.5-6b","score":28.7,"metric":"percent"},{"benchmark":"mbpp","model":"yi-1.5-6b","score":56.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"yi-1.5-6b","score":46.9,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-6b","score":62.2,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-6b","score":28.42,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-7b","score":48.4,"metric":"percent"},{"benchmark":"bbh","model":"gemma-7b","score":61,"metric":"percent"},{"benchmark":"agieval","model":"gemma-7b","score":46,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-7b","score":33.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"gemma-7b","score":28,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-7b","score":45.8,"metric":"percent"},{"benchmark":"mbpp-plus","model":"gemma-7b","score":32.8,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-7b","score":55.7,"metric":"percent"},{"benchmark":"math","model":"gemma-7b","score":24.8,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen1.5-7b","score":73.4,"metric":"percent"},{"benchmark":"bbh","model":"qwen1.5-7b","score":13.3,"metric":"percent"},{"benchmark":"agieval","model":"qwen1.5-7b","score":61.6,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen1.5-7b","score":31.1,"metric":"percent"},{"benchmark":"mbpp","model":"qwen1.5-7b","score":46.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen1.5-7b","score":37.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen1.5-7b","score":70.1,"metric":"percent"},{"benchmark":"bbh","model":"mistral-7b","score":58.2,"metric":"percent"},{"benchmark":"agieval","model":"mistral-7b","score":42.4,"metric":"percent"},{"benchmark":"humaneval","model":"mistral-7b","score":29.3,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mistral-7b","score":22.6,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mistral-7b","score":32.1,"metric":"percent"},{"benchmark":"math","model":"mistral-7b","score":15.5,"metric":"percent"},{"benchmark":"cmmlu","model":"mixtral-8x7b","score":53,"metric":"percent"},{"benchmark":"bbh","model":"mixtral-8x7b","score":70.5,"metric":"percent"},{"benchmark":"agieval","model":"mixtral-8x7b","score":49.5,"metric":"percent"},{"benchmark":"humaneval-plus","model":"mixtral-8x7b","score":31.1,"metric":"percent"},{"benchmark":"mbpp-plus","model":"mixtral-8x7b","score":31.1,"metric":"percent"},{"benchmark":"gsm8k","model":"mixtral-8x7b","score":65.7,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-8b","score":66.6,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-8b","score":50.9,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-8b","score":64.4,"metric":"percent"},{"benchmark":"agieval","model":"llama-3-8b","score":44.7,"metric":"percent"},{"benchmark":"humaneval","model":"llama-3-8b","score":34.7,"metric":"percent"},{"benchmark":"humaneval-plus","model":"llama-3-8b","score":31.7,"metric":"percent"},{"benchmark":"mbpp","model":"llama-3-8b","score":48,"metric":"percent"},{"benchmark":"mbpp-plus","model":"llama-3-8b","score":44.9,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b","score":54.7,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b","score":21.16,"metric":"percent"},{"benchmark":"mbpp","model":"codellama-7b","score":41.6,"metric":"percent"},{"benchmark":"humaneval","model":"starcoderbase-16b","score":36,"metric":"percent"},{"benchmark":"mbpp","model":"starcoderbase-16b","score":46.8,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-1.3b-base","score":31,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-6.7b-base","score":43.5,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-33b-base","score":48.6,"metric":"percent"},{"benchmark":"humaneval","model":"codeqwen1.5-7b","score":52.4,"metric":"percent"},{"benchmark":"humaneval","model":"yi-coder-1.5b","score":41.5,"metric":"percent"},{"benchmark":"mbpp","model":"yi-coder-1.5b","score":51.6,"metric":"percent"},{"benchmark":"crux-o","model":"yi-coder-1.5b","score":31.5,"metric":"percent"},{"benchmark":"humaneval","model":"yi-coder-9b","score":53.7,"metric":"percent"},{"benchmark":"mbpp","model":"yi-coder-9b","score":69.4,"metric":"percent"},{"benchmark":"crux-o","model":"yi-coder-9b","score":52.3,"metric":"percent"},{"benchmark":"crux-o","model":"gpt-4","score":59,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-1.3b-instruct","score":28.7,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-6.7b-instruct","score":78.9,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-6.7b-instruct","score":41.2,"metric":"percent"},{"benchmark":"crux-o","model":"deepseek-coder-33b-instruct","score":49.9,"metric":"percent"},{"benchmark":"humaneval","model":"codeqwen1.5-7b-chat","score":83.2,"metric":"percent"},{"benchmark":"crux-o","model":"codeqwen1.5-7b-chat","score":37.1,"metric":"percent"},{"benchmark":"humaneval","model":"codegeex4-all-9b","score":82.3,"metric":"percent"},{"benchmark":"crux-o","model":"codegeex4-all-9b","score":47.1,"metric":"percent"},{"benchmark":"humaneval","model":"yi-coder-1.5b-chat","score":67.7,"metric":"percent"},{"benchmark":"mbpp","model":"yi-coder-1.5b-chat","score":52.6,"metric":"percent"},{"benchmark":"crux-o","model":"yi-coder-1.5b-chat","score":29.7,"metric":"percent"},{"benchmark":"humaneval","model":"yi-coder-9b-chat","score":85.4,"metric":"percent"},{"benchmark":"mbpp","model":"yi-coder-9b-chat","score":73.8,"metric":"percent"},{"benchmark":"crux-o","model":"yi-coder-9b-chat","score":51.8,"metric":"percent"},{"benchmark":"livecodebench","model":"yi-coder-9b-chat","score":23.4,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-coder-33b-instruct","score":22.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-coder-6.7b-instruct","score":18.9,"metric":"percent"},{"benchmark":"livecodebench","model":"codegeex4-all-9b","score":17.8,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3.1-8b-instruct","score":17.6,"metric":"percent"},{"benchmark":"livecodebench","model":"starcoder2-15b","score":14.8,"metric":"percent"},{"benchmark":"livecodebench","model":"codellama-34b-instruct","score":13.3,"metric":"percent"},{"benchmark":"livecodebench","model":"codeqwen1.5-7b-chat","score":12,"metric":"percent"},{"benchmark":"livecodebench","model":"codegemma-7b","score":11.8,"metric":"percent"},{"benchmark":"aider-code-editing","model":"llama-3.1-405b-instruct","score":66.2,"metric":"percent"},{"benchmark":"aider-code-editing","model":"qwen2-72b-instruct","score":55.6,"metric":"percent"},{"benchmark":"aider-code-editing","model":"llama-3.1-8b-instruct","score":37.6,"metric":"percent"},{"benchmark":"aider-code-editing","model":"codeqwen1.5-7b-chat","score":34.6,"metric":"percent"},{"benchmark":"gsm8k","model":"codeshell-7b","score":15.8,"metric":"percent"},{"benchmark":"math","model":"codeshell-7b","score":8.6,"metric":"percent"},{"benchmark":"tabmwp","model":"codeshell-7b","score":28.2,"metric":"percent"},{"benchmark":"gsm8k","model":"codegeex2-6b","score":22.2,"metric":"percent"},{"benchmark":"math","model":"codegeex2-6b","score":9.7,"metric":"percent"},{"benchmark":"tabmwp","model":"codegeex2-6b","score":44.6,"metric":"percent"},{"benchmark":"gsm8k","model":"starcoderbase-16b","score":23.4,"metric":"percent"},{"benchmark":"math","model":"starcoderbase-16b","score":10.3,"metric":"percent"},{"benchmark":"tabmwp","model":"starcoderbase-16b","score":45,"metric":"percent"},{"benchmark":"gsm8k","model":"codellama-7b","score":31.2,"metric":"percent"},{"benchmark":"math","model":"codellama-7b","score":12.1,"metric":"percent"},{"benchmark":"tabmwp","model":"codellama-7b","score":52.9,"metric":"percent"},{"benchmark":"gsm8k","model":"codellama-13b","score":43.1,"metric":"percent"},{"benchmark":"math","model":"codellama-13b","score":14.4,"metric":"percent"},{"benchmark":"tabmwp","model":"codellama-13b","score":60.3,"metric":"percent"},{"benchmark":"gsm8k","model":"codellama-34b","score":58.2,"metric":"percent"},{"benchmark":"math","model":"codellama-34b","score":21.2,"metric":"percent"},{"benchmark":"tabmwp","model":"codellama-34b","score":69.8,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-1.3b-base","score":14.6,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-1.3b-base","score":16.8,"metric":"percent"},{"benchmark":"tabmwp","model":"deepseek-coder-1.3b-base","score":30,"metric":"percent"},{"benchmark":"tabmwp","model":"deepseek-coder-6.7b-base","score":67.9,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-33b-base","score":60.7,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-33b-base","score":29.1,"metric":"percent"},{"benchmark":"tabmwp","model":"deepseek-coder-33b-base","score":75.3,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-coder-1.5b","score":25.5,"metric":"percent"},{"benchmark":"math","model":"yi-coder-1.5b","score":11.4,"metric":"percent"},{"benchmark":"tabmwp","model":"yi-coder-1.5b","score":36.2,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-coder-9b","score":68.1,"metric":"percent"},{"benchmark":"math","model":"yi-coder-9b","score":29.1,"metric":"percent"},{"benchmark":"tabmwp","model":"yi-coder-9b","score":81.2,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b-chat","score":73.46,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-34b-chat","score":81.34,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b-chat","score":78.53,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-34b-chat","score":62.43,"metric":"percent"},{"benchmark":"bbh","model":"yi-34b-chat","score":71.74,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-34b-chat","score":75.97,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b-chat-8bits","score":73.69,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-34b-chat-8bits","score":81.23,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b-chat-8bits","score":78.97,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-34b-chat-8bits","score":61.84,"metric":"percent"},{"benchmark":"bbh","model":"yi-34b-chat-8bits","score":70.97,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-34b-chat-8bits","score":75.74,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b-chat-4bits","score":72.42,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b-chat-4bits","score":77.27,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-34b-chat-4bits","score":61.84,"metric":"percent"},{"benchmark":"bbh","model":"yi-34b-chat-4bits","score":69.39,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b-chat","score":60.99,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b-chat","score":74.71,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b-chat","score":74.22,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-6b-chat","score":50.58,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b-chat","score":47.15,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-6b-chat","score":44.88,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b-chat-8bits","score":60.96,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b-chat-8bits","score":74.69,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b-chat-8bits","score":73.85,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-6b-chat-8bits","score":49.85,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b-chat-8bits","score":47.26,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-6b-chat-8bits","score":44.88,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b-chat-4bits","score":59.89,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b-chat-4bits","score":73.29,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b-chat-4bits","score":72.29,"metric":"percent"},{"benchmark":"truthfulqa","model":"yi-6b-chat-4bits","score":50.29,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b-chat-4bits","score":43.62,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-6b-chat-4bits","score":38.36,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b-chat","score":47.33,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-13b-chat","score":35.08,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-13b-chat","score":35.88,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-2-13b-chat","score":36.84,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b-chat","score":58.22,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b-chat","score":2.73,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b-chat","score":59.86,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-2-70b-chat","score":40.99,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b-chat","score":41.31,"metric":"percent"},{"benchmark":"truthfulqa","model":"llama-2-70b-chat","score":53.95,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-70b-chat","score":58.53,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b-chat","score":58.68,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-chat","score":50.14,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-chat","score":59.47,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-chat","score":54.75,"metric":"percent"},{"benchmark":"truthfulqa","model":"baichuan2-13b-chat","score":48.98,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-chat","score":47.15,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-chat","score":23.28,"metric":"percent"},{"benchmark":"mmlu","model":"qwen-14b-chat","score":64.98,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen-14b-chat","score":70.57,"metric":"percent"},{"benchmark":"c-eval","model":"qwen-14b-chat","score":70.06,"metric":"percent"},{"benchmark":"truthfulqa","model":"qwen-14b-chat","score":52.49,"metric":"percent"},{"benchmark":"bbh","model":"qwen-14b-chat","score":54.98,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen-14b-chat","score":61.18,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-chat-20b","score":57.42,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm-chat-20b","score":53.75,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-chat-20b","score":53.57,"metric":"percent"},{"benchmark":"truthfulqa","model":"internlm-chat-20b","score":51.75,"metric":"percent"},{"benchmark":"bbh","model":"internlm-chat-20b","score":36.68,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-chat-20b","score":43.44,"metric":"percent"},{"benchmark":"cmmlu","model":"aquilachat2-34b","score":70.02,"metric":"percent"},{"benchmark":"c-eval","model":"aquilachat2-34b","score":89.38,"metric":"percent"},{"benchmark":"truthfulqa","model":"aquilachat2-34b","score":64.33,"metric":"percent"},{"benchmark":"bbh","model":"aquilachat2-34b","score":34.28,"metric":"percent"},{"benchmark":"gsm8k","model":"aquilachat2-34b","score":48.45,"metric":"percent"},{"benchmark":"mmlu","model":"yi-34b-200k","score":76.1,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-34b-200k","score":83.6,"metric":"percent"},{"benchmark":"c-eval","model":"yi-34b-200k","score":81.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"yi-34b-200k","score":83.4,"metric":"percent"},{"benchmark":"bbh","model":"yi-34b-200k","score":52.7,"metric":"percent"},{"benchmark":"mmlu","model":"yi-6b-200k","score":64,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-6b-200k","score":75.3,"metric":"percent"},{"benchmark":"c-eval","model":"yi-6b-200k","score":73.5,"metric":"percent"},{"benchmark":"gaokao-bench","model":"yi-6b-200k","score":73.9,"metric":"percent"},{"benchmark":"bbh","model":"yi-6b-200k","score":42,"metric":"percent"},{"benchmark":"gaokao-bench","model":"llama-2-70b","score":49.8,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-70b","score":51.2,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-base","score":48.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"skywork-13b-base","score":68.1,"metric":"percent"},{"benchmark":"bbh","model":"skywork-13b-base","score":41.7,"metric":"percent"},{"benchmark":"mmlu","model":"aquila2-34b","score":67.8,"metric":"percent"},{"benchmark":"math","model":"yi-6b","score":4.7,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-9b","score":73.2,"metric":"percent"},{"benchmark":"mbpp","model":"mistral-7b","score":39.6,"metric":"percent"},{"benchmark":"gsm8k","model":"mistral-7b","score":35.6,"metric":"percent"},{"benchmark":"math","model":"mistral-7b","score":9.5,"metric":"percent"},{"benchmark":"arc-challenge","model":"mistral-7b","score":57.2,"metric":"percent"},{"benchmark":"hellaswag","model":"mistral-7b","score":81.4,"metric":"percent"},{"benchmark":"winogrande","model":"mistral-7b","score":74,"metric":"percent"},{"benchmark":"cmmlu","model":"mistral-7b","score":44.5,"metric":"percent"},{"benchmark":"humaneval","model":"solar-10.7b-v1.0","score":29.3,"metric":"percent"},{"benchmark":"mbpp","model":"solar-10.7b-v1.0","score":38.9,"metric":"percent"},{"benchmark":"gsm8k","model":"solar-10.7b-v1.0","score":56.8,"metric":"percent"},{"benchmark":"math","model":"solar-10.7b-v1.0","score":6.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"solar-10.7b-v1.0","score":57.9,"metric":"percent"},{"benchmark":"hellaswag","model":"solar-10.7b-v1.0","score":82.1,"metric":"percent"},{"benchmark":"winogrande","model":"solar-10.7b-v1.0","score":74.6,"metric":"percent"},{"benchmark":"mmlu","model":"solar-10.7b-v1.0","score":64.2,"metric":"percent"},{"benchmark":"cmmlu","model":"solar-10.7b-v1.0","score":47.8,"metric":"percent"},{"benchmark":"humaneval","model":"gemma-7b","score":32.9,"metric":"percent"},{"benchmark":"mbpp","model":"gemma-7b","score":44.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-7b","score":48.1,"metric":"percent"},{"benchmark":"math","model":"gemma-7b","score":16.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"gemma-7b","score":58.2,"metric":"percent"},{"benchmark":"hellaswag","model":"gemma-7b","score":79.7,"metric":"percent"},{"benchmark":"winogrande","model":"gemma-7b","score":73.6,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-7b","score":63,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-7b","score":48.6,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-coder-7b-base-v1.5","score":42.1,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-coder-7b-base-v1.5","score":60.7,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-coder-7b-base-v1.5","score":41,"metric":"percent"},{"benchmark":"math","model":"deepseek-coder-7b-base-v1.5","score":13.9,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-coder-7b-base-v1.5","score":45,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-coder-7b-base-v1.5","score":67.9,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-coder-7b-base-v1.5","score":64,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-coder-7b-base-v1.5","score":49.2,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-coder-7b-base-v1.5","score":47.7,"metric":"percent"},{"benchmark":"humaneval","model":"deepseek-math-7b","score":31.1,"metric":"percent"},{"benchmark":"mbpp","model":"deepseek-math-7b","score":55.2,"metric":"percent"},{"benchmark":"gsm8k","model":"deepseek-math-7b","score":60.9,"metric":"percent"},{"benchmark":"math","model":"deepseek-math-7b","score":26,"metric":"percent"},{"benchmark":"arc-challenge","model":"deepseek-math-7b","score":48.6,"metric":"percent"},{"benchmark":"hellaswag","model":"deepseek-math-7b","score":67.5,"metric":"percent"},{"benchmark":"winogrande","model":"deepseek-math-7b","score":63.8,"metric":"percent"},{"benchmark":"mmlu","model":"deepseek-math-7b","score":53.2,"metric":"percent"},{"benchmark":"cmmlu","model":"deepseek-math-7b","score":51.7,"metric":"percent"},{"benchmark":"c-eval","model":"claude-v1.3","score":54.2,"metric":"percent"},{"benchmark":"c-eval","model":"claude-instant-1.0","score":45.9,"metric":"percent"},{"benchmark":"c-eval","model":"bloomz-7b1","score":35.7,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm-6b","score":34.5,"metric":"percent"},{"benchmark":"c-eval","model":"ziya-llama-13b-pretrain","score":30.2,"metric":"percent"},{"benchmark":"c-eval","model":"moss-moon-003-base","score":27.4,"metric":"percent"},{"benchmark":"c-eval","model":"tigerbot-7b-base","score":25.7,"metric":"percent"},{"benchmark":"c-eval","model":"aquila-7b","score":25.5,"metric":"percent"},{"benchmark":"c-eval","model":"open-llama-7b-v2","score":24,"metric":"percent"},{"benchmark":"c-eval","model":"bloom-7b1","score":22.8,"metric":"percent"},{"benchmark":"gaokao-bench","model":"bloomz-7b1","score":28.72,"metric":"percent"},{"benchmark":"gaokao-bench","model":"bloom-7b1","score":26.96,"metric":"percent"},{"benchmark":"gaokao-bench","model":"tigerbot-7b-base","score":25.94,"metric":"percent"},{"benchmark":"gaokao-bench","model":"falcon-7b","score":23.98,"metric":"percent"},{"benchmark":"gaokao-bench","model":"ziya-llama-13b-pretrain","score":23.17,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm-6b","score":21.41,"metric":"percent"},{"benchmark":"gaokao-bench","model":"open-llama-7b-v2","score":21.41,"metric":"percent"},{"benchmark":"gaokao-bench","model":"aquila-7b","score":24.39,"metric":"percent"},{"benchmark":"gaokao-bench","model":"baichuan-7b","score":36.24,"metric":"percent"},{"benchmark":"agieval","model":"bloomz-7b1","score":30.27,"metric":"percent"},{"benchmark":"agieval","model":"ziya-llama-13b-pretrain","score":27.64,"metric":"percent"},{"benchmark":"agieval","model":"falcon-7b","score":27.18,"metric":"percent"},{"benchmark":"agieval","model":"bloom-7b1","score":26.55,"metric":"percent"},{"benchmark":"agieval","model":"aquila-7b","score":25.58,"metric":"percent"},{"benchmark":"agieval","model":"tigerbot-7b-base","score":25.19,"metric":"percent"},{"benchmark":"agieval","model":"chatglm-6b","score":23.49,"metric":"percent"},{"benchmark":"agieval","model":"open-llama-7b-v2","score":23.49,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm-6b","score":36.9,"metric":"percent"},{"benchmark":"mmlu","model":"bloomz-7b1","score":36.1,"metric":"percent"},{"benchmark":"mmlu","model":"mpt-7b","score":35.6,"metric":"percent"},{"benchmark":"mmlu","model":"falcon-7b","score":35,"metric":"percent"},{"benchmark":"mmlu","model":"moss-moon-003-sft","score":31.9,"metric":"percent"},{"benchmark":"mmlu","model":"bloom-7b1","score":25.5,"metric":"percent"},{"benchmark":"mmlu","model":"moss-moon-003-base","score":23.6,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan-7b","score":44,"metric":"percent"},{"benchmark":"cmmlu","model":"chinese-alpaca-plus-13b","score":33.4,"metric":"percent"},{"benchmark":"cmmlu","model":"vicuna-13b","score":36.3,"metric":"percent"},{"benchmark":"c-eval","model":"chinese-llama-plus-13b","score":32.1,"metric":"percent"},{"benchmark":"mmlu","model":"chinese-llama-plus-13b","score":39.2,"metric":"percent"},{"benchmark":"cmmlu","model":"chinese-llama-plus-13b","score":33,"metric":"percent"},{"benchmark":"c-eval","model":"ziya-llama-13b-pretrain","score":30,"metric":"percent"},{"benchmark":"mmlu","model":"ziya-llama-13b-pretrain","score":42.9,"metric":"percent"},{"benchmark":"cmmlu","model":"ziya-llama-13b-pretrain","score":32.1,"metric":"percent"},{"benchmark":"cmmlu","model":"moss-moon-003-base","score":29.6,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-chat","score":56.74,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-chat","score":57.32,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-chat","score":59.68,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-chat-4bits","score":56.05,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-chat-4bits","score":56.24,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-13b-chat-4bits","score":58.82,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-chat","score":54.35,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-chat","score":52.93,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-chat","score":54.99,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-7b-chat-4bits","score":53.04,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-7b-chat-4bits","score":51.72,"metric":"percent"},{"benchmark":"cmmlu","model":"baichuan2-7b-chat-4bits","score":52.84,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-13b","score":47.73,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-13b","score":31.83,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-13b","score":22.03,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-13b","score":78.75,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-1-13b","score":52.47,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-13b","score":20.17,"metric":"percent"},{"benchmark":"race","model":"llama-1-13b","score":47.63,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1-13b","score":64.64,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-13b","score":37.93,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-13b","score":20.32,"metric":"percent"},{"benchmark":"piqa","model":"llama-1-13b","score":79.71,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-13b","score":14.02,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-13b","score":20.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-13b","score":54.99,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-13b","score":30.93,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-13b","score":82.42,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-13b","score":59.36,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-13b","score":24.85,"metric":"percent"},{"benchmark":"race","model":"llama-2-13b","score":58.86,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-13b","score":64.01,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-13b","score":45.62,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-13b","score":29.57,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-13b","score":79.76,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan2-13b-base","score":59.55,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan2-13b-base","score":59.01,"metric":"percent"},{"benchmark":"agieval","model":"baichuan2-13b-base","score":37.37,"metric":"percent"},{"benchmark":"triviaqa","model":"baichuan2-13b-base","score":46.61,"metric":"percent"},{"benchmark":"naturalquestions","model":"baichuan2-13b-base","score":16.32,"metric":"percent"},{"benchmark":"race","model":"baichuan2-13b-base","score":67.18,"metric":"percent"},{"benchmark":"winogrande","model":"baichuan2-13b-base","score":67.32,"metric":"percent"},{"benchmark":"bbh","model":"baichuan2-13b-base","score":48.98,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan2-13b-base","score":52.62,"metric":"percent"},{"benchmark":"piqa","model":"baichuan2-13b-base","score":78.07,"metric":"percent"},{"benchmark":"mmlu","model":"internlm-20b","score":62.05,"metric":"percent"},{"benchmark":"agieval","model":"internlm-20b","score":44.58,"metric":"percent"},{"benchmark":"boolq","model":"internlm-20b","score":87.46,"metric":"percent"},{"benchmark":"triviaqa","model":"internlm-20b","score":57.26,"metric":"percent"},{"benchmark":"naturalquestions","model":"internlm-20b","score":25.15,"metric":"percent"},{"benchmark":"race","model":"internlm-20b","score":83.28,"metric":"percent"},{"benchmark":"winogrande","model":"internlm-20b","score":69.38,"metric":"percent"},{"benchmark":"bbh","model":"internlm-20b","score":52.51,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-20b","score":52.62,"metric":"percent"},{"benchmark":"piqa","model":"internlm-20b","score":80.25,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-20b","score":25.61,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-33b","score":58.73,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-33b","score":37.47,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-33b","score":33.53,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-33b","score":84.43,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-1-33b","score":66.24,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-33b","score":30.89,"metric":"percent"},{"benchmark":"race","model":"llama-1-33b","score":62.61,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1-33b","score":66.85,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-33b","score":49.98,"metric":"percent"},{"benchmark":"piqa","model":"llama-1-33b","score":81.34,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-33b","score":17.68,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-33b","score":28.4,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-65b","score":63.71,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-65b","score":40.36,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-65b","score":33.92,"metric":"percent"},{"benchmark":"boolq","model":"llama-1-65b","score":86.61,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-1-65b","score":69.79,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-1-65b","score":33.41,"metric":"percent"},{"benchmark":"race","model":"llama-1-65b","score":68.01,"metric":"percent"},{"benchmark":"winogrande","model":"llama-1-65b","score":69.38,"metric":"percent"},{"benchmark":"bbh","model":"llama-1-65b","score":58.38,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-65b","score":54.44,"metric":"percent"},{"benchmark":"piqa","model":"llama-1-65b","score":82.15,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-65b","score":18.9,"metric":"percent"},{"benchmark":"mbpp","model":"llama-1-65b","score":33.6,"metric":"percent"},{"benchmark":"mmlu","model":"llama-2-70b","score":69.75,"metric":"percent"},{"benchmark":"c-eval","model":"llama-2-70b","score":50.13,"metric":"percent"},{"benchmark":"agieval","model":"llama-2-70b","score":40.02,"metric":"percent"},{"benchmark":"boolq","model":"llama-2-70b","score":87.74,"metric":"percent"},{"benchmark":"triviaqa","model":"llama-2-70b","score":70.71,"metric":"percent"},{"benchmark":"naturalquestions","model":"llama-2-70b","score":34.16,"metric":"percent"},{"benchmark":"race","model":"llama-2-70b","score":79.93,"metric":"percent"},{"benchmark":"winogrande","model":"llama-2-70b","score":69.77,"metric":"percent"},{"benchmark":"bbh","model":"llama-2-70b","score":64.91,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-2-70b","score":63.31,"metric":"percent"},{"benchmark":"piqa","model":"llama-2-70b","score":82.54,"metric":"percent"},{"benchmark":"humaneval","model":"llama-2-70b","score":26.22,"metric":"percent"},{"benchmark":"mbpp","model":"llama-2-70b","score":39.6,"metric":"percent"},{"benchmark":"c-eval","model":"internlm-chat-7b","score":53.2,"metric":"percent"},{"benchmark":"agieval","model":"internlm-chat-7b","score":42.5,"metric":"percent"},{"benchmark":"commonsenseqa","model":"internlm-chat-7b","score":75.2,"metric":"percent"},{"benchmark":"cluewsc","model":"internlm-chat-7b","score":78.6,"metric":"percent"},{"benchmark":"math","model":"internlm-chat-7b","score":6.4,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm-chat-7b","score":34.5,"metric":"percent"},{"benchmark":"humaneval","model":"internlm-chat-7b","score":14,"metric":"percent"},{"benchmark":"race","model":"internlm-chat-7b","score":76.3,"metric":"percent"},{"benchmark":"agieval","model":"internlm-7b","score":37.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"internlm-7b","score":59.5,"metric":"percent"},{"benchmark":"cluewsc","model":"internlm-7b","score":59.1,"metric":"percent"},{"benchmark":"math","model":"internlm-7b","score":7.1,"metric":"percent"},{"benchmark":"race","model":"internlm-7b","score":57.4,"metric":"percent"},{"benchmark":"c-eval","model":"llama-1-7b","score":24.2,"metric":"percent"},{"benchmark":"mmlu","model":"llama-1-7b","score":35.2,"metric":"percent"},{"benchmark":"agieval","model":"llama-1-7b","score":20.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"llama-1-7b","score":65,"metric":"percent"},{"benchmark":"cluewsc","model":"llama-1-7b","score":50.3,"metric":"percent"},{"benchmark":"math","model":"llama-1-7b","score":2.8,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-1-7b","score":10.1,"metric":"percent"},{"benchmark":"humaneval","model":"llama-1-7b","score":14,"metric":"percent"},{"benchmark":"race","model":"llama-1-7b","score":46.9,"metric":"percent"},{"benchmark":"c-eval","model":"baichuan-7b","score":42.7,"metric":"percent"},{"benchmark":"mmlu","model":"baichuan-7b","score":41.5,"metric":"percent"},{"benchmark":"agieval","model":"baichuan-7b","score":24.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"baichuan-7b","score":58.8,"metric":"percent"},{"benchmark":"cluewsc","model":"baichuan-7b","score":52.8,"metric":"percent"},{"benchmark":"math","model":"baichuan-7b","score":3,"metric":"percent"},{"benchmark":"gsm8k","model":"baichuan-7b","score":9.7,"metric":"percent"},{"benchmark":"race","model":"baichuan-7b","score":28.1,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm2-6b","score":50.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"chatglm2-6b","score":60,"metric":"percent"},{"benchmark":"cluewsc","model":"chatglm2-6b","score":59.8,"metric":"percent"},{"benchmark":"math","model":"chatglm2-6b","score":6.6,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b","score":29.2,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm2-6b","score":9.2,"metric":"percent"},{"benchmark":"race","model":"chatglm2-6b","score":66.3,"metric":"percent"},{"benchmark":"c-eval","model":"alpaca-7b","score":28.9,"metric":"percent"},{"benchmark":"mmlu","model":"alpaca-7b","score":39.7,"metric":"percent"},{"benchmark":"agieval","model":"alpaca-7b","score":24.1,"metric":"percent"},{"benchmark":"commonsenseqa","model":"alpaca-7b","score":68.7,"metric":"percent"},{"benchmark":"cluewsc","model":"alpaca-7b","score":50.3,"metric":"percent"},{"benchmark":"math","model":"alpaca-7b","score":2.2,"metric":"percent"},{"benchmark":"gsm8k","model":"alpaca-7b","score":6,"metric":"percent"},{"benchmark":"humaneval","model":"alpaca-7b","score":9.2,"metric":"percent"},{"benchmark":"race","model":"alpaca-7b","score":40.7,"metric":"percent"},{"benchmark":"c-eval","model":"vicuna-7b","score":31.2,"metric":"percent"},{"benchmark":"mmlu","model":"vicuna-7b","score":47.3,"metric":"percent"},{"benchmark":"agieval","model":"vicuna-7b","score":26.4,"metric":"percent"},{"benchmark":"commonsenseqa","model":"vicuna-7b","score":66.7,"metric":"percent"},{"benchmark":"cluewsc","model":"vicuna-7b","score":52.2,"metric":"percent"},{"benchmark":"math","model":"vicuna-7b","score":2.8,"metric":"percent"},{"benchmark":"gsm8k","model":"vicuna-7b","score":15.3,"metric":"percent"},{"benchmark":"humaneval","model":"vicuna-7b","score":11,"metric":"percent"},{"benchmark":"race","model":"vicuna-7b","score":54,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2.5-1.8b-chat","score":50.7,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2.5-1.8b-chat","score":62.2,"metric":"percent"},{"benchmark":"bbh","model":"internlm2.5-1.8b-chat","score":41.9,"metric":"percent"},{"benchmark":"math","model":"internlm2.5-1.8b-chat","score":40.2,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2.5-1.8b-chat","score":27.8,"metric":"percent"},{"benchmark":"mmlu","model":"minicpm-2b-sft","score":54.2,"metric":"percent"},{"benchmark":"cmmlu","model":"minicpm-2b-sft","score":50.6,"metric":"percent"},{"benchmark":"bbh","model":"minicpm-2b-sft","score":41.5,"metric":"percent"},{"benchmark":"math","model":"minicpm-2b-sft","score":15.5,"metric":"percent"},{"benchmark":"gpqa","model":"minicpm-2b-sft","score":23.7,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-1.5b-instruct","score":55.7,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2-1.5b-instruct","score":65.2,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-1.5b-instruct","score":36.5,"metric":"percent"},{"benchmark":"math","model":"qwen2-1.5b-instruct","score":21.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-1.5b-instruct","score":27.3,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2.5-1.8b","score":53.52,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2.5-1.8b","score":65.44,"metric":"percent"},{"benchmark":"bbh","model":"internlm2.5-1.8b","score":41.16,"metric":"percent"},{"benchmark":"math","model":"internlm2.5-1.8b","score":27.28,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2.5-1.8b","score":35.98,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2.5-1.8b","score":24.24,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-1.8b","score":45.99,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-1.8b","score":45.27,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-1.8b","score":36.03,"metric":"percent"},{"benchmark":"math","model":"internlm2-1.8b","score":9.42,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-1.8b","score":30.49,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2-1.8b","score":24.24,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-1.5b","score":57.45,"metric":"percent"},{"benchmark":"cmmlu","model":"qwen2-1.5b","score":70.58,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-1.5b","score":35.75,"metric":"percent"},{"benchmark":"math","model":"qwen2-1.5b","score":24.38,"metric":"percent"},{"benchmark":"humaneval","model":"qwen2-1.5b","score":34.15,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-1.5b","score":31.82,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2_5-20b-chat","score":73.5,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2_5-20b-chat","score":79.7,"metric":"percent"},{"benchmark":"bbh","model":"internlm2_5-20b-chat","score":76.3,"metric":"percent"},{"benchmark":"math","model":"internlm2_5-20b-chat","score":64.7,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2_5-20b-chat","score":33.3,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-27b-it","score":75,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-2-27b-it","score":63.3,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-27b-it","score":71.5,"metric":"percent"},{"benchmark":"math","model":"gemma-2-27b-it","score":50.1,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-27b-it","score":29.3,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2.5-20b","score":74.25,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2.5-20b","score":82.22,"metric":"percent"},{"benchmark":"bbh","model":"internlm2.5-20b","score":77.82,"metric":"percent"},{"benchmark":"math","model":"internlm2.5-20b","score":48,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2.5-20b","score":71.95,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2.5-20b","score":37.88,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2-20b","score":67.58,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-20b","score":68.29,"metric":"percent"},{"benchmark":"bbh","model":"internlm2-20b","score":71.36,"metric":"percent"},{"benchmark":"math","model":"internlm2-20b","score":32.66,"metric":"percent"},{"benchmark":"humaneval","model":"internlm2-20b","score":51.22,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2-20b","score":31.31,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2.5-7b-chat","score":78,"metric":"percent"},{"benchmark":"bbh","model":"internlm2.5-7b-chat","score":71.6,"metric":"percent"},{"benchmark":"math","model":"internlm2.5-7b-chat","score":60.1,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2.5-7b-chat","score":86,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2.5-7b-chat","score":38.4,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-8b-instruct","score":53.3,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-8b-instruct","score":54.4,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b-instruct","score":27.9,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b-instruct","score":72.9,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-8b-instruct","score":26.1,"metric":"percent"},{"benchmark":"mmlu","model":"gemma-2-9b-it","score":70.9,"metric":"percent"},{"benchmark":"cmmlu","model":"gemma-2-9b-it","score":60.3,"metric":"percent"},{"benchmark":"bbh","model":"gemma-2-9b-it","score":68.2,"metric":"percent"},{"benchmark":"math","model":"gemma-2-9b-it","score":46.9,"metric":"percent"},{"benchmark":"gsm8k","model":"gemma-2-9b-it","score":88.9,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-2-9b-it","score":33.8,"metric":"percent"},{"benchmark":"mmlu","model":"yi-1.5-9b-chat","score":71,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-1.5-9b-chat","score":74.5,"metric":"percent"},{"benchmark":"bbh","model":"yi-1.5-9b-chat","score":69.6,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-9b-chat","score":51.1,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-9b-chat","score":80.1,"metric":"percent"},{"benchmark":"gpqa","model":"yi-1.5-9b-chat","score":37.9,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4-9b-chat","score":71.4,"metric":"percent"},{"benchmark":"cmmlu","model":"glm-4-9b-chat","score":74.5,"metric":"percent"},{"benchmark":"bbh","model":"glm-4-9b-chat","score":69.6,"metric":"percent"},{"benchmark":"math","model":"glm-4-9b-chat","score":51.1,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4-9b-chat","score":85.3,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4-9b-chat","score":36.9,"metric":"percent"},{"benchmark":"mmlu","model":"qwen2-7b-instruct","score":70.8,"metric":"percent"},{"benchmark":"bbh","model":"qwen2-7b-instruct","score":65,"metric":"percent"},{"benchmark":"math","model":"qwen2-7b-instruct","score":48.6,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen2-7b-instruct","score":82.9,"metric":"percent"},{"benchmark":"gpqa","model":"qwen2-7b-instruct","score":38.4,"metric":"percent"},{"benchmark":"mmlu","model":"internlm2.5-7b","score":71.6,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2.5-7b","score":79.1,"metric":"percent"},{"benchmark":"bbh","model":"internlm2.5-7b","score":70.1,"metric":"percent"},{"benchmark":"math","model":"internlm2.5-7b","score":34,"metric":"percent"},{"benchmark":"gsm8k","model":"internlm2.5-7b","score":74.8,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2.5-7b","score":31.3,"metric":"percent"},{"benchmark":"cmmlu","model":"internlm2-7b","score":66.2,"metric":"percent"},{"benchmark":"gpqa","model":"internlm2-7b","score":28.3,"metric":"percent"},{"benchmark":"mmlu","model":"llama-3-8b","score":66.4,"metric":"percent"},{"benchmark":"cmmlu","model":"llama-3-8b","score":51,"metric":"percent"},{"benchmark":"bbh","model":"llama-3-8b","score":59.7,"metric":"percent"},{"benchmark":"math","model":"llama-3-8b","score":16.4,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b","score":54.3,"metric":"percent"},{"benchmark":"gpqa","model":"llama-3-8b","score":31.3,"metric":"percent"},{"benchmark":"mmlu","model":"yi-1.5-9b","score":71.6,"metric":"percent"},{"benchmark":"cmmlu","model":"yi-1.5-9b","score":74.1,"metric":"percent"},{"benchmark":"bbh","model":"yi-1.5-9b","score":71.1,"metric":"percent"},{"benchmark":"math","model":"yi-1.5-9b","score":31.9,"metric":"percent"},{"benchmark":"gsm8k","model":"yi-1.5-9b","score":74.5,"metric":"percent"},{"benchmark":"gpqa","model":"yi-1.5-9b","score":27.8,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4-turbo-2024-04-09","score":63.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"gpt-4-turbo-2024-04-09","score":58.1,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4-turbo-2024-04-09","score":89.4,"metric":"percent"},{"benchmark":"chartqa","model":"gpt-4-turbo-2024-04-09","score":78.1,"metric":"percent"},{"benchmark":"docvqa","model":"gpt-4-turbo-2024-04-09","score":87.2,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4-turbo-2024-04-09","score":67.8,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4o-2024-05-13","score":94.2,"metric":"percent"},{"benchmark":"ocrbench","model":"cambrian-1-34b","score":60,"metric":"percent"},{"benchmark":"mmmu","model":"llava-next-110b","score":50.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-next-110b","score":49,"metric":"percent"},{"benchmark":"ai2d","model":"llava-next-110b","score":80.4,"metric":"percent"},{"benchmark":"chartqa","model":"llava-next-110b","score":79.7,"metric":"percent"},{"benchmark":"docvqa","model":"llava-next-110b","score":85.7,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-pro","score":58.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"internvl2-pro","score":66.3,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-pro","score":87.3,"metric":"percent"},{"benchmark":"chartqa","model":"internvl2-pro","score":87.1,"metric":"percent"},{"benchmark":"docvqa","model":"internvl2-pro","score":95.1,"metric":"percent"},{"benchmark":"infovqa","model":"internvl2-pro","score":83.3,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl2-pro","score":83.7,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-2b","score":34.3,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-4b","score":47,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-8b","score":49.3,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-26b","score":48.3,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-40b","score":53.9,"metric":"percent"},{"benchmark":"ai2d","model":"internvl2-40b","score":87.1,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-llama-3-76b","score":55.2,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-8b","score":51.2,"metric":"percent"},{"benchmark":"gsm8k","model":"llama-3-8b","score":45.8,"metric":"percent"},{"benchmark":"c-eval","model":"llama-3-8b-instruct","score":51.3,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm3-6b-base","score":61.4,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm3-6b-base","score":69,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm3-6b-base","score":72.3,"metric":"percent"},{"benchmark":"math","model":"chatglm3-6b-base","score":25.7,"metric":"percent"},{"benchmark":"mmlu","model":"glm4-9b","score":74.7,"metric":"percent"},{"benchmark":"c-eval","model":"glm4-9b","score":77.1,"metric":"percent"},{"benchmark":"gpqa","model":"glm4-9b","score":34.3,"metric":"percent"},{"benchmark":"gsm8k","model":"glm4-9b","score":84,"metric":"percent"},{"benchmark":"math","model":"glm4-9b","score":30.4,"metric":"percent"},{"benchmark":"humaneval","model":"glm4-9b","score":70.1,"metric":"percent"},{"benchmark":"alignbench","model":"llama-3-8b-instruct","score":5.12,"metric":"score"},{"benchmark":"ifeval","model":"llama-3-8b-instruct","score":68.58,"metric":"percent"},{"benchmark":"naturalcodebench","model":"llama-3-8b-instruct","score":24.7,"metric":"percent"},{"benchmark":"alignbench","model":"chatglm3-6b","score":3.97,"metric":"score"},{"benchmark":"mt-bench","model":"chatglm3-6b","score":5.5,"metric":"percent"},{"benchmark":"ifeval","model":"chatglm3-6b","score":28.1,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm3-6b","score":66.4,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm3-6b","score":69,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm3-6b","score":58.5,"metric":"percent"},{"benchmark":"naturalcodebench","model":"chatglm3-6b","score":11.3,"metric":"percent"},{"benchmark":"ifeval","model":"glm-4-9b-chat","score":69,"metric":"percent"},{"benchmark":"naturalcodebench","model":"glm-4-9b-chat","score":32.2,"metric":"percent"},{"benchmark":"mmmlu","model":"llama-3-8b-instruct","score":49.6,"metric":"percent"},{"benchmark":"flores","model":"llama-3-8b-instruct","score":25,"metric":"percent"},{"benchmark":"mgsm","model":"llama-3-8b-instruct","score":54,"metric":"percent"},{"benchmark":"xwinograd","model":"llama-3-8b-instruct","score":61.7,"metric":"percent"},{"benchmark":"xstorycloze","model":"llama-3-8b-instruct","score":84.7,"metric":"percent"},{"benchmark":"xcopa","model":"llama-3-8b-instruct","score":73.3,"metric":"percent"},{"benchmark":"mmmlu","model":"glm-4-9b-chat","score":56.6,"metric":"percent"},{"benchmark":"flores","model":"glm-4-9b-chat","score":28.8,"metric":"percent"},{"benchmark":"mgsm","model":"glm-4-9b-chat","score":65.3,"metric":"percent"},{"benchmark":"xwinograd","model":"glm-4-9b-chat","score":73.1,"metric":"percent"},{"benchmark":"xstorycloze","model":"glm-4-9b-chat","score":90.7,"metric":"percent"},{"benchmark":"xcopa","model":"glm-4-9b-chat","score":80.1,"metric":"percent"},{"benchmark":"bfcl","model":"llama-3-8b-instruct","score":58.88,"metric":"percent"},{"benchmark":"bfcl","model":"gpt-4-turbo-2024-04-09","score":81.24,"metric":"percent"},{"benchmark":"bfcl","model":"chatglm3-6b","score":57.88,"metric":"percent"},{"benchmark":"bfcl","model":"glm-4-9b-chat","score":81,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gpt-4o-2024-05-13","score":77.1,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4o-2024-05-13","score":63.9,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4o-2024-05-13","score":2310.3,"metric":"points"},{"benchmark":"mmbench","model":"gpt-4-turbo-2024-04-09","score":81,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gpt-4-turbo-2024-04-09","score":80.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gpt-4-turbo-2024-04-09","score":73,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4-turbo-2024-04-09","score":56,"metric":"percent"},{"benchmark":"mmmu","model":"gpt-4-turbo-2024-04-09","score":61.7,"metric":"percent"},{"benchmark":"mme-elo","model":"gpt-4-turbo-2024-04-09","score":2070.2,"metric":"points"},{"benchmark":"hallusionbench","model":"gpt-4-turbo-2024-04-09","score":43.9,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4-turbo-2024-04-09","score":78.6,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4-turbo-2024-04-09","score":65.6,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gpt-4-1106-vision-preview","score":72.3,"metric":"percent"},{"benchmark":"mmstar","model":"gpt-4-1106-vision-preview","score":49.7,"metric":"percent"},{"benchmark":"hallusionbench","model":"gpt-4-1106-vision-preview","score":46.5,"metric":"percent"},{"benchmark":"ai2d","model":"gpt-4-1106-vision-preview","score":75.9,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4-1106-vision-preview","score":51.6,"metric":"percent"},{"benchmark":"mmbench","model":"internvl-chat-v1.5","score":82.3,"metric":"percent"},{"benchmark":"mmbench-cn","model":"internvl-chat-v1.5","score":80.7,"metric":"percent"},{"benchmark":"seed-bench-img","model":"internvl-chat-v1.5","score":75.2,"metric":"percent"},{"benchmark":"mmstar","model":"internvl-chat-v1.5","score":57.1,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl-chat-v1.5","score":2189.6,"metric":"points"},{"benchmark":"hallusionbench","model":"internvl-chat-v1.5","score":47.4,"metric":"percent"},{"benchmark":"ai2d","model":"internvl-chat-v1.5","score":80.6,"metric":"percent"},{"benchmark":"ocrbench","model":"internvl-chat-v1.5","score":72,"metric":"percent"},{"benchmark":"seed-bench-img","model":"llava-next-34b","score":75.7,"metric":"percent"},{"benchmark":"mmstar","model":"llava-next-34b","score":51.6,"metric":"percent"},{"benchmark":"mme-elo","model":"llava-next-34b","score":2050.2,"metric":"points"},{"benchmark":"mmstar","model":"step-1v-32k","score":50,"metric":"percent"},{"benchmark":"mmbench","model":"minicpm-llama3-v2.5","score":77.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"minicpm-llama3-v2.5","score":73.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"minicpm-llama3-v2.5","score":72.3,"metric":"percent"},{"benchmark":"mmstar","model":"minicpm-llama3-v2.5","score":51.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"qwen-vl-max","score":72.7,"metric":"percent"},{"benchmark":"mmstar","model":"qwen-vl-max","score":49.5,"metric":"percent"},{"benchmark":"mmbench","model":"gemini-1.0-pro-vision","score":73.6,"metric":"percent"},{"benchmark":"mmbench-cn","model":"gemini-1.0-pro-vision","score":74.3,"metric":"percent"},{"benchmark":"seed-bench-img","model":"gemini-1.0-pro-vision","score":70.7,"metric":"percent"},{"benchmark":"mmstar","model":"gemini-1.0-pro-vision","score":38.6,"metric":"percent"},{"benchmark":"mmmu","model":"gemini-1.0-pro-vision","score":49,"metric":"percent"},{"benchmark":"mme-elo","model":"gemini-1.0-pro-vision","score":2148.9,"metric":"points"},{"benchmark":"hallusionbench","model":"gemini-1.0-pro-vision","score":45.7,"metric":"percent"},{"benchmark":"ai2d","model":"gemini-1.0-pro-vision","score":72.9,"metric":"percent"},{"benchmark":"ocrbench","model":"gemini-1.0-pro-vision","score":68,"metric":"percent"},{"benchmark":"seed-bench-img","model":"claude-3-opus","score":64,"metric":"percent"},{"benchmark":"mmbench","model":"glm-4v-9b","score":81.1,"metric":"percent"},{"benchmark":"mmbench-cn","model":"glm-4v-9b","score":79.4,"metric":"percent"},{"benchmark":"seed-bench-img","model":"glm-4v-9b","score":76.8,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4v-9b","score":58.7,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4v-9b","score":47.2,"metric":"percent"},{"benchmark":"mme-elo","model":"glm-4v-9b","score":2163.8,"metric":"points"},{"benchmark":"hallusionbench","model":"glm-4v-9b","score":46.6,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4v-9b","score":81.1,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4v-9b","score":78.6,"metric":"percent"},{"benchmark":"naturalcodebench","model":"llama-3-70b-instruct","score":37,"metric":"percent"},{"benchmark":"livecodebench","model":"llama-3-70b-instruct","score":27.4,"metric":"percent"},{"benchmark":"naturalcodebench","model":"deepseek-coder-33b-instruct","score":39.3,"metric":"percent"},{"benchmark":"livecodebench","model":"deepseek-coder-33b-instruct","score":29.3,"metric":"percent"},{"benchmark":"humaneval-fim","model":"deepseek-coder-33b-instruct","score":78.2,"metric":"percent"},{"benchmark":"cruxeval","model":"deepseek-coder-33b-instruct","score":49.9,"metric":"percent"},{"benchmark":"naturalcodebench","model":"codestral-22b","score":46,"metric":"percent"},{"benchmark":"livecodebench","model":"codestral-22b","score":35.3,"metric":"percent"},{"benchmark":"humaneval-fim","model":"codestral-22b","score":91.6,"metric":"percent"},{"benchmark":"mbpp","model":"codegeex4-all-9b","score":75.7,"metric":"percent"},{"benchmark":"naturalcodebench","model":"codegeex4-all-9b","score":40.4,"metric":"percent"},{"benchmark":"livecodebench","model":"codegeex4-all-9b","score":28.5,"metric":"percent"},{"benchmark":"humaneval-fim","model":"codegeex4-all-9b","score":85,"metric":"percent"},{"benchmark":"cruxeval","model":"codegeex4-all-9b","score":47.1,"metric":"percent"},{"benchmark":"textvqa","model":"cogvlm-17b-chat","score":69.7,"metric":"percent"},{"benchmark":"chartqa","model":"cogvlm-17b-chat","score":68.3,"metric":"percent"},{"benchmark":"mmvet","model":"cogvlm-17b-chat","score":52,"metric":"percent"},{"benchmark":"ocrbench","model":"llava-1.5-13b","score":33.7,"metric":"percent"},{"benchmark":"chartqa","model":"llava-next-llama3","score":69.5,"metric":"percent"},{"benchmark":"mmbench","model":"llava-next-llama3","score":72.1,"metric":"percent"},{"benchmark":"mmmu","model":"llava-next-110b","score":49.1,"metric":"percent"},{"benchmark":"mmbench","model":"llava-next-110b","score":80.5,"metric":"percent"},{"benchmark":"mmvet","model":"internvl-chat-v1.5","score":55.4,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen-vl-plus","score":72.6,"metric":"percent"},{"benchmark":"mmmu","model":"qwen-vl-plus","score":51.4,"metric":"percent"},{"benchmark":"ocrbench","model":"gpt-4v","score":65.6,"metric":"percent"},{"benchmark":"textvqa","model":"cogvlm2-llama3-chat-19b","score":84.2,"metric":"percent"},{"benchmark":"docvqa","model":"cogvlm2-llama3-chat-19b","score":92.3,"metric":"percent"},{"benchmark":"chartqa","model":"cogvlm2-llama3-chat-19b","score":81,"metric":"percent"},{"benchmark":"ocrbench","model":"cogvlm2-llama3-chat-19b","score":75.6,"metric":"percent"},{"benchmark":"mmmu","model":"cogvlm2-llama3-chat-19b","score":44.3,"metric":"percent"},{"benchmark":"mmvet","model":"cogvlm2-llama3-chat-19b","score":60.4,"metric":"percent"},{"benchmark":"mmbench","model":"cogvlm2-llama3-chat-19b","score":80.5,"metric":"percent"},{"benchmark":"textvqa","model":"cogvlm2-llama3-chinese-chat-19b","score":85,"metric":"percent"},{"benchmark":"docvqa","model":"cogvlm2-llama3-chinese-chat-19b","score":88.4,"metric":"percent"},{"benchmark":"chartqa","model":"cogvlm2-llama3-chinese-chat-19b","score":74.7,"metric":"percent"},{"benchmark":"ocrbench","model":"cogvlm2-llama3-chinese-chat-19b","score":78,"metric":"percent"},{"benchmark":"mmmu","model":"cogvlm2-llama3-chinese-chat-19b","score":42.8,"metric":"percent"},{"benchmark":"mmvet","model":"cogvlm2-llama3-chinese-chat-19b","score":60.5,"metric":"percent"},{"benchmark":"mmbench","model":"cogvlm2-llama3-chinese-chat-19b","score":78.9,"metric":"percent"},{"benchmark":"chartqa","model":"step-1v-32k","score":57.7,"metric":"percent"},{"benchmark":"mme-elo","model":"gemini-1.5-pro","score":2110,"metric":"points"},{"benchmark":"mmvet","model":"gpt-4-1106-vision-preview","score":56.8,"metric":"percent"},{"benchmark":"mmstar","model":"cogvlm-17b-chat","score":39.9,"metric":"percent"},{"benchmark":"mme-elo","model":"cogvlm-17b-chat","score":1737,"metric":"points"},{"benchmark":"mmmu","model":"cambrian-34b","score":50.4,"metric":"percent"},{"benchmark":"mme-elo","model":"cambrian-34b","score":2050,"metric":"points"},{"benchmark":"chartqa","model":"cambrian-34b","score":73.7,"metric":"percent"},{"benchmark":"textvqa","model":"cambrian-34b","score":72.1,"metric":"percent"},{"benchmark":"ocrbench","model":"cambrian-34b","score":59.1,"metric":"percent"},{"benchmark":"mmbench","model":"llava-1.5-13b","score":69.2,"metric":"percent"},{"benchmark":"mmstar","model":"llava-1.5-13b","score":34.3,"metric":"percent"},{"benchmark":"mmvet","model":"llava-1.5-13b","score":36.3,"metric":"percent"},{"benchmark":"mme-elo","model":"llava-1.5-13b","score":1781,"metric":"points"},{"benchmark":"textvqa","model":"llava-1.5-13b","score":48.9,"metric":"percent"},{"benchmark":"mmstar","model":"internvl2-26b","score":61,"metric":"percent"},{"benchmark":"mmvet","model":"internvl2-26b","score":60,"metric":"percent"},{"benchmark":"mmmu","model":"internvl2-26b","score":50.7,"metric":"percent"},{"benchmark":"mme-elo","model":"internvl2-26b","score":2259,"metric":"points"},{"benchmark":"textvqa","model":"internvl2-26b","score":82.5,"metric":"percent"},{"benchmark":"mme-elo","model":"llava-next-34b","score":2006,"metric":"points"},{"benchmark":"chartqa","model":"llava-next-34b","score":67.6,"metric":"percent"},{"benchmark":"mmstar","model":"cogvlm2-llama3-chat-19b","score":50.5,"metric":"percent"},{"benchmark":"mme-elo","model":"cogvlm2-llama3-chat-19b","score":1870,"metric":"points"},{"benchmark":"ai2d","model":"cogvlm2-llama3-chat-19b","score":73.4,"metric":"percent"},{"benchmark":"chartqa","model":"glm-4v-9b","score":71.1,"metric":"percent"},{"benchmark":"textvqa","model":"glm-4v-9b","score":83,"metric":"percent"},{"benchmark":"docvqa","model":"glm-4v-9b","score":81,"metric":"percent"},{"benchmark":"mmbench","model":"glm-4v-plus","score":84.6,"metric":"percent"},{"benchmark":"mmstar","model":"glm-4v-plus","score":62.9,"metric":"percent"},{"benchmark":"mmvet","model":"glm-4v-plus","score":71.1,"metric":"percent"},{"benchmark":"mmmu","model":"glm-4v-plus","score":53,"metric":"percent"},{"benchmark":"mme-elo","model":"glm-4v-plus","score":2275,"metric":"points"},{"benchmark":"chartqa","model":"glm-4v-plus","score":83.1,"metric":"percent"},{"benchmark":"ai2d","model":"glm-4v-plus","score":83.9,"metric":"percent"},{"benchmark":"textvqa","model":"glm-4v-plus","score":86.6,"metric":"percent"},{"benchmark":"docvqa","model":"glm-4v-plus","score":92.3,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-4v-plus","score":83.3,"metric":"percent"},{"benchmark":"mvbench","model":"st-llm-7b","score":54.9,"metric":"percent"},{"benchmark":"mvbench","model":"sharegpt4video-8b","score":51.2,"metric":"percent"},{"benchmark":"mvbench","model":"videogpt-plus","score":58.7,"metric":"percent"},{"benchmark":"mvbench","model":"pllava-34b","score":58.1,"metric":"percent"},{"benchmark":"lvbench","model":"pllava-34b","score":26.1,"metric":"percent"},{"benchmark":"mvbench","model":"gpt-4o-2024-05-13","score":47.8,"metric":"percent"},{"benchmark":"lvbench","model":"gpt-4o-2024-05-13","score":34.7,"metric":"percent"},{"benchmark":"mvbench","model":"gemini-1.5-pro","score":52.6,"metric":"percent"},{"benchmark":"mvbench","model":"cogvlm2-video-llama3-chat","score":62.3,"metric":"percent"},{"benchmark":"lvbench","model":"cogvlm2-video-llama3-chat","score":28.1,"metric":"percent"},{"benchmark":"mvbench","model":"glm-4v-plus","score":71.2,"metric":"percent"},{"benchmark":"lvbench","model":"glm-4v-plus","score":38.3,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm-6b","score":40.63,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm-6b","score":38.9,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm-6b","score":4.82,"metric":"percent"},{"benchmark":"bbh","model":"chatglm-6b","score":18.73,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b-base","score":47.86,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b-base","score":32.37,"metric":"percent"},{"benchmark":"bbh","model":"chatglm2-6b-base","score":33.68,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b","score":45.46,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b","score":28.05,"metric":"percent"},{"benchmark":"bbh","model":"chatglm2-6b","score":30,"metric":"percent"},{"benchmark":"bbh","model":"chatglm3-6b-base","score":66.1,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm3-6b-base","score":67.5,"metric":"percent"},{"benchmark":"mbpp","model":"chatglm3-6b-base","score":52.4,"metric":"percent"},{"benchmark":"agieval","model":"chatglm3-6b-base","score":53.7,"metric":"percent"},{"benchmark":"longbench","model":"chatglm2-6b-32k","score":41.5,"metric":"percent"},{"benchmark":"longbench","model":"chatglm3-6b-32k","score":50.2,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm-6b","score":1.5,"metric":"percent"},{"benchmark":"math","model":"chatglm-6b","score":3.1,"metric":"percent"},{"benchmark":"bbh","model":"chatglm-6b","score":0,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm-6b","score":25.2,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm-6b","score":0,"metric":"percent"},{"benchmark":"boolq","model":"chatglm-6b","score":51.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"chatglm-6b","score":20.5,"metric":"percent"},{"benchmark":"hellaswag","model":"chatglm-6b","score":30.4,"metric":"percent"},{"benchmark":"piqa","model":"chatglm-6b","score":65.7,"metric":"percent"},{"benchmark":"drop","model":"chatglm-6b","score":3.9,"metric":"percent"},{"benchmark":"c-eval","model":"chatglm-6b","score":23.7,"metric":"percent"},{"benchmark":"cmmlu","model":"chatglm-6b","score":25.3,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm-6b","score":26.8,"metric":"percent"},{"benchmark":"c3","model":"chatglm-6b","score":35.1,"metric":"percent"},{"benchmark":"gsm8k","model":"chatglm2-6b-base","score":25.9,"metric":"percent"},{"benchmark":"math","model":"chatglm2-6b-base","score":6.9,"metric":"percent"},{"benchmark":"bbh","model":"chatglm2-6b-base","score":29.2,"metric":"percent"},{"benchmark":"mmlu","model":"chatglm2-6b-base","score":45.2,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm2-6b-base","score":9.8,"metric":"percent"},{"benchmark":"boolq","model":"chatglm2-6b-base","score":79,"metric":"percent"},{"benchmark":"commonsenseqa","model":"chatglm2-6b-base","score":65.4,"metric":"percent"},{"benchmark":"hellaswag","model":"chatglm2-6b-base","score":57,"metric":"percent"},{"benchmark":"piqa","model":"chatglm2-6b-base","score":69.6,"metric":"percent"},{"benchmark":"drop","model":"chatglm2-6b-base","score":25.6,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm2-6b-base","score":46.4,"metric":"percent"},{"benchmark":"c3","model":"chatglm2-6b-base","score":58.6,"metric":"percent"},{"benchmark":"gpqa","model":"chatglm3-6b-base","score":26.8,"metric":"percent"},{"benchmark":"humaneval","model":"chatglm3-6b-base","score":58.5,"metric":"percent"},{"benchmark":"boolq","model":"chatglm3-6b-base","score":87.9,"metric":"percent"},{"benchmark":"commonsenseqa","model":"chatglm3-6b-base","score":86.5,"metric":"percent"},{"benchmark":"hellaswag","model":"chatglm3-6b-base","score":79.7,"metric":"percent"},{"benchmark":"piqa","model":"chatglm3-6b-base","score":80.1,"metric":"percent"},{"benchmark":"drop","model":"chatglm3-6b-base","score":70.9,"metric":"percent"},{"benchmark":"gaokao-bench","model":"chatglm3-6b-base","score":67.3,"metric":"percent"},{"benchmark":"c3","model":"chatglm3-6b-base","score":73.9,"metric":"percent"},{"benchmark":"bbh","model":"glm4-9b","score":76.3,"metric":"percent"},{"benchmark":"boolq","model":"glm4-9b","score":89.6,"metric":"percent"},{"benchmark":"commonsenseqa","model":"glm4-9b","score":90.7,"metric":"percent"},{"benchmark":"hellaswag","model":"glm4-9b","score":82.6,"metric":"percent"},{"benchmark":"piqa","model":"glm4-9b","score":79.1,"metric":"percent"},{"benchmark":"drop","model":"glm4-9b","score":77.2,"metric":"percent"},{"benchmark":"cmmlu","model":"glm4-9b","score":75.1,"metric":"percent"},{"benchmark":"gaokao-bench","model":"glm4-9b","score":74.5,"metric":"percent"},{"benchmark":"c3","model":"glm4-9b","score":77.2,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4-0314","score":86.4,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4-0314","score":92,"metric":"percent"},{"benchmark":"math","model":"gpt-4-0314","score":52.9,"metric":"percent"},{"benchmark":"bbh","model":"gpt-4-0314","score":83.1,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4-0314","score":35.7,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4-0314","score":67,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4-1106-preview","score":84.7,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4-1106-preview","score":95.7,"metric":"percent"},{"benchmark":"bbh","model":"gpt-4-1106-preview","score":88.3,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4-1106-preview","score":42.5,"metric":"percent"},{"benchmark":"humaneval","model":"gpt-4-1106-preview","score":83.7,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-4-turbo-2024-04-09","score":86.7,"metric":"percent"},{"benchmark":"gsm8k","model":"gpt-4-turbo-2024-04-09","score":95.6,"metric":"percent"},{"benchmark":"bbh","model":"gpt-4-turbo-2024-04-09","score":88.2,"metric":"percent"},{"benchmark":"gpqa","model":"gpt-4-turbo-2024-04-09","score":49.3,"metric":"percent"},{"benchmark":"mmlu","model":"claude-3-opus","score":86.8,"metric":"percent"},{"benchmark":"math","model":"claude-3-opus","score":60.1,"metric":"percent"},{"benchmark":"bbh","model":"claude-3-opus","score":86.8,"metric":"percent"},{"benchmark":"gpqa","model":"claude-3-opus","score":50.4,"metric":"percent"},{"benchmark":"mmlu","model":"gemini-1.5-pro","score":85.9,"metric":"percent"},{"benchmark":"gpqa","model":"gemini-1.5-pro","score":46.2,"metric":"percent"},{"benchmark":"humaneval","model":"gemini-1.5-pro","score":84.1,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4-9b-chat","score":28.8,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4-air-0605","score":81.9,"metric":"percent"},{"benchmark":"gsm8k","model":"glm-4-air-0605","score":90.9,"metric":"percent"},{"benchmark":"math","model":"glm-4-air-0605","score":57.9,"metric":"percent"},{"benchmark":"bbh","model":"glm-4-air-0605","score":80.4,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4-air-0605","score":38.4,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4-air-0605","score":75.7,"metric":"percent"},{"benchmark":"mmlu","model":"glm-4-0116","score":81.5,"metric":"percent"},{"benchmark":"bbh","model":"glm-4-0116","score":82.3,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4-0116","score":35.7,"metric":"percent"},{"benchmark":"humaneval","model":"glm-4-0116","score":72,"metric":"percent"},{"benchmark":"bbh","model":"glm-4-0520","score":84.7,"metric":"percent"},{"benchmark":"gpqa","model":"glm-4-0520","score":39.9,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4-0613","score":77.1,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4-1106-preview","score":75.4,"metric":"percent"},{"benchmark":"ifeval","model":"gpt-4-turbo-2024-04-09","score":81.2,"metric":"percent"},{"benchmark":"ifeval","model":"claude-2","score":58,"metric":"percent"},{"benchmark":"ifeval","model":"claude-3-opus","score":85.5,"metric":"percent"},{"benchmark":"ifeval","model":"glm-4-air-0605","score":75.2,"metric":"percent"},{"benchmark":"ifeval","model":"glm-4-0520","score":79.1,"metric":"percent"},{"benchmark":"alignbench","model":"gpt-4-0613","score":7.46,"metric":"score"},{"benchmark":"alignbench","model":"gpt-4-1106-preview","score":7.9,"metric":"score"},{"benchmark":"alignbench","model":"gpt-4-turbo-2024-04-09","score":8,"metric":"score"},{"benchmark":"alignbench","model":"claude-2","score":6.26,"metric":"score"},{"benchmark":"alignbench","model":"claude-3-opus","score":7.53,"metric":"score"},{"benchmark":"alignbench","model":"gemini-1.5-pro","score":7.47,"metric":"score"},{"benchmark":"alignbench","model":"glm-4-air-0605","score":7.65,"metric":"score"},{"benchmark":"alignbench","model":"glm-4-0116","score":7.66,"metric":"score"},{"benchmark":"alignbench","model":"glm-4-0520","score":8,"metric":"score"},{"benchmark":"naturalcodebench","model":"gpt-4-0613","score":52.8,"metric":"percent"},{"benchmark":"naturalcodebench","model":"gpt-4-1106-preview","score":51.5,"metric":"percent"},{"benchmark":"naturalcodebench","model":"gpt-4-turbo-2024-04-09","score":53.8,"metric":"percent"},{"benchmark":"naturalcodebench","model":"claude-2","score":34.4,"metric":"percent"},{"benchmark":"naturalcodebench","model":"claude-3-opus","score":48.3,"metric":"percent"},{"benchmark":"naturalcodebench","model":"gemini-1.5-pro","score":42.3,"metric":"percent"},{"benchmark":"naturalcodebench","model":"glm-4-air-0605","score":40.8,"metric":"percent"},{"benchmark":"naturalcodebench","model":"glm-4-0520","score":47.1,"metric":"percent"},{"benchmark":"bfcl","model":"gpt-4o-2024-05-13","score":82.94,"metric":"percent"},{"benchmark":"bfcl","model":"glm-4-air-0605","score":80.94,"metric":"percent"},{"benchmark":"bfcl","model":"glm-4-0520","score":81.76,"metric":"percent"},{"benchmark":"agentbench","model":"gpt-4-0613","score":3.69,"metric":"score"},{"benchmark":"agentbench","model":"gpt-4-1106-preview","score":3.77,"metric":"score"},{"benchmark":"agentbench","model":"gpt-4-turbo-2024-04-09","score":3.68,"metric":"score"},{"benchmark":"agentbench","model":"claude-2","score":2.03,"metric":"score"},{"benchmark":"agentbench","model":"claude-3-opus","score":3.62,"metric":"score"},{"benchmark":"agentbench","model":"glm-4-air-0605","score":3.58,"metric":"score"},{"benchmark":"agentbench","model":"glm-4-0520","score":3.79,"metric":"score"},{"benchmark":"safetybench","model":"gpt-4-0613","score":89.7,"metric":"percent"},{"benchmark":"safetybench","model":"gpt-4-1106-preview","score":88.1,"metric":"percent"},{"benchmark":"safetybench","model":"gpt-4-turbo-2024-04-09","score":87.9,"metric":"percent"},{"benchmark":"safetybench","model":"claude-3-opus","score":87.5,"metric":"percent"},{"benchmark":"safetybench","model":"glm-4-0520","score":87.2,"metric":"percent"},{"benchmark":"mmlu","model":"glm-130b","score":44.75,"metric":"percent"},{"benchmark":"lambada","model":"glm-130b","score":80.21,"metric":"percent"},{"benchmark":"mmlu","model":"gpt-3","score":43.9,"metric":"percent"},{"benchmark":"lambada","model":"gpt-3","score":76.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"gpt-3","score":57.2,"metric":"percent"},{"benchmark":"commonsenseqa","model":"bloom-176b","score":42.8,"metric":"percent"},{"benchmark":"commonsenseqa","model":"glm-130b","score":61.6,"metric":"percent"},{"benchmark":"textvqa","model":"minigpt-4-v1-7b","score":0.6,"metric":"percent"},{"benchmark":"scienceqa","model":"minigpt-4-v1-7b","score":39.6,"metric":"percent"},{"benchmark":"mmvet","model":"minigpt-4-v1-7b","score":22.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"minigpt-4-v1-7b","score":47.4,"metric":"percent"},{"benchmark":"mmbench","model":"minigpt-4-v1-7b","score":23,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"minigpt-4-v1-7b","score":45.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"minigpt-4-v1-7b","score":23.1,"metric":"percent"},{"benchmark":"vqav2","model":"idefics-80b-instruct","score":37.4,"metric":"percent"},{"benchmark":"okvqa","model":"idefics-80b-instruct","score":36.9,"metric":"percent"},{"benchmark":"textvqa","model":"idefics-80b-instruct","score":32.9,"metric":"percent"},{"benchmark":"scienceqa","model":"idefics-80b-instruct","score":61.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"idefics-80b-instruct","score":53.2,"metric":"percent"},{"benchmark":"vqav2","model":"openflamingo-v2","score":53,"metric":"percent"},{"benchmark":"okvqa","model":"openflamingo-v2","score":38.3,"metric":"percent"},{"benchmark":"textvqa","model":"openflamingo-v2","score":28.3,"metric":"percent"},{"benchmark":"scienceqa","model":"openflamingo-v2","score":44.8,"metric":"percent"},{"benchmark":"mmvet","model":"openflamingo-v2","score":24.8,"metric":"percent"},{"benchmark":"seed-bench-img","model":"openflamingo-v2","score":42.7,"metric":"percent"},{"benchmark":"mmbench","model":"openflamingo-v2","score":5.7,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"openflamingo-v2","score":34.2,"metric":"percent"},{"benchmark":"mmmu","model":"openflamingo-v2","score":26.3,"metric":"percent"},{"benchmark":"mathvista-mini","model":"openflamingo-v2","score":18.6,"metric":"percent"},{"benchmark":"vqav2","model":"dreamllm-7b","score":56.6,"metric":"percent"},{"benchmark":"okvqa","model":"dreamllm-7b","score":44.3,"metric":"percent"},{"benchmark":"textvqa","model":"dreamllm-7b","score":34.9,"metric":"percent"},{"benchmark":"mmvet","model":"dreamllm-7b","score":35.9,"metric":"percent"},{"benchmark":"mmbench","model":"dreamllm-7b","score":49.9,"metric":"percent"},{"benchmark":"textvqa","model":"instructblip-7b","score":50.1,"metric":"percent"},{"benchmark":"scienceqa","model":"instructblip-7b","score":60.5,"metric":"percent"},{"benchmark":"seed-bench-img","model":"instructblip-7b","score":58.8,"metric":"percent"},{"benchmark":"mmbench","model":"instructblip-7b","score":33.9,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"instructblip-7b","score":59.8,"metric":"percent"},{"benchmark":"pope","model":"instructblip-7b","score":53.8,"metric":"percent"},{"benchmark":"vqav2","model":"fuyu-8b","score":74.2,"metric":"percent"},{"benchmark":"okvqa","model":"fuyu-8b","score":60.6,"metric":"percent"},{"benchmark":"mmmu","model":"fuyu-8b","score":27.4,"metric":"percent"},{"benchmark":"scienceqa","model":"qwen-vl-chat","score":68.8,"metric":"percent"},{"benchmark":"mmmu","model":"qwen-vl-chat","score":32.9,"metric":"percent"},{"benchmark":"scienceqa","model":"llava-1.5-7b","score":66.8,"metric":"percent"},{"benchmark":"mmvet","model":"llava-1.5-7b","score":30.5,"metric":"percent"},{"benchmark":"seed-bench-img","model":"llava-1.5-7b","score":58.6,"metric":"percent"},{"benchmark":"mmbench","model":"llava-1.5-7b","score":64.3,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"llava-1.5-7b","score":60.7,"metric":"percent"},{"benchmark":"pope","model":"llava-1.5-7b","score":85.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"llava-1.5-7b","score":23.6,"metric":"percent"},{"benchmark":"vqav2","model":"mplug-owl2","score":79.4,"metric":"percent"},{"benchmark":"okvqa","model":"mplug-owl2","score":57.7,"metric":"percent"},{"benchmark":"textvqa","model":"mplug-owl2","score":58.2,"metric":"percent"},{"benchmark":"scienceqa","model":"mplug-owl2","score":68.7,"metric":"percent"},{"benchmark":"mmvet","model":"mplug-owl2","score":36.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"mplug-owl2","score":64.1,"metric":"percent"},{"benchmark":"mmbench","model":"mplug-owl2","score":64.5,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"mplug-owl2","score":25,"metric":"percent"},{"benchmark":"pope","model":"mplug-owl2","score":86.2,"metric":"percent"},{"benchmark":"mmmu","model":"mplug-owl2","score":32.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"mplug-owl2","score":25.3,"metric":"percent"},{"benchmark":"vqav2","model":"unified-io-2-xxl","score":79.4,"metric":"percent"},{"benchmark":"okvqa","model":"unified-io-2-xxl","score":55.5,"metric":"percent"},{"benchmark":"scienceqa","model":"unified-io-2-xxl","score":86.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"unified-io-2-xxl","score":65.6,"metric":"percent"},{"benchmark":"mmbench","model":"unified-io-2-xxl","score":71.5,"metric":"percent"},{"benchmark":"pope","model":"unified-io-2-xxl","score":87.7,"metric":"percent"},{"benchmark":"scienceqa","model":"llava-1.5-13b","score":71.6,"metric":"percent"},{"benchmark":"seed-bench-img","model":"llava-1.5-13b","score":61.6,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"llava-1.5-13b","score":64.6,"metric":"percent"},{"benchmark":"mmmu","model":"llava-1.5-13b","score":33.6,"metric":"percent"},{"benchmark":"vqav2","model":"sphinx-2k","score":80.7,"metric":"percent"},{"benchmark":"okvqa","model":"sphinx-2k","score":62.6,"metric":"percent"},{"benchmark":"textvqa","model":"sphinx-2k","score":61.2,"metric":"percent"},{"benchmark":"ocrvqa","model":"sphinx-2k","score":67.8,"metric":"percent"},{"benchmark":"scienceqa","model":"sphinx-2k","score":70.6,"metric":"percent"},{"benchmark":"mmvet","model":"sphinx-2k","score":40.2,"metric":"percent"},{"benchmark":"seed-bench-img","model":"sphinx-2k","score":71.6,"metric":"percent"},{"benchmark":"mmbench","model":"sphinx-2k","score":65.9,"metric":"percent"},{"benchmark":"pope","model":"sphinx-2k","score":87.2,"metric":"percent"},{"benchmark":"mmmu","model":"sphinx-2k","score":32.9,"metric":"percent"},{"benchmark":"mathvista-mini","model":"sphinx-2k","score":27.8,"metric":"percent"},{"benchmark":"vqav2","model":"emu2-chat","score":84.9,"metric":"percent"},{"benchmark":"okvqa","model":"emu2-chat","score":64.8,"metric":"percent"},{"benchmark":"textvqa","model":"emu2-chat","score":66.6,"metric":"percent"},{"benchmark":"mmvet","model":"emu2-chat","score":48.5,"metric":"percent"},{"benchmark":"seed-bench-img","model":"emu2-chat","score":62.8,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"emu2-chat","score":56.4,"metric":"percent"},{"benchmark":"mmmu","model":"emu2-chat","score":34.1,"metric":"percent"},{"benchmark":"vqav2","model":"cogvlm-17b-chat","score":82.3,"metric":"percent"},{"benchmark":"okvqa","model":"cogvlm-17b-chat","score":64.8,"metric":"percent"},{"benchmark":"ocrvqa","model":"cogvlm-17b-chat","score":73.8,"metric":"percent"},{"benchmark":"scienceqa","model":"cogvlm-17b-chat","score":91.2,"metric":"percent"},{"benchmark":"mmvet","model":"cogvlm-17b-chat","score":51.1,"metric":"percent"},{"benchmark":"seed-bench-img","model":"cogvlm-17b-chat","score":72.5,"metric":"percent"},{"benchmark":"mmbench","model":"cogvlm-17b-chat","score":77.6,"metric":"percent"},{"benchmark":"llava-bench-in-the-wild","model":"cogvlm-17b-chat","score":77.8,"metric":"percent"},{"benchmark":"pope","model":"cogvlm-17b-chat","score":87.9,"metric":"percent"},{"benchmark":"mmmu","model":"cogvlm-17b-chat","score":41.1,"metric":"percent"},{"benchmark":"mathvista-mini","model":"cogvlm-17b-chat","score":34.5,"metric":"percent"},{"benchmark":"refcoco","model":"ferret-13b","score":89.48,"metric":"percent"},{"benchmark":"refcocoplus","model":"ferret-13b","score":82.81,"metric":"percent"},{"benchmark":"refcocog","model":"ferret-13b","score":85.83,"metric":"percent"},{"benchmark":"refcoco","model":"cogvlm-grounding-generalist","score":92.76,"metric":"percent"},{"benchmark":"refcocoplus","model":"cogvlm-grounding-generalist","score":88.68,"metric":"percent"},{"benchmark":"refcocog","model":"cogvlm-grounding-generalist","score":89.75,"metric":"percent"},{"benchmark":"okvqa","model":"ureader","score":57.6,"metric":"percent"},{"benchmark":"textvqa","model":"llava-1.5-13b","score":61.5,"metric":"percent"},{"benchmark":"vqav2","model":"cogagent-18b","score":83.7,"metric":"percent"},{"benchmark":"okvqa","model":"cogagent-18b","score":61.2,"metric":"percent"},{"benchmark":"ocrvqa","model":"cogagent-18b","score":75,"metric":"percent"},{"benchmark":"stvqa","model":"cogagent-18b","score":80.5,"metric":"percent"},{"benchmark":"mmvet","model":"instructblip-13b","score":25.6,"metric":"percent"},{"benchmark":"mmvet","model":"cogagent-18b","score":52.8,"metric":"percent"},{"benchmark":"automationbench","model":"minimax-m3.1-flash","score":62.2,"metric":"percent"},{"benchmark":"deepswe-v1.1","model":"minimax-m3.1-flash","score":73.7,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"minimax-m3.1-flash","score":38.1,"metric":"percent"},{"benchmark":"osworld-2.0","model":"minimax-m3.1-flash","score":61.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"minimax-m3.1-flash","score":29.6,"metric":"percent"},{"benchmark":"babyvision-with-tools","model":"minimax-m3.1-flash","score":91,"metric":"percent"},{"benchmark":"hle","model":"minimax-m3.1-flash","score":43.4,"metric":"percent"},{"benchmark":"osworld-2.0","model":"gpt-5.6-sol","score":65.7,"metric":"percent"},{"benchmark":"agents-last-exam","model":"gpt-5.6-sol","score":30.6,"metric":"percent"},{"benchmark":"hle","model":"claude-opus-5","score":55.6,"metric":"percent"},{"benchmark":"bankertoolbench","model":"minimax-m3.1-flash","score":76.2,"metric":"percent"},{"benchmark":"cybergym","model":"minimax-m3.1-flash","score":82,"metric":"percent"},{"benchmark":"automationbench","model":"minimax-m3.1-flash-low","score":52.8,"metric":"percent"},{"benchmark":"automationbench","model":"minimax-m3.1-flash-max","score":62.8,"metric":"percent"},{"benchmark":"vals-index","model":"minimax-m3.1-flash-max","score":53.78,"metric":"percent"},{"benchmark":"emb-v1.1","model":"minimax-m3.1-flash-max","score":67.84,"metric":"percent"},{"benchmark":"financeagent-v2","model":"minimax-m3.1-flash-max","score":58.83,"metric":"percent"},{"benchmark":"legal-research-bench","model":"minimax-m3.1-flash-max","score":34.13,"metric":"percent"},{"benchmark":"tax-agent-bench","model":"minimax-m3.1-flash-max","score":32.14,"metric":"percent"},{"benchmark":"vibe-code-bench-v1.1","model":"minimax-m3.1-flash-max","score":73.94,"metric":"percent"},{"benchmark":"hlab-vals-1.1","model":"minimax-m3.1-flash-max","score":7.5,"metric":"percent"},{"benchmark":"terminal-bench-4.0","model":"minimax-m3.1-flash-max","score":25.25,"metric":"percent"},{"benchmark":"aa-index","model":"minimax-m3.1-flash-max","score":43,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"mercury-3","score":1237.2,"metric":"elo"},{"benchmark":"tau3-banking","model":"mercury-3","score":30.24,"metric":"percent"},{"benchmark":"multichallenge","model":"mercury-3","score":60.35,"metric":"percent"},{"benchmark":"aa-omniscience-public-accuracy","model":"mercury-3","score":46.44,"metric":"percent"},{"benchmark":"ifbench","model":"mercury-3","score":76.84,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"mercury-3","score":89.23,"metric":"percent"},{"benchmark":"aa-lcr","model":"mercury-3","score":77.67,"metric":"percent"},{"benchmark":"mrcr-v2","model":"mercury-3","score":75.5,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"mercury-3","score":51.08,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"mercury-3","score":46.31,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"mercury-3","score":55.18,"metric":"percent"},{"benchmark":"deepsearchqa","model":"mercury-3","score":71.33,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"gpt-6-luna-medium","score":1204,"metric":"elo"},{"benchmark":"tau3-banking","model":"gpt-6-luna-medium","score":23,"metric":"percent"},{"benchmark":"multichallenge","model":"gpt-6-luna-medium","score":51.49,"metric":"percent"},{"benchmark":"aa-omniscience-public-accuracy","model":"gpt-6-luna-medium","score":46.94,"metric":"percent"},{"benchmark":"ifbench","model":"gpt-6-luna-medium","score":61.82,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gpt-6-luna-medium","score":86.36,"metric":"percent"},{"benchmark":"aa-lcr","model":"gpt-6-luna-medium","score":78.3,"metric":"percent"},{"benchmark":"mrcr-v2","model":"gpt-6-luna-medium","score":62.72,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"gpt-6-luna-medium","score":33.33,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"gpt-6-luna-medium","score":37.76,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gpt-6-luna-medium","score":50.5,"metric":"percent"},{"benchmark":"deepsearchqa","model":"gpt-6-luna-medium","score":60,"metric":"percent"},{"benchmark":"gdpval-aa-elo","model":"claude-haiku-5.5-medium","score":1225,"metric":"elo"},{"benchmark":"tau3-banking","model":"claude-haiku-5.5-medium","score":13.06,"metric":"percent"},{"benchmark":"multichallenge","model":"claude-haiku-5.5-medium","score":52.48,"metric":"percent"},{"benchmark":"aa-omniscience-public-accuracy","model":"claude-haiku-5.5-medium","score":37.22,"metric":"percent"},{"benchmark":"ifbench","model":"claude-haiku-5.5-medium","score":54.65,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"claude-haiku-5.5-medium","score":84.51,"metric":"percent"},{"benchmark":"aa-lcr","model":"claude-haiku-5.5-medium","score":74.7,"metric":"percent"},{"benchmark":"mrcr-v2","model":"claude-haiku-5.5-medium","score":78.4,"metric":"percent"},{"benchmark":"swe-atlas-qna","model":"claude-haiku-5.5-medium","score":32.26,"metric":"percent"},{"benchmark":"deepswe-v1.0","model":"claude-haiku-5.5-medium","score":51.62,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"claude-haiku-5.5-medium","score":45.78,"metric":"percent"},{"benchmark":"deepsearchqa","model":"claude-haiku-5.5-medium","score":65.22,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"flint","score":54.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"flint-nvfp4","score":53.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.5-35b-a3b","score":38.7,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"laguna-xs-2.1","score":24.7,"metric":"percent"},{"benchmark":"swe-bench-pro-v2","model":"flint","score":89.7,"metric":"percent"},{"benchmark":"swe-bench-pro-v2","model":"flint-nvfp4","score":88.5,"metric":"percent"},{"benchmark":"swe-bench-pro-v2","model":"qwen3.5-35b-a3b","score":68.6,"metric":"percent"},{"benchmark":"swe-bench-pro-v2","model":"qwen3.6-35b-a3b","score":73.8,"metric":"percent"},{"benchmark":"swe-bench-pro-v2","model":"laguna-xs-2.1","score":38.6,"metric":"percent"},{"benchmark":"swe-bench-pro-v2","model":"qwen3.8-27b","score":94.9,"metric":"percent"},{"benchmark":"swe-bench-pro-v2","model":"muse-glimmer-30b","score":86,"metric":"percent"},{"benchmark":"swe-bench-pro-v2","model":"gemma-4-31b-it","score":61.7,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"flint","score":74.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"flint-nvfp4","score":74.1,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.8-27b","score":75.6,"metric":"percent"},{"benchmark":"livecodebench","model":"flint","score":80.3,"metric":"percent"},{"benchmark":"livecodebench","model":"flint-nvfp4","score":80.8,"metric":"percent"},{"benchmark":"livecodebench","model":"laguna-xs-2.1","score":49.5,"metric":"percent"},{"benchmark":"livecodebench","model":"muse-glimmer-30b","score":63.5,"metric":"percent"},{"benchmark":"ifbench","model":"flint","score":89.2,"metric":"percent"},{"benchmark":"ifbench","model":"flint-nvfp4","score":88.1,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":67.9,"metric":"percent"},{"benchmark":"ifbench","model":"laguna-xs-2.1","score":34.4,"metric":"percent"},{"benchmark":"ifeval","model":"flint","score":95.1,"metric":"percent"},{"benchmark":"ifeval","model":"flint-nvfp4","score":94.6,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.6-35b-a3b","score":89.6,"metric":"percent"},{"benchmark":"ifeval","model":"laguna-xs-2.1","score":73.7,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.8-27b","score":94.6,"metric":"percent"},{"benchmark":"ifeval","model":"muse-glimmer-30b","score":94.7,"metric":"percent"},{"benchmark":"ifeval","model":"gemma-4-31b-it","score":94.6,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"sage-a1.5","score":61.2,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"agents-a1","score":43.6,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"sage-a1.5","score":72.7,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"agents-a1","score":58.7,"metric":"percent"},{"benchmark":"scicode","model":"sage-a1.5","score":44.3,"metric":"percent"},{"benchmark":"scicode","model":"ornith-1.5-35b-a3b","score":39.5,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"sage-a1.5","score":65.2,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"ornith-1.5-35b-a3b","score":39.4,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"glm-5.3","score":72.7,"metric":"percent"},{"benchmark":"mle-bench-lite","model":"gpt-5.6-sol","score":77.3,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"sage-a1.5","score":81,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"ornith-1.5-35b-a3b","score":70,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"kimi-k3","score":69,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"glm-5.3","score":67,"metric":"percent"},{"benchmark":"frontierscience-olympiad","model":"gpt-5.6-sol","score":73,"metric":"percent"},{"benchmark":"hle-with-tools","model":"sage-a1.5","score":55.1,"metric":"percent"},{"benchmark":"critpt","model":"sage-a1.5","score":20,"metric":"percent"},{"benchmark":"critpt","model":"agents-a1","score":4.3,"metric":"percent"},{"benchmark":"critpt","model":"ornith-1.5-35b-a3b","score":2.9,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"sage-a1.5","score":80,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"agents-a1","score":72,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"ornith-1.5-35b-a3b","score":26,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"kimi-k3","score":34,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"glm-5.3","score":40,"metric":"percent"},{"benchmark":"cmt-benchmark","model":"gpt-5.6-sol","score":50,"metric":"percent"},{"benchmark":"agents-last-exam","model":"sage-a1.5","score":19.1,"metric":"percent"},{"benchmark":"agents-last-exam","model":"agents-a1","score":10.2,"metric":"percent"},{"benchmark":"agents-last-exam","model":"ornith-1.5-35b-a3b","score":14.3,"metric":"percent"},{"benchmark":"pinchbench","model":"sage-a1.5","score":90,"metric":"percent"},{"benchmark":"pinchbench","model":"agents-a1","score":76.9,"metric":"percent"},{"benchmark":"pinchbench","model":"ornith-1.5-35b-a3b","score":88.6,"metric":"percent"},{"benchmark":"pinchbench","model":"kimi-k3","score":88.2,"metric":"percent"},{"benchmark":"pinchbench","model":"glm-5.3","score":86.6,"metric":"percent"},{"benchmark":"pinchbench","model":"gpt-5.6-sol","score":87.3,"metric":"percent"},{"benchmark":"browsecomp","model":"sage-a1.5","score":82.8,"metric":"percent"},{"benchmark":"browsecomp","model":"glm-5.3","score":76.2,"metric":"percent"},{"benchmark":"ifbench","model":"sage-a1.5","score":81.6,"metric":"percent"},{"benchmark":"ifbench","model":"ornith-1.5-35b-a3b","score":44.6,"metric":"percent"},{"benchmark":"ifbench","model":"kimi-k3","score":72.1,"metric":"percent"},{"benchmark":"ifbench","model":"glm-5.3","score":53.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"spark-x2.6-4b","score":71.8,"metric":"percent"},{"benchmark":"vitabench-2.0","model":"spark-x2.6-4b","score":30.8,"metric":"percent"},{"benchmark":"vitabench-2.0","model":"spark-x2.5-4b","score":25.2,"metric":"percent"},{"benchmark":"vitabench-2.0","model":"qwen3.5-9b","score":15.6,"metric":"percent"},{"benchmark":"vitabench-2.0","model":"qwen3.5-4b","score":18.2,"metric":"percent"},{"benchmark":"vitabench-2.0","model":"gemma-4-12b-it","score":12.4,"metric":"percent"},{"benchmark":"vitabench-2.0","model":"gemma-4-e4b-it","score":4.8,"metric":"percent"},{"benchmark":"mcp-atlas","model":"spark-x2.6-4b","score":62.4,"metric":"percent"},{"benchmark":"enterpriseops-gym","model":"spark-x2.6-4b","score":33.6,"metric":"percent"},{"benchmark":"enterpriseops-gym","model":"spark-x2.5-4b","score":27.3,"metric":"percent"},{"benchmark":"enterpriseops-gym","model":"qwen3.5-9b","score":24.7,"metric":"percent"},{"benchmark":"enterpriseops-gym","model":"qwen3.5-4b","score":22.9,"metric":"percent"},{"benchmark":"enterpriseops-gym","model":"gemma-4-12b-it","score":24.5,"metric":"percent"},{"benchmark":"enterpriseops-gym","model":"gemma-4-e4b-it","score":8.6,"metric":"percent"},{"benchmark":"claw-eval","model":"spark-x2.6-4b","score":69.9,"metric":"percent"},{"benchmark":"claw-eval","model":"spark-x2.5-4b","score":66.2,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-9b","score":66.5,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.5-4b","score":62.3,"metric":"percent"},{"benchmark":"claw-eval","model":"gemma-4-12b-it","score":58.3,"metric":"percent"},{"benchmark":"claw-eval","model":"gemma-4-e4b-it","score":58,"metric":"percent"},{"benchmark":"browsecomp","model":"spark-x2.6-4b","score":53.1,"metric":"percent"},{"benchmark":"swebbench","model":"spark-x2.6-4b","score":71.7,"metric":"percent"},{"benchmark":"swebbench","model":"spark-x2.5-4b","score":46.3,"metric":"percent"},{"benchmark":"swebbench","model":"qwen3.5-9b","score":33.2,"metric":"percent"},{"benchmark":"swebbench","model":"qwen3.5-4b","score":36.3,"metric":"percent"},{"benchmark":"swebbench","model":"gemma-4-12b-it","score":32,"metric":"percent"},{"benchmark":"swebbench","model":"gemma-4-e4b-it","score":19.3,"metric":"percent"},{"benchmark":"pagentbench","model":"spark-x2.6-4b","score":74.1,"metric":"percent"},{"benchmark":"pagentbench","model":"spark-x2.5-4b","score":59.4,"metric":"percent"},{"benchmark":"pagentbench","model":"qwen3.5-9b","score":53.8,"metric":"percent"},{"benchmark":"pagentbench","model":"qwen3.5-4b","score":51.4,"metric":"percent"},{"benchmark":"pagentbench","model":"gemma-4-12b-it","score":51.8,"metric":"percent"},{"benchmark":"pagentbench","model":"gemma-4-e4b-it","score":37,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"spark-x2.6-4b","score":54.3,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"spark-x2.6-4b","score":62.8,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"spark-x2.6-4b","score":64.7,"metric":"percent"},{"benchmark":"scicode","model":"spark-x2.6-4b","score":36.8,"metric":"percent"},{"benchmark":"gaokao-math-2026","model":"spark-x2.6-4b","score":134.9,"metric":"points"},{"benchmark":"gaokao-math-2026","model":"spark-x2.5-4b","score":133.4,"metric":"points"},{"benchmark":"gaokao-math-2026","model":"qwen3.5-9b","score":135.5,"metric":"points"},{"benchmark":"gaokao-math-2026","model":"qwen3.5-4b","score":130.3,"metric":"points"},{"benchmark":"gaokao-math-2026","model":"gemma-4-12b-it","score":130.6,"metric":"points"},{"benchmark":"gaokao-math-2026","model":"gemma-4-e4b-it","score":102.4,"metric":"points"},{"benchmark":"aime-2026-i","model":"spark-x2.6-4b","score":91.2,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"spark-x2.6-4b","score":81.3,"metric":"percent"},{"benchmark":"imo-answerbench","model":"spark-x2.6-4b","score":75.2,"metric":"percent"},{"benchmark":"aa-lcr","model":"spark-x2.6-4b","score":67.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"spark-x2.5-4b","score":64.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-9b","score":70,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.5-4b","score":63,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-12b-it","score":63.7,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-e4b-it","score":32,"metric":"percent"},{"benchmark":"longbench-v2","model":"spark-x2.6-4b","score":53.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"spark-x2.5-4b","score":48.7,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemma-4-12b-it","score":45.3,"metric":"percent"},{"benchmark":"longbench-v2","model":"gemma-4-e4b-it","score":27.8,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"spark-x2.6-4b","score":92.2,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"spark-x2.5-4b","score":47.1,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"qwen3.5-9b","score":88.4,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"qwen3.5-4b","score":79,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"gemma-4-12b-it","score":68.6,"metric":"percent"},{"benchmark":"graphwalks-bfs-256k","model":"gemma-4-e4b-it","score":54.8,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"spark-x2.6-4b","score":34.2,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"spark-x2.5-4b","score":2.5,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"qwen3.5-9b","score":25.3,"metric":"percent"},{"benchmark":"graphwalks-bfs-1m","model":"qwen3.5-4b","score":15.8,"metric":"percent"},{"benchmark":"ifeval","model":"spark-x2.6-4b","score":93.6,"metric":"percent"},{"benchmark":"ifbench","model":"spark-x2.6-4b","score":75.8,"metric":"percent"},{"benchmark":"hle","model":"spark-x2.6-4b","score":17.9,"metric":"percent"},{"benchmark":"hle-with-tools","model":"spark-x2.6-4b","score":36.9,"metric":"percent"},{"benchmark":"hle-with-tools","model":"spark-x2.5-4b","score":21.8,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.5-9b","score":17.9,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.5-4b","score":20.2,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gemma-4-12b-it","score":19,"metric":"percent"},{"benchmark":"hle-with-tools","model":"gemma-4-e4b-it","score":10.1,"metric":"percent"},{"benchmark":"gpqa","model":"spark-x2.6-4b","score":69.9,"metric":"percent"},{"benchmark":"gpqa","model":"spark-x2.5-4b","score":67.4,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-9b","score":77.2,"metric":"percent"},{"benchmark":"gpqa","model":"qwen3.5-4b","score":67.2,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-4-12b-it","score":72.8,"metric":"percent"},{"benchmark":"gpqa","model":"gemma-4-e4b-it","score":54.5,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"spark-x2.6-4b","score":77.1,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"spark-x2.5-4b","score":73.7,"metric":"percent"},{"benchmark":"where2place","model":"gpt-5.5","score":45.25,"metric":"percent"},{"benchmark":"where2place","model":"gpt-5.6-sol","score":46.23,"metric":"percent"},{"benchmark":"where2place","model":"gpt-6-astra","score":71.1,"metric":"percent"},{"benchmark":"where2place","model":"claude-opus-5.5","score":66.44,"metric":"percent"},{"benchmark":"where2place","model":"gemini-4-argon","score":71.2,"metric":"percent"},{"benchmark":"where2place","model":"ace-brain-0.6-9b","score":81.44,"metric":"percent"},{"benchmark":"pixmocount","model":"gpt-5.5","score":82.61,"metric":"percent"},{"benchmark":"pixmocount","model":"gpt-5.6-sol","score":83.55,"metric":"percent"},{"benchmark":"pixmocount","model":"gpt-6-astra","score":88.1,"metric":"percent"},{"benchmark":"pixmocount","model":"claude-opus-5.5","score":83.74,"metric":"percent"},{"benchmark":"pixmocount","model":"gemini-4-argon","score":87.71,"metric":"percent"},{"benchmark":"pixmocount","model":"ace-brain-0.6-9b","score":86.96,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-5.5","score":59.19,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-5.6-sol","score":64.34,"metric":"percent"},{"benchmark":"robospatialhome","model":"gpt-6-astra","score":69.55,"metric":"percent"},{"benchmark":"robospatialhome","model":"claude-opus-5.5","score":73.3,"metric":"percent"},{"benchmark":"robospatialhome","model":"gemini-4-argon","score":80.94,"metric":"percent"},{"benchmark":"robospatialhome","model":"ace-brain-0.6-9b","score":76.56,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5.5","score":60.29,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-5.6-sol","score":54.51,"metric":"percent"},{"benchmark":"refspatialbench","model":"gpt-6-astra","score":80.14,"metric":"percent"},{"benchmark":"refspatialbench","model":"claude-opus-5.5","score":71.1,"metric":"percent"},{"benchmark":"refspatialbench","model":"gemini-4-argon","score":51.56,"metric":"percent"},{"benchmark":"refspatialbench","model":"ace-brain-0.6-9b","score":71.84,"metric":"percent"},{"benchmark":"pointarena","model":"gpt-5.5","score":68.02,"metric":"percent"},{"benchmark":"pointarena","model":"gpt-5.6-sol","score":69.76,"metric":"percent"},{"benchmark":"pointarena","model":"gpt-6-astra","score":75.36,"metric":"percent"},{"benchmark":"pointarena","model":"claude-opus-5.5","score":61.2,"metric":"percent"},{"benchmark":"pointarena","model":"gemini-4-argon","score":66.4,"metric":"percent"},{"benchmark":"pointarena","model":"ace-brain-0.6-9b","score":74.13,"metric":"percent"},{"benchmark":"roboafford","model":"gpt-5.5","score":68.04,"metric":"percent"},{"benchmark":"roboafford","model":"gpt-5.6-sol","score":71.45,"metric":"percent"},{"benchmark":"roboafford","model":"gpt-6-astra","score":84.94,"metric":"percent"},{"benchmark":"roboafford","model":"claude-opus-5.5","score":75.1,"metric":"percent"},{"benchmark":"roboafford","model":"gemini-4-argon","score":71.48,"metric":"percent"},{"benchmark":"roboafford","model":"ace-brain-0.6-9b","score":88.14,"metric":"percent"},{"benchmark":"sharerobot-affordance","model":"gpt-5.5","score":38.57,"metric":"percent"},{"benchmark":"sharerobot-affordance","model":"gpt-5.6-sol","score":36.66,"metric":"percent"},{"benchmark":"sharerobot-affordance","model":"gpt-6-astra","score":46.6,"metric":"percent"},{"benchmark":"sharerobot-affordance","model":"claude-opus-5.5","score":40.2,"metric":"percent"},{"benchmark":"sharerobot-affordance","model":"gemini-4-argon","score":29.53,"metric":"percent"},{"benchmark":"sharerobot-affordance","model":"ace-brain-0.6-9b","score":48.82,"metric":"percent"},{"benchmark":"robotgrounding-inhouse","model":"gpt-5.5","score":83.96,"metric":"percent"},{"benchmark":"robotgrounding-inhouse","model":"gpt-5.6-sol","score":85.18,"metric":"percent"},{"benchmark":"robotgrounding-inhouse","model":"gpt-6-astra","score":91.1,"metric":"percent"},{"benchmark":"robotgrounding-inhouse","model":"claude-opus-5.5","score":90.89,"metric":"percent"},{"benchmark":"robotgrounding-inhouse","model":"gemini-4-argon","score":78.51,"metric":"percent"},{"benchmark":"robotgrounding-inhouse","model":"ace-brain-0.6-9b","score":93.42,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"qwen3.5-ocr","score":91.27,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"qwen3.8-max","score":93.7,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"monkeyocrv2-b-parsing","score":91.57,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"ovisocr2","score":96.58,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"xiaomi-ocr-0","score":96.83,"metric":"percent"},{"benchmark":"omnidocbench-v1.6","model":"ovisocr3","score":96.74,"metric":"percent"},{"benchmark":"mdpbench","model":"qwen3.5-ocr","score":60.6,"metric":"percent"},{"benchmark":"mdpbench","model":"qwen3.8-max","score":86.4,"metric":"percent"},{"benchmark":"mdpbench","model":"glm-ocr","score":67.3,"metric":"percent"},{"benchmark":"mdpbench","model":"paddleocr-vl-1.6","score":78.9,"metric":"percent"},{"benchmark":"mdpbench","model":"monkeyocrv2-b-parsing","score":83.3,"metric":"percent"},{"benchmark":"mdpbench","model":"ovisocr2","score":69,"metric":"percent"},{"benchmark":"mdpbench","model":"hunyuanocr-1.5","score":76.8,"metric":"percent"},{"benchmark":"mdpbench","model":"xiaomi-ocr-0","score":73,"metric":"percent"},{"benchmark":"mdpbench","model":"ovisocr3","score":88.8,"metric":"percent"},{"benchmark":"puredocbench","model":"qwen3.5-ocr","score":68.38,"metric":"percent"},{"benchmark":"puredocbench","model":"qwen3.8-max","score":80.56,"metric":"percent"},{"benchmark":"puredocbench","model":"glm-ocr","score":63.34,"metric":"percent"},{"benchmark":"puredocbench","model":"paddleocr-vl-1.6","score":65.44,"metric":"percent"},{"benchmark":"puredocbench","model":"monkeyocrv2-b-parsing","score":64.91,"metric":"percent"},{"benchmark":"puredocbench","model":"ovisocr2","score":75.1,"metric":"percent"},{"benchmark":"puredocbench","model":"hunyuanocr-1.5","score":67.58,"metric":"percent"},{"benchmark":"puredocbench","model":"xiaomi-ocr-0","score":74.6,"metric":"percent"},{"benchmark":"puredocbench","model":"ovisocr3","score":82.31,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"qwen3.5-ocr","score":82.48,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"qwen3.8-max","score":86.86,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"monkeyocrv2-b-parsing","score":89.22,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"ovisocr2","score":92.29,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"hunyuanocr-1.5","score":88.53,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"xiaomi-ocr-0","score":92.73,"metric":"percent"},{"benchmark":"real5-omnidocbench","model":"ovisocr3","score":93.63,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-2b","score":85.4,"metric":"percent"},{"benchmark":"ocrbench","model":"qwen3.5-ocr","score":76.8,"metric":"percent"},{"benchmark":"ocrbench","model":"paddleocr-vl-1.6","score":55.9,"metric":"percent"},{"benchmark":"ocrbench","model":"hunyuanocr-1.5","score":86.1,"metric":"percent"},{"benchmark":"ocrbench","model":"glm-ocr","score":83.8,"metric":"percent"},{"benchmark":"ocrbench","model":"xiaomi-ocr-0","score":84.6,"metric":"percent"},{"benchmark":"ocrbench","model":"ovisocr3","score":88.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-0.8b","score":41.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-4b","score":54.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"qwen3.5-ocr","score":44.5,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"paddleocr-vl-1.6","score":23.8,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"hunyuanocr-1.5","score":50.7,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"glm-ocr","score":32.9,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"xiaomi-ocr-0","score":40.1,"metric":"percent"},{"benchmark":"ocrbenchv2-en","model":"ovisocr3","score":65.9,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.5-0.8b","score":43.9,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.5-2b","score":55.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.5-4b","score":61,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"qwen3.5-ocr","score":43.8,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"paddleocr-vl-1.6","score":30.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"hunyuanocr-1.5","score":57.7,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"glm-ocr","score":48.1,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"xiaomi-ocr-0","score":48.4,"metric":"percent"},{"benchmark":"ocrbenchv2-cn","model":"ovisocr3","score":61.3,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"qwen3.5-ocr","score":78.5,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"glm-ocr","score":79,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"hunyuanocr-1.5","score":81,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"xiaomi-ocr-0","score":76.5,"metric":"percent"},{"benchmark":"ocrbench-kie","model":"ovisocr3","score":90.5,"metric":"percent"},{"benchmark":"ocrbenchv2-kie","model":"qwen3.5-ocr","score":72.9,"metric":"percent"},{"benchmark":"ocrbenchv2-kie","model":"glm-ocr","score":74.22,"metric":"percent"},{"benchmark":"ocrbenchv2-kie","model":"hunyuanocr-1.5","score":68.63,"metric":"percent"},{"benchmark":"ocrbenchv2-kie","model":"xiaomi-ocr-0","score":74.66,"metric":"percent"},{"benchmark":"ocrbenchv2-kie","model":"ovisocr3","score":83.01,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"qwen3.5-ocr","score":88.43,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"glm-ocr","score":68.36,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"hunyuanocr-1.5","score":66.08,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"xiaomi-ocr-0","score":79.53,"metric":"percent"},{"benchmark":"cc-ocr-kie","model":"ovisocr3","score":88.69,"metric":"percent"},{"benchmark":"ovisocr-kie-inhouse","model":"qwen3.5-ocr","score":59.9,"metric":"percent"},{"benchmark":"ovisocr-kie-inhouse","model":"glm-ocr","score":75.25,"metric":"percent"},{"benchmark":"ovisocr-kie-inhouse","model":"hunyuanocr-1.5","score":75.96,"metric":"percent"},{"benchmark":"ovisocr-kie-inhouse","model":"xiaomi-ocr-0","score":75.68,"metric":"percent"},{"benchmark":"ovisocr-kie-inhouse","model":"ovisocr3","score":77.73,"metric":"percent"},{"benchmark":"docfigcapbench-loc-f1","model":"hunyuanocr-1.5","score":48.24,"metric":"percent"},{"benchmark":"docfigcapbench-loc-f1","model":"qwen3.5-ocr","score":78.47,"metric":"percent"},{"benchmark":"docfigcapbench-loc-f1","model":"ovisocr2","score":82.18,"metric":"percent"},{"benchmark":"docfigcapbench-loc-f1","model":"mineru2.5-pro","score":85,"metric":"percent"},{"benchmark":"docfigcapbench-loc-f1","model":"paddleocr-vl-1.6","score":85.32,"metric":"percent"},{"benchmark":"docfigcapbench-loc-f1","model":"qwen3.8-max","score":86.67,"metric":"percent"},{"benchmark":"docfigcapbench-loc-f1","model":"ovisocr3","score":90.97,"metric":"percent"},{"benchmark":"docfigcapbench-caption","model":"qwen3.5-ocr","score":4.74,"metric":"score"},{"benchmark":"docfigcapbench-caption","model":"mineru2.5-pro","score":4.61,"metric":"score"},{"benchmark":"docfigcapbench-caption","model":"paddleocr-vl-1.6","score":4.29,"metric":"score"},{"benchmark":"docfigcapbench-caption","model":"qwen3.8-max","score":7.3,"metric":"score"},{"benchmark":"docfigcapbench-caption","model":"ovisocr3","score":6.93,"metric":"score"},{"benchmark":"crosstabbench-relation-f1","model":"paddleocr-vl-1.6","score":42.61,"metric":"percent"},{"benchmark":"crosstabbench-relation-f1","model":"logics-parsing-v3","score":44.55,"metric":"percent"},{"benchmark":"crosstabbench-relation-f1","model":"mineru2.5-pro","score":59.14,"metric":"percent"},{"benchmark":"crosstabbench-relation-f1","model":"mineru2.5-pro-popo","score":54.76,"metric":"percent"},{"benchmark":"crosstabbench-relation-f1","model":"qwen3.8-max","score":94.47,"metric":"percent"},{"benchmark":"crosstabbench-relation-f1","model":"ovisocr3","score":97.07,"metric":"percent"},{"benchmark":"crosstabbench-teds","model":"paddleocr-vl-1.6","score":24.24,"metric":"percent"},{"benchmark":"crosstabbench-teds","model":"logics-parsing-v3","score":26.1,"metric":"percent"},{"benchmark":"crosstabbench-teds","model":"mineru2.5-pro","score":41.02,"metric":"percent"},{"benchmark":"crosstabbench-teds","model":"mineru2.5-pro-popo","score":36.42,"metric":"percent"},{"benchmark":"crosstabbench-teds","model":"qwen3.8-max","score":91.71,"metric":"percent"},{"benchmark":"crosstabbench-teds","model":"ovisocr3","score":89.66,"metric":"percent"},{"benchmark":"mpdocbench-truncated-table-teds","model":"paddleocr-vl-1.6","score":83.39,"metric":"percent"},{"benchmark":"mpdocbench-truncated-table-teds","model":"logics-parsing-v3","score":88.05,"metric":"percent"},{"benchmark":"mpdocbench-truncated-table-teds","model":"mineru2.5-pro","score":91.44,"metric":"percent"},{"benchmark":"mpdocbench-truncated-table-teds","model":"mineru2.5-pro-popo","score":91.87,"metric":"percent"},{"benchmark":"mpdocbench-truncated-table-teds","model":"qwen3.8-max","score":89.57,"metric":"percent"},{"benchmark":"mpdocbench-truncated-table-teds","model":"ovisocr3","score":92.04,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.8-27b","score":91.46,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.8-27b-ud-q4-k-xl","score":93.35,"metric":"percent"},{"benchmark":"mmlu-redux","model":"qwen3.8-27b-iq2-xxs","score":88.93,"metric":"percent"},{"benchmark":"mmlu-redux","model":"ternary-bonsai-2-27b","score":89.09,"metric":"percent"},{"benchmark":"musr","model":"qwen3.8-27b","score":79.63,"metric":"percent"},{"benchmark":"musr","model":"qwen3.8-27b-ud-q4-k-xl","score":73.01,"metric":"percent"},{"benchmark":"musr","model":"qwen3.8-27b-iq2-xxs","score":66.99,"metric":"percent"},{"benchmark":"musr","model":"ternary-bonsai-2-27b","score":70.63,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.8-27b","score":97.19,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.8-27b-ud-q4-k-xl","score":96.66,"metric":"percent"},{"benchmark":"gsm8k","model":"qwen3.8-27b-iq2-xxs","score":89.9,"metric":"percent"},{"benchmark":"gsm8k","model":"ternary-bonsai-2-27b","score":96.66,"metric":"percent"},{"benchmark":"math500","model":"qwen3.8-27b","score":99.8,"metric":"percent"},{"benchmark":"math500","model":"qwen3.8-27b-ud-q4-k-xl","score":99.4,"metric":"percent"},{"benchmark":"math500","model":"qwen3.8-27b-iq2-xxs","score":84.6,"metric":"percent"},{"benchmark":"math500","model":"ternary-bonsai-2-27b","score":98.8,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.8-27b","score":96.67,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.8-27b-ud-q4-k-xl","score":92.91,"metric":"percent"},{"benchmark":"aime-2025","model":"qwen3.8-27b-iq2-xxs","score":66.67,"metric":"percent"},{"benchmark":"aime-2025","model":"ternary-bonsai-2-27b","score":95,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.8-27b","score":94.58,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.8-27b-ud-q4-k-xl","score":93,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.8-27b-iq2-xxs","score":57.5,"metric":"percent"},{"benchmark":"aime-2026-i","model":"ternary-bonsai-2-27b","score":95.83,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.8-27b","score":93.29,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.8-27b-ud-q4-k-xl","score":95.73,"metric":"percent"},{"benchmark":"humaneval-plus","model":"qwen3.8-27b-iq2-xxs","score":91.46,"metric":"percent"},{"benchmark":"humaneval-plus","model":"ternary-bonsai-2-27b","score":95.12,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.8-27b","score":83.86,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.8-27b-ud-q4-k-xl","score":83.86,"metric":"percent"},{"benchmark":"mbpp-plus","model":"qwen3.8-27b-iq2-xxs","score":78.89,"metric":"percent"},{"benchmark":"mbpp-plus","model":"ternary-bonsai-2-27b","score":83.07,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.8-27b","score":90.05,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.8-27b-ud-q4-k-xl","score":87.96,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.8-27b-iq2-xxs","score":56.4,"metric":"percent"},{"benchmark":"livecodebench","model":"ternary-bonsai-2-27b","score":90.07,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.8-27b","score":91.5,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.8-27b-ud-q4-k-xl","score":88.83,"metric":"percent"},{"benchmark":"ifeval","model":"qwen3.8-27b-iq2-xxs","score":84.03,"metric":"percent"},{"benchmark":"ifeval","model":"ternary-bonsai-2-27b","score":91.31,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-27b","score":71,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-27b-ud-q4-k-xl","score":65.65,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-27b-iq2-xxs","score":53.76,"metric":"percent"},{"benchmark":"ifbench","model":"ternary-bonsai-2-27b","score":74,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.8-27b","score":76.74,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.8-27b-ud-q4-k-xl","score":75.05,"metric":"percent"},{"benchmark":"bfcl-v3","model":"qwen3.8-27b-iq2-xxs","score":70.28,"metric":"percent"},{"benchmark":"bfcl-v3","model":"ternary-bonsai-2-27b","score":74.92,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.8-27b","score":81.73,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.8-27b-ud-q4-k-xl","score":81.73,"metric":"percent"},{"benchmark":"mmmu-pro","model":"qwen3.8-27b-iq2-xxs","score":65.19,"metric":"percent"},{"benchmark":"mmmu-pro","model":"ternary-bonsai-2-27b","score":75.49,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"ornith-1.5-122b","score":81.2,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-flash-next","score":83.4,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"qwen3.8-27b","score":71.9,"metric":"percent"},{"benchmark":"terminal-bench-2.1","model":"nemotron-3.5-super-vl-120b-a12b","score":66.7,"metric":"percent"},{"benchmark":"cybergym","model":"ornith-1.5-122b","score":80,"metric":"percent"},{"benchmark":"cybergym","model":"qwen3.8-flash-next","score":78,"metric":"percent"},{"benchmark":"cybergym","model":"qwen3.8-27b","score":55,"metric":"percent"},{"benchmark":"cybergym","model":"nemotron-3.5-super-vl-120b-a12b","score":34,"metric":"percent"},{"benchmark":"cybergym","model":"beam","score":59,"metric":"percent"},{"benchmark":"nl2repo","model":"ornith-1.5-122b","score":51.2,"metric":"percent"},{"benchmark":"nl2repo","model":"qwen3.8-flash-next","score":45.2,"metric":"percent"},{"benchmark":"nl2repo","model":"nemotron-3.5-super-vl-120b-a12b","score":21,"metric":"percent"},{"benchmark":"nl2repo","model":"beam","score":49.4,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"ornith-1.5-122b","score":76.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.8-flash-next","score":43.9,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"qwen3.8-27b","score":65.5,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"nemotron-3.5-super-vl-120b-a12b","score":42.5,"metric":"percent"},{"benchmark":"swe-bench-pro","model":"beam","score":57,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"ornith-1.5-122b","score":84.5,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.8-flash-next","score":82.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.8-27b","score":76.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"nemotron-3.5-super-vl-120b-a12b","score":61.2,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"ornith-1.5-122b","score":76.4,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.8-flash-next","score":73,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"qwen3.8-27b","score":70.3,"metric":"percent"},{"benchmark":"swe-bench-multilingual","model":"nemotron-3.5-super-vl-120b-a12b","score":48,"metric":"percent"},{"benchmark":"hle-with-tools","model":"ornith-1.5-122b","score":48,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.8-flash-next","score":38,"metric":"percent"},{"benchmark":"hle-with-tools","model":"qwen3.8-27b","score":31.3,"metric":"percent"},{"benchmark":"hle-with-tools","model":"nemotron-3.5-super-vl-120b-a12b","score":33.2,"metric":"percent"},{"benchmark":"hle","model":"ornith-1.5-122b","score":37.68,"metric":"percent"},{"benchmark":"hle","model":"qwen3.8-flash-next","score":34.16,"metric":"percent"},{"benchmark":"hle","model":"qwen3.8-27b","score":29.32,"metric":"percent"},{"benchmark":"hle","model":"nemotron-3.5-super-vl-120b-a12b","score":31.79,"metric":"percent"},{"benchmark":"scicode","model":"ornith-1.5-122b","score":53.8,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-flash-next","score":47.5,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-27b","score":43.6,"metric":"percent"},{"benchmark":"scicode","model":"nemotron-3.5-super-vl-120b-a12b","score":47.1,"metric":"percent"},{"benchmark":"wide-search","model":"ornith-1.5-122b","score":75.2,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.8-flash-next","score":71.8,"metric":"percent"},{"benchmark":"wide-search","model":"qwen3.8-27b","score":62.6,"metric":"percent"},{"benchmark":"wide-search","model":"nemotron-3.5-super-vl-120b-a12b","score":69.2,"metric":"percent"},{"benchmark":"wide-search","model":"beam","score":68.5,"metric":"percent"},{"benchmark":"browsecomp","model":"ornith-1.5-122b","score":78.5,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.8-flash-next","score":75.3,"metric":"percent"},{"benchmark":"browsecomp","model":"qwen3.8-27b","score":71.4,"metric":"percent"},{"benchmark":"browsecomp","model":"nemotron-3.5-super-vl-120b-a12b","score":61,"metric":"percent"},{"benchmark":"browsecomp","model":"deepseek-v4-flash-0731","score":80.2,"metric":"percent"},{"benchmark":"browsecomp","model":"beam","score":67.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"ornith-1.5-122b","score":74.6,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.8-flash-next","score":74.1,"metric":"percent"},{"benchmark":"mcp-atlas","model":"qwen3.8-27b","score":69,"metric":"percent"},{"benchmark":"mcp-atlas","model":"nemotron-3.5-super-vl-120b-a12b","score":63.3,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"ornith-1.5-122b","score":70.8,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"qwen3.8-flash-next","score":71.4,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"nemotron-3.5-super-vl-120b-a12b","score":60.1,"metric":"percent"},{"benchmark":"toolathlon-verified","model":"beam","score":63.5,"metric":"percent"},{"benchmark":"claw-eval","model":"ornith-1.5-122b","score":79.4,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.8-flash-next","score":76.5,"metric":"percent"},{"benchmark":"claw-eval","model":"qwen3.8-27b","score":75.4,"metric":"percent"},{"benchmark":"claw-eval","model":"nemotron-3.5-super-vl-120b-a12b","score":61.2,"metric":"percent"},{"benchmark":"aa-omniscience","model":"raon-1-mini-preview","score":3.5,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3.6-35b-a3b","score":-7.2,"metric":"index"},{"benchmark":"aa-omniscience","model":"gemma-4-26b-a4b","score":-46.6,"metric":"index"},{"benchmark":"aa-omniscience","model":"qwen3.8-27b","score":-0.5,"metric":"index"},{"benchmark":"aa-omniscience","model":"muse-glimmer-30b","score":-34.7,"metric":"index"},{"benchmark":"mmlu-pro","model":"raon-1-mini-preview","score":76.5,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.6-35b-a3b","score":85.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"gemma-4-26b-a4b","score":82.9,"metric":"percent"},{"benchmark":"mmlu-pro","model":"qwen3.8-27b","score":85.7,"metric":"percent"},{"benchmark":"mmlu-pro","model":"muse-glimmer-30b","score":84,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"raon-1-mini-preview","score":84.3,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.6-35b-a3b","score":83.2,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"gemma-4-26b-a4b","score":80.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"qwen3.8-27b","score":89.7,"metric":"percent"},{"benchmark":"gpqa-diamond","model":"muse-glimmer-30b","score":82.6,"metric":"percent"},{"benchmark":"aime-2026-i","model":"raon-1-mini-preview","score":93.3,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.6-35b-a3b","score":92.9,"metric":"percent"},{"benchmark":"aime-2026-i","model":"gemma-4-26b-a4b","score":87.1,"metric":"percent"},{"benchmark":"aime-2026-i","model":"qwen3.8-27b","score":98.8,"metric":"percent"},{"benchmark":"aime-2026-i","model":"muse-glimmer-30b","score":92.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"raon-1-mini-preview","score":84.1,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.6-35b-a3b","score":84.5,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"gemma-4-26b-a4b","score":79.9,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"qwen3.8-27b","score":95.8,"metric":"percent"},{"benchmark":"hmmt-feb-2026","model":"muse-glimmer-30b","score":74.6,"metric":"percent"},{"benchmark":"ifbench","model":"raon-1-mini-preview","score":84.2,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.6-35b-a3b","score":66.6,"metric":"percent"},{"benchmark":"ifbench","model":"gemma-4-26b-a4b","score":80.9,"metric":"percent"},{"benchmark":"ifbench","model":"qwen3.8-27b","score":82.4,"metric":"percent"},{"benchmark":"ifbench","model":"muse-glimmer-30b","score":78.7,"metric":"percent"},{"benchmark":"multichallenge","model":"raon-1-mini-preview","score":59,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.6-35b-a3b","score":58.2,"metric":"percent"},{"benchmark":"multichallenge","model":"gemma-4-26b-a4b","score":58.4,"metric":"percent"},{"benchmark":"multichallenge","model":"qwen3.8-27b","score":63.6,"metric":"percent"},{"benchmark":"multichallenge","model":"muse-glimmer-30b","score":63.4,"metric":"percent"},{"benchmark":"livecodebench","model":"raon-1-mini-preview","score":81.6,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.6-35b-a3b","score":81.2,"metric":"percent"},{"benchmark":"livecodebench","model":"gemma-4-26b-a4b","score":83.4,"metric":"percent"},{"benchmark":"livecodebench","model":"qwen3.8-27b","score":79.3,"metric":"percent"},{"benchmark":"livecodebench","model":"muse-glimmer-30b","score":77.4,"metric":"percent"},{"benchmark":"scicode","model":"raon-1-mini-preview","score":38.7,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.6-35b-a3b","score":35.6,"metric":"percent"},{"benchmark":"scicode","model":"gemma-4-26b-a4b","score":39.6,"metric":"percent"},{"benchmark":"scicode","model":"qwen3.8-27b","score":44.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"raon-1-mini-preview","score":70.8,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.6-35b-a3b","score":63.2,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"gemma-4-26b-a4b","score":61.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"qwen3.8-27b","score":74.6,"metric":"percent"},{"benchmark":"swe-bench-verified","model":"muse-glimmer-30b","score":72,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"raon-1-mini-preview","score":47,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"qwen3.6-35b-a3b","score":63.3,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"gemma-4-26b-a4b","score":52,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"qwen3.8-27b","score":67,"metric":"percent"},{"benchmark":"terminal-bench-lite","model":"muse-glimmer-30b","score":70.7,"metric":"percent"},{"benchmark":"gdpval","model":"raon-1-mini-preview","score":66,"metric":"percent"},{"benchmark":"gdpval","model":"qwen3.6-35b-a3b","score":67.4,"metric":"percent"},{"benchmark":"gdpval","model":"gemma-4-26b-a4b","score":57.5,"metric":"percent"},{"benchmark":"gdpval","model":"qwen3.8-27b","score":63.5,"metric":"percent"},{"benchmark":"gdpval","model":"muse-glimmer-30b","score":67.3,"metric":"percent"},{"benchmark":"automationbench","model":"raon-1-mini-preview","score":29.7,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.6-35b-a3b","score":24.9,"metric":"percent"},{"benchmark":"automationbench","model":"gemma-4-26b-a4b","score":36.2,"metric":"percent"},{"benchmark":"automationbench","model":"qwen3.8-27b","score":58.7,"metric":"percent"},{"benchmark":"automationbench","model":"muse-glimmer-30b","score":32.1,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"raon-1-mini-preview","score":55.7,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"qwen3.6-35b-a3b","score":34.8,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"gemma-4-26b-a4b","score":32.2,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"qwen3.8-27b","score":58,"metric":"percent"},{"benchmark":"browsecomp-plus","model":"muse-glimmer-30b","score":52.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"raon-1-mini-preview","score":59.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.6-35b-a3b","score":64.7,"metric":"percent"},{"benchmark":"bfcl-v4","model":"gemma-4-26b-a4b","score":65.8,"metric":"percent"},{"benchmark":"bfcl-v4","model":"qwen3.8-27b","score":72.4,"metric":"percent"},{"benchmark":"bfcl-v4","model":"muse-glimmer-30b","score":51.8,"metric":"percent"},{"benchmark":"aa-lcr","model":"raon-1-mini-preview","score":67.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.6-35b-a3b","score":69.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"gemma-4-26b-a4b","score":67,"metric":"percent"},{"benchmark":"aa-lcr","model":"qwen3.8-27b","score":80.3,"metric":"percent"},{"benchmark":"aa-lcr","model":"muse-glimmer-30b","score":81.3,"metric":"percent"},{"benchmark":"gdp-pdf","model":"raon-1-mini-preview","score":5.8,"metric":"percent"},{"benchmark":"gdp-pdf","model":"qwen3.6-35b-a3b","score":6.6,"metric":"percent"},{"benchmark":"gdp-pdf","model":"gemma-4-26b-a4b","score":3.6,"metric":"percent"},{"benchmark":"gdp-pdf","model":"qwen3.8-27b","score":11.2,"metric":"percent"},{"benchmark":"gdp-pdf","model":"muse-glimmer-30b","score":8.4,"metric":"percent"},{"benchmark":"ifeval","model":"underdog-saluki-27b-1.0","score":93.5,"metric":"percent"},{"benchmark":"ifbench","model":"underdog-saluki-27b-1.0","score":72.7,"metric":"percent"},{"benchmark":"mbpp-plus","model":"underdog-saluki-27b-1.0","score":78,"metric":"percent"},{"benchmark":"musr","model":"underdog-saluki-27b-1.0","score":67.5,"metric":"percent"},{"benchmark":"aime-2025","model":"underdog-saluki-27b-1.0","score":79.2,"metric":"avg@4"},{"benchmark":"aime-2026-i","model":"underdog-saluki-27b-1.0","score":80,"metric":"avg@4"},{"benchmark":"locomo","model":"memt-1.0-flash","score":65.1,"metric":"percent"},{"benchmark":"locomo","model":"memt-1.0-nano","score":57.5,"metric":"percent"},{"benchmark":"memoryagentbench","model":"memt-1.0-flash","score":17.4,"metric":"percent"},{"benchmark":"memoryagentbench","model":"memt-1.0-nano","score":15.5,"metric":"percent"},{"benchmark":"implicitmembench","model":"memt-1.0-flash","score":49.2,"metric":"percent"},{"benchmark":"implicitmembench","model":"memt-1.0-nano","score":43.1,"metric":"percent"},{"benchmark":"membench","model":"memt-1.0-flash","score":73.5,"metric":"percent"},{"benchmark":"membench","model":"memt-1.0-nano","score":71.8,"metric":"percent"},{"benchmark":"permemsafe","model":"memt-1.0-flash","score":33.5,"metric":"percent"},{"benchmark":"permemsafe","model":"memt-1.0-nano","score":38.7,"metric":"percent"},{"benchmark":"personamem","model":"memt-1.0-flash","score":61.6,"metric":"percent"},{"benchmark":"personamem","model":"memt-1.0-nano","score":52.3,"metric":"percent"}]